diff --git a/.gitignore b/.gitignore index 544dd20e..5f2dd0f5 100644 --- a/.gitignore +++ b/.gitignore @@ -41,4 +41,5 @@ output/ *.log # R environment settings file -.Renviron \ No newline at end of file +.Renviron +.DS_Store diff --git a/DESCRIPTION b/DESCRIPTION index 31aca523..0a04a07b 100755 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,8 +1,8 @@ Package: Achilles Type: Package Title: Achilles Data Source Characterization -Version: 1.8 -Date: 2025-10-10 +Version: 1.8.0 +Date: 2025-12-02 Authors@R: c( person("Frank", "DeFalco", email = "fdefalco@ohdsi.org", role = c("aut","cre")), person("Patrick", "Ryan", email = "ryan@ohdsi.org", role = c("aut")), @@ -24,12 +24,12 @@ Description: Automated Characterization of Health Information at Large-Scale variety of Observational Health Data Sciences and Informatics community applications. Depends: - DatabaseConnector (>= 2.0.0), + DatabaseConnector (>= 7.0.0), R (>= 4.0.0) Imports: - DBI, + DBI (>= 1.0.0), duckdb, - SqlRender (>= 1.6.0), + SqlRender (>= 1.19.2), dplyr, jsonlite, ParallelLogger, @@ -49,7 +49,7 @@ Suggests: VignetteBuilder: knitr License: Apache License Roxygen: list() -RoxygenNote: 7.2.3 +RoxygenNote: 7.3.3 Encoding: UTF-8 URL: https://ohdsi.github.io/Achilles/, https://github.com/OHDSI/Achilles BugReports: https://github.com/OHDSI/Achilles/issues diff --git a/NAMESPACE b/NAMESPACE index 929c06a7..8fc8e256 100755 --- a/NAMESPACE +++ b/NAMESPACE @@ -41,8 +41,7 @@ import(ParallelLogger) import(SqlRender) import(dplyr) importFrom(data.table,fwrite) -importFrom(dplyr,desc) -importFrom(dplyr,ntile) +importFrom(dplyr,rename_with) importFrom(rlang,.data) importFrom(stats,aggregate) importFrom(stats,cycle) diff --git a/NEWS.md b/NEWS.md index 7003c4f7..79ee53c4 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,3 +1,47 @@ +# Achilles 1.8 + +## Improvements and New Features + +- **Export Enhancements** + - Added `unit_concept_id` to ARES export of measurement tables. + - Improved unit concept ID naming and handling. + - Added export of the location table to ARES. + - Added database summary reporting. + +- **Performance Improvements** + - Refactored performance logs to be captured directly (not just through console logs). + - Improved performance of ARES export, especially for DuckDB. + - Optimized analyses for better performance, including analyses 117 and 1815. + +- **Code Quality and Maintenance** + - Fixed ambiguous `dplyr::select` statements and standardized column name casing (e.g., `IS_DEFAULT` → `is_default`). + - Added missing SQL scripts for performance tracking. + - Fixed fromJSON method usage for correctness. + - Fixed errors when creating metadata tables with zero-length vectors. + - Moved repeated subqueries to temp tables in some analyses. + - Trimmed trailing whitespaces in export scripts. + +- **Bug Fixes** + - Fixed crash during `exportToAres` (DuckDB) related to unit concept IDs. + - Handled missing server values in temporal characterization functions. + +- **Documentation** + - Updated and added links in the `DESCRIPTION` file. + +## Notable Commits + +- [Fix column name case: IS_DEFAULT → is_default](https://github.com/OHDSI/Achilles/commit/134bc0a7e0159dde85653ac41c1e73d8f4123fd1) +- [Ambiguous dplyr::select statements](https://github.com/OHDSI/Achilles/commit/889999c7a8b59476b8d4d95ee0d4d4a842db81ff) +- [Add db summary](https://github.com/OHDSI/Achilles/commit/87790da7453f0c8c2aa6d8e5071f5fa7a0a397fe) +- [Location table export to ARES](https://github.com/OHDSI/Achilles/commit/d5199716fca61bf4b45ab38ee8c1c441633743bc) +- [Improve performance of analysis 117](https://github.com/OHDSI/Achilles/commit/f9405e4a3b1a03ba4e4603db5774de96c5d8d3f6) +- [Add links to DESCRIPTION](https://github.com/OHDSI/Achilles/commit/c0f1a934c949a5b989f02eb56e271101306e1ed9) +- [Fix fromJSON correct method usage](https://github.com/OHDSI/Achilles/commit/b6ff65524a34da285e6340236791b00f6e32a39d) + +--- + +For more, visit the [develop branch commit history](https://github.com/OHDSI/Achilles/commits?sha=develop&sort=updated). + # Achilles 1.7.2 1. Improved test setup management diff --git a/R/Achilles.R b/R/Achilles.R index 84b05e78..9c336021 100755 --- a/R/Achilles.R +++ b/R/Achilles.R @@ -1,6 +1,6 @@ # @file Achilles # -# Copyright 2023 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles # @@ -113,14 +113,16 @@ #' @examples #' \dontrun{ #' connectionDetails <- createConnectionDetails(dbms = "sql server", server = "some_server") -#' achillesResults <- achilles(connectionDetails = connectionDetails, +#' achillesResults <- achilles( +#' connectionDetails = connectionDetails, #' cdmDatabaseSchema = "cdm", #' resultsDatabaseSchema = "results", #' scratchDatabaseSchema = "scratch", #' sourceName = "Some Source", #' cdmVersion = "5.3", #' numThreads = 10, -#' outputFolder = "output") +#' outputFolder = "output" +#' ) #' } #' #' @export @@ -147,39 +149,38 @@ achilles <- function(connectionDetails, updateGivenAnalysesOnly = FALSE, excludeAnalysisIds, sqlDialect = NULL) { - totalStart <- Sys.time() achillesSql <- c() - - performanceTable <- data.frame(analysis_id = integer(), elapsed_seconds = numeric(), start_time = numeric(), end_time = numeric ()) - + + performanceTable <- data.frame(analysis_id = integer(), elapsed_seconds = numeric(), start_time = numeric(), end_time = numeric()) + # Check if the correct parameters are supplied when running in sqlOnly mode if (sqlOnly && missing(connectionDetails) && is.null(sqlDialect)) { stop("Error: When specifying sqlOnly = TRUE, sqlDialect or connectionDetails must be supplied.") } - + if (sqlOnly && !missing(connectionDetails)) { print("Running Achilles in SQL ONLY mode. Using connectionDetails, sqlDialect is ignored. Please wait for script generation.") } - + if (sqlOnly && missing(connectionDetails) && !is.null(sqlDialect)) { connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = sqlDialect) print("Running Achilles in SQL ONLY mode. Using dialect supplied by sqlDialect. Please wait for script generation.") } - + if (!dir.exists(outputFolder)) { dir.create(outputFolder) } - + timestamp <- format(Sys.time(), "%Y%m%d_%H%M%S") - logFile <- file.path(outputFolder, paste("log_achilles_", timestamp,".txt", sep = '')) + logFile <- file.path(outputFolder, paste("log_achilles_", timestamp, ".txt", sep = "")) ParallelLogger::clearLoggers() ParallelLogger::addDefaultFileLogger(logFile) ParallelLogger::addDefaultErrorReportLogger(file.path(outputFolder, "errorReportR.txt")) - + ParallelLogger::logInfo("Performing database characterization.") - + # Try to get CDM Version if not provided if (!missing(cdmVersion)) { ParallelLogger::logInfo(paste("CDM Version", cdmVersion, "passed as parameter.")) @@ -187,27 +188,27 @@ achilles <- function(connectionDetails, cdmVersion <- .getCdmVersion(connectionDetails, cdmDatabaseSchema) ParallelLogger::logInfo(paste("CDM Version", cdmVersion, "found in cdm_source table.")) } - + cdmVersion <- as.character(cdmVersion) - + # Check CDM version is valid if (compareVersion(a = as.character(cdmVersion), b = "5") < 0) { stop("Error: Invalid CDM Version number. CDM V5 and greater are supported.") } - + # Establish folder paths if (!dir.exists(outputFolder)) { dir.create(path = outputFolder, recursive = TRUE) } - + # Get source name if none provided if (missing(sourceName) & !sqlOnly) { sourceName <- .getSourceName(connectionDetails, cdmDatabaseSchema) } - + # Obtain analyses to run analysisDetails <- getAnalysisDetails() - + if (!missing(analysisIds)) { # If specific analysis_ids are given, run only those analysisDetails <- analysisDetails[analysisDetails$analysis_id %in% analysisIds, ] @@ -215,13 +216,13 @@ achilles <- function(connectionDetails, # If specific analyses are not given, determine whether or not to run only default analyses analysisDetails <- analysisDetails[analysisDetails$is_default == 1, ] } - + # Remove unwanted analyses that have not already been excluded, if any are specified if (!missing(excludeAnalysisIds) && - any(analysisDetails$analysis_id %in% excludeAnalysisIds)) { + any(analysisDetails$analysis_id %in% excludeAnalysisIds)) { analysisDetails <- analysisDetails[-which(analysisDetails$analysis_id %in% excludeAnalysisIds), ] } - + resultsTables <- list( list( detailType = "results", @@ -230,7 +231,7 @@ achilles <- function(connectionDetails, file = system.file("csv", "schemas", "schema_achilles_results.csv", package = "Achilles"), header = TRUE ), - analysisIds = analysisDetails[analysisDetails$distribution <= 0,]$analysis_id + analysisIds = analysisDetails[analysisDetails$distribution <= 0, ]$analysis_id ), list( detailType = "results_dist", @@ -244,31 +245,31 @@ achilles <- function(connectionDetails, ), header = TRUE ), - analysisIds = analysisDetails[abs(analysisDetails$distribution) == 1,]$analysis_id + analysisIds = analysisDetails[abs(analysisDetails$distribution) == 1, ]$analysis_id ) ) schemaDelim <- "." - + if (sqlOnly) { if (.supportsTempTables(connectionDetails) && - connectionDetails$dbms != "oracle") { + connectionDetails$dbms != "oracle") { scratchDatabaseSchema <- "#" schemaDelim <- "s_" } } else { connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) on.exit(DatabaseConnector::disconnect(connection), add = TRUE) - + if (numThreads == 1 || scratchDatabaseSchema == "#") { numThreads <- 1 - + if (.supportsTempTables(connectionDetails) && - connectionDetails$dbms != "oracle") { + connectionDetails$dbms != "oracle") { scratchDatabaseSchema <- "#" schemaDelim <- "s_" } - + ParallelLogger::logInfo("Beginning single-threaded execution") } else if (!requireNamespace("ParallelLogger", quietly = TRUE)) { stop( @@ -285,59 +286,57 @@ achilles <- function(connectionDetails, ParallelLogger::logInfo("Beginning multi-threaded execution") } } - + # Determine whether or not to create Achilles support tables if (!createTable && missing(analysisIds)) { createTable <- TRUE preserveResults <- FALSE } else if (!createTable && - !missing(analysisIds) && !updateGivenAnalysesOnly) { + !missing(analysisIds) && !updateGivenAnalysesOnly) { createTable <- TRUE preserveResults <- FALSE } else if (!createTable && - !missing(analysisIds) && updateGivenAnalysesOnly) { + !missing(analysisIds) && updateGivenAnalysesOnly) { preserveResults <- TRUE } - + ## If not creating support tables, then either remove ALL prior results or only those results for the given analysisIds if (!sqlOnly) { if (!createTable && !preserveResults) { .deleteExistingResults( connectionDetails = connectionDetails, resultsDatabaseSchema = resultsDatabaseSchema, - analysisDetails = analysisDetails ) } else if (!createTable && preserveResults) { .deleteGivenAnalyses( connectionDetails = connectionDetails, resultsDatabaseSchema = resultsDatabaseSchema, - analysisIds = analysisIds ) } } - + # Create and populate the achilles_analysis table if (createTable) { sql <- SqlRender::loadRenderTranslateSql( sqlFilename = "analyses/achilles_analysis_ddl.sql", packageName = "Achilles", - dbms = connectionDetails$dbms, - resultsDatabaseSchema = resultsDatabaseSchema + dbms = connectionDetails$dbms, + resultsDatabaseSchema = resultsDatabaseSchema ) - - sqlPerformanceTable <- SqlRender::loadRenderTranslateSql( + + sqlPerformanceTable <- SqlRender::loadRenderTranslateSql( sqlFilename = "analyses/achilles_performance_ddl.sql", packageName = "Achilles", - dbms = connectionDetails$dbms, - resultsDatabaseSchema = resultsDatabaseSchema + dbms = connectionDetails$dbms, + resultsDatabaseSchema = resultsDatabaseSchema ) # Populate achilles_analysis without the "distribution" and "distributed_field" # columns from achilles_analysis_details.csv analysisDetailsCsv <- Achilles::getAnalysisDetails() - analysisDetailsCsv <- analysisDetailsCsv[,-c(2, 3)] + analysisDetailsCsv <- analysisDetailsCsv[, -c(2, 3)] if (!sqlOnly) { # Create empty achilles_analysis @@ -361,7 +360,7 @@ achilles <- function(connectionDetails, progressBar = F, reportOverallTime = F ) - + # Populate achilles_analysis with data from achilles_analysis_details.csv from above suppressMessages( DatabaseConnector::insertTable( @@ -377,16 +376,16 @@ achilles <- function(connectionDetails, ) } } - + # Clean up existing scratch tables if ((numThreads > 1 || - !.supportsTempTables(connectionDetails)) && !sqlOnly) { + !.supportsTempTables(connectionDetails)) && !sqlOnly) { # Drop the scratch tables ParallelLogger::logInfo(sprintf( "Dropping any existing scratch Achilles tables from schema %s", scratchDatabaseSchema )) - + dropAllScratchTables( connectionDetails = connectionDetails, scratchDatabaseSchema = scratchDatabaseSchema, @@ -397,7 +396,7 @@ achilles <- function(connectionDetails, defaultAnalysesOnly = defaultAnalysesOnly ) } - + # Generate Main Analyses mainAnalysisIds <- analysisDetails$analysis_id @@ -421,9 +420,9 @@ achilles <- function(connectionDetails, ) ) }) - + achillesSql <- c(achillesSql, lapply(mainSqls, function(s) s$sql)) - + if (!sqlOnly) { analysisCount <- length(mainSqls) if (analysisCount > 1) { @@ -431,8 +430,8 @@ achilles <- function(connectionDetails, } else { analysisMessage <- paste(analysisCount, "analysis.") } - ParallelLogger::logInfo(paste("Running",analysisMessage)) - + ParallelLogger::logInfo(paste("Running", analysisMessage)) + if (numThreads == 1) { for (mainSql in mainSqls) { start <- Sys.time() @@ -457,7 +456,7 @@ achilles <- function(connectionDetails, endTime <- Sys.time() delta <- endTime - start analysisId <- as.integer(mainSql$analysisId) - performanceTable[nrow(performanceTable) + 1,] <- c(analysisId,delta,start,endTime) + performanceTable[nrow(performanceTable) + 1, ] <- c(analysisId, delta, start, endTime) ParallelLogger::logInfo(sprintf( "[Main Analysis] [COMPLETE] %d (%f %s)", as.integer(mainSql$analysisId), @@ -469,16 +468,17 @@ achilles <- function(connectionDetails, } else { cluster <- ParallelLogger::makeCluster(numberOfThreads = numThreads, singleThreadToMain = TRUE) results <- ParallelLogger::clusterApply(cluster = cluster, x = mainSqls, function(mainSql) { - start <- Sys.time() - connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) - ParallelLogger::logInfo( - sprintf( - "[Main Analysis] [START] %d (%s)", - as.integer(mainSql$analysisId), - analysisDetails$analysis_name[analysisDetails$analysis_id == mainSql$analysisId] - ) + start <- Sys.time() + connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) + ParallelLogger::logInfo( + sprintf( + "[Main Analysis] [START] %d (%s)", + as.integer(mainSql$analysisId), + analysisDetails$analysis_name[analysisDetails$analysis_id == mainSql$analysisId] ) - tryCatch({ + ) + tryCatch( + { DatabaseConnector::executeSql( connection = connection, sql = mainSql$sql, @@ -493,20 +493,20 @@ achilles <- function(connectionDetails, ParallelLogger::logInfo(sprintf( "[Main Analysis] [COMPLETE] %d (%f %s)", as.integer(mainSql$analysisId), - delta, attr(delta, "units") )) - }, error = function(e) { + }, + error = function(e) { ParallelLogger::logError(sprintf( "[Main Analysis] [ERROR] %d (%s)", as.integer(mainSql$analysisId), - e )) - }) - }) - + } + ) + }) + ParallelLogger::stopCluster(cluster = cluster) } @@ -521,13 +521,13 @@ achilles <- function(connectionDetails, progressBar = F ) } - + # Merge scratch tables into final analysis tables include <- sapply(resultsTables, function(d) { any(d$analysisIds %in% analysisDetails$analysis_id) }) resultsTablesToMerge <- resultsTables[include] - + mergeSqls <- lapply(resultsTablesToMerge, function(table) { .mergeAchillesScratchTables( resultsTable = table, @@ -548,44 +548,50 @@ achilles <- function(connectionDetails, performanceTable = performanceTable ) }) - + achillesSql <- c(achillesSql, mergeSqls) - + if (!sqlOnly) { ParallelLogger::logInfo("Merging scratch Achilles tables") - + if (numThreads == 1) { - tryCatch({ - for (sql in mergeSqls) { - DatabaseConnector::executeSql(connection = connection, sql = sql, progressBar = F, reportOverallTime = F) + tryCatch( + { + for (sql in mergeSqls) { + DatabaseConnector::executeSql(connection = connection, sql = sql, progressBar = F, reportOverallTime = F) + } + }, + error = function(e) { + ParallelLogger::logError(sprintf("Merging scratch Achilles tables [ERROR] (%s)", e)) } - }, error = function(e) { - ParallelLogger::logError(sprintf("Merging scratch Achilles tables [ERROR] (%s)", e)) - }) + ) } else { - tryCatch({ - cluster <- ParallelLogger::makeCluster(numberOfThreads = numThreads, singleThreadToMain = TRUE) - connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) - clusterApplyResults <- - ParallelLogger::clusterApply(cluster = cluster, x = mergeSqls, function(sql) { - DatabaseConnector::executeSql(connection = connection, sql = sql, progressBar = F, reportOverallTime = F) - }) - }, error = function(e) { - ParallelLogger::logError( - sprintf("Merging scratch Achilles tables (merging scratch Achilles tables) [ERROR] (%s)", e) - ) - DatabaseConnector::disconnect(connection = connection) - ParallelLogger::stopCluster(cluster = cluster) - }) + tryCatch( + { + cluster <- ParallelLogger::makeCluster(numberOfThreads = numThreads, singleThreadToMain = TRUE) + connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) + clusterApplyResults <- + ParallelLogger::clusterApply(cluster = cluster, x = mergeSqls, function(sql) { + DatabaseConnector::executeSql(connection = connection, sql = sql, progressBar = F, reportOverallTime = F) + }) + }, + error = function(e) { + ParallelLogger::logError( + sprintf("Merging scratch Achilles tables (merging scratch Achilles tables) [ERROR] (%s)", e) + ) + DatabaseConnector::disconnect(connection = connection) + ParallelLogger::stopCluster(cluster = cluster) + } + ) } } - + if (!sqlOnly) { ParallelLogger::logInfo( - sprintf("Done. Achilles results can now be found in schema %s", resultsDatabaseSchema ) + sprintf("Done. Achilles results can now be found in schema %s", resultsDatabaseSchema) ) } - + # Clean up scratch tables - single threaded, drop and disconnect. For multithreaded, do not disconnect if (numThreads == 1 && dropScratchTables && !sqlOnly) { if (connectionDetails$dbms == "oracle") { @@ -598,16 +604,21 @@ achilles <- function(connectionDetails, # Oracle TEMP tables are created as persistent tables and are given randomly generated string # prefixes preceding tempAchillesPrefix, therefore, they need their own code to drop the # scratch tables. - + allTables <- DatabaseConnector::getTableNames(connection, scratchDatabaseSchema) - + tablesToDrop <- - c(allTables[which(grepl(tempAchillesPrefix, allTables, fixed = TRUE))], + c( + allTables[which(grepl(tempAchillesPrefix, allTables, fixed = TRUE))], allTables[which(grepl(tolower(tempAchillesPrefix), - allTables, fixed = TRUE))], allTables[which(grepl(toupper(tempAchillesPrefix), allTables, - fixed = TRUE))]) - + allTables, + fixed = TRUE + ))], allTables[which(grepl(toupper(tempAchillesPrefix), allTables, + fixed = TRUE + ))] + ) + dropSqls <- lapply(tablesToDrop, function(scratchTable) { sql <- SqlRender::render( @@ -619,10 +630,10 @@ achilles <- function(connectionDetails, sql <- SqlRender::translate(sql = sql, targetDialect = connectionDetails$dbms) }) - + dropSqls <- unlist(dropSqls) for (k in 1:length(dropSqls)) { - DatabaseConnector::executeSql(connection, dropSqls[k],progressBar = F, reportOverallTime = F) + DatabaseConnector::executeSql(connection, dropSqls[k], progressBar = F, reportOverallTime = F) } ParallelLogger::logInfo( sprintf( @@ -630,7 +641,7 @@ achilles <- function(connectionDetails, scratchDatabaseSchema ) ) - + DatabaseConnector::disconnect(connection = connection) } else { ParallelLogger::logInfo( @@ -639,18 +650,17 @@ achilles <- function(connectionDetails, scratchDatabaseSchema ) ) - + dropAllScratchTables( connectionDetails = connectionDetails, scratchDatabaseSchema = scratchDatabaseSchema, - tempAchillesPrefix = tempAchillesPrefix, numThreads = numThreads, tableTypes = c("achilles"), outputFolder = outputFolder, defaultAnalysesOnly = defaultAnalysesOnly ) - + ParallelLogger::logInfo( sprintf( "Temporary Achilles tables removed from schema %s", @@ -664,18 +674,17 @@ achilles <- function(connectionDetails, "Dropping scratch Achilles tables from schema %s", scratchDatabaseSchema )) - + dropAllScratchTables( connectionDetails = connectionDetails, scratchDatabaseSchema = scratchDatabaseSchema, - tempAchillesPrefix = tempAchillesPrefix, numThreads = numThreads, tableTypes = c("achilles"), outputFolder = outputFolder, defaultAnalysesOnly = defaultAnalysesOnly ) - + ParallelLogger::logInfo( sprintf( "Temporary Achilles tables removed from schema %s", @@ -683,10 +692,10 @@ achilles <- function(connectionDetails, ) ) } - + # Create indices indicesSql <- "/* INDEX CREATION SKIPPED PER USER REQUEST */" - + if (createIndices) { achillesTables <- lapply(unique(analysisDetails$distribution), function(a) { @@ -707,20 +716,24 @@ achilles <- function(connectionDetails, ) } achillesSql <- c(achillesSql, indicesSql) - + if (sqlOnly) { SqlRender::writeSql( sql = paste(achillesSql, collapse = "\n\n"), - targetFile = file.path(outputFolder, - "achilles.sql") + targetFile = file.path( + outputFolder, + "achilles.sql" + ) ) ParallelLogger::logInfo(sprintf( "All Achilles SQL scripts can be found in folder: %s", - file.path(outputFolder, - "achilles.sql") + file.path( + outputFolder, + "achilles.sql" + ) )) } - + achillesResults <- list( resultsConnectionDetails = connectionDetails, @@ -733,11 +746,11 @@ achilles <- function(connectionDetails, indicesSql = indicesSql, call = match.call() ) - + class(achillesResults) <- "achillesResults" - + invisible(achillesResults) - + totalDelta <- Sys.time() - totalStart ParallelLogger::logInfo(sprintf("[Total Runtime] %f %s", totalDelta, attr(totalDelta, "units"))) } @@ -773,7 +786,6 @@ createIndices <- function(connectionDetails, sqlOnly = FALSE, verboseMode = TRUE, achillesTables = c("achilles_results", "achilles_results_dist")) { - # Log execution if (verboseMode) { appenders <- list( @@ -791,14 +803,16 @@ createIndices <- function(connectionDetails, ) ) } - logger <- ParallelLogger::createLogger(name = "createIndices", - threshold = "INFO", - appenders = appenders) + logger <- ParallelLogger::createLogger( + name = "createIndices", + threshold = "INFO", + appenders = appenders + ) ParallelLogger::registerLogger(logger) - + dropIndicesSql <- c() indicesSql <- c() - + # dbms specific index operations if (connectionDetails$dbms %in% c("redshift", "netezza", "bigquery", "snowflake", "spark")) { return(sprintf( @@ -806,7 +820,7 @@ createIndices <- function(connectionDetails, toupper(connectionDetails$dbms) )) } - + if (connectionDetails$dbms == "pdw") { indicesSql <- c( indicesSql, @@ -816,57 +830,59 @@ createIndices <- function(connectionDetails, ) ) } - + indices <- read.csv( file = system.file("csv", - "post_processing", - "indices.csv", - package = "Achilles"), + "post_processing", + "indices.csv", + package = "Achilles" + ), header = TRUE, stringsAsFactors = FALSE ) - + # create index SQLs for (i in 1:nrow(indices)) { - if (indices[i,]$table_name %in% achillesTables) { + if (indices[i, ]$table_name %in% achillesTables) { sql <- SqlRender::render( sql = "drop index @resultsDatabaseSchema.@indexName;", resultsDatabaseSchema = resultsDatabaseSchema, - - indexName = indices[i,]$INDEX_NAME + indexName = indices[i, ]$INDEX_NAME ) sql <- SqlRender::translate(sql = sql, targetDialect = connectionDetails$dbms) dropIndicesSql <- c(dropIndicesSql, sql) - + sql <- SqlRender::render( sql = "create index @indexName on @resultsDatabaseSchema.@tableName (@fields);", resultsDatabaseSchema = resultsDatabaseSchema, - tableName = indices[i,]$table_name, - indexName = indices[i,]$index_name, - fields = paste(strsplit( - x = indices[i,]$fields, split = "~" - )[[1]], - collapse = ",") + tableName = indices[i, ]$table_name, + indexName = indices[i, ]$index_name, + fields = paste( + strsplit( + x = indices[i, ]$fields, split = "~" + )[[1]], + collapse = "," + ) ) sql <- SqlRender::translate(sql = sql, targetDialect = connectionDetails$dbms) indicesSql <- c(indicesSql, sql) } } - + if (!sqlOnly) { connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) on.exit(DatabaseConnector::disconnect(connection = connection), add = TRUE) - - try(DatabaseConnector::executeSql(connection = connection,sql = paste(dropIndicesSql, collapse = "\n\n"), progressBar = F, reportOverallTime = F), silent = TRUE) - DatabaseConnector::executeSql(connection = connection,sql = paste(indicesSql, collapse = "\n\n"), progressBar = F, reportOverallTime = F) + + try(DatabaseConnector::executeSql(connection = connection, sql = paste(dropIndicesSql, collapse = "\n\n"), progressBar = F, reportOverallTime = F), silent = TRUE) + DatabaseConnector::executeSql(connection = connection, sql = paste(indicesSql, collapse = "\n\n"), progressBar = F, reportOverallTime = F) } - + ParallelLogger::unregisterLogger("createIndices") - + invisible(c(dropIndicesSql, indicesSql)) } @@ -923,58 +939,60 @@ dropAllScratchTables <- function(connectionDetails, outputFolder, verboseMode = TRUE, defaultAnalysesOnly = TRUE) { - appenders <- list( ParallelLogger::createFileAppender( layout = ParallelLogger::layoutParallel, fileName = file.path(outputFolder, "log_dropScratchTables.txt") ) ) - - logger <- ParallelLogger::createLogger(name = "dropAllScratchTables", - threshold = "INFO", - appenders = appenders + + logger <- ParallelLogger::createLogger( + name = "dropAllScratchTables", + threshold = "INFO", + appenders = appenders ) ParallelLogger::registerLogger(logger) - + # Initialize thread and scratchDatabaseSchema settings schemaDelim <- "." - + if (numThreads == 1 || scratchDatabaseSchema == "#") { numThreads <- 1 - + if (.supportsTempTables(connectionDetails) && - connectionDetails$dbms != "oracle") { + connectionDetails$dbms != "oracle") { scratchDatabaseSchema <- "#" schemaDelim <- "s_" } } - + if ("achilles" %in% tableTypes) { # Drop Achilles Scratch Tables analysisDetails <- getAnalysisDetails() - + if (defaultAnalysesOnly) { resultsTables <- lapply(analysisDetails$analysis_id[analysisDetails$distribution <= 0 & - analysisDetails$is_default == - 1], function(id) { - sprintf("%s_%d", tempAchillesPrefix, id) - }) + analysisDetails$is_default == + 1], function(id) { + sprintf("%s_%d", tempAchillesPrefix, id) + }) } else { resultsTables <- - lapply(analysisDetails$analysis_id[analysisDetails$distribution <= 0], - function(id) { - sprintf("%s_%d", tempAchillesPrefix, id) - }) + lapply( + analysisDetails$analysis_id[analysisDetails$distribution <= 0], + function(id) { + sprintf("%s_%d", tempAchillesPrefix, id) + } + ) } - + resultsDistTables <- lapply(analysisDetails$analysis_id[abs(analysisDetails$distribution) == - 1], function(id) { - sprintf("%s_dist_%d", tempAchillesPrefix, id) - }) - + 1], function(id) { + sprintf("%s_dist_%d", tempAchillesPrefix, id) + }) + dropSqls <- lapply(c(resultsTables, resultsDistTables), function(scratchTable) { sql <- @@ -987,23 +1005,26 @@ dropAllScratchTables <- function(connectionDetails, sql <- SqlRender::translate(sql = sql, targetDialect = connectionDetails$dbms) }) - + cluster <- ParallelLogger::makeCluster(numberOfThreads = numThreads, singleThreadToMain = TRUE) connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) - on.exit(DatabaseConnector::disconnect(connection), add=TRUE) - + on.exit(DatabaseConnector::disconnect(connection), add = TRUE) + clusterApplyResults <- ParallelLogger::clusterApply(cluster = cluster, x = dropSqls, function(sql) { - tryCatch({ - DatabaseConnector::executeSql(connection = connection, sql = sql, progressBar = F, reportOverallTime = F) - }, error = function(e) { - ParallelLogger::logError(sprintf("Drop Achilles Scratch Table -- ERROR (%s)", e)) - }) + tryCatch( + { + DatabaseConnector::executeSql(connection = connection, sql = sql, progressBar = F, reportOverallTime = F) + }, + error = function(e) { + ParallelLogger::logError(sprintf("Drop Achilles Scratch Table -- ERROR (%s)", e)) + } + ) }) - + ParallelLogger::stopCluster(cluster = cluster) } - + ParallelLogger::unregisterLogger("dropAllScratchTables") } @@ -1036,7 +1057,6 @@ dropAllScratchTables <- function(connectionDetails, optimizeAtlasCache <- function(connectionDetails, resultsDatabaseSchema, vocabDatabaseSchema = resultsDatabaseSchema, - outputFolder = "output", sqlOnly = FALSE, verboseMode = TRUE, @@ -1064,21 +1084,25 @@ optimizeAtlasCache <- function(connectionDetails, ) } logger <- - ParallelLogger::createLogger(name = "optimizeAtlasCache", - threshold = "INFO", - appenders = appenders) + ParallelLogger::createLogger( + name = "optimizeAtlasCache", + threshold = "INFO", + appenders = appenders + ) ParallelLogger::registerLogger(logger) - - resultsConceptCountTable <- list(tablePrefix = tempAchillesPrefix, - schema = read.csv( - file = system.file( - "csv", - "schemas", - "schema_achilles_results_concept_count.csv", - package = "Achilles" - ), - header = TRUE - )) + + resultsConceptCountTable <- list( + tablePrefix = tempAchillesPrefix, + schema = read.csv( + file = system.file( + "csv", + "schemas", + "schema_achilles_results_concept_count.csv", + package = "Achilles" + ), + header = TRUE + ) + ) optimizeAtlasCacheSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "analyses/create_result_concept_table.sql", @@ -1087,7 +1111,8 @@ optimizeAtlasCache <- function(connectionDetails, resultsDatabaseSchema = resultsDatabaseSchema, vocabDatabaseSchema = vocabDatabaseSchema, fieldNames = paste(resultsConceptCountTable$schema$field_name, - collapse = ", ") + collapse = ", " + ) ) if (!sqlOnly) { connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) @@ -1101,16 +1126,18 @@ optimizeAtlasCache <- function(connectionDetails, DatabaseConnector::disconnect(connection = connection) }) } - + ParallelLogger::unregisterLogger("optimizeAtlasCache") - + invisible(optimizeAtlasCacheSql) } .getCdmVersion <- function(connectionDetails, cdmDatabaseSchema) { sql <- - SqlRender::render(sql = "select cdm_version from @cdmDatabaseSchema.cdm_source", - cdmDatabaseSchema = cdmDatabaseSchema) + SqlRender::render( + sql = "select cdm_version from @cdmDatabaseSchema.cdm_source", + cdmDatabaseSchema = cdmDatabaseSchema + ) sql <- SqlRender::translate(sql = sql, targetDialect = connectionDetails$dbms) connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) @@ -1118,17 +1145,19 @@ optimizeAtlasCache <- function(connectionDetails, c <- tolower(( DatabaseConnector::querySql(connection = connection, sql = sql) - )[1,]) - gsub(pattern = "v", - replacement = "", - x = c) + )[1, ]) + gsub( + pattern = "v", + replacement = "", + x = c + ) }, error = function(e) { "" }, finally = { DatabaseConnector::disconnect(connection = connection) rm(connection) }) - + cdmVersion } @@ -1141,7 +1170,6 @@ optimizeAtlasCache <- function(connectionDetails, schemaDelim, scratchDatabaseSchema, cdmDatabaseSchema, - resultsDatabaseSchema, tempEmulationSchema, cdmVersion, @@ -1151,8 +1179,10 @@ optimizeAtlasCache <- function(connectionDetails, numThreads, outputFolder) { SqlRender::loadRenderTranslateSql( - sqlFilename = file.path("analyses", - paste(analysisId, "sql", sep = ".")), + sqlFilename = file.path( + "analyses", + paste(analysisId, "sql", sep = ".") + ), packageName = "Achilles", dbms = connectionDetails$dbms, warnOnMissingParameters = FALSE, @@ -1166,7 +1196,7 @@ optimizeAtlasCache <- function(connectionDetails, achilles_version = packageVersion(pkg = "Achilles"), cdmVersion = cdmVersion, singleThreaded = (scratchDatabaseSchema == - "#") + "#") ) } @@ -1193,49 +1223,55 @@ optimizeAtlasCache <- function(connectionDetails, fieldType = field["field_type"] ) }) - + # obtain the analysis SQLs to union in the merge if (!sqlOnly) { logs <- .parseLogs(logFile) } - detailSqls <- lapply(resultsTable$analysisIds[resultsTable$analysisIds %in% analysisIds], - function(analysisId) { - analysisSql <- SqlRender::render( - sql = "select @castedNames from @scratchDatabaseSchema@schemaDelim@tablePrefix_@analysisId", - scratchDatabaseSchema = scratchDatabaseSchema, - schemaDelim = schemaDelim, - castedNames = paste(castedNames, collapse = ", "), - tablePrefix = resultsTable$tablePrefix, - analysisId = analysisId - ) - - if (!sqlOnly) { - # obtain the runTime for this analysis - runTime <- .getAchillesResultBenchmark(analysisId, logs) - - benchmarkSelects <- - lapply(resultsTable$schema$field_name, function(c) { - if (tolower(c) == "analysis_id") { - sprintf("%d as analysis_id", - .getBenchmarkOffset() + as.integer(analysisId)) - } else if (tolower(c) == "stratum_1") { - sprintf("'%s' as stratum_1", runTime) - } else if (tolower(c) == "count_value") { - sprintf("%d as count_value", smallCellCount + 1) - } else { - sprintf("NULL as %s", c) - } - }) - - benchmarkSql <- SqlRender::render(sql = "select @benchmarkSelect", - benchmarkSelect = paste(benchmarkSelects, collapse = ", ")) - - analysisSql <- - paste(c(analysisSql, benchmarkSql), collapse = " union all ") - } - analysisSql - }) - + detailSqls <- lapply( + resultsTable$analysisIds[resultsTable$analysisIds %in% analysisIds], + function(analysisId) { + analysisSql <- SqlRender::render( + sql = "select @castedNames from @scratchDatabaseSchema@schemaDelim@tablePrefix_@analysisId", + scratchDatabaseSchema = scratchDatabaseSchema, + schemaDelim = schemaDelim, + castedNames = paste(castedNames, collapse = ", "), + tablePrefix = resultsTable$tablePrefix, + analysisId = analysisId + ) + + if (!sqlOnly) { + # obtain the runTime for this analysis + runTime <- .getAchillesResultBenchmark(analysisId, logs) + + benchmarkSelects <- + lapply(resultsTable$schema$field_name, function(c) { + if (tolower(c) == "analysis_id") { + sprintf( + "%d as analysis_id", + .getBenchmarkOffset() + as.integer(analysisId) + ) + } else if (tolower(c) == "stratum_1") { + sprintf("'%s' as stratum_1", runTime) + } else if (tolower(c) == "count_value") { + sprintf("%d as count_value", smallCellCount + 1) + } else { + sprintf("NULL as %s", c) + } + }) + + benchmarkSql <- SqlRender::render( + sql = "select @benchmarkSelect", + benchmarkSelect = paste(benchmarkSelects, collapse = ", ") + ) + + analysisSql <- + paste(c(analysisSql, benchmarkSql), collapse = " union all ") + } + analysisSql + } + ) + SqlRender::loadRenderTranslateSql( sqlFilename = "analyses/merge_achilles_tables.sql", packageName = "Achilles", @@ -1253,15 +1289,17 @@ optimizeAtlasCache <- function(connectionDetails, .getSourceName <- function(connectionDetails, cdmDatabaseSchema) { sql <- - SqlRender::render(sql = "select cdm_source_name from @cdmDatabaseSchema.cdm_source", - cdmDatabaseSchema = cdmDatabaseSchema) + SqlRender::render( + sql = "select cdm_source_name from @cdmDatabaseSchema.cdm_source", + cdmDatabaseSchema = cdmDatabaseSchema + ) sql <- SqlRender::translate(sql = sql, targetDialect = connectionDetails$dbms) connection <- DatabaseConnector::connect(connectionDetails = connectionDetails) sourceName <- tryCatch({ s <- DatabaseConnector::querySql(connection = connection, sql = sql) - s[1,] + s[1, ] }, error = function(e) { "" }, finally = { @@ -1279,7 +1317,7 @@ optimizeAtlasCache <- function(connectionDetails, analysisDetails$analysis_id[analysisDetails$distribution == 0] distIds <- analysisDetails$analysis_id[analysisDetails$distribution == 1] - + if (length(resultIds) > 0) { sql <- SqlRender::render( @@ -1289,12 +1327,12 @@ optimizeAtlasCache <- function(connectionDetails, ) sql <- SqlRender::translate(sql = sql, targetDialect = connectionDetails$dbms) - + connection <- suppressMessages(DatabaseConnector::connect(connectionDetails = connectionDetails)) on.exit(DatabaseConnector::disconnect(connection = connection)) DatabaseConnector::executeSql(connection = connection, sql = sql, progressBar = F, reportOverallTime = F) } - + if (length(distIds) > 0) { sql <- SqlRender::render( @@ -1316,35 +1354,37 @@ optimizeAtlasCache <- function(connectionDetails, analysisIds) { conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(conn)) - + sql <- "delete from @resultsDatabaseSchema.achilles_results where analysis_id in (@analysisIds);" sql <- SqlRender::render( sql, resultsDatabaseSchema = resultsDatabaseSchema, analysisIds = paste(analysisIds, - collapse = ",") + collapse = "," + ) ) sql <- SqlRender::translate(sql, targetDialect = connectionDetails$dbms) - + DatabaseConnector::executeSql(conn, sql, progressBar = F, reportOverallTime = F) - + sql <- "delete from @resultsDatabaseSchema.achilles_results_dist where analysis_id in (@analysisIds);" - sql <- SqlRender::render( sql, + sql <- SqlRender::render(sql, resultsDatabaseSchema = resultsDatabaseSchema, analysisIds = paste(analysisIds, - collapse = ",") + collapse = "," + ) ) sql <- SqlRender::translate(sql, targetDialect = connectionDetails$dbms) - + DatabaseConnector::executeSql(conn, sql, progressBar = F, reportOverallTime = F) } .getAchillesResultBenchmark <- function(analysisId, logs) { - logs <- logs[logs$analysis_id == analysisId,] + logs <- logs[logs$analysis_id == analysisId, ] if (nrow(logs) == 1) { - runTime <- logs[1,]$elapsed_seconds + runTime <- logs[1, ]$elapsed_seconds runTimeValue <- round(runTime[1], 2) runTimeValue } else { @@ -1359,20 +1399,22 @@ optimizeAtlasCache <- function(connectionDetails, sep = "\t", stringsAsFactors = FALSE ) - + names(logs) <- - c("startTime", + c( + "startTime", "thread", "logType", "package", "packageFunction", - "comment") - logs <- logs[grepl(pattern = "COMPLETE", x = logs$comment),] + "comment" + ) + logs <- logs[grepl(pattern = "COMPLETE", x = logs$comment), ] logs$analysisId <- logs$runTime <- NA - + for (i in 1:nrow(logs)) { - logs[i,]$analysisId <- .parseAnalysisId(logs[i,]$comment) - logs[i,]$runTime <- .parseRunTime(logs[i,]$comment) + logs[i, ]$analysisId <- .parseAnalysisId(logs[i, ]$comment) + logs[i, ]$runTime <- .parseRunTime(logs[i, ]$comment) } logs } diff --git a/R/createTimeSeries.r b/R/createTimeSeries.r index 1e73a313..adf77906 100644 --- a/R/createTimeSeries.r +++ b/R/createTimeSeries.r @@ -1,6 +1,6 @@ # @file createTimeSeries # -# Copyright 2023 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles # @@ -49,9 +49,15 @@ #' @examples #' # Example 1: #' temporalData <- data.frame(START_DATE = seq.Date(as.Date("20210101", "%Y%m%d"), -#' as.Date("20231201", -#' "%Y%m%d"), by = "month"), COUNT_VALUE = round(runif(36, 1, 1000)), PREVALENCE = round(runif(36, -#' 0, 10), 2), PROPORTION_WITHIN_YEAR = round(runif(36, 0, 1), 2), stringsAsFactors = FALSE) +#' as.Date( +#' "20231201", +#' "%Y%m%d" +#' ), +#' by = "month" +#' ), COUNT_VALUE = round(runif(36, 1, 1000)), PREVALENCE = round(runif( +#' 36, +#' 0, 10 +#' ), 2), PROPORTION_WITHIN_YEAR = round(runif(36, 0, 1), 2), stringsAsFactors = FALSE) #' dummyTs <- createTimeSeries(temporalData) #' dummyTs.cv <- dummyTs[, "COUNT_VALUE"] #' dummyTs.pv <- dummyTs[, "PREVALENCE"] @@ -60,8 +66,10 @@ #' \dontrun{ #' # Example 2: #' pneumonia <- 255848 -#' temporalData <- getTemporalData(connectionDetails = connectionDetails, cdmDatabaseSchema = "cdm", -#' resultsDatabaseSchema = "results", conceptId = pneumonia) +#' temporalData <- getTemporalData( +#' connectionDetails = connectionDetails, cdmDatabaseSchema = "cdm", +#' resultsDatabaseSchema = "results", conceptId = pneumonia +#' ) #' pneumoniaTs <- createTimeSeries(temporalData) #' pneumoniaTs.cv <- pneumoniaTs[, "COUNT_VALUE"] #' pneumoniaTs.pv <- pneumoniaTs[, "PREVALENCE"] @@ -71,13 +79,16 @@ #' @export createTimeSeries <- function(temporalData) { - requiredColumns <- c("START_DATE", "COUNT_VALUE", "PREVALENCE", "PROPORTION_WITHIN_YEAR") - if (sum(colnames(temporalData) %in% requiredColumns) < 4) - stop(paste0("ERROR: INVALID DATA FRAME FORMAT. The data frame must contain columns: ", - paste(requiredColumns, - collapse = ", "))) + if (sum(colnames(temporalData) %in% requiredColumns) < 4) { + stop(paste0( + "ERROR: INVALID DATA FRAME FORMAT. The data frame must contain columns: ", + paste(requiredColumns, + collapse = ", " + ) + )) + } if (nrow(temporalData) == 0) { stop("ERROR: Cannot create time series from an empty data frame") @@ -95,9 +106,13 @@ createTimeSeries <- function(temporalData) { # series lastRow <- nrow(resultSetData) - denseDates <- seq.Date(from = as.Date(resultSetData$START_DATE[1], "%Y%m%d"), - to = as.Date(resultSetData$START_DATE[lastRow], - "%Y%m%d"), by = "month") + denseDates <- seq.Date( + from = as.Date(resultSetData$START_DATE[1], "%Y%m%d"), + to = as.Date( + resultSetData$START_DATE[lastRow], + "%Y%m%d" + ), by = "month" + ) # Find gaps, if any, in data (e.g., dates that have no data, give that date a 0 count and 0 # prevalence) @@ -110,23 +125,33 @@ createTimeSeries <- function(temporalData) { joinResults$PROPORTION_WITHIN_YEAR[which(is.na(joinResults$PROPORTION_WITHIN_YEAR))] <- 0 # Now that we no longer have sparse dates, keep only necessary columns and build the time series - joinResults <- joinResults[, c("START_DATE", - "COUNT_VALUE", - "PREVALENCE", - "PROPORTION_WITHIN_YEAR")] + joinResults <- joinResults[, c( + "START_DATE", + "COUNT_VALUE", + "PREVALENCE", + "PROPORTION_WITHIN_YEAR" + )] # Find the end of the dense results lastRow <- nrow(joinResults) # Create the multivariate time series - tsData <- data.frame(COUNT_VALUE = joinResults$COUNT_VALUE, PREVALENCE = joinResults$PREVALENCE, - PROPORTION_WITHIN_YEAR = joinResults$PROPORTION_WITHIN_YEAR) - - resultSetDataTs <- ts(data = tsData, start = c(as.numeric(substring(joinResults$START_DATE[1], 1, - 4)), as.numeric(substring(joinResults$START_DATE[1], - 6, - 7))), end = c(as.numeric(substring(joinResults$START_DATE[lastRow], - 1, 4)), as.numeric(substring(joinResults$START_DATE[lastRow], 6, 7))), frequency = 12) + tsData <- data.frame( + COUNT_VALUE = joinResults$COUNT_VALUE, PREVALENCE = joinResults$PREVALENCE, + PROPORTION_WITHIN_YEAR = joinResults$PROPORTION_WITHIN_YEAR + ) + + resultSetDataTs <- ts(data = tsData, start = c(as.numeric(substring( + joinResults$START_DATE[1], 1, + 4 + )), as.numeric(substring( + joinResults$START_DATE[1], + 6, + 7 + ))), end = c(as.numeric(substring( + joinResults$START_DATE[lastRow], + 1, 4 + )), as.numeric(substring(joinResults$START_DATE[lastRow], 6, 7))), frequency = 12) return(resultSetDataTs) } diff --git a/R/exportToAres.R b/R/exportToAres.R index 7fec7011..081242bf 100644 --- a/R/exportToAres.R +++ b/R/exportToAres.R @@ -9,17 +9,21 @@ normalizeEmptyValue <- function(x) { } } +querySqlWithUpperCaseColumns <- function(...) { + DatabaseConnector::querySql(...) |> + dplyr::rename_with(toupper) +} + saveConceptsAsJson <- function( - concept_id, - reports, - columnsToNormalize, - columnsToConvertToDataFrame, - dir -) { - report <- reports[reports$CONCEPT_ID == concept_id,] + concept_id, + reports, + columnsToNormalize, + columnsToConvertToDataFrame, + dir) { + report <- reports[reports$CONCEPT_ID == concept_id, ] report <- as.list(report) - #Normalize the specified columns + # Normalize the specified columns for (col in columnsToNormalize) { report[[col]] <- normalizeEmptyValue(report[[col]]) } @@ -37,11 +41,10 @@ saveConceptsAsJson <- function( } saveConceptsAsDuckDb <- function( - duckdbCon, - conceptData, - domain, - schema -) { + duckdbCon, + conceptData, + domain, + schema) { for (tableName in names(conceptData$reports)) { tableData <- conceptData$reports[[tableName]] @@ -68,15 +71,14 @@ saveConceptsAsDuckDb <- function( } processAndExportConceptData <- function( - duckdbCon, - conceptData, - outputPath, - outputFormat, - columnsToNormalize, - columnsToConvertToDataFrame, - domain, - schema -) { + duckdbCon, + conceptData, + outputPath, + outputFormat, + columnsToNormalize, + columnsToConvertToDataFrame, + domain, + schema) { if (is.null(conceptData)) { return() } @@ -109,8 +111,7 @@ processAndExportConceptData <- function( } -generateAOProcedureReports <- function(connectionDetails, proceduresData, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ +generateAOProcedureReports <- function(connectionDetails, proceduresData, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { if (nrow(proceduresData) == 0) { return(NULL) } @@ -157,25 +158,25 @@ generateAOProcedureReports <- function(connectionDetails, proceduresData, cdmDat conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) dataProceduresByType <- - DatabaseConnector::querySql(conn, queryProceduresByType) %>% - dplyr::select(c("CONCEPT_ID" = "PROCEDURE_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) + querySqlWithUpperCaseColumns(conn, queryProceduresByType) %>% + dplyr::select(c("CONCEPT_ID" = "PROCEDURE_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) dataAgeAtFirstOccurrence <- - DatabaseConnector::querySql(conn, queryAgeAtFirstOccurrence) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstOccurrence) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataProcedureFrequencyDistribution <- - DatabaseConnector::querySql(conn, queryProcedureFrequencyDistribution) %>% - dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) + querySqlWithUpperCaseColumns(conn, queryProcedureFrequencyDistribution) %>% + dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) uniqueConcepts <- data.frame( @@ -184,18 +185,18 @@ generateAOProcedureReports <- function(connectionDetails, proceduresData, cdmDat ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - proceduresData, - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "CDM_TABLE_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) + dplyr::left_join( + proceduresData, + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "CDM_TABLE_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) if (outputFormat == "duckdb") { reports <- list( @@ -209,50 +210,49 @@ generateAOProcedureReports <- function(connectionDetails, proceduresData, cdmDat } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataProcedureFrequencyDistribution %>% - tidyr::nest(PROCEDURE_FREQUENCY_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataProceduresByType %>% - tidyr::nest(PROCEDURES_BY_TYPE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataAgeAtFirstOccurrence %>% - tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataProcedureFrequencyDistribution %>% + tidyr::nest(PROCEDURE_FREQUENCY_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataProceduresByType %>% + tidyr::nest(PROCEDURES_BY_TYPE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataAgeAtFirstOccurrence %>% + tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAOPersonReport <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputPath) -{ - output = { } +generateAOPersonReport <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputPath) { + output <- { } conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) renderedSql <- SqlRender::loadRenderTranslateSql( @@ -265,8 +265,8 @@ generateAOPersonReport <- function(connectionDetails, cdmDatabaseSchema, results vocab_database_schema = vocabDatabaseSchema ) - personSummaryData <- DatabaseConnector::querySql(conn, renderedSql) - output$SUMMARY = personSummaryData + personSummaryData <- querySqlWithUpperCaseColumns(conn, renderedSql) + output$SUMMARY <- personSummaryData renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/person/population_age_gender.sql", @@ -277,8 +277,8 @@ generateAOPersonReport <- function(connectionDetails, cdmDatabaseSchema, results results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - ageGenderData <- DatabaseConnector::querySql(conn, renderedSql) - output$AGE_GENDER_DATA = ageGenderData + ageGenderData <- querySqlWithUpperCaseColumns(conn, renderedSql) + output$AGE_GENDER_DATA <- ageGenderData renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/person/gender.sql", @@ -289,8 +289,8 @@ generateAOPersonReport <- function(connectionDetails, cdmDatabaseSchema, results results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - genderData <- DatabaseConnector::querySql(conn, renderedSql) - output$GENDER_DATA = genderData + genderData <- querySqlWithUpperCaseColumns(conn, renderedSql) + output$GENDER_DATA <- genderData renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/person/race.sql", @@ -301,8 +301,8 @@ generateAOPersonReport <- function(connectionDetails, cdmDatabaseSchema, results results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - raceData <- DatabaseConnector::querySql(conn, renderedSql) - output$RACE_DATA = raceData + raceData <- querySqlWithUpperCaseColumns(conn, renderedSql) + output$RACE_DATA <- raceData renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/person/ethnicity.sql", @@ -313,8 +313,8 @@ generateAOPersonReport <- function(connectionDetails, cdmDatabaseSchema, results results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - ethnicityData <- DatabaseConnector::querySql(conn, renderedSql) - output$ETHNICITY_DATA = ethnicityData + ethnicityData <- querySqlWithUpperCaseColumns(conn, renderedSql) + output$ETHNICITY_DATA <- ethnicityData renderedSql <- SqlRender::loadRenderTranslateSql( @@ -326,32 +326,29 @@ generateAOPersonReport <- function(connectionDetails, cdmDatabaseSchema, results results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - birthYearData <- DatabaseConnector::querySql(conn, renderedSql) + birthYearData <- querySqlWithUpperCaseColumns(conn, renderedSql) output$BIRTH_YEAR_DATA <- birthYearData return(output) } -generateAOAchillesPerformanceReport <- function(connection, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputPath) -{ - - queryAchillesPerformance <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/performance/sqlAchillesPerformance.sql", - packageName = "Achilles", - dbms = connection@dbms, - warnOnMissingParameters = FALSE, - cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, - vocab_database_schema = vocabDatabaseSchema +generateAOAchillesPerformanceReport <- function(connection, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputPath) { + queryAchillesPerformance <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/performance/sqlAchillesPerformance.sql", + packageName = "Achilles", + dbms = connection@dbms, + warnOnMissingParameters = FALSE, + cdm_database_schema = cdmDatabaseSchema, + results_database_schema = resultsDatabaseSchema, + vocab_database_schema = vocabDatabaseSchema ) - dataPerformance <- DatabaseConnector::querySql(connection, queryAchillesPerformance) + dataPerformance <- querySqlWithUpperCaseColumns(connection, queryAchillesPerformance) names(dataPerformance) <- c("analysis_id", "analysis_name", "category", "elapsed_seconds") dataPerformance$elapsed_seconds <- format(round(as.numeric(dataPerformance$elapsed_seconds), digits = 2), nsmall = 2) return(dataPerformance) } -generateAODeathReport <- function(connection, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputPath) -{ - +generateAODeathReport <- function(connection, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputPath) { queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/death/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", @@ -382,29 +379,28 @@ generateAODeathReport <- function(connection, cdmDatabaseSchema, resultsDatabase results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - deathByTypeData <- DatabaseConnector::querySql(connection, queryDeathByType) - prevalenceByGenderAgeYearData <- DatabaseConnector::querySql(connection, queryPrevalenceByGenderAgeYear) - prevalenceByMonthData <- DatabaseConnector::querySql(connection, queryPrevalenceByMonth) - ageAtDeathData <- DatabaseConnector::querySql(connection, queryAgeAtDeath) + deathByTypeData <- querySqlWithUpperCaseColumns(connection, queryDeathByType) + prevalenceByGenderAgeYearData <- querySqlWithUpperCaseColumns(connection, queryPrevalenceByGenderAgeYear) + prevalenceByMonthData <- querySqlWithUpperCaseColumns(connection, queryPrevalenceByMonth) + ageAtDeathData <- querySqlWithUpperCaseColumns(connection, queryAgeAtDeath) - output = { } - output$PREVALENCE_BY_GENDER_AGE_YEAR = prevalenceByGenderAgeYearData - output$PREVALENCE_BY_MONTH = prevalenceByMonthData - output$DEATH_BY_TYPE = deathByTypeData - output$AGE_AT_DEATH = ageAtDeathData + output <- { } + output$PREVALENCE_BY_GENDER_AGE_YEAR <- prevalenceByGenderAgeYearData + output$PREVALENCE_BY_MONTH <- prevalenceByMonthData + output$DEATH_BY_TYPE <- deathByTypeData + output$AGE_AT_DEATH <- ageAtDeathData return(output) } -generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputPath) -{ - output = { } +generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputPath) { + output <- { } renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/observationperiod/ageatfirst.sql", packageName = "Achilles", dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - ageAtFirstObservationData <- DatabaseConnector::querySql(connection, renderedSql) + ageAtFirstObservationData <- querySqlWithUpperCaseColumns(connection, renderedSql) output$AGE_AT_FIRST_OBSERVATION <- ageAtFirstObservationData renderedSql <- SqlRender::loadRenderTranslateSql( @@ -414,8 +410,8 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - ageByGenderData <- DatabaseConnector::querySql(connection, renderedSql) - output$AGE_BY_GENDER = ageByGenderData + ageByGenderData <- querySqlWithUpperCaseColumns(connection, renderedSql) + output$AGE_BY_GENDER <- ageByGenderData observationLengthHist <- { } renderedSql <- SqlRender::loadRenderTranslateSql( @@ -424,11 +420,11 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - observationLengthStats <- DatabaseConnector::querySql(connection, renderedSql) - observationLengthHist$MIN = observationLengthStats$MIN_VALUE - observationLengthHist$MAX = observationLengthStats$MAX_VALUE - observationLengthHist$INTERVAL_SIZE = observationLengthStats$INTERVAL_SIZE - observationLengthHist$INTERVALS = (observationLengthStats$MAX_VALUE - observationLengthStats$MIN_VALUE) / observationLengthStats$INTERVAL_SIZE + observationLengthStats <- querySqlWithUpperCaseColumns(connection, renderedSql) + observationLengthHist$MIN <- observationLengthStats$MIN_VALUE + observationLengthHist$MAX <- observationLengthStats$MAX_VALUE + observationLengthHist$INTERVAL_SIZE <- observationLengthStats$INTERVAL_SIZE + observationLengthHist$INTERVALS <- (observationLengthStats$MAX_VALUE - observationLengthStats$MIN_VALUE) / observationLengthStats$INTERVAL_SIZE renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/observationperiod/observationlength_data.sql", @@ -436,8 +432,8 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - observationLengthData <- DatabaseConnector::querySql(connection, renderedSql) - output$OBSERVATION_LENGTH_HISTOGRAM = observationLengthHist + observationLengthData <- querySqlWithUpperCaseColumns(connection, renderedSql) + output$OBSERVATION_LENGTH_HISTOGRAM <- observationLengthHist renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/observationperiod/cumulativeduration.sql", @@ -445,11 +441,11 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - cumulativeDurationData <- DatabaseConnector::querySql(connection, renderedSql) + cumulativeDurationData <- querySqlWithUpperCaseColumns(connection, renderedSql) cumulativeDurationData$X_LENGTH_OF_OBSERVATION <- cumulativeDurationData$X_LENGTH_OF_OBSERVATION / 365.25 cumulativeDurationData$SERIES_NAME <- NULL names(cumulativeDurationData) <- c("YEARS", "PERCENT_PEOPLE") - output$CUMULATIVE_DURATION = cumulativeDurationData + output$CUMULATIVE_DURATION <- cumulativeDurationData renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/observationperiod/observationlengthbygender.sql", @@ -458,7 +454,7 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - opLengthByGenderData <- DatabaseConnector::querySql(connection, renderedSql) + opLengthByGenderData <- querySqlWithUpperCaseColumns(connection, renderedSql) opLengthByGenderData$MIN_VALUE <- opLengthByGenderData$MIN_VALUE / 365.25 opLengthByGenderData$P10_VALUE <- opLengthByGenderData$P10_VALUE / 365.25 opLengthByGenderData$P25_VALUE <- opLengthByGenderData$P25_VALUE / 365.25 @@ -467,7 +463,7 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res opLengthByGenderData$P90_VALUE <- opLengthByGenderData$P90_VALUE / 365.25 opLengthByGenderData$MAX_VALUE <- opLengthByGenderData$MAX_VALUE / 365.25 - output$OBSERVATION_PERIOD_LENGTH_BY_GENDER = opLengthByGenderData + output$OBSERVATION_PERIOD_LENGTH_BY_GENDER <- opLengthByGenderData renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/observationperiod/observationlengthbyage.sql", @@ -475,7 +471,7 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - opLengthByAgeData <- DatabaseConnector::querySql(connection, renderedSql) + opLengthByAgeData <- querySqlWithUpperCaseColumns(connection, renderedSql) opLengthByAgeData$MIN_VALUE <- opLengthByAgeData$MIN_VALUE / 365.25 opLengthByAgeData$P10_VALUE <- opLengthByAgeData$P10_VALUE / 365.25 opLengthByAgeData$P25_VALUE <- opLengthByAgeData$P25_VALUE / 365.25 @@ -483,7 +479,7 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res opLengthByAgeData$P75_VALUE <- opLengthByAgeData$P75_VALUE / 365.25 opLengthByAgeData$P90_VALUE <- opLengthByAgeData$P90_VALUE / 365.25 opLengthByAgeData$MAX_VALUE <- opLengthByAgeData$MAX_VALUE / 365.25 - output$OBSERVATION_PERIOD_LENGTH_BY_AGE = opLengthByAgeData + output$OBSERVATION_PERIOD_LENGTH_BY_AGE <- opLengthByAgeData observedByYearHist <- { } renderedSql <- SqlRender::loadRenderTranslateSql( @@ -492,11 +488,11 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - observedByYearStats <- DatabaseConnector::querySql(connection, renderedSql) - observedByYearHist$MIN = observedByYearStats$MIN_VALUE - observedByYearHist$MAX = observedByYearStats$MAX_VALUE - observedByYearHist$INTERVAL_SIZE = observedByYearStats$INTERVAL_SIZE - observedByYearHist$INTERVALS = (observedByYearStats$MAX_VALUE - observedByYearStats$MIN_VALUE) / observedByYearStats$INTERVAL_SIZE + observedByYearStats <- querySqlWithUpperCaseColumns(connection, renderedSql) + observedByYearHist$MIN <- observedByYearStats$MIN_VALUE + observedByYearHist$MAX <- observedByYearStats$MAX_VALUE + observedByYearHist$INTERVAL_SIZE <- observedByYearStats$INTERVAL_SIZE + observedByYearHist$INTERVALS <- (observedByYearStats$MAX_VALUE - observedByYearStats$MIN_VALUE) / observedByYearStats$INTERVAL_SIZE renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/observationperiod/observedbyyear_data.sql", @@ -504,9 +500,9 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - observedByYearData <- DatabaseConnector::querySql(connection, renderedSql) + observedByYearData <- querySqlWithUpperCaseColumns(connection, renderedSql) observedByYearHist$DATA <- observedByYearData - output$OBSERVED_BY_YEAR_HISTOGRAM = observedByYearHist + output$OBSERVED_BY_YEAR_HISTOGRAM <- observedByYearHist observedByMonth <- { } renderedSql <- SqlRender::loadRenderTranslateSql( @@ -515,8 +511,8 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - observedByMonth <- DatabaseConnector::querySql(connection, renderedSql) - output$OBSERVED_BY_MONTH = observedByMonth + observedByMonth <- querySqlWithUpperCaseColumns(connection, renderedSql) + output$OBSERVED_BY_MONTH <- observedByMonth renderedSql <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/observationperiod/periodsperperson.sql", @@ -524,14 +520,12 @@ generateAOObservationPeriodReport <- function(connection, cdmDatabaseSchema, res dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - personPeriodsData <- DatabaseConnector::querySql(connection, renderedSql) - output$PERSON_PERIODS_DATA = personPeriodsData + personPeriodsData <- querySqlWithUpperCaseColumns(connection, renderedSql) + output$PERSON_PERIODS_DATA <- personPeriodsData return(output) } -generateAOVisitReports <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ - +generateAOVisitReports <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { queryVisits <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/visit/sqlVisitTreemap.sql", packageName = "Achilles", @@ -574,31 +568,31 @@ generateAOVisitReports <- function(connectionDetails, cdmDatabaseSchema, results conn <- DatabaseConnector::connect(connectionDetails) dataVisits <- - DatabaseConnector::querySql(conn, queryVisits) %>% - dplyr::rename(dplyr::all_of(c("CONCEPT_NAME" = "CONCEPT_PATH"))) %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) + querySqlWithUpperCaseColumns(conn, queryVisits) %>% + dplyr::rename(dplyr::all_of(c("CONCEPT_NAME" = "CONCEPT_PATH"))) %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) if (nrow(dataVisits) == 0) { return(NULL) } dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) dataVisitDurationByType <- - DatabaseConnector::querySql(conn, queryVisitDurationByType) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryVisitDurationByType) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataAgeAtFirstOccurrence <- - DatabaseConnector::querySql(conn, queryAgeAtFirstOccurrence) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstOccurrence) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(dataVisits$CONCEPT_ID), @@ -606,10 +600,10 @@ generateAOVisitReports <- function(connectionDetails, cdmDatabaseSchema, results ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - dataVisits, - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) + dplyr::left_join( + dataVisits, + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) if (outputFormat == "duckdb") { reports <- list( concept_metadata = conceptMetadata, @@ -621,41 +615,40 @@ generateAOVisitReports <- function(connectionDetails, cdmDatabaseSchema, results } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataVisitDurationByType %>% - tidyr::nest(VISIT_DURATION_BY_TYPE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataAgeAtFirstOccurrence %>% - tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataVisitDurationByType %>% + tidyr::nest(VISIT_DURATION_BY_TYPE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataAgeAtFirstOccurrence %>% + tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAOVisitDetailReports <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ +generateAOVisitDetailReports <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { queryVisitDetails <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/visitdetail/sqlVisitDetailTreemap.sql", packageName = "Achilles", @@ -707,32 +700,32 @@ generateAOVisitDetailReports <- function(connectionDetails, cdmDatabaseSchema, r conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataVisitDetails <- - DatabaseConnector::querySql(conn, queryVisitDetails) %>% - dplyr::rename(dplyr::all_of(c("CONCEPT_NAME" = "CONCEPT_PATH"))) %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) + querySqlWithUpperCaseColumns(conn, queryVisitDetails) %>% + dplyr::rename(dplyr::all_of(c("CONCEPT_NAME" = "CONCEPT_PATH"))) %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) if (nrow(dataVisitDetails) == 0) { return(NULL) } dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) dataVisitDetailDurationByType <- - DatabaseConnector::querySql(conn, queryVisitDetailDurationByType) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryVisitDetailDurationByType) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataAgeAtFirstOccurrence <- - DatabaseConnector::querySql(conn, queryAgeAtFirstOccurrence) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstOccurrence) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(dataVisitDetails$CONCEPT_ID), @@ -740,10 +733,10 @@ generateAOVisitDetailReports <- function(connectionDetails, cdmDatabaseSchema, r ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - dataVisitDetails, - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) + dplyr::left_join( + dataVisitDetails, + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) if (outputFormat == "duckdb") { reports <- list( @@ -756,56 +749,53 @@ generateAOVisitDetailReports <- function(connectionDetails, cdmDatabaseSchema, r } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataVisitDetailDurationByType %>% - tidyr::nest(VISIT_DETAIL_DURATION_BY_TYPE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataAgeAtFirstOccurrence %>% - tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataVisitDetailDurationByType %>% + tidyr::nest(VISIT_DETAIL_DURATION_BY_TYPE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataAgeAtFirstOccurrence %>% + tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAOMetadataReport <- function(connection, cdmDatabaseSchema, outputPath) -{ - if (DatabaseConnector::existsTable(connection = connection, databaseSchema = cdmDatabaseSchema, tableName = "METADATA")) - { +generateAOMetadataReport <- function(connection, cdmDatabaseSchema, outputPath) { + if (DatabaseConnector::existsTable(connection = connection, databaseSchema = cdmDatabaseSchema, tableName = "METADATA")) { queryMetadata <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/metadata/sqlMetadata.sql", packageName = "Achilles", dbms = connection@dbms, cdm_database_schema = cdmDatabaseSchema ) - dataMetadata <- DatabaseConnector::querySql(connection, queryMetadata) + dataMetadata <- querySqlWithUpperCaseColumns(connection, queryMetadata) return(dataMetadata) } } -generateAOObservationReports <- function(connectionDetails, observationsData, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ +generateAOObservationReports <- function(connectionDetails, observationsData, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { if (nrow(observationsData) == 0) { return(NULL) } @@ -853,20 +843,20 @@ generateAOObservationReports <- function(connectionDetails, observationsData, cd conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) dataObservationsByType <- - DatabaseConnector::querySql(conn, queryObservationsByType) %>% - dplyr::select(c("CONCEPT_ID" = "OBSERVATION_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) + querySqlWithUpperCaseColumns(conn, queryObservationsByType) %>% + dplyr::select(c("CONCEPT_ID" = "OBSERVATION_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) dataAgeAtFirstOccurrence <- - DatabaseConnector::querySql(conn, queryAgeAtFirstOccurrence) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstOccurrence) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataObsFrequencyDistribution <- - DatabaseConnector::querySql(conn, queryObsFrequencyDistribution) %>% - dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) + querySqlWithUpperCaseColumns(conn, queryObsFrequencyDistribution) %>% + dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(observationsData$CONCEPT_ID), @@ -874,18 +864,18 @@ generateAOObservationReports <- function(connectionDetails, observationsData, cd ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - observationsData, - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "CDM_TABLE_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) + dplyr::left_join( + observationsData, + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "CDM_TABLE_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) if (outputFormat == "duckdb") { reports <- list( @@ -899,50 +889,48 @@ generateAOObservationReports <- function(connectionDetails, observationsData, cd } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataObsFrequencyDistribution %>% - tidyr::nest(OBS_FREQUENCY_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataObservationsByType %>% - tidyr::nest(OBSERVATIONS_BY_TYPE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataAgeAtFirstOccurrence %>% - tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataObsFrequencyDistribution %>% + tidyr::nest(OBS_FREQUENCY_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataObservationsByType %>% + tidyr::nest(OBSERVATIONS_BY_TYPE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataAgeAtFirstOccurrence %>% + tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAOCdmSourceReport <- function(connection, cdmDatabaseSchema, outputPath) -{ - if (DatabaseConnector::existsTable(connection = connection, databaseSchema = cdmDatabaseSchema, tableName = "CDM_SOURCE")) - { +generateAOCdmSourceReport <- function(connection, cdmDatabaseSchema, outputPath) { + if (DatabaseConnector::existsTable(connection = connection, databaseSchema = cdmDatabaseSchema, tableName = "CDM_SOURCE")) { queryCdmSource <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/metadata/sqlCdmSource.sql", packageName = "Achilles", @@ -950,13 +938,12 @@ generateAOCdmSourceReport <- function(connection, cdmDatabaseSchema, outputPath) cdm_database_schema = cdmDatabaseSchema ) - dataCdmSource <- DatabaseConnector::querySql(connection, queryCdmSource) + dataCdmSource <- querySqlWithUpperCaseColumns(connection, queryCdmSource) return(dataCdmSource) } } -generateAODashboardReport <- function(outputPath) -{ +generateAODashboardReport <- function(outputPath) { output <- { } personReport <- jsonlite::fromJSON(file = paste(outputPath, "/person.json", sep = "")) output$SUMMARY <- personReport$SUMMARY @@ -971,8 +958,7 @@ generateAODashboardReport <- function(outputPath) write(jsonOutput, file = paste(outputPath, "/dashboard.json", sep = "")) } -generateAOMeasurementReports <- function(connectionDetails, dataMeasurements, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ +generateAOMeasurementReports <- function(connectionDetails, dataMeasurements, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/measurement/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", @@ -1056,39 +1042,39 @@ generateAOMeasurementReports <- function(connectionDetails, dataMeasurements, cd conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) if (nrow(dataPrevalenceByMonth) == 0) { return(NULL) } dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataMeasurementsByType <- - DatabaseConnector::querySql(conn, queryMeasurementsByType) %>% - dplyr::select(c("CONCEPT_ID" = "MEASUREMENT_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) + querySqlWithUpperCaseColumns(conn, queryMeasurementsByType) %>% + dplyr::select(c("CONCEPT_ID" = "MEASUREMENT_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) dataAgeAtFirstOccurrence <- - DatabaseConnector::querySql(conn, queryAgeAtFirstOccurrence) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstOccurrence) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataRecordsByUnit <- - DatabaseConnector::querySql(conn, queryRecordsByUnit) %>% - dplyr::select(c("CONCEPT_ID" = "MEASUREMENT_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE", "UNIT_CONCEPT_ID")) + querySqlWithUpperCaseColumns(conn, queryRecordsByUnit) %>% + dplyr::select(c("CONCEPT_ID" = "MEASUREMENT_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE", "UNIT_CONCEPT_ID")) dataMeasurementValueDistribution <- - DatabaseConnector::querySql(conn, queryMeasurementValueDistribution) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE", "UNIT_CONCEPT_ID")) + querySqlWithUpperCaseColumns(conn, queryMeasurementValueDistribution) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE", "UNIT_CONCEPT_ID")) dataLowerLimitDistribution <- - DatabaseConnector::querySql(conn, queryLowerLimitDistribution) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryLowerLimitDistribution) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataUpperLimitDistribution <- - DatabaseConnector::querySql(conn, queryUpperLimitDistribution) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryUpperLimitDistribution) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataValuesRelativeToNorm <- - DatabaseConnector::querySql(conn, queryValuesRelativeToNorm) %>% - dplyr::select(c("CONCEPT_ID" = "MEASUREMENT_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) + querySqlWithUpperCaseColumns(conn, queryValuesRelativeToNorm) %>% + dplyr::select(c("CONCEPT_ID" = "MEASUREMENT_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) dataFrequencyDistribution <- - DatabaseConnector::querySql(conn, queryFrequencyDistribution) %>% - dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) + querySqlWithUpperCaseColumns(conn, queryFrequencyDistribution) %>% + dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(dataPrevalenceByMonth$CONCEPT_ID), @@ -1096,19 +1082,19 @@ generateAOMeasurementReports <- function(connectionDetails, dataMeasurements, cd ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - ( - dataMeasurements %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) + dplyr::left_join( + ( + dataMeasurements %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) if (outputFormat == "duckdb") { reports <- list( @@ -1127,83 +1113,82 @@ generateAOMeasurementReports <- function(connectionDetails, dataMeasurements, cd } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataFrequencyDistribution %>% - tidyr::nest(FREQUENCY_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataMeasurementsByType %>% - tidyr::nest(MEASUREMENTS_BY_TYPE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataAgeAtFirstOccurrence %>% - tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataRecordsByUnit %>% - tidyr::nest(RECORDS_BY_UNIT = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataMeasurementValueDistribution %>% - tidyr::nest(MEASUREMENT_VALUE_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataLowerLimitDistribution %>% - tidyr::nest(LOWER_LIMIT_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataUpperLimitDistribution %>% - tidyr::nest(UPPER_LIMIT_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataValuesRelativeToNorm %>% - tidyr::nest(VALUES_RELATIVE_TO_NORM = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataFrequencyDistribution %>% + tidyr::nest(FREQUENCY_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataMeasurementsByType %>% + tidyr::nest(MEASUREMENTS_BY_TYPE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataAgeAtFirstOccurrence %>% + tidyr::nest(AGE_AT_FIRST_OCCURRENCE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataRecordsByUnit %>% + tidyr::nest(RECORDS_BY_UNIT = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataMeasurementValueDistribution %>% + tidyr::nest(MEASUREMENT_VALUE_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataLowerLimitDistribution %>% + tidyr::nest(LOWER_LIMIT_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataUpperLimitDistribution %>% + tidyr::nest(UPPER_LIMIT_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataValuesRelativeToNorm %>% + tidyr::nest(VALUES_RELATIVE_TO_NORM = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAODrugEraReports <- function(connectionDetails, dataDrugEra, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ +generateAODrugEraReports <- function(connectionDetails, dataDrugEra, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { if (nrow(dataDrugEra) == 0) { return(NULL) } @@ -1243,17 +1228,17 @@ generateAODrugEraReports <- function(connectionDetails, dataDrugEra, cdmDatabase conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataAgeAtFirstExposure <- - DatabaseConnector::querySql(conn, queryAgeAtFirstExposure) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstExposure) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) dataLengthOfEra <- - DatabaseConnector::querySql(conn, queryLengthOfEra) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryLengthOfEra) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(dataDrugEra$CONCEPT_ID), @@ -1261,19 +1246,19 @@ generateAODrugEraReports <- function(connectionDetails, dataDrugEra, cdmDatabase ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - ( - dataDrugEra %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) + dplyr::left_join( + ( + dataDrugEra %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) if (outputFormat == "duckdb") { reports <- list( @@ -1286,42 +1271,40 @@ generateAODrugEraReports <- function(connectionDetails, dataDrugEra, cdmDatabase } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataAgeAtFirstExposure %>% - tidyr::nest(AGE_AT_FIRST_EXPOSURE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataLengthOfEra %>% - tidyr::nest(LENGTH_OF_ERA = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataAgeAtFirstExposure %>% + tidyr::nest(AGE_AT_FIRST_EXPOSURE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataLengthOfEra %>% + tidyr::nest(LENGTH_OF_ERA = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAODrugReports <- function(connectionDetails, dataDrugs, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ - +generateAODrugReports <- function(connectionDetails, dataDrugs, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { queryAgeAtFirstExposure <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/drug/sqlAgeAtFirstExposure.sql", packageName = "Achilles", @@ -1389,33 +1372,33 @@ generateAODrugReports <- function(connectionDetails, dataDrugs, cdmDatabaseSchem conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) if (nrow(dataPrevalenceByMonth) == 0) { return(NULL) } dataAgeAtFirstExposure <- - DatabaseConnector::querySql(conn, queryAgeAtFirstExposure) %>% - dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstExposure) %>% + dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataDaysSupplyDistribution <- - DatabaseConnector::querySql(conn, queryDaysSupplyDistribution) %>% - dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryDaysSupplyDistribution) %>% + dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataDrugsByType <- - DatabaseConnector::querySql(conn, queryDrugsByType) %>% - dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) + querySqlWithUpperCaseColumns(conn, queryDrugsByType) %>% + dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataQuantityDistribution <- - DatabaseConnector::querySql(conn, queryQuantityDistribution) %>% - dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryQuantityDistribution) %>% + dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataRefillsDistribution <- - DatabaseConnector::querySql(conn, queryRefillsDistribution) %>% - dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryRefillsDistribution) %>% + dplyr::select(c("CONCEPT_ID" = "DRUG_CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataDrugFrequencyDistribution <- - DatabaseConnector::querySql(conn, queryDrugFrequencyDistribution) %>% - dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) + querySqlWithUpperCaseColumns(conn, queryDrugFrequencyDistribution) %>% + dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(dataPrevalenceByMonth$CONCEPT_ID), @@ -1423,19 +1406,19 @@ generateAODrugReports <- function(connectionDetails, dataDrugs, cdmDatabaseSchem ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - ( - dataDrugs %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) + dplyr::left_join( + ( + dataDrugs %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) if (outputFormat == "duckdb") { reports <- list( @@ -1452,69 +1435,68 @@ generateAODrugReports <- function(connectionDetails, dataDrugs, cdmDatabaseSchem } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataAgeAtFirstExposure %>% - tidyr::nest(AGE_AT_FIRST_EXPOSURE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataDaysSupplyDistribution %>% - tidyr::nest(DAYS_SUPPLY_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataDrugsByType %>% - tidyr::nest(DRUGS_BY_TYPE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataDrugFrequencyDistribution %>% - tidyr::nest(DRUG_FREQUENCY_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataQuantityDistribution %>% - tidyr::nest(QUANTITY_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataRefillsDistribution %>% - tidyr::nest(REFILLS_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataAgeAtFirstExposure %>% + tidyr::nest(AGE_AT_FIRST_EXPOSURE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataDaysSupplyDistribution %>% + tidyr::nest(DAYS_SUPPLY_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataDrugsByType %>% + tidyr::nest(DRUGS_BY_TYPE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataDrugFrequencyDistribution %>% + tidyr::nest(DRUG_FREQUENCY_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataQuantityDistribution %>% + tidyr::nest(QUANTITY_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataRefillsDistribution %>% + tidyr::nest(REFILLS_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAODeviceReports <- function(connectionDetails, dataDevices, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ +generateAODeviceReports <- function(connectionDetails, dataDevices, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { if (nrow(dataDevices) == 0) { return(NULL) } @@ -1562,20 +1544,20 @@ generateAODeviceReports <- function(connectionDetails, dataDevices, cdmDatabaseS conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataAgeAtFirstExposure <- - DatabaseConnector::querySql(conn, queryAgeAtFirstExposure) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstExposure) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataDevicesByType <- - DatabaseConnector::querySql(conn, queryDevicesByType) %>% - dplyr::select(c("CONCEPT_ID" = "DEVICE_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) + querySqlWithUpperCaseColumns(conn, queryDevicesByType) %>% + dplyr::select(c("CONCEPT_ID" = "DEVICE_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) dataDeviceFrequencyDistribution <- - DatabaseConnector::querySql(conn, queryDeviceFrequencyDistribution) %>% - dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) + querySqlWithUpperCaseColumns(conn, queryDeviceFrequencyDistribution) %>% + dplyr::select(c("CONCEPT_ID", "Y_NUM_PERSONS", "X_COUNT")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(dataDevices$CONCEPT_ID), @@ -1583,19 +1565,19 @@ generateAODeviceReports <- function(connectionDetails, dataDevices, cdmDatabaseS ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - ( - dataDevices %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) + dplyr::left_join( + ( + dataDevices %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) if (outputFormat == "duckdb") { reports <- list( @@ -1609,48 +1591,47 @@ generateAODeviceReports <- function(connectionDetails, dataDevices, cdmDatabaseS } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataAgeAtFirstExposure %>% - tidyr::nest(AGE_AT_FIRST_EXPOSURE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataDevicesByType %>% - tidyr::nest(DEVICES_BY_TYPE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataDeviceFrequencyDistribution %>% - tidyr::nest(DEVICE_FREQUENCY_DISTRIBUTION = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataAgeAtFirstExposure %>% + tidyr::nest(AGE_AT_FIRST_EXPOSURE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataDevicesByType %>% + tidyr::nest(DEVICES_BY_TYPE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataDeviceFrequencyDistribution %>% + tidyr::nest(DEVICE_FREQUENCY_DISTRIBUTION = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAOConditionReports <- function(connectionDetails, dataConditions, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ +generateAOConditionReports <- function(connectionDetails, dataConditions, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( sqlFilename = "export/condition/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", @@ -1694,21 +1675,21 @@ generateAOConditionReports <- function(connectionDetails, dataConditions, cdmDat conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) if (nrow(dataPrevalenceByMonth) == 0) { return(NULL) } dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataConditionsByType <- - DatabaseConnector::querySql(conn, queryConditionsByType) %>% - dplyr::select(c("CONCEPT_ID" = "CONDITION_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) + querySqlWithUpperCaseColumns(conn, queryConditionsByType) %>% + dplyr::select(c("CONCEPT_ID" = "CONDITION_CONCEPT_ID", "CONCEPT_NAME", "COUNT_VALUE")) dataAgeAtFirstDiagnosis <- - DatabaseConnector::querySql(conn, queryAgeAtFirstDiagnosis) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstDiagnosis) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(dataPrevalenceByMonth$CONCEPT_ID), @@ -1716,19 +1697,19 @@ generateAOConditionReports <- function(connectionDetails, dataConditions, cdmDat ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - ( - dataConditions %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) + dplyr::left_join( + ( + dataConditions %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) if (outputFormat == "duckdb") { reports <- list( @@ -1741,41 +1722,40 @@ generateAOConditionReports <- function(connectionDetails, dataConditions, cdmDat } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataConditionsByType %>% - tidyr::nest(CONDITIONS_BY_TYPE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataAgeAtFirstDiagnosis %>% - tidyr::nest(AGE_AT_FIRST_DIAGNOSIS = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataConditionsByType %>% + tidyr::nest(CONDITIONS_BY_TYPE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataAgeAtFirstDiagnosis %>% + tidyr::nest(AGE_AT_FIRST_DIAGNOSIS = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } -generateAOConditionEraReports <- function(connectionDetails, dataConditionEra, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) -{ +generateAOConditionEraReports <- function(connectionDetails, dataConditionEra, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, outputFormat) { if (nrow(dataConditionEra) == 0) { return(NULL) } @@ -1823,17 +1803,17 @@ generateAOConditionEraReports <- function(connectionDetails, dataConditionEra, c conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) dataPrevalenceByGenderAgeYear <- - DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) %>% - dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByGenderAgeYear) %>% + dplyr::select(c("CONCEPT_ID", "TRELLIS_NAME", "SERIES_NAME", "X_CALENDAR_YEAR", "Y_PREVALENCE_1000PP")) dataPrevalenceByMonth <- - DatabaseConnector::querySql(conn, queryPrevalenceByMonth) %>% - dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) + querySqlWithUpperCaseColumns(conn, queryPrevalenceByMonth) %>% + dplyr::select(c("CONCEPT_ID", "X_CALENDAR_MONTH", "Y_PREVALENCE_1000PP")) dataLengthOfEra <- - DatabaseConnector::querySql(conn, queryLengthOfEra) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryLengthOfEra) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) dataAgeAtFirstDiagnosis <- - DatabaseConnector::querySql(conn, queryAgeAtFirstDiagnosis) %>% - dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) + querySqlWithUpperCaseColumns(conn, queryAgeAtFirstDiagnosis) %>% + dplyr::select(c("CONCEPT_ID", "CATEGORY", "MIN_VALUE", "P10_VALUE", "P25_VALUE", "MEDIAN_VALUE", "P75_VALUE", "P90_VALUE", "MAX_VALUE")) uniqueConcepts <- data.frame( CONCEPT_ID = unique(dataConditionEra$CONCEPT_ID), @@ -1841,19 +1821,19 @@ generateAOConditionEraReports <- function(connectionDetails, dataConditionEra, c ) conceptMetadata <- uniqueConcepts %>% - dplyr::left_join( - ( - dataConditionEra %>% - dplyr::select( - "CONCEPT_ID", - "CONCEPT_NAME", - "NUM_PERSONS", - "PERCENT_PERSONS", - "RECORDS_PER_PERSON" - ) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) + dplyr::left_join( + ( + dataConditionEra %>% + dplyr::select( + "CONCEPT_ID", + "CONCEPT_NAME", + "NUM_PERSONS", + "PERCENT_PERSONS", + "RECORDS_PER_PERSON" + ) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) if (outputFormat == "duckdb") { reports <- list( @@ -1866,35 +1846,35 @@ generateAOConditionEraReports <- function(connectionDetails, dataConditionEra, c } else { reports <- conceptMetadata %>% - dplyr::left_join( - ( - dataAgeAtFirstDiagnosis %>% - tidyr::nest(AGE_AT_FIRST_EXPOSURE = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByGenderAgeYear %>% - tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataPrevalenceByMonth %>% - tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::left_join( - ( - dataLengthOfEra %>% - tidyr::nest(LENGTH_OF_ERA = c(-1)) - ), - by = c("CONCEPT_ID" = "CONCEPT_ID") - ) %>% - dplyr::collect() + dplyr::left_join( + ( + dataAgeAtFirstDiagnosis %>% + tidyr::nest(AGE_AT_FIRST_EXPOSURE = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByGenderAgeYear %>% + tidyr::nest(PREVALENCE_BY_GENDER_AGE_YEAR = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataPrevalenceByMonth %>% + tidyr::nest(PREVALENCE_BY_MONTH = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::left_join( + ( + dataLengthOfEra %>% + tidyr::nest(LENGTH_OF_ERA = c(-1)) + ), + by = c("CONCEPT_ID" = "CONCEPT_ID") + ) %>% + dplyr::collect() } return(list("reports" = reports, "uniqueConcepts" = uniqueConcepts)) } @@ -1908,7 +1888,7 @@ generateDataDensityTotal <- function(connection, resultsDatabaseSchema) { results_database_schema = resultsDatabaseSchema ) - totalRecordsData <- DatabaseConnector::querySql(connection, renderedSql) + totalRecordsData <- querySqlWithUpperCaseColumns(connection, renderedSql) colnames(totalRecordsData) <- c("domain", "date", "records") totalRecordsData$date <- lubridate::parse_date_time(totalRecordsData$date, "ym") @@ -1926,7 +1906,7 @@ generateLocationData <- function(connection, resultsDatabaseSchema) { results_database_schema = resultsDatabaseSchema ) - locationData <- DatabaseConnector::querySql(connection, renderedSql) + locationData <- querySqlWithUpperCaseColumns(connection, renderedSql) return(locationData) } @@ -1938,7 +1918,7 @@ generateDataDensityRecordsPerPerson <- function(connection, resultsDatabaseSchem results_database_schema = resultsDatabaseSchema ) - recordsPerPerson <- DatabaseConnector::querySql(connection, renderedSql) + recordsPerPerson <- querySqlWithUpperCaseColumns(connection, renderedSql) colnames(recordsPerPerson) <- c("domain", "date", "records") recordsPerPerson$date <- lubridate::parse_date_time(recordsPerPerson$date, "ym") recordsPerPerson$records <- round(recordsPerPerson$records, 2) @@ -1952,10 +1932,10 @@ generateDataDensityConceptsPerPerson <- function(connection, resultsDatabaseSche dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - conceptsPerPerson <- DatabaseConnector::querySql(connection, renderedSql) + conceptsPerPerson <- querySqlWithUpperCaseColumns(connection, renderedSql) return(conceptsPerPerson) - #data.table::fwrite(conceptsPerPerson, file=paste0(sourceOutputPath, "/datadensity-concepts-per-person.csv")) - #dbWriteTable(duckdbCon, "concepts_per_person", conceptsPerPerson) + # data.table::fwrite(conceptsPerPerson, file=paste0(sourceOutputPath, "/datadensity-concepts-per-person.csv")) + # dbWriteTable(duckdbCon, "concepts_per_person", conceptsPerPerson) } generateDataDensityDomainsPerPerson <- function(connection, resultsDatabaseSchema) { @@ -1965,11 +1945,11 @@ generateDataDensityDomainsPerPerson <- function(connection, resultsDatabaseSchem dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - domainsPerPerson <- DatabaseConnector::querySql(connection, renderedSql) + domainsPerPerson <- querySqlWithUpperCaseColumns(connection, renderedSql) domainsPerPerson$PERCENT_VALUE <- round(as.numeric(domainsPerPerson$PERCENT_VALUE), 2) return(domainsPerPerson) - #data.table::fwrite(domainsPerPerson, file=paste0(sourceOutputPath, "/datadensity-domains-per-person.csv")) - #dbWriteTable(duckdbCon, "domains_per_person", domainsPerPerson) + # data.table::fwrite(domainsPerPerson, file=paste0(sourceOutputPath, "/datadensity-domains-per-person.csv")) + # dbWriteTable(duckdbCon, "domains_per_person", domainsPerPerson) } generateDomainSummaryConditions <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -1980,14 +1960,14 @@ generateDomainSummaryConditions <- function(connection, resultsDatabaseSchema, v results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataConditions <- DatabaseConnector::querySql(connection, queryConditions) + dataConditions <- querySqlWithUpperCaseColumns(connection, queryConditions) dataConditions$PERCENT_PERSONS <- format(round(dataConditions$PERCENT_PERSONS, 4), nsmall = 4) dataConditions$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataConditions$PERCENT_PERSONS), 10) dataConditions$RECORDS_PER_PERSON <- format(round(dataConditions$RECORDS_PER_PERSON, 1), nsmall = 1) dataConditions$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataConditions$RECORDS_PER_PERSON), 10) return(dataConditions) - #data.table::fwrite(dataConditions, file=paste0(sourceOutputPath, "/domain-summary-condition_occurrence.csv")) - #dbWriteTable(duckdbCon, "domain_summary", dataConditions, append = TRUE) + # data.table::fwrite(dataConditions, file=paste0(sourceOutputPath, "/domain-summary-condition_occurrence.csv")) + # dbWriteTable(duckdbCon, "domain_summary", dataConditions, append = TRUE) } generateDomainSummaryConditionEras <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -1998,13 +1978,13 @@ generateDomainSummaryConditionEras <- function(connection, resultsDatabaseSchema results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataConditionEra <- DatabaseConnector::querySql(connection, queryConditionEra) + dataConditionEra <- querySqlWithUpperCaseColumns(connection, queryConditionEra) dataConditionEra$PERCENT_PERSONS <- format(round(dataConditionEra$PERCENT_PERSONS, 4), nsmall = 4) dataConditionEra$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataConditionEra$PERCENT_PERSONS), 10) dataConditionEra$RECORDS_PER_PERSON <- format(round(dataConditionEra$RECORDS_PER_PERSON, 1), nsmall = 1) dataConditionEra$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataConditionEra$RECORDS_PER_PERSON), 10) return(dataConditionEra) - #data.table::fwrite(dataConditionEra, file=paste0(sourceOutputPath, "/domain-summary-condition_era.csv")) + # data.table::fwrite(dataConditionEra, file=paste0(sourceOutputPath, "/domain-summary-condition_era.csv")) } generateDomainSummaryDrugs <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2015,13 +1995,13 @@ generateDomainSummaryDrugs <- function(connection, resultsDatabaseSchema, vocabD results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataDrugs <- DatabaseConnector::querySql(connection, queryDrugs) + dataDrugs <- querySqlWithUpperCaseColumns(connection, queryDrugs) dataDrugs$PERCENT_PERSONS <- format(round(dataDrugs$PERCENT_PERSONS, 4), nsmall = 4) dataDrugs$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataDrugs$PERCENT_PERSONS), 10) dataDrugs$RECORDS_PER_PERSON <- format(round(dataDrugs$RECORDS_PER_PERSON, 1), nsmall = 1) dataDrugs$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataDrugs$RECORDS_PER_PERSON), 10) return(dataDrugs) - #data.table::fwrite(dataDrugs, file=paste0(sourceOutputPath, "/domain-summary-drug_exposure.csv")) + # data.table::fwrite(dataDrugs, file=paste0(sourceOutputPath, "/domain-summary-drug_exposure.csv")) } generateDomainDrugStratification <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2032,9 +2012,9 @@ generateDomainDrugStratification <- function(connection, resultsDatabaseSchema, results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataDrugType <- DatabaseConnector::querySql(connection, queryDrugType) + dataDrugType <- querySqlWithUpperCaseColumns(connection, queryDrugType) return(dataDrugType) - #data.table::fwrite(dataDrugType, file=paste0(sourceOutputPath, "/domain-drug-stratification.csv")) + # data.table::fwrite(dataDrugType, file=paste0(sourceOutputPath, "/domain-drug-stratification.csv")) } generateDomainSummaryDrugEra <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2045,13 +2025,13 @@ generateDomainSummaryDrugEra <- function(connection, resultsDatabaseSchema, voca results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataDrugEra <- DatabaseConnector::querySql(connection, queryDrugEra) + dataDrugEra <- querySqlWithUpperCaseColumns(connection, queryDrugEra) dataDrugEra$PERCENT_PERSONS <- format(round(dataDrugEra$PERCENT_PERSONS, 4), nsmall = 4) dataDrugEra$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataDrugEra$PERCENT_PERSONS), 10) dataDrugEra$RECORDS_PER_PERSON <- format(round(dataDrugEra$RECORDS_PER_PERSON, 1), nsmall = 1) dataDrugEra$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataDrugEra$RECORDS_PER_PERSON), 10) return(dataDrugEra) - #data.table::fwrite(dataDrugEra, file=paste0(sourceOutputPath, "/domain-summary-drug_era.csv")) + # data.table::fwrite(dataDrugEra, file=paste0(sourceOutputPath, "/domain-summary-drug_era.csv")) } generateDomainSummaryMeasurements <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2062,13 +2042,13 @@ generateDomainSummaryMeasurements <- function(connection, resultsDatabaseSchema, results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataMeasurements <- DatabaseConnector::querySql(connection, queryMeasurements) + dataMeasurements <- querySqlWithUpperCaseColumns(connection, queryMeasurements) dataMeasurements$PERCENT_PERSONS <- format(round(dataMeasurements$PERCENT_PERSONS, 4), nsmall = 4) dataMeasurements$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataMeasurements$PERCENT_PERSONS), 10) dataMeasurements$RECORDS_PER_PERSON <- format(round(dataMeasurements$RECORDS_PER_PERSON, 1), nsmall = 1) dataMeasurements$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataMeasurements$RECORDS_PER_PERSON), 10) return(dataMeasurements) - #data.table::fwrite(dataMeasurements, file=paste0(sourceOutputPath, "/domain-summary-measurement.csv")) + # data.table::fwrite(dataMeasurements, file=paste0(sourceOutputPath, "/domain-summary-measurement.csv")) } generateDomainSummaryObservations <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2079,13 +2059,13 @@ generateDomainSummaryObservations <- function(connection, resultsDatabaseSchema, results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataObservations <- DatabaseConnector::querySql(connection, queryObservations) + dataObservations <- querySqlWithUpperCaseColumns(connection, queryObservations) dataObservations$PERCENT_PERSONS <- format(round(dataObservations$PERCENT_PERSONS, 4), nsmall = 4) dataObservations$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataObservations$PERCENT_PERSONS), 10) dataObservations$RECORDS_PER_PERSON <- format(round(dataObservations$RECORDS_PER_PERSON, 1), nsmall = 1) dataObservations$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataObservations$RECORDS_PER_PERSON), 10) return(dataObservations) - #data.table::fwrite(dataObservations, file=paste0(sourceOutputPath, "/domain-summary-observation.csv")) + # data.table::fwrite(dataObservations, file=paste0(sourceOutputPath, "/domain-summary-observation.csv")) } generateDomainSummaryVisitDetails <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2096,14 +2076,14 @@ generateDomainSummaryVisitDetails <- function(connection, resultsDatabaseSchema, results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataVisitDetails <- DatabaseConnector::querySql(connection, queryVisitDetails) + dataVisitDetails <- querySqlWithUpperCaseColumns(connection, queryVisitDetails) dataVisitDetails$PERCENT_PERSONS <- format(round(dataVisitDetails$PERCENT_PERSONS, 4), nsmall = 4) dataVisitDetails$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataVisitDetails$PERCENT_PERSONS), 10) dataVisitDetails$RECORDS_PER_PERSON <- format(round(dataVisitDetails$RECORDS_PER_PERSON, 1), nsmall = 1) dataVisitDetails$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataVisitDetails$RECORDS_PER_PERSON), 10) - names(dataVisitDetails)[names(dataVisitDetails) == 'CONCEPT_PATH'] <- 'CONCEPT_NAME' + names(dataVisitDetails)[names(dataVisitDetails) == "CONCEPT_PATH"] <- "CONCEPT_NAME" return(dataVisitDetails) - #data.table::fwrite(dataVisitDetails, file=paste0(sourceOutputPath, "/domain-summary-visit_detail.csv")) + # data.table::fwrite(dataVisitDetails, file=paste0(sourceOutputPath, "/domain-summary-visit_detail.csv")) } generateDomainSummaryVisits <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2114,14 +2094,14 @@ generateDomainSummaryVisits <- function(connection, resultsDatabaseSchema, vocab results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataVisits <- DatabaseConnector::querySql(connection, queryVisits) + dataVisits <- querySqlWithUpperCaseColumns(connection, queryVisits) dataVisits$PERCENT_PERSONS <- format(round(dataVisits$PERCENT_PERSONS, 4), nsmall = 4) dataVisits$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataVisits$PERCENT_PERSONS), 10) dataVisits$RECORDS_PER_PERSON <- format(round(dataVisits$RECORDS_PER_PERSON, 1), nsmall = 1) dataVisits$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataVisits$RECORDS_PER_PERSON), 10) - names(dataVisits)[names(dataVisits) == 'CONCEPT_PATH'] <- 'CONCEPT_NAME' + names(dataVisits)[names(dataVisits) == "CONCEPT_PATH"] <- "CONCEPT_NAME" return(dataVisits) - #data.table::fwrite(dataVisits, file=paste0(sourceOutputPath, "/domain-summary-visit_occurrence.csv")) + # data.table::fwrite(dataVisits, file=paste0(sourceOutputPath, "/domain-summary-visit_occurrence.csv")) } generateDomainVisitStratification <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2132,9 +2112,9 @@ generateDomainVisitStratification <- function(connection, resultsDatabaseSchema, results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataVisits <- DatabaseConnector::querySql(connection, queryVisits) + dataVisits <- querySqlWithUpperCaseColumns(connection, queryVisits) return(dataVisits) - #data.table::fwrite(dataVisits, file=paste0(sourceOutputPath, "/domain-visit-stratification.csv")) + # data.table::fwrite(dataVisits, file=paste0(sourceOutputPath, "/domain-visit-stratification.csv")) } generateDomainSummaryProcedures <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2145,13 +2125,13 @@ generateDomainSummaryProcedures <- function(connection, resultsDatabaseSchema, v results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataProcedures <- DatabaseConnector::querySql(connection, queryProcedures) + dataProcedures <- querySqlWithUpperCaseColumns(connection, queryProcedures) dataProcedures$PERCENT_PERSONS <- format(round(dataProcedures$PERCENT_PERSONS, 4), nsmall = 4) dataProcedures$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataProcedures$PERCENT_PERSONS), 10) dataProcedures$RECORDS_PER_PERSON <- format(round(dataProcedures$RECORDS_PER_PERSON, 1), nsmall = 1) dataProcedures$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataProcedures$RECORDS_PER_PERSON), 10) return(dataProcedures) - #data.table::fwrite(dataProcedures, file=paste0(sourceOutputPath, "/domain-summary-procedure_occurrence.csv")) + # data.table::fwrite(dataProcedures, file=paste0(sourceOutputPath, "/domain-summary-procedure_occurrence.csv")) } generateDomainSummaryDevices <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2162,13 +2142,13 @@ generateDomainSummaryDevices <- function(connection, resultsDatabaseSchema, voca results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema ) - dataDevices <- DatabaseConnector::querySql(connection, queryDevices) + dataDevices <- querySqlWithUpperCaseColumns(connection, queryDevices) dataDevices$PERCENT_PERSONS <- format(round(dataDevices$PERCENT_PERSONS, 4), nsmall = 4) dataDevices$PERCENT_PERSONS_NTILE <- dplyr::ntile(dplyr::desc(dataDevices$PERCENT_PERSONS), 10) dataDevices$RECORDS_PER_PERSON <- format(round(dataDevices$RECORDS_PER_PERSON, 1), nsmall = 1) dataDevices$RECORDS_PER_PERSON_NTILE <- dplyr::ntile(dplyr::desc(dataDevices$RECORDS_PER_PERSON), 10) return(dataDevices) - #data.table::fwrite(dataDevices, file=paste0(sourceOutputPath, "/domain-summary-device_exposure.csv")) + # data.table::fwrite(dataDevices, file=paste0(sourceOutputPath, "/domain-summary-device_exposure.csv")) } generateDomainSummaryProvider <- function(connection, resultsDatabaseSchema, vocabDatabaseSchema) { @@ -2180,11 +2160,11 @@ generateDomainSummaryProvider <- function(connection, resultsDatabaseSchema, voc vocab_database_schema = vocabDatabaseSchema ) writeLines("Generating provider reports") - dataProviders <- DatabaseConnector::querySql(connection, queryProviders) + dataProviders <- querySqlWithUpperCaseColumns(connection, queryProviders) dataProviders$PERCENT_PERSONS <- format(round(dataProviders$PERCENT_PERSONS, 4), nsmall = 4) return(dataProviders) - #data.table::fwrite(dataProviders, file=paste0(sourceOutputPath, "/domain-summary-provider.csv")) - #dbWriteTable(duckdbCon, "domain_summary", dataProviders, append = TRUE) + # data.table::fwrite(dataProviders, file=paste0(sourceOutputPath, "/domain-summary-provider.csv")) + # dbWriteTable(duckdbCon, "domain_summary", dataProviders, append = TRUE) } generateQualityCompleteness <- function(connection, resultsDatabaseSchema) { @@ -2194,13 +2174,13 @@ generateQualityCompleteness <- function(connection, resultsDatabaseSchema) { dbms = connection@dbms, results_database_schema = resultsDatabaseSchema ) - dataCompleteness <- DatabaseConnector::querySql(connection, queryCompleteness) - dataCompleteness <- dataCompleteness[order(-dataCompleteness$RECORD_COUNT),] + dataCompleteness <- querySqlWithUpperCaseColumns(connection, queryCompleteness) + dataCompleteness <- dataCompleteness[order(-dataCompleteness$RECORD_COUNT), ] # prevent downstream crashes with large files if (nrow(dataCompleteness) > 100000) { - dataCompleteness <- dataCompleteness[1:100000,] + dataCompleteness <- dataCompleteness[1:100000, ] } - #data.table::fwrite(dataCompleteness, file=paste0(sourceOutputPath, "/quality-completeness.csv")) + # data.table::fwrite(dataCompleteness, file=paste0(sourceOutputPath, "/quality-completeness.csv")) return(dataCompleteness) } @@ -2224,26 +2204,24 @@ generateQualityCompleteness <- function(connection, resultsDatabaseSchema) { #' #' @return none #' -#'@import DBI -#'@importFrom data.table fwrite -#'@importFrom dplyr ntile desc -#'@export +#' @import DBI +#' @importFrom data.table fwrite +#' @export exportToAres <- function( - connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - vocabDatabaseSchema, - outputPath, - outputFormat = "default", - reports = c()) -{ + connectionDetails, + cdmDatabaseSchema, + resultsDatabaseSchema, + vocabDatabaseSchema, + outputPath, + outputFormat = "default", + reports = c()) { conn <- DatabaseConnector::connect(connectionDetails) on.exit(DatabaseConnector::disconnect(connection = conn)) # generate a folder name for this release of the cdm characterization sql <- SqlRender::render(sql = "select * from @cdmDatabaseSchema.cdm_source;", cdmDatabaseSchema = cdmDatabaseSchema) sql <- SqlRender::translate(sql = sql, targetDialect = connectionDetails$dbms) - metadata <- DatabaseConnector::querySql(conn, sql) + metadata <- querySqlWithUpperCaseColumns(conn, sql) sourceKey <- gsub(" ", "_", metadata$CDM_SOURCE_ABBREVIATION) releaseDateKey <- format(lubridate::ymd(metadata$CDM_RELEASE_DATE), "%Y%m%d") sourceOutputPath <- file.path(outputPath, sourceKey, releaseDateKey) @@ -2253,7 +2231,7 @@ exportToAres <- function( conceptsFolder <- file.path(sourceOutputPath, "concepts") dir.create(conceptsFolder, showWarnings = F) if (outputFormat == "duckdb") { - conceptsDatabasePath <- file.path(conceptsFolder, 'data.duckdb') + conceptsDatabasePath <- file.path(conceptsFolder, "data.duckdb") if (file.exists(conceptsDatabasePath)) { unlink(conceptsDatabasePath) } @@ -2373,7 +2351,6 @@ exportToAres <- function( # quality - completeness currentTable <- generateQualityCompleteness(conn, resultsDatabaseSchema) data.table::fwrite(currentTable, file = paste0(sourceOutputPath, "/quality-completeness.csv")) - } if (length(reports) == 0 || (length(reports) > 0 && "performance" %in% reports)) { @@ -2652,7 +2629,7 @@ exportToAres <- function( if (length(reports) == 0 || (length(reports) > 0 && "person" %in% reports)) { writeLines("Generating person report") currentTable <- generateAOPersonReport(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, vocabDatabaseSchema, sourceOutputPath) - jsonOutput = jsonlite::toJSON(currentTable) + jsonOutput <- jsonlite::toJSON(currentTable) write(jsonOutput, file = paste0(sourceOutputPath, "/person.json")) } -} \ No newline at end of file +} diff --git a/R/exportToCSV.R b/R/exportToCSV.R index 1a1a5f63..9987e52c 100644 --- a/R/exportToCSV.R +++ b/R/exportToCSV.R @@ -22,7 +22,7 @@ #' minCellCount) are deleted. Set to 0 for complete summary without #' small cell count restrictions. #' @param exportFolder Path to store results -#' @returns +#' @returns #' No return value. Called to export CSV file to the file system. #' @export @@ -30,8 +30,7 @@ exportResultsToCSV <- function(connectionDetails, resultsDatabaseSchema, analysisIds = c(), minCellCount = 5, - - exportFolder) { + exportFolder) { # Ensure the export folder exists if (!file.exists(exportFolder)) { dir.create(exportFolder, recursive = TRUE) @@ -42,13 +41,14 @@ exportResultsToCSV <- function(connectionDetails, on.exit(DatabaseConnector::disconnect(connection)) # Obtain the data from the achilles tables - sql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/raw/export_raw_achilles_results.sql", + sql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/raw/export_raw_achilles_results.sql", packageName = "Achilles", dbms = connectionDetails$dbms, warnOnMissingParameters = FALSE, results_database_schema = resultsDatabaseSchema, - min_cell_count = minCellCount, analysis_ids = analysisIds) + min_cell_count = minCellCount, analysis_ids = analysisIds + ) ParallelLogger::logInfo("Querying achilles_results") results <- DatabaseConnector::querySql(connection = connection, sql = sql) # Save the data to the export folder readr::write_csv(results, file.path(exportFolder, "achilles_results.csv")) } - diff --git a/R/exportToJson.R b/R/exportToJson.R index d463780e..d6193c71 100755 --- a/R/exportToJson.R +++ b/R/exportToJson.R @@ -1,15 +1,15 @@ # @file exportToJson # -# Copyright 2023 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles -# +# # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at -# +# # https://www.apache.org/licenses/LICENSE-2.0 -# +# # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. @@ -28,8 +28,10 @@ # When adding a new report, append it to inst/csv/export/all_reports.csv getAllReports <- function() { - reports <- read.csv(file = system.file("csv", "export", "all_reports.csv", package = "Achilles"), - stringsAsFactors = FALSE, header = TRUE)$REPORT + reports <- read.csv( + file = system.file("csv", "export", "all_reports.csv", package = "Achilles"), + stringsAsFactors = FALSE, header = TRUE + )$REPORT return(reports) } @@ -99,8 +101,10 @@ showReportTypes <- function() { #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportToJson(connectionDetails, cdmDatabaseSchema = "cdm4_sim", outputPath = "your/output/path") #' } #' @export @@ -108,12 +112,11 @@ exportToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - reports = getAllReports(), vocabDatabaseSchema = cdmDatabaseSchema, compressIntoOneFile = FALSE) { - + reports = getAllReports(), vocabDatabaseSchema = cdmDatabaseSchema, compressIntoOneFile = FALSE) { start <- Sys.time() - if (missing(resultsDatabaseSchema)) + if (missing(resultsDatabaseSchema)) { resultsDatabaseSchema <- cdmDatabaseSchema + } initOutputPath(outputPath) @@ -124,150 +127,190 @@ exportToJson <- function(connectionDetails, # generate reports if ("CONDITION" %in% reports) { - generateConditionTreemap(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) - generateConditionReports(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) + generateConditionTreemap( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateConditionReports( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } if ("CONDITION_ERA" %in% reports) { - generateConditionEraTreemap(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) - generateConditionEraReports(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) + generateConditionEraTreemap( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateConditionEraReports( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } - if ("DATA_DENSITY" %in% reports) - generateDataDensityReport(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) + if ("DATA_DENSITY" %in% reports) { + generateDataDensityReport( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + } if ("DEATH" %in% reports) { - generateDeathReports(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) + generateDeathReports( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } if ("DRUG_ERA" %in% reports) { - generateDrugEraTreemap(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) - generateDrugEraReports(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) + generateDrugEraTreemap( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateDrugEraReports( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } if ("DRUG" %in% reports) { - generateDrugTreemap(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - - vocabDatabaseSchema) - generateDrugReports(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - - vocabDatabaseSchema) + generateDrugTreemap( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + vocabDatabaseSchema + ) + generateDrugReports( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + vocabDatabaseSchema + ) } if (("META" %in% reports)) { - generateMetadataReport(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) - generateCdmSourceReport(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) + generateMetadataReport( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateCdmSourceReport( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } if (("MEASUREMENT" %in% reports)) { - generateMeasurementTreemap(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) - generateMeasurementReports(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) + generateMeasurementTreemap( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateMeasurementReports( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } if ("OBSERVATION" %in% reports) { - generateObservationTreemap(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) - generateObservationReports(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) + generateObservationTreemap( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateObservationReports( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } - if ("OBSERVATION_PERIOD" %in% reports) - generateObservationPeriodReport(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) + if ("OBSERVATION_PERIOD" %in% reports) { + generateObservationPeriodReport( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + } - if ("PERSON" %in% reports) - generatePersonReport(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) + if ("PERSON" %in% reports) { + generatePersonReport( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + } if ("PROCEDURE" %in% reports) { - generateProcedureTreemap(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) - generateProcedureReports(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) + generateProcedureTreemap( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateProcedureReports( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } if ("VISIT" %in% reports) { - generateVisitTreemap(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) - generateVisitReports(conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, - outputPath, vocabDatabaseSchema) + generateVisitTreemap( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateVisitReports( + conn, connectionDetails$dbms, cdmDatabaseSchema, resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } if ("VISIT_DETAIL" %in% reports) { - generateVisitDetailTreemap(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) - generateVisitDetailReports(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) + generateVisitDetailTreemap( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) + generateVisitDetailReports( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } if ("PERFORMANCE" %in% reports) { - generateAchillesPerformanceReport(conn, - connectionDetails$dbms, - cdmDatabaseSchema, - resultsDatabaseSchema, - - outputPath, vocabDatabaseSchema) + generateAchillesPerformanceReport( + conn, + connectionDetails$dbms, + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, vocabDatabaseSchema + ) } # dashboard is always last @@ -278,9 +321,13 @@ exportToJson <- function(connectionDetails, DatabaseConnector::disconnect(conn) if (compressIntoOneFile) { - zip(zipfile = file.path(outputPath, - sprintf("%s.zip", cdmDatabaseSchema)), files = c(outputPath), - flags = c("-r")) + zip( + zipfile = file.path( + outputPath, + sprintf("%s.zip", cdmDatabaseSchema) + ), files = c(outputPath), + flags = c("-r") + ) } delta <- Sys.time() - start @@ -314,26 +361,28 @@ exportToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportConditionToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportConditionToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("CONDITION"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("CONDITION"), + vocabDatabaseSchema + ) } #' @title @@ -362,26 +411,28 @@ exportConditionToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportConditionEraToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportConditionEraToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("CONDITION_ERA"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("CONDITION_ERA"), + vocabDatabaseSchema + ) } #' @title @@ -413,26 +464,28 @@ exportConditionEraToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportDashboardToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportDashboardToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("DASHBOARD"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("DASHBOARD"), + vocabDatabaseSchema + ) } #' @title @@ -462,26 +515,28 @@ exportDashboardToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportDataDensityToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportDataDensityToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("DATA_DENSITY"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("DATA_DENSITY"), + vocabDatabaseSchema + ) } #' @title @@ -511,26 +566,28 @@ exportDataDensityToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportDeathToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportDeathToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("DEATH"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("DEATH"), + vocabDatabaseSchema + ) } #' @title @@ -560,26 +617,28 @@ exportDeathToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportDrugToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportDrugToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("DRUG"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("DRUG"), + vocabDatabaseSchema + ) } #' @title @@ -609,26 +668,28 @@ exportDrugToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportDrugEraToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportDrugEraToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("DRUG_ERA"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("DRUG_ERA"), + vocabDatabaseSchema + ) } @@ -659,26 +720,28 @@ exportDrugEraToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportMetaToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportMetaToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("META"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("META"), + vocabDatabaseSchema + ) } #' @title @@ -708,26 +771,28 @@ exportMetaToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportMeasurementToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportMeasurementToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("MEASUREMENT"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("MEASUREMENT"), + vocabDatabaseSchema + ) } #' @title @@ -757,26 +822,28 @@ exportMeasurementToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportObservationToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportObservationToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("OBSERVATION"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("OBSERVATION"), + vocabDatabaseSchema + ) } #' @title @@ -807,11 +874,14 @@ exportObservationToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportObservationPeriodToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportObservationPeriodToJson <- function(connectionDetails, @@ -856,26 +926,28 @@ exportObservationPeriodToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportPersonToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportPersonToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("PERSON"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("PERSON"), + vocabDatabaseSchema + ) } #' @title @@ -905,26 +977,28 @@ exportPersonToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportProcedureToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportProcedureToJson <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { exportToJson(connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - outputPath, - reports = c("PROCEDURE"), - - vocabDatabaseSchema) + cdmDatabaseSchema, + resultsDatabaseSchema, + outputPath, + reports = c("PROCEDURE"), + vocabDatabaseSchema + ) } #' @title @@ -953,11 +1027,14 @@ exportProcedureToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportVisitToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportVisitToJson <- function(connectionDetails, @@ -971,7 +1048,6 @@ exportVisitToJson <- function(connectionDetails, resultsDatabaseSchema, outputPath, reports = c("VISIT"), - vocabDatabaseSchema ) } @@ -1003,11 +1079,14 @@ exportVisitToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportVisitDetailToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportVisitDetailToJson <- function(connectionDetails, @@ -1052,11 +1131,14 @@ exportVisitDetailToJson <- function(connectionDetails, #' none #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' exportPerformanceToJson(connectionDetails, -#' cdmDatabaseSchema = "cdm4_sim", -#' outputPath = "your/output/path") +#' cdmDatabaseSchema = "cdm4_sim", +#' outputPath = "your/output/path" +#' ) #' } #' @export exportPerformanceToJson <- function(connectionDetails, @@ -1070,7 +1152,6 @@ exportPerformanceToJson <- function(connectionDetails, resultsDatabaseSchema, outputPath, reports = c("PERFORMANCE"), - vocabDatabaseSchema ) } @@ -1081,29 +1162,33 @@ generateAchillesPerformanceReport <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating achilles performance report") output <- { } - queryAchillesPerformance <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/performance/sqlAchillesPerformance.sql", + queryAchillesPerformance <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/performance/sqlAchillesPerformance.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) output$MESSAGES <- DatabaseConnector::querySql(conn, queryAchillesPerformance) jsonOutput <- jsonlite::toJSON(output) write(jsonOutput, file = paste(outputPath, "/achillesperformance.json", sep = "")) } -generateMetadataReport <- function(conn, dbms, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - vocabDatabaseSchema = cdmDatabaseSchema) { +generateMetadataReport <- function( + conn, dbms, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating metadata report") output <- { } - queryMetadata <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/metadata/sqlMetadata.sql", - packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema) + queryMetadata <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/metadata/sqlMetadata.sql", + packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema + ) if ("METADATA" %in% DatabaseConnector::getTableNames(connection = conn, databaseSchema = cdmDatabaseSchema)) { output$MESSAGES <- DatabaseConnector::querySql(conn, queryMetadata) @@ -1119,14 +1204,15 @@ generateCdmSourceReport <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating cdm source report") output <- { } - queryCdmSource <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/metadata/sqlCdmSource.sql", - packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema) + queryCdmSource <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/metadata/sqlCdmSource.sql", + packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema + ) if ("CDM_SOURCE" %in% DatabaseConnector::getTableNames(connection = conn, databaseSchema = cdmDatabaseSchema)) { output$MESSAGES <- DatabaseConnector::querySql(conn, queryCdmSource) @@ -1137,20 +1223,24 @@ generateCdmSourceReport <- function(conn, } } -generateDrugEraTreemap <- function(conn, dbms, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - vocabDatabaseSchema = cdmDatabaseSchema) { +generateDrugEraTreemap <- function( + conn, dbms, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating drug era treemap") progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryDrugEraTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drugera/sqlDrugEraTreemap.sql", + queryDrugEraTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drugera/sqlDrugEraTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataDrugEraTreemap <- DatabaseConnector::querySql(conn, queryDrugEraTreemap) write(jsonlite::toJSON(dataDrugEraTreemap, method = "C"), paste(outputPath, "/drugera_treemap.json", - sep = "")) + sep = "" + )) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1167,14 +1257,18 @@ generateDrugTreemap <- function(conn, progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryDrugTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlDrugTreemap.sql", + queryDrugTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlDrugTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataDrugTreemap <- DatabaseConnector::querySql(conn, queryDrugTreemap) - write(jsonlite::toJSON(dataDrugTreemap, method = "C"), - paste(outputPath, "/drug_treemap.json", sep = "")) + write( + jsonlite::toJSON(dataDrugTreemap, method = "C"), + paste(outputPath, "/drug_treemap.json", sep = "") + ) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1186,21 +1280,25 @@ generateConditionTreemap <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating condition treemap") progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryConditionTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/condition/sqlConditionTreemap.sql", + queryConditionTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/condition/sqlConditionTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataConditionTreemap <- DatabaseConnector::querySql(conn, queryConditionTreemap) - write(jsonlite::toJSON(dataConditionTreemap, method = "C"), - paste(outputPath, "/condition_treemap.json", - sep = "")) + write( + jsonlite::toJSON(dataConditionTreemap, method = "C"), + paste(outputPath, "/condition_treemap.json", + sep = "" + ) + ) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1212,21 +1310,25 @@ generateConditionEraTreemap <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating condition era treemap") progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryConditionEraTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/conditionera/sqlConditionEraTreemap.sql", + queryConditionEraTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/conditionera/sqlConditionEraTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataConditionEraTreemap <- DatabaseConnector::querySql(conn, queryConditionEraTreemap) - write(jsonlite::toJSON(dataConditionEraTreemap, method = "C"), - paste(outputPath, "/conditionera_treemap.json", - sep = "")) + write( + jsonlite::toJSON(dataConditionEraTreemap, method = "C"), + paste(outputPath, "/conditionera_treemap.json", + sep = "" + ) + ) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1238,15 +1340,16 @@ generateConditionReports <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating condition reports") treemapFile <- file.path(outputPath, "condition_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -1260,27 +1363,34 @@ generateConditionReports <- function(conn, writeLines(paste("Warning: folder ", conditionsFolder, " already exists")) } else { dir.create(paste(conditionsFolder, "/", sep = "")) - } progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/condition/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/condition/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/condition/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/condition/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryConditionsByType <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/condition/sqlConditionsByType.sql", + queryConditionsByType <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/condition/sqlConditionsByType.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryAgeAtFirstDiagnosis <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/condition/sqlAgeAtFirstDiagnosis.sql", + queryAgeAtFirstDiagnosis <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/condition/sqlAgeAtFirstDiagnosis.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataPrevalenceByGenderAgeYear <- DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) dataPrevalenceByMonth <- DatabaseConnector::querySql(conn, queryPrevalenceByMonth) @@ -1293,8 +1403,10 @@ generateConditionReports <- function(conn, } report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(3, 4, 5, 6)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(3, 4)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(3, 4) + ] report$CONDITIONS_BY_TYPE <- dataConditionsByType[dataConditionsByType$CONDITION_CONCEPT_ID == concept_id, c(2, 3)] report$AGE_AT_FIRST_DIAGNOSIS <- dataAgeAtFirstDiagnosis[dataAgeAtFirstDiagnosis$CONCEPT_ID == @@ -1307,8 +1419,10 @@ generateConditionReports <- function(conn, env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildConditionReport) @@ -1322,15 +1436,16 @@ generateConditionEraReports <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating condition era reports") treemapFile <- file.path(outputPath, "conditionera_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -1343,27 +1458,34 @@ generateConditionEraReports <- function(conn, writeLines(paste("Warning: folder ", conditionsFolder, " already exists")) } else { dir.create(paste(conditionsFolder, "/", sep = "")) - } progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/conditionera/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/conditionera/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/conditionera/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/conditionera/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryAgeAtFirstDiagnosis <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/conditionera/sqlAgeAtFirstDiagnosis.sql", + queryAgeAtFirstDiagnosis <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/conditionera/sqlAgeAtFirstDiagnosis.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryLengthOfEra <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/conditionera/sqlLengthOfEra.sql", + queryLengthOfEra <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/conditionera/sqlLengthOfEra.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataPrevalenceByGenderAgeYear <- DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) dataPrevalenceByMonth <- DatabaseConnector::querySql(conn, queryPrevalenceByMonth) @@ -1376,10 +1498,14 @@ generateConditionEraReports <- function(conn, } report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(2, 3, 4, 5)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(2, 3)] - report$LENGTH_OF_ERA <- dataLengthOfEra[dataLengthOfEra$CONCEPT_ID == concept_id, c(2, 3, 4, - 5, 6, 7, 8, 9)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(2, 3) + ] + report$LENGTH_OF_ERA <- dataLengthOfEra[dataLengthOfEra$CONCEPT_ID == concept_id, c( + 2, 3, 4, + 5, 6, 7, 8, 9 + )] report$AGE_AT_FIRST_DIAGNOSIS <- dataAgeAtFirstDiagnosis[dataAgeAtFirstDiagnosis$CONCEPT_ID == concept_id, c(2, 3, 4, 5, 6, 7, 8, 9)] filename <- paste(outputPath, "/conditioneras/condition_", concept_id, ".json", sep = "") @@ -1390,8 +1516,10 @@ generateConditionEraReports <- function(conn, env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildConditionEraReport) @@ -1400,16 +1528,19 @@ generateConditionEraReports <- function(conn, close(progressBar) } -generateDrugEraReports <- function(conn, dbms, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - vocabDatabaseSchema = cdmDatabaseSchema) { +generateDrugEraReports <- function( + conn, dbms, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating drug era reports") treemapFile <- file.path(outputPath, "drugera_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -1428,21 +1559,29 @@ generateDrugEraReports <- function(conn, dbms, cdmDatabaseSchema, resultsDatabas progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryAgeAtFirstExposure <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drugera/sqlAgeAtFirstExposure.sql", + queryAgeAtFirstExposure <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drugera/sqlAgeAtFirstExposure.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drugera/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drugera/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drugera/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drugera/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryLengthOfEra <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drugera/sqlLengthOfEra.sql", + queryLengthOfEra <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drugera/sqlLengthOfEra.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataAgeAtFirstExposure <- DatabaseConnector::querySql(conn, queryAgeAtFirstExposure) dataPrevalenceByGenderAgeYear <- DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) @@ -1452,14 +1591,20 @@ generateDrugEraReports <- function(conn, dbms, cdmDatabaseSchema, resultsDatabas buildDrugEraReport <- function(concept_id) { report <- { } - report$AGE_AT_FIRST_EXPOSURE <- dataAgeAtFirstExposure[dataAgeAtFirstExposure$CONCEPT_ID == concept_id, - c(2, 3, 4, 5, 6, 7, 8, 9)] + report$AGE_AT_FIRST_EXPOSURE <- dataAgeAtFirstExposure[ + dataAgeAtFirstExposure$CONCEPT_ID == concept_id, + c(2, 3, 4, 5, 6, 7, 8, 9) + ] report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(2, 3, 4, 5)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(2, 3)] - report$LENGTH_OF_ERA <- dataLengthOfEra[dataLengthOfEra$CONCEPT_ID == concept_id, c(2, 3, 4, - 5, 6, 7, 8, 9)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(2, 3) + ] + report$LENGTH_OF_ERA <- dataLengthOfEra[dataLengthOfEra$CONCEPT_ID == concept_id, c( + 2, 3, 4, + 5, 6, 7, 8, 9 + )] filename <- paste(outputPath, "/drugeras/drug_", concept_id, ".json", sep = "") @@ -1469,8 +1614,10 @@ generateDrugEraReports <- function(conn, dbms, cdmDatabaseSchema, resultsDatabas env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildDrugEraReport) @@ -1489,9 +1636,11 @@ generateDrugReports <- function(conn, treemapFile <- file.path(outputPath, "drug_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -1509,37 +1658,53 @@ generateDrugReports <- function(conn, progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryAgeAtFirstExposure <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlAgeAtFirstExposure.sql", + queryAgeAtFirstExposure <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlAgeAtFirstExposure.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryDaysSupplyDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlDaysSupplyDistribution.sql", + queryDaysSupplyDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlDaysSupplyDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryDrugsByType <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlDrugsByType.sql", + queryDrugsByType <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlDrugsByType.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryDrugFrequencyDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlFrequencyDistribution.sql", + queryDrugFrequencyDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlFrequencyDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryQuantityDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlQuantityDistribution.sql", + queryQuantityDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlQuantityDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryRefillsDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/drug/sqlRefillsDistribution.sql", + queryRefillsDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/drug/sqlRefillsDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataAgeAtFirstExposure <- DatabaseConnector::querySql(conn, queryAgeAtFirstExposure) dataDaysSupplyDistribution <- DatabaseConnector::querySql(conn, queryDaysSupplyDistribution) @@ -1560,8 +1725,10 @@ generateDrugReports <- function(conn, report$DRUGS_BY_TYPE <- dataDrugsByType[dataDrugsByType$DRUG_CONCEPT_ID == concept_id, c(3, 4)] report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(3, 4, 5, 6)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(3, 4)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(3, 4) + ] report$DRUG_FREQUENCY_DISTRIBUTION <- dataDrugFrequencyDistribution[dataDrugFrequencyDistribution$CONCEPT_ID == concept_id, c(3, 4)] report$QUANTITY_DISTRIBUTION <- dataQuantityDistribution[dataQuantityDistribution$DRUG_CONCEPT_ID == @@ -1577,8 +1744,10 @@ generateDrugReports <- function(conn, env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildDrugReport) @@ -1592,21 +1761,25 @@ generateProcedureTreemap <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating procedure treemap") progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryProcedureTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/procedure/sqlProcedureTreemap.sql", + queryProcedureTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/procedure/sqlProcedureTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataProcedureTreemap <- DatabaseConnector::querySql(conn, queryProcedureTreemap) - write(jsonlite::toJSON(dataProcedureTreemap, method = "C"), - paste(outputPath, "/procedure_treemap.json", - sep = "")) + write( + jsonlite::toJSON(dataProcedureTreemap, method = "C"), + paste(outputPath, "/procedure_treemap.json", + sep = "" + ) + ) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1618,15 +1791,16 @@ generateProcedureReports <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating procedure reports") treemapFile <- file.path(outputPath, "procedure_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -1639,46 +1813,59 @@ generateProcedureReports <- function(conn, writeLines(paste("Warning: folder ", proceduresFolder, " already exists")) } else { dir.create(paste(proceduresFolder, "/", sep = "")) - } progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/procedure/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/procedure/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/procedure/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/procedure/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryProcedureFrequencyDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/procedure/sqlFrequencyDistribution.sql", + queryProcedureFrequencyDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/procedure/sqlFrequencyDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryProceduresByType <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/procedure/sqlProceduresByType.sql", + queryProceduresByType <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/procedure/sqlProceduresByType.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/procedure/sqlAgeAtFirstOccurrence.sql", + queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/procedure/sqlAgeAtFirstOccurrence.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataPrevalenceByGenderAgeYear <- DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) dataPrevalenceByMonth <- DatabaseConnector::querySql(conn, queryPrevalenceByMonth) dataProceduresByType <- DatabaseConnector::querySql(conn, queryProceduresByType) dataAgeAtFirstOccurrence <- DatabaseConnector::querySql(conn, queryAgeAtFirstOccurrence) - dataProcedureFrequencyDistribution <- DatabaseConnector::querySql(conn, - queryProcedureFrequencyDistribution) + dataProcedureFrequencyDistribution <- DatabaseConnector::querySql( + conn, + queryProcedureFrequencyDistribution + ) buildProcedureReport <- function(concept_id) { report <- { } report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(3, 4, 5, 6)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(3, 4)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(3, 4) + ] report$PROCEDURE_FREQUENCY_DISTRIBUTION <- dataProcedureFrequencyDistribution[dataProcedureFrequencyDistribution$CONCEPT_ID == concept_id, c(3, 4)] report$PROCEDURES_BY_TYPE <- dataProceduresByType[dataProceduresByType$PROCEDURE_CONCEPT_ID == @@ -1693,8 +1880,10 @@ generateProcedureReports <- function(conn, env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildProcedureReport) @@ -1717,11 +1906,12 @@ generatePersonReport <- function(conn, # 1. Title: Population a. Visualization: Table b.Row #1: CDM source name c.Row #2: # of persons - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/person/population.sql", - packageName = "Achilles", - + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/person/population.sql", + packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, results_database_schema = resultsDatabaseSchema, - vocab_database_schema = vocabDatabaseSchema) + vocab_database_schema = vocabDatabaseSchema + ) personSummaryData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -1731,11 +1921,12 @@ generatePersonReport <- function(conn, # 2. Title: Gender distribution a. Visualization: Pie b.Category: Gender c.Value: % of persons - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/person/gender.sql", - packageName = "Achilles", - + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/person/gender.sql", + packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, results_database_schema = resultsDatabaseSchema, - vocab_database_schema = vocabDatabaseSchema) + vocab_database_schema = vocabDatabaseSchema + ) genderData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1744,11 +1935,12 @@ generatePersonReport <- function(conn, # 3. Title: Race distribution a. Visualization: Pie b.Category: Race c.Value: % of persons - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/person/race.sql", - packageName = "Achilles", - + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/person/race.sql", + packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, results_database_schema = resultsDatabaseSchema, - vocab_database_schema = vocabDatabaseSchema) + vocab_database_schema = vocabDatabaseSchema + ) raceData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1758,11 +1950,12 @@ generatePersonReport <- function(conn, # 4. Title: Ethnicity distribution a. Visualization: Pie b.Category: Ethnicity c.Value: % of # persons - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/person/ethnicity.sql", - packageName = "Achilles", - + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/person/ethnicity.sql", + packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, results_database_schema = resultsDatabaseSchema, - vocab_database_schema = vocabDatabaseSchema) + vocab_database_schema = vocabDatabaseSchema + ) ethnicityData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1774,9 +1967,11 @@ generatePersonReport <- function(conn, birthYearHist <- { } - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/person/yearofbirth_stats.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/person/yearofbirth_stats.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) birthYearStats <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1784,11 +1979,13 @@ generatePersonReport <- function(conn, birthYearHist$MIN <- birthYearStats$MIN_VALUE birthYearHist$MAX <- birthYearStats$MAX_VALUE birthYearHist$INTERVAL_SIZE <- birthYearStats$INTERVAL_SIZE - birthYearHist$INTERVALS <- (birthYearStats$MAX_VALUE - birthYearStats$MIN_VALUE)/birthYearStats$INTERVAL_SIZE + birthYearHist$INTERVALS <- (birthYearStats$MAX_VALUE - birthYearStats$MIN_VALUE) / birthYearStats$INTERVAL_SIZE - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/person/yearofbirth_data.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/person/yearofbirth_data.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) birthYearData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1811,8 +2008,7 @@ generateObservationPeriodReport <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating observation period reports") progressBar <- utils::txtProgressBar(max = 11, style = 3) progress <- 0 @@ -1831,9 +2027,11 @@ generateObservationPeriodReport <- function(conn, ageAtFirstObservationHist$INTERVAL_SIZE <- 1 ageAtFirstObservationHist$INTERVALS <- 100 - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/ageatfirst.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/ageatfirst.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) ageAtFirstObservationData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1843,9 +2041,11 @@ generateObservationPeriodReport <- function(conn, # 2. Title: Age by gender a.Visualization: Side-by-side boxplot b.Category: Gender c.Values: # Min/25%/Median/95%/Max - age at time of first observation - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/agebygender.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/agebygender.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) ageByGenderData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1857,9 +2057,11 @@ generateObservationPeriodReport <- function(conn, observationLengthHist <- { } - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/observationlength_stats.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/observationlength_stats.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) observationLengthStats <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -1867,11 +2069,13 @@ generateObservationPeriodReport <- function(conn, observationLengthHist$MIN <- observationLengthStats$MIN_VALUE observationLengthHist$MAX <- observationLengthStats$MAX_VALUE observationLengthHist$INTERVAL_SIZE <- observationLengthStats$INTERVAL_SIZE - observationLengthHist$INTERVALS <- (observationLengthStats$MAX_VALUE - observationLengthStats$MIN_VALUE)/observationLengthStats$INTERVAL_SIZE + observationLengthHist$INTERVALS <- (observationLengthStats$MAX_VALUE - observationLengthStats$MIN_VALUE) / observationLengthStats$INTERVAL_SIZE - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/observationlength_data.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/observationlength_data.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) observationLengthData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1884,9 +2088,11 @@ generateObservationPeriodReport <- function(conn, # survival plot, but information is the same as shown in a length of observation barchart, just # plotted as cumulative - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/cumulativeduration.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/cumulativeduration.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) cumulativeDurationData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -1896,9 +2102,11 @@ generateObservationPeriodReport <- function(conn, # 5. Title: Observation period length distribution, by gender a.Visualization: side-by-side # boxplot b.Category: Gender c.Values: Min/25%/Median/95%/Max length of observation period - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/observationlengthbygender.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/observationlengthbygender.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) opLengthByGenderData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1907,9 +2115,11 @@ generateObservationPeriodReport <- function(conn, # 6. Title: Observation period length distribution, by age a.Visualization: side-by-side boxplot # b.Category: Age decile c.Values: Min/25%/Median/95%/Max length of observation period - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/observationlengthbyage.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/observationlengthbyage.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) opLengthByAgeData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1920,20 +2130,24 @@ generateObservationPeriodReport <- function(conn, observedByYearHist <- { } - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/observedbyyear_stats.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/observedbyyear_stats.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) observedByYearStats <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) observedByYearHist$MIN <- observedByYearStats$MIN_VALUE observedByYearHist$MAX <- observedByYearStats$MAX_VALUE observedByYearHist$INTERVAL_SIZE <- observedByYearStats$INTERVAL_SIZE - observedByYearHist$INTERVALS <- (observedByYearStats$MAX_VALUE - observedByYearStats$MIN_VALUE)/observedByYearStats$INTERVAL_SIZE + observedByYearHist$INTERVALS <- (observedByYearStats$MAX_VALUE - observedByYearStats$MIN_VALUE) / observedByYearStats$INTERVAL_SIZE - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/observedbyyear_data.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/observedbyyear_data.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) observedByYearData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -1948,9 +2162,11 @@ generateObservationPeriodReport <- function(conn, observedByMonth <- { } - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/observedbymonth.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/observedbymonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) observedByMonth <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -1960,9 +2176,11 @@ generateObservationPeriodReport <- function(conn, # 9. Title: Number of observation periods per person a.Visualization: Pie b.Category: Number of # observation periods c.Values: # of persons - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observationperiod/periodsperperson.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observationperiod/periodsperperson.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) personPeriodsData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -2014,8 +2232,7 @@ generateDataDensityReport <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating data density reports") progressBar <- utils::txtProgressBar(max = 3, style = 3) progress <- 0 @@ -2025,9 +2242,11 @@ generateDataDensityReport <- function(conn, # 1. Title: Total records a.Visualization: scatterplot b.X-axis: month/year c.y-axis: records # d.series: person, visit, condition, drug, procedure, observation - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/datadensity/totalrecords.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/datadensity/totalrecords.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) totalRecordsData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -2037,9 +2256,11 @@ generateDataDensityReport <- function(conn, # 2. Title: Records per person a.Visualization: scatterplot b.X-axis: month/year c.y-axis: # records/person d.series: person, visit, condition, drug, procedure, observation - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/datadensity/recordsperperson.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/datadensity/recordsperperson.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) recordsPerPerson <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -2050,9 +2271,11 @@ generateDataDensityReport <- function(conn, # Condition/Drug/Procedure/Observation c.Values: Min/25%/Median/95%/Max number of distinct # concepts per person - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/datadensity/conceptsperperson.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/datadensity/conceptsperperson.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) conceptsPerPerson <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -2063,7 +2286,6 @@ generateDataDensityReport <- function(conn, jsonOutput <- jsonlite::toJSON(output) write(jsonOutput, file = paste(outputPath, "/datadensity.json", sep = "")) close(progressBar) - } generateMeasurementTreemap <- function(conn, @@ -2071,26 +2293,29 @@ generateMeasurementTreemap <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating measurement treemap") progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryMeasurementTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlMeasurementTreemap.sql", + queryMeasurementTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlMeasurementTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataMeasurementTreemap <- DatabaseConnector::querySql(conn, queryMeasurementTreemap) - write(jsonlite::toJSON(dataMeasurementTreemap, method = "C"), - paste(outputPath, "/measurement_treemap.json", - sep = "")) + write( + jsonlite::toJSON(dataMeasurementTreemap, method = "C"), + paste(outputPath, "/measurement_treemap.json", + sep = "" + ) + ) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) close(progressBar) - } generateMeasurementReports <- function(conn, @@ -2098,15 +2323,16 @@ generateMeasurementReports <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating Measurement reports") treemapFile <- file.path(outputPath, "measurement_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -2119,59 +2345,80 @@ generateMeasurementReports <- function(conn, writeLines(paste("Warning: folder ", measurementsFolder, " already exists")) } else { dir.create(paste(measurementsFolder, "/", sep = "")) - } progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryFrequencyDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlFrequencyDistribution.sql", + queryFrequencyDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlFrequencyDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryMeasurementsByType <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlMeasurementsByType.sql", + queryMeasurementsByType <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlMeasurementsByType.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlAgeAtFirstOccurrence.sql", + queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlAgeAtFirstOccurrence.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryRecordsByUnit <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlRecordsByUnit.sql", + queryRecordsByUnit <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlRecordsByUnit.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryMeasurementValueDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlMeasurementValueDistribution.sql", + queryMeasurementValueDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlMeasurementValueDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryLowerLimitDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlLowerLimitDistribution.sql", + queryLowerLimitDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlLowerLimitDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryUpperLimitDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlUpperLimitDistribution.sql", + queryUpperLimitDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlUpperLimitDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryValuesRelativeToNorm <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/measurement/sqlValuesRelativeToNorm.sql", + queryValuesRelativeToNorm <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/measurement/sqlValuesRelativeToNorm.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataPrevalenceByGenderAgeYear <- DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) dataPrevalenceByMonth <- DatabaseConnector::querySql(conn, queryPrevalenceByMonth) dataMeasurementsByType <- DatabaseConnector::querySql(conn, queryMeasurementsByType) dataAgeAtFirstOccurrence <- DatabaseConnector::querySql(conn, queryAgeAtFirstOccurrence) dataRecordsByUnit <- DatabaseConnector::querySql(conn, queryRecordsByUnit) - dataMeasurementValueDistribution <- DatabaseConnector::querySql(conn, - queryMeasurementValueDistribution) + dataMeasurementValueDistribution <- DatabaseConnector::querySql( + conn, + queryMeasurementValueDistribution + ) dataLowerLimitDistribution <- DatabaseConnector::querySql(conn, queryLowerLimitDistribution) dataUpperLimitDistribution <- DatabaseConnector::querySql(conn, queryUpperLimitDistribution) dataValuesRelativeToNorm <- DatabaseConnector::querySql(conn, queryValuesRelativeToNorm) @@ -2182,8 +2429,10 @@ generateMeasurementReports <- function(conn, } report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(3, 4, 5, 6)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(3, 4)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(3, 4) + ] report$FREQUENCY_DISTRIBUTION <- dataFrequencyDistribution[dataFrequencyDistribution$CONCEPT_ID == concept_id, c(3, 4)] report$MEASUREMENTS_BY_TYPE <- dataMeasurementsByType[dataMeasurementsByType$MEASUREMENT_CONCEPT_ID == @@ -2191,8 +2440,10 @@ generateMeasurementReports <- function(conn, report$AGE_AT_FIRST_OCCURRENCE <- dataAgeAtFirstOccurrence[dataAgeAtFirstOccurrence$CONCEPT_ID == concept_id, c(2, 3, 4, 5, 6, 7, 8, 9)] - report$RECORDS_BY_UNIT <- dataRecordsByUnit[dataRecordsByUnit$MEASUREMENT_CONCEPT_ID == concept_id, - c(4, 5)] + report$RECORDS_BY_UNIT <- dataRecordsByUnit[ + dataRecordsByUnit$MEASUREMENT_CONCEPT_ID == concept_id, + c(4, 5) + ] report$MEASUREMENT_VALUE_DISTRIBUTION <- dataMeasurementValueDistribution[dataMeasurementValueDistribution$CONCEPT_ID == concept_id, c(2, 3, 4, 5, 6, 7, 8, 9)] report$LOWER_LIMIT_DISTRIBUTION <- dataLowerLimitDistribution[dataLowerLimitDistribution$CONCEPT_ID == @@ -2210,15 +2461,16 @@ generateMeasurementReports <- function(conn, env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildMeasurementReport) utils::setTxtProgressBar(progressBar, 1) close(progressBar) - } generateObservationTreemap <- function(conn, @@ -2226,26 +2478,29 @@ generateObservationTreemap <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating observation treemap") progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryObservationTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observation/sqlObservationTreemap.sql", + queryObservationTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observation/sqlObservationTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataObservationTreemap <- DatabaseConnector::querySql(conn, queryObservationTreemap) - write(jsonlite::toJSON(dataObservationTreemap, method = "C"), - paste(outputPath, "/observation_treemap.json", - sep = "")) + write( + jsonlite::toJSON(dataObservationTreemap, method = "C"), + paste(outputPath, "/observation_treemap.json", + sep = "" + ) + ) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) close(progressBar) - } generateObservationReports <- function(conn, @@ -2253,15 +2508,16 @@ generateObservationReports <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating Observation reports") treemapFile <- file.path(outputPath, "observation_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -2274,31 +2530,40 @@ generateObservationReports <- function(conn, writeLines(paste("Warning: folder ", observationsFolder, " already exists")) } else { dir.create(paste(observationsFolder, "/", sep = "")) - } progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observation/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observation/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observation/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observation/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryObsFrequencyDistribution <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observation/sqlFrequencyDistribution.sql", + queryObsFrequencyDistribution <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observation/sqlFrequencyDistribution.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryObservationsByType <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observation/sqlObservationsByType.sql", + queryObservationsByType <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observation/sqlObservationsByType.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/observation/sqlAgeAtFirstOccurrence.sql", + queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/observation/sqlAgeAtFirstOccurrence.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataPrevalenceByGenderAgeYear <- DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) @@ -2313,8 +2578,10 @@ generateObservationReports <- function(conn, } report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(3, 4, 5, 6)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(3, 4)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(3, 4) + ] report$OBS_FREQUENCY_DISTRIBUTION <- dataObsFrequencyDistribution[dataObsFrequencyDistribution$CONCEPT_ID == concept_id, c(3, 4)] report$OBSERVATIONS_BY_TYPE <- dataObservationsByType[dataObservationsByType$OBSERVATION_CONCEPT_ID == @@ -2331,15 +2598,16 @@ generateObservationReports <- function(conn, env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildObservationReport) utils::setTxtProgressBar(progressBar, 1) close(progressBar) - } generateVisitTreemap <- function(conn, @@ -2352,14 +2620,18 @@ generateVisitTreemap <- function(conn, progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryVisitTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visit/sqlVisitTreemap.sql", + queryVisitTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visit/sqlVisitTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataVisitTreemap <- DatabaseConnector::querySql(conn, queryVisitTreemap) - write(jsonlite::toJSON(dataVisitTreemap, method = "C"), - paste(outputPath, "/visit_treemap.json", sep = "")) + write( + jsonlite::toJSON(dataVisitTreemap, method = "C"), + paste(outputPath, "/visit_treemap.json", sep = "") + ) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -2376,9 +2648,11 @@ generateVisitReports <- function(conn, treemapFile <- file.path(outputPath, "visit_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -2391,27 +2665,34 @@ generateVisitReports <- function(conn, writeLines(paste("Warning: folder ", visitsFolder, " already exists")) } else { dir.create(paste(visitsFolder, "/", sep = "")) - } progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visit/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visit/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visit/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visit/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryVisitDurationByType <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visit/sqlVisitDurationByType.sql", + queryVisitDurationByType <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visit/sqlVisitDurationByType.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visit/sqlAgeAtFirstOccurrence.sql", + queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visit/sqlAgeAtFirstOccurrence.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataPrevalenceByGenderAgeYear <- DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) dataPrevalenceByMonth <- DatabaseConnector::querySql(conn, queryPrevalenceByMonth) @@ -2423,8 +2704,10 @@ generateVisitReports <- function(conn, } report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(3, 4, 5, 6)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(3, 4)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(3, 4) + ] report$VISIT_DURATION_BY_TYPE <- dataVisitDurationByType[dataVisitDurationByType$CONCEPT_ID == concept_id, c(2, 3, 4, 5, 6, 7, 8, 9)] report$AGE_AT_FIRST_OCCURRENCE <- dataAgeAtFirstOccurrence[dataAgeAtFirstOccurrence$CONCEPT_ID == @@ -2437,8 +2720,10 @@ generateVisitReports <- function(conn, env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildVisitReport) @@ -2463,9 +2748,11 @@ generateDeathReports <- function(conn, # lineplot b.Trellis category: age decile c.X-axis: year d.y-axis: condition prevalence (% # persons) e.series: male, female - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/death/sqlPrevalenceByGenderAgeYear.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/death/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) prevalenceByGenderAgeYearData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -2475,9 +2762,11 @@ generateDeathReports <- function(conn, # 2. Title: Prevalence by month a.Visualization: scatterplot b.X-axis: month/year c.y-axis: % of # persons d.Comment: plot to show seasonality - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/death/sqlPrevalenceByMonth.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/death/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) prevalenceByMonthData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -2487,9 +2776,11 @@ generateDeathReports <- function(conn, # 3. Title: Death records by type a.Visualization: pie b.Category: death type c.value: % of # records - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/death/sqlDeathByType.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/death/sqlDeathByType.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) deathByTypeData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -2499,9 +2790,11 @@ generateDeathReports <- function(conn, # 4. Title: Age at death a.Visualization: side-by-side boxplot b.Category: gender c.Values: # Min/25%/Median/95%/Max as age at death - renderedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/death/sqlAgeAtDeath.sql", + renderedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/death/sqlAgeAtDeath.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) ageAtDeathData <- DatabaseConnector::querySql(conn, renderedSql) progress <- progress + 1 @@ -2519,21 +2812,25 @@ generateVisitDetailTreemap <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating visit_detail treemap") progressBar <- utils::txtProgressBar(max = 1, style = 3) progress <- 0 - queryVisitDetailTreemap <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visitdetail/sqlVisitDetailTreemap.sql", + queryVisitDetailTreemap <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visitdetail/sqlVisitDetailTreemap.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataVisitDetailTreemap <- DatabaseConnector::querySql(conn, queryVisitDetailTreemap) - write(jsonlite::toJSON(dataVisitDetailTreemap, method = "C"), - paste(outputPath, "/visitdetail_treemap.json", - sep = "")) + write( + jsonlite::toJSON(dataVisitDetailTreemap, method = "C"), + paste(outputPath, "/visitdetail_treemap.json", + sep = "" + ) + ) progress <- progress + 1 utils::setTxtProgressBar(progressBar, progress) @@ -2545,15 +2842,16 @@ generateVisitDetailReports <- function(conn, cdmDatabaseSchema, resultsDatabaseSchema, outputPath, - - vocabDatabaseSchema = cdmDatabaseSchema) { + vocabDatabaseSchema = cdmDatabaseSchema) { writeLines("Generating visit_detail reports") treemapFile <- file.path(outputPath, "visitdetail_treemap.json") if (!file.exists(treemapFile)) { - writeLines(paste("Warning: treemap file", - treemapFile, - "does not exist. Skipping detail report generation.")) + writeLines(paste( + "Warning: treemap file", + treemapFile, + "does not exist. Skipping detail report generation." + )) return() } @@ -2566,27 +2864,34 @@ generateVisitDetailReports <- function(conn, writeLines(paste("Warning: folder ", visitdetailFolder, " already exists")) } else { dir.create(paste(visitdetailFolder, "/", sep = "")) - } progressBar <- utils::txtProgressBar(style = 3) progress <- 0 - queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visitdetail/sqlPrevalenceByGenderAgeYear.sql", + queryPrevalenceByGenderAgeYear <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visitdetail/sqlPrevalenceByGenderAgeYear.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visitdetail/sqlPrevalenceByMonth.sql", + queryPrevalenceByMonth <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visitdetail/sqlPrevalenceByMonth.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryVisitDetailDurationByType <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visitdetail/sqlVisitDetailDurationByType.sql", + queryVisitDetailDurationByType <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visitdetail/sqlVisitDetailDurationByType.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) - queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql(sqlFilename = "export/visitdetail/sqlAgeAtFirstOccurrence.sql", + queryAgeAtFirstOccurrence <- SqlRender::loadRenderTranslateSql( + sqlFilename = "export/visitdetail/sqlAgeAtFirstOccurrence.sql", packageName = "Achilles", dbms = dbms, warnOnMissingParameters = FALSE, cdm_database_schema = cdmDatabaseSchema, - results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema) + results_database_schema = resultsDatabaseSchema, vocab_database_schema = vocabDatabaseSchema + ) dataPrevalenceByGenderAgeYear <- DatabaseConnector::querySql(conn, queryPrevalenceByGenderAgeYear) dataPrevalenceByMonth <- DatabaseConnector::querySql(conn, queryPrevalenceByMonth) @@ -2598,8 +2903,10 @@ generateVisitDetailReports <- function(conn, } report$PREVALENCE_BY_GENDER_AGE_YEAR <- dataPrevalenceByGenderAgeYear[dataPrevalenceByGenderAgeYear$CONCEPT_ID == concept_id, c(3, 4, 5, 6)] - report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[dataPrevalenceByMonth$CONCEPT_ID == concept_id, - c(3, 4)] + report$PREVALENCE_BY_MONTH <- dataPrevalenceByMonth[ + dataPrevalenceByMonth$CONCEPT_ID == concept_id, + c(3, 4) + ] report$VISIT_DETAIL_DURATION_BY_TYPE <- dataVisitDetailDurationByType[dataVisitDetailDurationByType$CONCEPT_ID == concept_id, c(2, 3, 4, 5, 6, 7, 8, 9)] report$AGE_AT_FIRST_OCCURRENCE <- dataAgeAtFirstOccurrence[dataAgeAtFirstOccurrence$CONCEPT_ID == @@ -2612,8 +2919,10 @@ generateVisitDetailReports <- function(conn, env <- parent.env(environment()) curVal <- get("progress", envir = env) assign("progress", curVal + 1, envir = env) - utils::setTxtProgressBar(get("progressBar", envir = env), - (curVal + 1)/get("totalCount", envir = env)) + utils::setTxtProgressBar( + get("progressBar", envir = env), + (curVal + 1) / get("totalCount", envir = env) + ) } dummy <- lapply(uniqueConcepts, buildVisitDetailReport) @@ -2621,4 +2930,3 @@ generateVisitDetailReports <- function(conn, utils::setTxtProgressBar(progressBar, 1) close(progressBar) } - diff --git a/R/generateDbSummary.R b/R/generateDbSummary.R index 859b4d35..4da824a1 100644 --- a/R/generateDbSummary.R +++ b/R/generateDbSummary.R @@ -1,15 +1,15 @@ # @file generateDbSummary # -# Copyright 2021 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles -# +# # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at -# +# # https://www.apache.org/licenses/LICENSE-2.0 -# +# # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. @@ -21,7 +21,7 @@ #' generateDbSummary #' #' @description -#' \code{generateDbSummary} can be run after the Achilles analyses are complete +#' \code{generateDbSummary} can be run after the Achilles analyses are complete #' to create a high-level database summary. #' #' @details @@ -48,24 +48,26 @@ #' #' @examples #' \dontrun{ -#' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", -#' server = "yourserver") +#' connectionDetails <- DatabaseConnector::createConnectionDetails( +#' dbms = "sql server", +#' server = "yourserver" +#' ) #' dbSummary <- generateDbSummary(connectionDetails, -#' cdmDatabaseSchema = "cdm_schema", -#' resultsDatabaseSchema = "results_schema", -#' country = "Country of Origin", -#' provenance = "Provenance of data") +#' cdmDatabaseSchema = "cdm_schema", +#' resultsDatabaseSchema = "results_schema", +#' country = "Country of Origin", +#' provenance = "Provenance of data" +#' ) #' } #' @export -generateDbSummary <- function (connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - country, - provenance){ - +generateDbSummary <- function(connectionDetails, + cdmDatabaseSchema, + resultsDatabaseSchema, + country, + provenance) { conn <- DatabaseConnector::connect(connectionDetails) - + sql <- SqlRender::loadRenderTranslateSql( sqlFilename = "summary/generateDbSummary.sql", @@ -77,9 +79,9 @@ generateDbSummary <- function (connectionDetails, country = country, provenance = provenance ) - + dbSummary <- DatabaseConnector::querySql(conn, sql) - + sql <- SqlRender::loadRenderTranslateSql( sqlFilename = "summary/dbSourceVocabs.sql", @@ -91,9 +93,9 @@ generateDbSummary <- function (connectionDetails, country = country, provenance = provenance ) - + dbSourceVocabs <- DatabaseConnector::querySql(conn, sql) - + sql <- SqlRender::loadRenderTranslateSql( sqlFilename = "summary/dbVisitDist.sql", @@ -105,20 +107,20 @@ generateDbSummary <- function (connectionDetails, country = country, provenance = provenance ) - + dbVisitDist <- DatabaseConnector::querySql(conn, sql) - + DatabaseConnector::dbDisconnect(conn) # extract columns and pivot - dbInfo <- dbSummary[1,c(1,2,3,4)] + dbInfo <- dbSummary[1, c(1, 2, 3, 4)] row.names(dbSummary) <- dbSummary$ATTRIBUTE_NAME - df <- dbSummary[,c('ATTRIBUTE_VALUE')] + df <- dbSummary[, c("ATTRIBUTE_VALUE")] df_t <- t(df) colnames(df_t) <- rownames(dbSummary) dbSummaryFinal <- cbind(dbInfo, df_t) - + colnames(dbSummaryFinal)[1:4] <- c("Data Source Name", "Data Source Abbreviation", "Source Country", "Data Provenance") - - return(list(summary=dbSummaryFinal, visitDist=dbVisitDist, sourceVocabs = dbSourceVocabs)) -} \ No newline at end of file + + return(list(summary = dbSummaryFinal, visitDist = dbVisitDist, sourceVocabs = dbSourceVocabs)) +} diff --git a/R/generateDomainOverlapSql.R b/R/generateDomainOverlapSql.R index 23e1f43f..2b690f63 100644 --- a/R/generateDomainOverlapSql.R +++ b/R/generateDomainOverlapSql.R @@ -7,21 +7,26 @@ generateDomainOverlapSql <- function() { # creates a matrix of domain overlap possibilities. If you want to add a domain, you would add # to the list directly below. - domainMatrix <- tidyr::crossing(condition_occurrence = 0:1, - drug_exposure = 0:1, - device_exposure = 0:1, - - measurement = 0:1, death = 0:1, procedure_occurrence = 0:1, observation = 0:1) + domainMatrix <- tidyr::crossing( + condition_occurrence = 0:1, + drug_exposure = 0:1, + device_exposure = 0:1, + measurement = 0:1, death = 0:1, procedure_occurrence = 0:1, observation = 0:1 + ) domainMatrixResults <- domainMatrix domainMatrixResults <- domainMatrixResults %>% mutate(count = 0, proportion = 0, dataSource = "") # Creates notes - write(x = "-- Analysis 2004: Number of distinct patients that overlap between specific domains", - sqlFile, append = TRUE) - write(x = "-- Bit String Breakdown: 1) Condition Occurrence 2) Drug Exposure 3) Device Exposure 4) Measurement 5) Death 6) Procedure Occurrence 7) Observation", - sqlFile, append = TRUE) + write( + x = "-- Analysis 2004: Number of distinct patients that overlap between specific domains", + sqlFile, append = TRUE + ) + write( + x = "-- Bit String Breakdown: 1) Condition Occurrence 2) Drug Exposure 3) Device Exposure 4) Measurement 5) Death 6) Procedure Occurrence 7) Observation", + sqlFile, append = TRUE + ) write(x = "", sqlFile, append = TRUE) # Creates temp tables for each specific domain @@ -29,7 +34,7 @@ generateDomainOverlapSql <- function() { write(x = "select distinct person_id into #drexp from @cdmDatabaseSchema.drug_exposure;", sqlFile, append = TRUE) write(x = "select distinct person_id into #dvexp from @cdmDatabaseSchema.device_exposure;", sqlFile, append = TRUE) write(x = "select distinct person_id into #msmt from @cdmDatabaseSchema.measurement;", sqlFile, append = TRUE) - write(x = "select distinct person_id into #death from @cdmDatabaseSchema.death;", sqlFile,append = TRUE) + write(x = "select distinct person_id into #death from @cdmDatabaseSchema.death;", sqlFile, append = TRUE) write(x = "select distinct person_id into #prococ from @cdmDatabaseSchema.procedure_occurrence;", sqlFile, append = TRUE) write(x = "select distinct person_id into #obs from @cdmDatabaseSchema.observation;", sqlFile, append = TRUE) write(x = "", sqlFile, append = TRUE) @@ -121,8 +126,7 @@ generateDomainOverlapSql <- function() { sql <- paste0(sql, " intersect select person_id from #obs") } } - - } # End for loop for domainMatrix by column + } # End for loop for domainMatrix by column sql <- paste0(sql, ")") @@ -155,10 +159,9 @@ generateDomainOverlapSql <- function() { } else { write(x = sql, sqlFile, append = TRUE) } + } # End for loop for domainMatrix by row + - } # End for loop for domainMatrix by row - - # clean up temp tables # Creates temp tables for each specific domain write(x = "drop table #conoc;", sqlFile, append = TRUE) @@ -168,5 +171,5 @@ generateDomainOverlapSql <- function() { write(x = "drop table #death;", sqlFile, append = TRUE) write(x = "drop table #prococ;", sqlFile, append = TRUE) write(x = "drop table #obs;", sqlFile, append = TRUE) - write(x = "", sqlFile, append = TRUE) -} # End function + write(x = "", sqlFile, append = TRUE) +} # End function diff --git a/R/getSeasonalityScore.r b/R/getSeasonalityScore.r index 37cb9461..ed1d2f9c 100644 --- a/R/getSeasonalityScore.r +++ b/R/getSeasonalityScore.r @@ -1,41 +1,40 @@ -#'@title Get the seasonality score for a given monthly time series +#' @title Get the seasonality score for a given monthly time series #' -#'@description The seasonality score of a monthly time series is computed as its departure from a uniform distribution. +#' @description The seasonality score of a monthly time series is computed as its departure from a uniform distribution. #' -#'@details +#' @details #' The degree of seasonality of a monthly time series is based on its departure from a uniform distribution. -#' If the number of cases for a given concept is uniformly distributed across all time periods (in this case, all months), +#' If the number of cases for a given concept is uniformly distributed across all time periods (in this case, all months), #' then its monthly proportion would be approximately constant. In this case, the time series would be #' considered "strictly non-seasonal" and its "seasonality score" would be zero. #' Similarly, if all cases recur at a single point in time (that is, in a single month), such a time series would be considered #' "strictly seasonal" and its seasonality score would be 1. All other time series would have #' a seasonality score between 0 and 1. Currently, only monthly time series are supported. -#' -#'@param tsData A time series object. #' -#'@return A numeric value between 0 and 1 (inclusive) representing the seasonality of a time series. +#' @param tsData A time series object. #' -#'@export +#' @return A numeric value between 0 and 1 (inclusive) representing the seasonality of a time series. +#' +#' @export + +getSeasonalityScore <- function(tsData) { + unifDist <- 1 / 12 + a <- c(1, rep(0, 11)) + maxDist <- sum(abs(a - unifDist)) + + tsObj <- tsData + tsObj <- Achilles::tsCompleteYears(tsObj) -getSeasonalityScore <- function(tsData) -{ - unifDist <- 1/12 - a <- c(1,rep(0,11)) - maxDist <- sum(abs(a-unifDist)) - - tsObj <- tsData - tsObj <- Achilles::tsCompleteYears(tsObj) - - # Matrix version: switch to and update this version once the rare-events issue is corrected - # NB: Remember to avoid dividing by zero with the matrix approach - # M <- matrix(data=tsObj, ncol=12, byrow=TRUE) - # ss <- sum(abs(t((rep(1,dim(M)[1]) %*% M)/as.integer(rep(1,dim(M)[1]) %*% M %*% rep(1,12))) - unifDist))/maxDist + # Matrix version: switch to and update this version once the rare-events issue is corrected + # NB: Remember to avoid dividing by zero with the matrix approach + # M <- matrix(data=tsObj, ncol=12, byrow=TRUE) + # ss <- sum(abs(t((rep(1,dim(M)[1]) %*% M)/as.integer(rep(1,dim(M)[1]) %*% M %*% rep(1,12))) - unifDist))/maxDist - # Original version using sum across years - tsObj.yrProp <- Achilles::sumAcrossYears(tsObj)$PROP - tsObj.ss <- round(sum(abs(tsObj.yrProp-unifDist))/maxDist,2) + # Original version using sum across years + tsObj.yrProp <- Achilles::sumAcrossYears(tsObj)$PROP + tsObj.ss <- round(sum(abs(tsObj.yrProp - unifDist)) / maxDist, 2) - tsObj.ss <- round(tsObj.ss,2) + tsObj.ss <- round(tsObj.ss, 2) - return (tsObj.ss) -} \ No newline at end of file + return(tsObj.ss) +} diff --git a/R/getTemporalData.r b/R/getTemporalData.r index 6bf418c2..95e802c2 100644 --- a/R/getTemporalData.r +++ b/R/getTemporalData.r @@ -1,6 +1,6 @@ # @file getTemporalData # -# Copyright 2023 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles # @@ -61,12 +61,14 @@ #' @examples #' \dontrun{ #' pneumonia <- 255848 -#' monthlyResults <- getTemporalData(connectionDetails = connectionDetails, -#' cdmDatabaseSchema = "cdm", -#' -#' resultsDatabaseSchema = "results", conceptId = pneumonia) +#' monthlyResults <- getTemporalData( +#' connectionDetails = connectionDetails, +#' cdmDatabaseSchema = "cdm", +#' resultsDatabaseSchema = "results", conceptId = pneumonia +#' ) #' } #' +#' @importFrom dplyr rename_with #' @export @@ -74,17 +76,21 @@ getTemporalData <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, analysisIds = NULL, - - conceptId = NULL) { + conceptId = NULL) { if (!is.null(conceptId)) { - print(paste0("Retrieving Achilles monthly data for temporal support for concept_id: ", - conceptId)) + print(paste0( + "Retrieving Achilles monthly data for temporal support for concept_id: ", + conceptId + )) conceptIdGiven <- TRUE analysisIdGiven <- FALSE } else if (!is.null(analysisIds)) { - print(paste0("Retrieving Achilles monthly data for temporal support for analyses: ", - paste(analysisIds, - collapse = ", "))) + print(paste0( + "Retrieving Achilles monthly data for temporal support for analyses: ", + paste(analysisIds, + collapse = ", " + ) + )) conceptIdGiven <- FALSE analysisIdGiven <- TRUE } else { @@ -101,17 +107,18 @@ getTemporalData <- function(connectionDetails, dbName <- NA } - translatedSql <- SqlRender::loadRenderTranslateSql(sqlFilename = "temporal/achilles_temporal_data.sql", + translatedSql <- SqlRender::loadRenderTranslateSql( + sqlFilename = "temporal/achilles_temporal_data.sql", packageName = "Achilles", dbms = connectionDetails$dbms, db_name = dbName, cdm_schema = cdmDatabaseSchema, results_schema = resultsDatabaseSchema, concept_id = conceptId, analysis_ids = analysisIds, concept_id_given = conceptIdGiven, - analysis_id_given = analysisIdGiven) + analysis_id_given = analysisIdGiven + ) conn <- DatabaseConnector::connect(connectionDetails) - queryResults <- DatabaseConnector::querySql(conn, translatedSql) + queryResults <- DatabaseConnector::querySql(conn, translatedSql) |> dplyr::rename_with(toupper) on.exit(DatabaseConnector::disconnect(conn)) return(queryResults) - } diff --git a/R/isStationary.r b/R/isStationary.r index 240609e4..0afe5c48 100644 --- a/R/isStationary.r +++ b/R/isStationary.r @@ -1,29 +1,29 @@ -#'@title Determine whether or not a time series is stationary in the mean +#' @title Determine whether or not a time series is stationary in the mean #' -#'@description Uses the Augmented Dickey-Fuller test to determine when the time series has a unit root. +#' @description Uses the Augmented Dickey-Fuller test to determine when the time series has a unit root. #' -#'@details +#' @details #' A time series must have a minimum of three complete years of data. -#' For details on the implementation of the Augmented Dickey-Fuller test, +#' For details on the implementation of the Augmented Dickey-Fuller test, #' see the tseries package on cran. #' -#'@param tsData A time series object. +#' @param tsData A time series object. #' -#'@return A boolean indicating whether or not the given time series is stationary. +#' @return A boolean indicating whether or not the given time series is stationary. #' -#'@export +#' @export -isStationary <- function(tsData) -{ - tsObj <- tsData - minMonths <- 36 +isStationary <- function(tsData) { + tsObj <- tsData + minMonths <- 36 - tsObj <- Achilles::tsCompleteYears(tsObj) + tsObj <- Achilles::tsCompleteYears(tsObj) - if (length(tsObj) < minMonths) - stop("ERROR: Time series must have a minimum of three complete years of data") - - ADF_IS_STATIONARY <- suppressWarnings(tseries::adf.test(tsObj, alternative="stationary")$p.value <= .05) + if (length(tsObj) < minMonths) { + stop("ERROR: Time series must have a minimum of three complete years of data") + } - return (ADF_IS_STATIONARY) -} \ No newline at end of file + ADF_IS_STATIONARY <- suppressWarnings(tseries::adf.test(tsObj, alternative = "stationary")$p.value <= .05) + + return(ADF_IS_STATIONARY) +} diff --git a/R/listMissingAnalyses.r b/R/listMissingAnalyses.r index becbb39f..b1156dce 100644 --- a/R/listMissingAnalyses.r +++ b/R/listMissingAnalyses.r @@ -1,6 +1,6 @@ # @file listMissingAnalyses # -# Copyright 2023 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles # @@ -44,14 +44,15 @@ #' #' @examples #' \dontrun{ -#' Achilles::listMissingAnalyses(connectionDetails = connectionDetails, -#' resultsDatabaseSchema = "results") +#' Achilles::listMissingAnalyses( +#' connectionDetails = connectionDetails, +#' resultsDatabaseSchema = "results" +#' ) #' } #' #' @export listMissingAnalyses <- function(connectionDetails, resultsDatabaseSchema) { - # Determine which analyses are missing by comparing analysisDetails with achilles_results and # achilles_results_dist analysisDetails <- getAnalysisDetails() @@ -73,7 +74,7 @@ listMissingAnalyses <- function(connectionDetails, resultsDatabaseSchema) { missingAnalysisIds <- setdiff(allAnalysisIds, existingAnalysisIds) - colsToDisplay <- c("analysis_id","distribution","category","is_default","analysis_name") + colsToDisplay <- c("analysis_id", "distribution", "category", "is_default", "analysis_name") retVal <- analysisDetails[analysisDetails$analysis_id %in% missingAnalysisIds, colsToDisplay] retVal <- retVal[order(retVal$analysis_id), ] diff --git a/R/performTemporalCharacterization.r b/R/performTemporalCharacterization.r index 026ca568..4859c85f 100644 --- a/R/performTemporalCharacterization.r +++ b/R/performTemporalCharacterization.r @@ -1,6 +1,6 @@ # @file performTemporalCharacterization # -# Copyright 2023 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles # @@ -26,7 +26,7 @@ # @author Taha Abdul-Basser # @author Anthony Molinaro -#'@title performTemporalCharacterization +#' @title performTemporalCharacterization #' #' @description #' \code{performTemporalCharacterization} Perform temporal characterization on a concept or family of concepts belonging to a supported Achilles analysis. @@ -54,7 +54,7 @@ #' Server, 'cdm_results.dbo'. #' @param analysisIds (OPTIONAL) A vector containing the set of Achilles analysisIds for #' which results will be returned. The following are supported: \code{202,402,602,702,802,1802,2102}. -#' If not specified, data for all analysis will be returned. Ignored if \code{conceptId} is given. +#' If not specified, data for all analysis will be returned. Ignored if \code{conceptId} is given. #' @param conceptId (OPTIONAL) A SNOMED concept_id from the \code{CONCEPT} table for which a monthly Achilles analysis exists. #' If not specified, all concepts for a given analysis will be returned. #' @param outputFile CSV file where temporal characterization will be written. Default is temporal-characterization.csv. @@ -67,95 +67,95 @@ #' # Example 1: #' pneumonia <- 255848 #' performTemporalCharacterization( -#' connectionDetails = connectionDetails, -#' cdmDatabaseSchema = "cdm", -#' resultsDatabaseSchema = "results", -#' conceptId = pneumonia, -#' outputFolder = "output/pneumoniaTemporalChar.csv") +#' connectionDetails = connectionDetails, +#' cdmDatabaseSchema = "cdm", +#' resultsDatabaseSchema = "results", +#' conceptId = pneumonia, +#' outputFolder = "output/pneumoniaTemporalChar.csv" +#' ) #' #' # Example 2: #' performTemporalCharacterization( -#' connectionDetails = connectionDetails, -#' cdmDatabaseSchema = "cdm", -#' resultsDatabaseSchema = "results", -#' analysisIds = c(402,702), -#' outputFolder = "output/conditionAndDrugTemporalChar.csv") +#' connectionDetails = connectionDetails, +#' cdmDatabaseSchema = "cdm", +#' resultsDatabaseSchema = "results", +#' analysisIds = c(402, 702), +#' outputFolder = "output/conditionAndDrugTemporalChar.csv" +#' ) #' #' # Example 3: #' performTemporalCharacterization( -#' connectionDetails = connectionDetails, -#' cdmDatabaseSchema = "cdm", -#' resultsDatabaseSchema = "results", -#' outputFolder = "output/CompleteTemporalChar.csv") +#' connectionDetails = connectionDetails, +#' cdmDatabaseSchema = "cdm", +#' resultsDatabaseSchema = "results", +#' outputFolder = "output/CompleteTemporalChar.csv" +#' ) #' } #' -#'@export +#' @export -performTemporalCharacterization <- function( - connectionDetails, - cdmDatabaseSchema, - resultsDatabaseSchema, - analysisIds = NULL, - conceptId = NULL, - outputFile = "temporal-characterization.csv") -{ +performTemporalCharacterization <- function(connectionDetails, + cdmDatabaseSchema, + resultsDatabaseSchema, + analysisIds = NULL, + conceptId = NULL, + outputFile = "temporal-characterization.csv") { + # Minimum number of months of data to perform temporal characterization + minMonths <- 36 - # Minimum number of months of data to perform temporal characterization - minMonths <- 36 - - # Pull temporal data from Achilles and get list of unique concept_ids - temporalData <- Achilles::getTemporalData(connectionDetails,cdmDatabaseSchema,resultsDatabaseSchema,analysisIds,conceptId) - - if (nrow(temporalData) == 0) { - stop("CANNOT PERFORM TEMPORAL CHARACTERIZATION: NO ACHILLES DATA FOUND") - } - - allConceptIds <- unique(temporalData$CONCEPT_ID) - print(paste0("Attempting temporal characterization on ", length(allConceptIds), " individual concepts")) - - # Loop through temporal data, perform temporal characterization, and write out results - rowData <- - temporalData %>% - tidyr::nest( - tempData = c( - "START_DATE", - "COUNT_VALUE", - "PREVALENCE", - "PROPORTION_WITHIN_YEAR" - ) - ) %>% - ## rowwise allows to work with nested list vars as with usual ones - dplyr::rowwise() %>% - dplyr::mutate( - tempData.ts = list( - Achilles::createTimeSeries(.data$tempData) - ), - tempData.ts = list( - .data$tempData.ts[, "PREVALENCE"] - ), - tempData.ts = list( - Achilles::tsCompleteYears(.data$tempData.ts) - ) - ) %>% - dplyr::filter( - length(.data$tempData.ts) >= minMonths - ) %>% - dplyr::mutate( - tempData.ts.ss = Achilles::getSeasonalityScore(.data$tempData.ts), - tempData.ts.is = Achilles::isStationary(.data$tempData.ts) - ) %>% - ## now we don't need to handle variables row wise - dplyr::ungroup() %>% - dplyr::select( - DB_NAME = .data$DB_NAME, - CDM_TABLE_NAME = .data$CDM_TABLE_NAME, - CONCEPT_ID = .data$CONCEPT_ID, - CONCEPT_NAME = .data$CONCEPT_NAME, - SEASONALITY_SCORE = .data$tempData.ts.ss, - IS_STATIONARY = .data$tempData.ts.is, - ) %>% - dplyr::collect() - write.csv(rowData,outputFile,row.names = FALSE) - print(paste0("Temporal characterization complete. Results can be found in ", outputFile)) - invisible(rowData) + # Pull temporal data from Achilles and get list of unique concept_ids + temporalData <- Achilles::getTemporalData(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema, analysisIds, conceptId) + + if (nrow(temporalData) == 0) { + stop("CANNOT PERFORM TEMPORAL CHARACTERIZATION: NO ACHILLES DATA FOUND") + } + + allConceptIds <- unique(temporalData$CONCEPT_ID) + print(paste0("Attempting temporal characterization on ", length(allConceptIds), " individual concepts")) + + # Loop through temporal data, perform temporal characterization, and write out results + rowData <- + temporalData %>% + tidyr::nest( + tempData = c( + "START_DATE", + "COUNT_VALUE", + "PREVALENCE", + "PROPORTION_WITHIN_YEAR" + ) + ) %>% + ## rowwise allows to work with nested list vars as with usual ones + dplyr::rowwise() %>% + dplyr::mutate( + tempData.ts = list( + Achilles::createTimeSeries(.data$tempData) + ), + tempData.ts = list( + .data$tempData.ts[, "PREVALENCE"] + ), + tempData.ts = list( + Achilles::tsCompleteYears(.data$tempData.ts) + ) + ) %>% + dplyr::filter( + length(.data$tempData.ts) >= minMonths + ) %>% + dplyr::mutate( + tempData.ts.ss = Achilles::getSeasonalityScore(.data$tempData.ts), + tempData.ts.is = Achilles::isStationary(.data$tempData.ts) + ) %>% + ## now we don't need to handle variables row wise + dplyr::ungroup() %>% + dplyr::select( + DB_NAME = .data$DB_NAME, + CDM_TABLE_NAME = .data$CDM_TABLE_NAME, + CONCEPT_ID = .data$CONCEPT_ID, + CONCEPT_NAME = .data$CONCEPT_NAME, + SEASONALITY_SCORE = .data$tempData.ts.ss, + IS_STATIONARY = .data$tempData.ts.is, + ) %>% + dplyr::collect() + write.csv(rowData, outputFile, row.names = FALSE) + print(paste0("Temporal characterization complete. Results can be found in ", outputFile)) + invisible(rowData) } diff --git a/R/runMissingAnalyses.r b/R/runMissingAnalyses.r index 2b3f0d87..9ee66090 100644 --- a/R/runMissingAnalyses.r +++ b/R/runMissingAnalyses.r @@ -1,6 +1,6 @@ # @file runMissingAnalyses # -# Copyright 2023 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles # @@ -59,16 +59,17 @@ #' @param defaultAnalysesOnly Boolean to determine if only default analyses should be run. #' Including non-default analyses is substantially more resource #' intensive. Default = TRUE -#' @returns +#' @returns #' No return value. Run to execute analyses currently missing from results. -#' +#' #' @examples #' \dontrun{ -#' Achilles::runMissingAnalyses(connectionDetails = connectionDetails, -#' cdmDatabaseSchema = "cdm", -#' resultsDatabaseSchema = "results", -#' -#' outputFolder = "/tmp") +#' Achilles::runMissingAnalyses( +#' connectionDetails = connectionDetails, +#' cdmDatabaseSchema = "cdm", +#' resultsDatabaseSchema = "results", +#' outputFolder = "/tmp" +#' ) #' } #' #' @export @@ -76,38 +77,38 @@ runMissingAnalyses <- function(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema = cdmDatabaseSchema, - scratchDatabaseSchema = resultsDatabaseSchema, - vocabDatabaseSchema = cdmDatabaseSchema, - tempEmulationSchema = resultsDatabaseSchema, - outputFolder = "output", - defaultAnalysesOnly = TRUE) -{ - - missingAnalyses <- Achilles::listMissingAnalyses(connectionDetails,resultsDatabaseSchema) + scratchDatabaseSchema = resultsDatabaseSchema, + vocabDatabaseSchema = cdmDatabaseSchema, + tempEmulationSchema = resultsDatabaseSchema, + outputFolder = "output", + defaultAnalysesOnly = TRUE) { + missingAnalyses <- Achilles::listMissingAnalyses(connectionDetails, resultsDatabaseSchema) if (nrow(missingAnalyses) == 0) { stop("NO MISSING ANALYSES FOUND") } - + if (defaultAnalysesOnly) { - missingAnalyses <- missingAnalyses[missingAnalyses$is_default == 1,] - } + missingAnalyses <- missingAnalyses[missingAnalyses$is_default == 1, ] + } if (nrow(missingAnalyses) == 0) { stop("NO DEFAULT MISSING ANALYSES FOUND") } - + # By supplying analysisIds along with specifying createTable=F and updateGivenAnalysesOnly=T, # we add the missing analysis_ids without removing existing data - achilles(connectionDetails = connectionDetails, - cdmDatabaseSchema = cdmDatabaseSchema, - resultsDatabaseSchema = resultsDatabaseSchema, - scratchDatabaseSchema = scratchDatabaseSchema, - vocabDatabaseSchema = cdmDatabaseSchema, - tempEmulationSchema = tempEmulationSchema, - analysisIds = missingAnalyses$analysis_id, - defaultAnalysesOnly = defaultAnalysesOnly, - outputFolder = outputFolder, - createTable = FALSE, - updateGivenAnalysesOnly = TRUE) + achilles( + connectionDetails = connectionDetails, + cdmDatabaseSchema = cdmDatabaseSchema, + resultsDatabaseSchema = resultsDatabaseSchema, + scratchDatabaseSchema = scratchDatabaseSchema, + vocabDatabaseSchema = cdmDatabaseSchema, + tempEmulationSchema = tempEmulationSchema, + analysisIds = missingAnalyses$analysis_id, + defaultAnalysesOnly = defaultAnalysesOnly, + outputFolder = outputFolder, + createTable = FALSE, + updateGivenAnalysesOnly = TRUE + ) } diff --git a/R/sumAcrossYears.r b/R/sumAcrossYears.r index b98bc744..5ec698f7 100644 --- a/R/sumAcrossYears.r +++ b/R/sumAcrossYears.r @@ -1,22 +1,22 @@ -#'@title For a monhtly time series, compute sum and proportion by month across all years +#' @title For a monhtly time series, compute sum and proportion by month across all years #' -#'@param tsData A time series object +#' @param tsData A time series object #' -#'@return A data frame reporting the monthly sum across all years and the proportion this sum contributes to the total. +#' @return A data frame reporting the monthly sum across all years and the proportion this sum contributes to the total. #' -#'@export +#' @export -sumAcrossYears <- function(tsData) -{ - - # Read the time series into a data frame with character string months - tsAsDf <- data.frame(MONTH_NUM=cycle(tsData), TS_VALUE=tsData, stringsAsFactors = F) - # Summarize by month across all years - tsAggregatedByMonth <- tsAsDf %>% dplyr::group_by(.data$MONTH_NUM) %>% dplyr::summarize(SUM=sum(.data$TS_VALUE)) - # Compute proportion for each month - tsPropByMonth <- data.frame(MONTH_NUM=tsAggregatedByMonth$MONTH_NUM, PROP=tsAggregatedByMonth$SUM/sum(tsData), stringsAsFactors = F) - # Get sum and proportion in a single data frame - tsSummary <- merge(tsAggregatedByMonth, tsPropByMonth, by.x = "MONTH_NUM", by.y="MONTH_NUM") +sumAcrossYears <- function(tsData) { + # Read the time series into a data frame with character string months + tsAsDf <- data.frame(MONTH_NUM = cycle(tsData), TS_VALUE = tsData, stringsAsFactors = F) + # Summarize by month across all years + tsAggregatedByMonth <- tsAsDf %>% + dplyr::group_by(.data$MONTH_NUM) %>% + dplyr::summarize(SUM = sum(.data$TS_VALUE)) + # Compute proportion for each month + tsPropByMonth <- data.frame(MONTH_NUM = tsAggregatedByMonth$MONTH_NUM, PROP = tsAggregatedByMonth$SUM / sum(tsData), stringsAsFactors = F) + # Get sum and proportion in a single data frame + tsSummary <- merge(tsAggregatedByMonth, tsPropByMonth, by.x = "MONTH_NUM", by.y = "MONTH_NUM") - return (tsSummary[order(tsSummary$PROP, decreasing = T),]) -} \ No newline at end of file + return(tsSummary[order(tsSummary$PROP, decreasing = T), ]) +} diff --git a/R/tsCompleteYears.r b/R/tsCompleteYears.r index 099db174..ff63146d 100644 --- a/R/tsCompleteYears.r +++ b/R/tsCompleteYears.r @@ -1,32 +1,30 @@ -#'@title Trim a monthly time series object to so that partial years are removed +#' @title Trim a monthly time series object to so that partial years are removed #' -#'@details This function is only supported for monthly time series +#' @details This function is only supported for monthly time series #' -#'@param tsData A time series object +#' @param tsData A time series object #' -#'@return A time series with partial years removed. +#' @return A time series with partial years removed. #' -#'@export +#' @export -tsCompleteYears <- function(tsData) -{ +tsCompleteYears <- function(tsData) { + if (frequency(tsData) != 12) { + stop("This function is only supported for monthly time series.") + } - if (frequency(tsData) != 12) { - stop("This function is only supported for monthly time series.") - } + origStartMonth <- start(tsData)[2] + origStartYear <- start(tsData)[1] + origEndMonth <- end(tsData)[2] + origEndYear <- end(tsData)[1] - origStartMonth <- start(tsData)[2] - origStartYear <- start(tsData)[1] - origEndMonth <- end(tsData)[2] - origEndYear <- end(tsData)[1] + newStartMonth <- 1 + newEndMonth <- 12 - newStartMonth <- 1 - newEndMonth <- 12 + tsObj <- tsData - tsObj <- tsData + if (origStartMonth > 1) tsObj <- window(tsObj, start = c(origStartYear + 1, newStartMonth)) + if (origEndMonth < 12) tsObj <- window(tsObj, end = c(origEndYear - 1, newEndMonth)) - if (origStartMonth > 1) tsObj <- window(tsObj, start=c(origStartYear+1,newStartMonth)) - if (origEndMonth < 12) tsObj <- window(tsObj, end=c(origEndYear-1,newEndMonth)) - - return (tsObj) + return(tsObj) } diff --git a/docs/404.html b/docs/404.html index 4a370b97..7bc9e8e5 100644 --- a/docs/404.html +++ b/docs/404.html @@ -6,7 +6,7 @@ Page not found (404) • Achilles - + @@ -18,7 +18,7 @@ - +
@@ -44,7 +44,7 @@
    • @@ -72,7 +78,7 @@ - +
    @@ -100,16 +106,16 @@

    Page not found (404)

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/articles/GettingStarted.html b/docs/articles/GettingStarted.html index 8093a1d7..75f7d4a4 100644 --- a/docs/articles/GettingStarted.html +++ b/docs/articles/GettingStarted.html @@ -6,20 +6,19 @@ Getting Started with Achilles • Achilles - + - - +
    @@ -45,7 +44,7 @@
    • @@ -73,16 +78,16 @@
    - +

    Getting Started with Achilles

    -

    2023-05-11

    - +

    2025-12-02

    + Source: vignettes/GettingStarted.Rmd
    @@ -160,9 +165,7 @@

    License - -

    +
    @@ -175,16 +178,16 @@

    License

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/articles/RunningAchilles.html b/docs/articles/RunningAchilles.html index ff574a5d..502652ab 100644 --- a/docs/articles/RunningAchilles.html +++ b/docs/articles/RunningAchilles.html @@ -6,20 +6,19 @@ Running Achilles on Your CDM • Achilles - + - - +
    @@ -45,7 +44,7 @@
    • @@ -73,16 +78,16 @@ - +

    Running Achilles on Your CDM

    -

    2023-05-11

    - +

    2025-12-02

    + Source: vignettes/RunningAchilles.Rmd
    @@ -264,15 +269,19 @@

    Running Achilles: Single-Threaded scratchDatabaseSchema, as temporary tables will be used.

    -connectionDetails <- createConnectionDetails(dbms = "postgresql", 
-                                             server = "localhost/synpuf", 
-                                             user = "cdm_user", 
-                                             password = "cdm_password")
+connectionDetails <- createConnectionDetails(
+  dbms = "postgresql",
+  server = "localhost/synpuf",
+  user = "cdm_user",
+  password = "cdm_password"
+)
 
-achilles(connectionDetails = connectionDetails, 
-         cdmDatabaseSchema = "cdm", 
-         resultsDatabaseSchema = "results", 
-         outputFolder = "output")
    +achilles( + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", + outputFolder = "output" +)

    Running Achilles: Multi-Threaded Mode @@ -281,17 +290,21 @@

    Running Achilles: Multi-Threaded M scratchDatabaseSchema and use > 1 for numThreads.

    -connectionDetails <- createConnectionDetails(dbms = "postgresql", 
-                                             server = "localhost/synpuf", 
-                                             user = "cdm_user", 
-                                             password = "cdm_password")
+connectionDetails <- createConnectionDetails(
+  dbms = "postgresql",
+  server = "localhost/synpuf",
+  user = "cdm_user",
+  password = "cdm_password"
+)
 
-achilles(connectionDetails = connectionDetails, 
-         cdmDatabaseSchema = "cdm", 
-         resultsDatabaseSchema = "results", 
-         scratchDatabaseSchema = "scratch", 
-         numThreads = 5,
-         outputFolder = "output")
    +achilles( + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", + scratchDatabaseSchema = "scratch", + numThreads = 5, + outputFolder = "output" +)

    Post-Processing @@ -307,14 +320,18 @@

    Creating IndicesTo improve query performance of the Achilles results tables, run the createIndices function.

     +createIndices( + connectionDetails = connectionDetails, + resultsDatabaseSchema = "results", + outputFolder = "output" +)

    Dropping All Staging Tables (Multi-threaded only) @@ -325,13 +342,17 @@

    Dropping All Staging Ta

    The tableTypes parameter can be used to specify which batch of staging tables to drop (“achilles”).

    -connectionDetails <- createConnectionDetails(dbms = "postgresql", 
-                                             server = "localhost/synpuf", 
-                                             user = "cdm_user", 
-                                             password = "cdm_password")
+connectionDetails <- createConnectionDetails(
+  dbms = "postgresql",
+  server = "localhost/synpuf",
+  user = "cdm_user",
+  password = "cdm_password"
+)
 
-dropAllScratchTables(connectionDetails = connectionDetails, 
-                     scratchDatabaseSchema = "scratch", numThreads = 5)
    +dropAllScratchTables( + connectionDetails = connectionDetails, + scratchDatabaseSchema = "scratch", numThreads = 5 +)

    @@ -341,29 +362,29 @@

    AcknowledgmentsAchilles package.

     citation("Achilles")
    -
    #> 
-#> To cite package 'Achilles' in publications use:
+
    #> To cite package 'Achilles' in publications use:
 #> 
 #>   DeFalco F, Ryan P, Schuemie M, Huser V, Knoll C, Londhe A,
-#>   Abdul-Basser T, Molinaro A (2023). _Achilles: Achilles Data Source
-#>   Characterization_. R package version 1.7.1.
+#>   Abdul-Basser T, Molinaro A (2025). _Achilles: Achilles Data Source
+#>   Characterization_. R package version 1.8.0,
+#>   https://github.com/OHDSI/Achilles,
+#>   <https://ohdsi.github.io/Achilles/>.
 #> 
 #> A BibTeX entry for LaTeX users is
 #> 
 #>   @Manual{,
 #>     title = {Achilles: Achilles Data Source Characterization},
 #>     author = {Frank DeFalco and Patrick Ryan and Martijn Schuemie and Vojtech Huser and Chris Knoll and Ajit Londhe and Taha Abdul-Basser and Anthony Molinaro},
-#>     year = {2023},
-#>     note = {R package version 1.7.1},
+#>     year = {2025},
+#>     note = {R package version 1.8.0, https://github.com/OHDSI/Achilles},
+#>     url = {https://ohdsi.github.io/Achilles/},
 #>   }

    + @@ -376,16 +397,16 @@

    Acknowledgments

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/articles/index.html b/docs/articles/index.html index 4138f4fb..6c8ded0d 100644 --- a/docs/articles/index.html +++ b/docs/articles/index.html @@ -1,9 +1,9 @@ -Articles • AchillesArticles • Achilles - +
    @@ -28,7 +28,7 @@
    • - +
    @@ -74,15 +80,15 @@

    All vignettes

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/authors.html b/docs/authors.html index 67e37cad..253d2919 100644 --- a/docs/authors.html +++ b/docs/authors.html @@ -1,9 +1,9 @@ -Authors and Citation • AchillesAuthors and Citation • Achilles - +
    @@ -28,7 +28,7 @@
    • - +
    -

    Authors

    +

    Authors and Citation

    - +
    • -

      Frank DeFalco. Author, maintainer. +

      Frank DeFalco. Author, maintainer.

    • -

      Patrick Ryan. Author. +

      Patrick Ryan. Author.

    • -

      Martijn Schuemie. Author. +

      Martijn Schuemie. Author.

    • -

      Vojtech Huser. Author. +

      Vojtech Huser. Author.

    • -

      Chris Knoll. Author. +

      Chris Knoll. Author.

    • -

      Ajit Londhe. Author. +

      Ajit Londhe. Author.

    • -

      Taha Abdul-Basser. Author. +

      Taha Abdul-Basser. Author.

    • -

      Anthony Molinaro. Author. +

      Anthony Molinaro. Author.

    • -

      Observational Health Data Science and Informatics. Copyright holder. +

      Observational Health Data Science and Informatics. Copyright holder.

    Citation

    - + Source: DESCRIPTION
    -

    DeFalco F, Ryan P, Schuemie M, Huser V, Knoll C, Londhe A, Abdul-Basser T, Molinaro A (2023). +

    DeFalco F, Ryan P, Schuemie M, Huser V, Knoll C, Londhe A, Abdul-Basser T, Molinaro A (2025). Achilles: Achilles Data Source Characterization. -R package version 1.7.2. +R package version 1.8.0, https://github.com/OHDSI/Achilles, https://ohdsi.github.io/Achilles/. 

    @Manual{,
   title = {Achilles: Achilles Data Source Characterization},
   author = {Frank DeFalco and Patrick Ryan and Martijn Schuemie and Vojtech Huser and Chris Knoll and Ajit Londhe and Taha Abdul-Basser and Anthony Molinaro},
-  year = {2023},
-  note = {R package version 1.7.2},
+  year = {2025},
+  note = {R package version 1.8.0, https://github.com/OHDSI/Achilles},
+  url = {https://ohdsi.github.io/Achilles/},
 }
    @@ -125,15 +132,15 @@

    Citation

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/index.html b/docs/index.html index 93787110..165ca29e 100644 --- a/docs/index.html +++ b/docs/index.html @@ -6,26 +6,20 @@ Achilles Data Source Characterization • Achilles - + - + - +
    @@ -51,7 +45,7 @@
    • @@ -79,7 +79,7 @@ - +
    @@ -175,6 +175,8 @@

    AcknowledgementsLinks

    @@ -197,14 +199,14 @@

    Citation

    Developers

      -
    • Frank DeFalco
      Author, maintainer
      • -
    • Patrick Ryan
      Author
      • -
    • Martijn Schuemie
      Author
      • -
    • Vojtech Huser
      Author
      • -
    • Chris Knoll
      Author
      • -
    • Ajit Londhe
      Author
      • -
    • Taha Abdul-Basser
      Author
      • -
    • Anthony Molinaro
      Author
      • +
    • Frank DeFalco
      Author, maintainer
      • +
    • Patrick Ryan
      Author
      • +
    • Martijn Schuemie
      Author
      • +
    • Vojtech Huser
      Author
      • +
    • Chris Knoll
      Author
      • +
    • Ajit Londhe
      Author
      • +
    • Taha Abdul-Basser
      Author
      • +
    • Anthony Molinaro
      Author
    • More about authors...
    @@ -222,16 +224,16 @@

    Developers

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/news/index.html b/docs/news/index.html index 982e58e1..7c7ee063 100644 --- a/docs/news/index.html +++ b/docs/news/index.html @@ -1,9 +1,9 @@ -Changelog • AchillesChangelog • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    Changelog

    - + Source: NEWS.md
    -

    Achilles 1.7.2

    +

    Achilles 1.8

    +
    +

    Improvements and New Features

    +
    • +Export Enhancements +
      • Added unit_concept_id to ARES export of measurement tables.
        • +
      • Improved unit concept ID naming and handling.
        • +
      • Added export of the location table to ARES.
        • +
      • Added database summary reporting.
        • +
      • +
    • +Performance Improvements +
      • Refactored performance logs to be captured directly (not just through console logs).
        • +
      • Improved performance of ARES export, especially for DuckDB.
        • +
      • Optimized analyses for better performance, including analyses 117 and 1815.
        • +
      • +
    • +Code Quality and Maintenance +
      • Fixed ambiguous dplyr::select statements and standardized column name casing (e.g., IS_DEFAULT → is_default).
        • +
      • Added missing SQL scripts for performance tracking.
        • +
      • Fixed fromJSON method usage for correctness.
        • +
      • Fixed errors when creating metadata tables with zero-length vectors.
        • +
      • Moved repeated subqueries to temp tables in some analyses.
        • +
      • Trimmed trailing whitespaces in export scripts.
        • +
      • +
    • +Bug Fixes +
      • Fixed crash during exportToAres (DuckDB) related to unit concept IDs.
        • +
      • Handled missing server values in temporal characterization functions.
        • +
      • +
    • +Documentation +
      • Updated and added links in the DESCRIPTION file.
        • +
      • +
    +
    +

    Notable Commits

    +

    For more, visit the develop branch commit history.

    +
    +
    +
    +

    Achilles 1.7.22023-05-11

    1. Improved test setup management
    @@ -88,15 +142,15 @@

    Achilles 1.7.0
    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index 9a56aa41..32fd07e1 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -1,8 +1,7 @@ -pandoc: 2.19.2 -pkgdown: 2.0.7 +pandoc: 3.6.3 +pkgdown: 2.1.3 pkgdown_sha: ~ articles: GettingStarted: GettingStarted.html RunningAchilles: RunningAchilles.html -last_built: 2023-05-11T14:56Z - +last_built: 2025-12-02T20:06Z diff --git a/docs/reference/achilles.html b/docs/reference/achilles.html index 2b591376..72d76727 100644 --- a/docs/reference/achilles.html +++ b/docs/reference/achilles.html @@ -1,9 +1,9 @@ -achilles — achilles • Achillesachilles — achilles • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    achilles

    - + Source: R/Achilles.R
    @@ -92,26 +98,28 @@

    achilles

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Fully qualified name of database schema that contains OMOP CDM schema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_instance.dbo'.

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Fully qualified name of database schema that we can write final results to. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_results.dbo'.

    -
    scratchDatabaseSchema
    +
    scratchDatabaseSchema

    Fully qualified name of the database schema that will store all of the intermediate scratch tables, so for example, on SQL Server, 'cdm_scratch.dbo'. Must be accessible to/from the cdmDatabaseSchema @@ -120,95 +128,95 @@

    Arguments

    temporary tables instead of permanent tables.

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    String name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    -
    tempEmulationSchema
    +
    tempEmulationSchema

    Formerly oracleTempSchema. For databases like Oracle where you must specify the name of the database schema where you want all temporary tables to be managed. Requires create/insert permissions to this database.

    -
    sourceName
    +
    sourceName

    String name of the data source name. If blank, CDM_SOURCE table will be queried to try to obtain this.

    -
    analysisIds
    +
    analysisIds

    (OPTIONAL) A vector containing the set of Achilles analysisIds for which results will be generated. If not specified, all analyses will be executed. Use getAnalysisDetails to get a list of all Achilles analyses and their Ids.

    -
    createTable
    +
    createTable

    If true, new results tables will be created in the results schema. If not, the tables are assumed to already exist, and analysis results will be inserted (slower on MPP).

    -
    smallCellCount
    +
    smallCellCount

    To avoid patient identification, cells with small counts (<= smallCellCount) are deleted. Set to 0 for complete summary without small cell count restrictions.

    -
    cdmVersion
    +
    cdmVersion

    Define the OMOP CDM version used: currently supports v5 and above. Use major release number or minor number only (e.g. 5, 5.3)

    -
    createIndices
    +
    createIndices

    Boolean to determine if indices should be created on the resulting Achilles tables. Default= TRUE

    -
    numThreads
    +
    numThreads

    (OPTIONAL, multi-threaded mode) The number of threads to use to run Achilles in parallel. Default is 1 thread.

    -
    tempAchillesPrefix
    +
    tempAchillesPrefix

    (OPTIONAL, multi-threaded mode) The prefix to use for the scratch Achilles analyses tables. Default is "tmpach"

    -
    dropScratchTables
    +
    dropScratchTables

    (OPTIONAL, multi-threaded mode) TRUE = drop the scratch tables (may take time depending on dbms), FALSE = leave them in place for later removal.

    -
    sqlOnly
    +
    sqlOnly

    Boolean to determine if Achilles should be fully executed. TRUE = just generate SQL files, don't actually run, FALSE = run Achilles

    -
    outputFolder
    +
    outputFolder

    Path to store logs and SQL files

    -
    verboseMode
    +
    verboseMode

    Boolean to determine if the console will show all execution steps. Default = TRUE

    -
    optimizeAtlasCache
    +
    optimizeAtlasCache

    Boolean to determine if the atlas cache has to be optimized. Default = FALSE

    -
    defaultAnalysesOnly
    +
    defaultAnalysesOnly

    Boolean to determine if only default analyses should be run. Including non-default analyses is substantially more resource intensive. Default = TRUE

    -
    updateGivenAnalysesOnly
    +
    updateGivenAnalysesOnly

    Boolean to determine whether to preserve the results of the analyses NOT specified with the analysisIds parameter. To update only analyses specified by analysisIds, set @@ -217,26 +225,24 @@

    Arguments

    of Achilles when supplied analysisIds.

    -
    excludeAnalysisIds
    +
    excludeAnalysisIds

    (OPTIONAL) A vector containing the set of Achilles analyses to exclude.

    -
    sqlDialect
    -

    (OPTIONAL) String to be used when specifying sqlOnly = TRUE and -NOT supplying the connectionDetails parameter. -if the connectionDetails parameter is supplied, sqlDialect -is ignored. If the connectionDetails parameter is not supplied, -sqlDialect must be supplied to enable SqlRender -to translate properly. sqlDialect takes the value normally +

    sqlDialect
    +

    (OPTIONAL) String to be used when specifying sqlOnly = TRUE and +NOT supplying the connectionDetails parameter. +if the connectionDetails parameter is supplied, sqlDialect +is ignored. If the connectionDetails parameter is not supplied, +sqlDialect must be supplied to enable SqlRender +to translate properly. sqlDialect takes the value normally supplied to connectionDetails$dbms. Default = NULL.

    Value

    - - -

    An object of type achillesResults containing details for connecting to the database +

    An object of type achillesResults containing details for connecting to the database containing the results

    @@ -246,17 +252,19 @@

    Details

    Examples

    - 
    if (FALSE) {
+    
    if (FALSE) { # \dontrun{
 connectionDetails <- createConnectionDetails(dbms = "sql server", server = "some_server")
-achillesResults <- achilles(connectionDetails = connectionDetails,
+achillesResults <- achilles(
+  connectionDetails = connectionDetails,
   cdmDatabaseSchema = "cdm",
   resultsDatabaseSchema = "results",
-  scratchDatabaseSchema = "scratch", 
-  sourceName = "Some Source", 
-  cdmVersion = "5.3", 
-  numThreads = 10, 
-  outputFolder = "output")
-}
+  scratchDatabaseSchema = "scratch",
+  sourceName = "Some Source",
+  cdmVersion = "5.3",
+  numThreads = 10,
+  outputFolder = "output"
+)
+} # }
    @@ -272,15 +280,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/createIndices.html b/docs/reference/createIndices.html index 3c5bced1..329cd356 100644 --- a/docs/reference/createIndices.html +++ b/docs/reference/createIndices.html @@ -1,9 +1,9 @@ -Create indicies — createIndices • AchillesCreate indicies — createIndices • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    Create indicies

    - + Source: R/Achilles.R
    @@ -75,43 +81,43 @@

    Create indicies

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Fully qualified name of database schema that we can write final results to. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_results.dbo'.

    -
    outputFolder
    +
    outputFolder

    Path to store logs and SQL files

    -
    sqlOnly
    +
    sqlOnly

    TRUE = just generate SQL files, don't actually run, FALSE = run Achilles

    -
    verboseMode
    +
    verboseMode

    Boolean to determine if the console will show all execution steps. Default = TRUE

    -
    achillesTables
    +
    achillesTables

    Which achilles tables should be indexed? Default is both achilles_results and achilles_results_dist.

    Value

    - - -

    A collection of queries that were executed to drop any existing indices and create new indicies as +

    A collection of queries that were executed to drop any existing indices and create new indicies as specified.

    @@ -131,15 +137,15 @@

    Details

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/createTimeSeries.html b/docs/reference/createTimeSeries.html index 7263e578..5e9241b7 100644 --- a/docs/reference/createTimeSeries.html +++ b/docs/reference/createTimeSeries.html @@ -1,10 +1,10 @@ -createTimeSeries — createTimeSeries • AchillescreateTimeSeries — createTimeSeries • Achilles - +
    @@ -29,7 +29,7 @@
    • - +

    createTimeSeries

    - + Source: R/createTimeSeries.r
    @@ -70,15 +76,15 @@

    createTimeSeries

    Arguments

    -
    temporalData
    + + +
    temporalData

    A data frame from which to create the time series

    Value

    - - -

    A multivariate time series object

    +

    A multivariate time series object

    Details

    @@ -93,24 +99,32 @@

    Details

    Examples

    # Example 1:
 temporalData <- data.frame(START_DATE = seq.Date(as.Date("20210101", "%Y%m%d"),
-                                                 as.Date("20231201",
-  "%Y%m%d"), by = "month"), COUNT_VALUE = round(runif(36, 1, 1000)), PREVALENCE = round(runif(36,
-  0, 10), 2), PROPORTION_WITHIN_YEAR = round(runif(36, 0, 1), 2), stringsAsFactors = FALSE)
+  as.Date(
+    "20231201",
+    "%Y%m%d"
+  ),
+  by = "month"
+), COUNT_VALUE = round(runif(36, 1, 1000)), PREVALENCE = round(runif(
+  36,
+  0, 10
+), 2), PROPORTION_WITHIN_YEAR = round(runif(36, 0, 1), 2), stringsAsFactors = FALSE)
 dummyTs <- createTimeSeries(temporalData)
 dummyTs.cv <- dummyTs[, "COUNT_VALUE"]
 dummyTs.pv <- dummyTs[, "PREVALENCE"]
 dummyTs.pwy <- dummyTs[, "PROPORTION_WITHIN_YEAR"]
 
-if (FALSE) {
+if (FALSE) { # \dontrun{
 # Example 2:
 pneumonia <- 255848
-temporalData <- getTemporalData(connectionDetails = connectionDetails, cdmDatabaseSchema = "cdm",
-  resultsDatabaseSchema = "results", conceptId = pneumonia)
+temporalData <- getTemporalData(
+  connectionDetails = connectionDetails, cdmDatabaseSchema = "cdm",
+  resultsDatabaseSchema = "results", conceptId = pneumonia
+)
 pneumoniaTs <- createTimeSeries(temporalData)
 pneumoniaTs.cv <- pneumoniaTs[, "COUNT_VALUE"]
 pneumoniaTs.pv <- pneumoniaTs[, "PREVALENCE"]
 pneumoniaTs.pwy <- pneumoniaTs[, "PROPORTION_WITHIN_YEAR"]
-}
+} # }
    @@ -126,15 +140,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/dropAllScratchTables.html b/docs/reference/dropAllScratchTables.html index dedad4db..da72b579 100644 --- a/docs/reference/dropAllScratchTables.html +++ b/docs/reference/dropAllScratchTables.html @@ -1,9 +1,9 @@ -Drop all possible scratch tables — dropAllScratchTables • AchillesDrop all possible scratch tables — dropAllScratchTables • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    Drop all possible scratch tables

    - + Source: R/Achilles.R
    @@ -77,41 +83,43 @@

    Drop all possible scratch tables

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

    -
    scratchDatabaseSchema
    +
    scratchDatabaseSchema

    string name of database schema that Achilles scratch tables were written to.

    -
    tempAchillesPrefix
    +
    tempAchillesPrefix

    The prefix to use for the "temporary" (but actually permanent) Achilles analyses tables. Default is "tmpach"

    -
    numThreads
    +
    numThreads

    The number of threads to use to run this function. Default is 1 thread.

    -
    tableTypes
    +
    tableTypes

    The types of Achilles scratch tables to drop: achilles

    -
    outputFolder
    +
    outputFolder

    Path to store logs and SQL files

    -
    verboseMode
    +
    verboseMode

    Boolean to determine if the console will show all execution steps. Default = TRUE

    -
    defaultAnalysesOnly
    +
    defaultAnalysesOnly

    Boolean to determine if only default analyses should be run. Including non-default analyses is substantially more resource intensive. Default = TRUE

    @@ -119,9 +127,7 @@

    Arguments

    Value

    - - -

    No return value, called to drop interim scratch tables.

    +

    No return value, called to drop interim scratch tables.

    Details

    @@ -140,15 +146,15 @@

    Details

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportConditionEraToJson.html b/docs/reference/exportConditionEraToJson.html index e71f452e..7e073618 100644 --- a/docs/reference/exportConditionEraToJson.html +++ b/docs/reference/exportConditionEraToJson.html @@ -1,9 +1,9 @@ -exportConditionEraToJson — exportConditionEraToJson • AchillesexportConditionEraToJson — exportConditionEraToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportConditionEraToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportConditionEraToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportConditionEraToJson(connectionDetails,
-                         cdmDatabaseSchema = "cdm4_sim",
-                         outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportConditionToJson.html b/docs/reference/exportConditionToJson.html index b0274b09..887b6729 100644 --- a/docs/reference/exportConditionToJson.html +++ b/docs/reference/exportConditionToJson.html @@ -1,9 +1,9 @@ -exportConditionToJson — exportConditionToJson • AchillesexportConditionToJson — exportConditionToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportConditionToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportConditionToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportConditionToJson(connectionDetails,
-                      cdmDatabaseSchema = "cdm4_sim",
-                      outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportDashboardToJson.html b/docs/reference/exportDashboardToJson.html index befed0c1..3484105c 100644 --- a/docs/reference/exportDashboardToJson.html +++ b/docs/reference/exportDashboardToJson.html @@ -1,9 +1,9 @@ -exportDashboardToJson — exportDashboardToJson • AchillesexportDashboardToJson — exportDashboardToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportDashboardToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportDashboardToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -115,13 +121,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportDashboardToJson(connectionDetails,
-                      cdmDatabaseSchema = "cdm4_sim",
-                      outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -136,15 +145,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportDataDensityToJson.html b/docs/reference/exportDataDensityToJson.html index d6dd35f8..29bc818a 100644 --- a/docs/reference/exportDataDensityToJson.html +++ b/docs/reference/exportDataDensityToJson.html @@ -1,9 +1,9 @@ -exportDataDensityToJson — exportDataDensityToJson • AchillesexportDataDensityToJson — exportDataDensityToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportDataDensityToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportDataDensityToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportDataDensityToJson(connectionDetails,
-                        cdmDatabaseSchema = "cdm4_sim",
-                        outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportDeathToJson.html b/docs/reference/exportDeathToJson.html index b991f859..56f44198 100644 --- a/docs/reference/exportDeathToJson.html +++ b/docs/reference/exportDeathToJson.html @@ -1,9 +1,9 @@ -exportDeathToJson — exportDeathToJson • AchillesexportDeathToJson — exportDeathToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportDeathToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportDeathToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportDeathToJson(connectionDetails,
-                  cdmDatabaseSchema = "cdm4_sim",
-                  outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportDrugEraToJson.html b/docs/reference/exportDrugEraToJson.html index b09e9a7f..b7e53507 100644 --- a/docs/reference/exportDrugEraToJson.html +++ b/docs/reference/exportDrugEraToJson.html @@ -1,9 +1,9 @@ -exportDrugEraToJson — exportDrugEraToJson • AchillesexportDrugEraToJson — exportDrugEraToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportDrugEraToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportDrugEraToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportDrugEraToJson(connectionDetails,
-                    cdmDatabaseSchema = "cdm4_sim",
-                    outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportDrugToJson.html b/docs/reference/exportDrugToJson.html index 6e8edf91..c843d6fe 100644 --- a/docs/reference/exportDrugToJson.html +++ b/docs/reference/exportDrugToJson.html @@ -1,9 +1,9 @@ -exportDrugToJson — exportDrugToJson • AchillesexportDrugToJson — exportDrugToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportDrugToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportDrugToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportDrugToJson(connectionDetails,
-                 cdmDatabaseSchema = "cdm4_sim",
-                 outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportMeasurementToJson.html b/docs/reference/exportMeasurementToJson.html index 3839cb36..6f1fd130 100644 --- a/docs/reference/exportMeasurementToJson.html +++ b/docs/reference/exportMeasurementToJson.html @@ -1,9 +1,9 @@ -exportMeasurementToJson — exportMeasurementToJson • AchillesexportMeasurementToJson — exportMeasurementToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportMeasurementToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportMeasurementToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportMeasurementToJson(connectionDetails,
-                        cdmDatabaseSchema = "cdm4_sim",
-                        outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportMetaToJson.html b/docs/reference/exportMetaToJson.html index 48831fb0..adae394b 100644 --- a/docs/reference/exportMetaToJson.html +++ b/docs/reference/exportMetaToJson.html @@ -1,9 +1,9 @@ -exportMetaToJson — exportMetaToJson • AchillesexportMetaToJson — exportMetaToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportMetaToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportMetaToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportMetaToJson(connectionDetails,
-                 cdmDatabaseSchema = "cdm4_sim",
-                 outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportObservationPeriodToJson.html b/docs/reference/exportObservationPeriodToJson.html index 5b48b2ef..8c6dc740 100644 --- a/docs/reference/exportObservationPeriodToJson.html +++ b/docs/reference/exportObservationPeriodToJson.html @@ -1,10 +1,10 @@ -exportObservationPeriodToJson — exportObservationPeriodToJson • AchillesexportObservationPeriodToJson — exportObservationPeriodToJson • Achilles - +
    @@ -29,7 +29,7 @@
    • - +

    exportObservationPeriodToJson

    - + Source: R/exportToJson.R
    @@ -76,27 +82,29 @@

    exportObservationPeriodToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -104,9 +112,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -115,13 +121,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportObservationPeriodToJson(connectionDetails,
-                              cdmDatabaseSchema = "cdm4_sim",
-                              outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -136,15 +145,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportObservationToJson.html b/docs/reference/exportObservationToJson.html index 68690070..a1e5c3a6 100644 --- a/docs/reference/exportObservationToJson.html +++ b/docs/reference/exportObservationToJson.html @@ -1,9 +1,9 @@ -exportObservationToJson — exportObservationToJson • AchillesexportObservationToJson — exportObservationToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportObservationToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportObservationToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportObservationToJson(connectionDetails,
-                        cdmDatabaseSchema = "cdm4_sim",
-                        outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportPerformanceToJson.html b/docs/reference/exportPerformanceToJson.html index 602806e9..c2ef56f1 100644 --- a/docs/reference/exportPerformanceToJson.html +++ b/docs/reference/exportPerformanceToJson.html @@ -1,9 +1,9 @@ -exportPerformanceToJson exportPerformanceToJson — exportPerformanceToJson • AchillesexportPerformanceToJson exportPerformanceToJson — exportPerformanceToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportPerformanceToJson exportPerformanceToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportPerformanceToJson exportPerformanceToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportPerformanceToJson(connectionDetails,
-                        cdmDatabaseSchema = "cdm4_sim",
-                        outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportPersonToJson.html b/docs/reference/exportPersonToJson.html index fd69ffc4..d5005654 100644 --- a/docs/reference/exportPersonToJson.html +++ b/docs/reference/exportPersonToJson.html @@ -1,9 +1,9 @@ -exportPersonToJson — exportPersonToJson • AchillesexportPersonToJson — exportPersonToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportPersonToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportPersonToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportPersonToJson(connectionDetails,
-                   cdmDatabaseSchema = "cdm4_sim",
-                   outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportProcedureToJson.html b/docs/reference/exportProcedureToJson.html index 60472848..c110e641 100644 --- a/docs/reference/exportProcedureToJson.html +++ b/docs/reference/exportProcedureToJson.html @@ -1,9 +1,9 @@ -exportProcedureToJson — exportProcedureToJson • AchillesexportProcedureToJson — exportProcedureToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportProcedureToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportProcedureToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportProcedureToJson(connectionDetails,
-                      cdmDatabaseSchema = "cdm4_sim",
-                      outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportResultsToCSV.html b/docs/reference/exportResultsToCSV.html index 732861a0..b82ba005 100644 --- a/docs/reference/exportResultsToCSV.html +++ b/docs/reference/exportResultsToCSV.html @@ -1,9 +1,9 @@ -exportResultsToCSV — exportResultsToCSV • AchillesexportResultsToCSV — exportResultsToCSV • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportResultsToCSV

    - + Source: R/exportToCSV.R
    @@ -74,41 +80,41 @@

    exportResultsToCSV

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Fully qualified name of database schema that we can write final results to. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_results.dbo'.

    -
    analysisIds
    +
    analysisIds

    (OPTIONAL) A vector containing the set of Achilles analysisIds for which results will be generated. If not specified, all analyses will be executed. Use getAnalysisDetails to get a list of all Achilles analyses and their Ids.

    -
    minCellCount
    +
    minCellCount

    To avoid patient identification, cells with small counts (<= minCellCount) are deleted. Set to 0 for complete summary without small cell count restrictions.

    -
    exportFolder
    +
    exportFolder

    Path to store results

    Value

    - - -

    No return value. Called to export CSV file to the file system.

    +

    No return value. Called to export CSV file to the file system.

    Details

    @@ -127,15 +133,15 @@

    Details

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportToAres.html b/docs/reference/exportToAres.html index 87ddd3cd..bf05aa85 100644 --- a/docs/reference/exportToAres.html +++ b/docs/reference/exportToAres.html @@ -1,9 +1,9 @@ -exportToAres — exportToAres • AchillesexportToAres — exportToAres • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportToAres

    - + Source: R/exportToAres.R
    @@ -69,42 +75,47 @@

    exportToAres

    resultsDatabaseSchema, vocabDatabaseSchema, outputPath, + outputFormat = "default", reports = c() )

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the OMOP CDM.

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    string name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    -
    outputPath
    +
    outputPath

    A folder location to save the JSON files. Default is current working folder

    -
    reports
    +
    outputFormat
    +

    default or alternatively "duckdb" to use parquet and duckdb formats.

    + + +
    reports

    vector of reports to run, c() defaults to all reports

    See showReportTypes for a list of all report types

    Value

    - - -

    none

    +

    none

    Details

    @@ -123,15 +134,15 @@

    Details

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportToJson.html b/docs/reference/exportToJson.html index c625bef2..72768a34 100644 --- a/docs/reference/exportToJson.html +++ b/docs/reference/exportToJson.html @@ -1,9 +1,9 @@ -exportToJson — exportToJson • AchillesexportToJson — exportToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportToJson

    - + Source: R/exportToJson.R
    @@ -76,38 +82,40 @@

    exportToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the OMOP CDM.

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    A folder location to save the JSON files. Default is current working folder

    -
    reports
    +
    reports

    A character vector listing the set of reports to generate. Default is all reports.

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    string name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    -
    compressIntoOneFile
    +
    compressIntoOneFile

    Boolean indicating if the JSON files should be compressed into one zip file. Please note that in Windows, the zip application must be stored in the system environment, e.g. Sys.setenv("R_ZIPCMD", @@ -118,9 +126,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -129,11 +135,13 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportToJson(connectionDetails, cdmDatabaseSchema = "cdm4_sim", outputPath = "your/output/path")
-}
+} # }
    @@ -148,15 +156,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportVisitDetailToJson.html b/docs/reference/exportVisitDetailToJson.html index 4ea87966..be44b636 100644 --- a/docs/reference/exportVisitDetailToJson.html +++ b/docs/reference/exportVisitDetailToJson.html @@ -1,9 +1,9 @@ -exportVisitDetailToJson — exportVisitDetailToJson • AchillesexportVisitDetailToJson — exportVisitDetailToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportVisitDetailToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportVisitDetailToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportVisitDetailToJson(connectionDetails,
-                        cdmDatabaseSchema = "cdm4_sim",
-                        outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/exportVisitToJson.html b/docs/reference/exportVisitToJson.html index 0a4bbe17..861bba09 100644 --- a/docs/reference/exportVisitToJson.html +++ b/docs/reference/exportVisitToJson.html @@ -1,9 +1,9 @@ -exportVisitToJson — exportVisitToJson • AchillesexportVisitToJson — exportVisitToJson • Achilles - +
    @@ -28,7 +28,7 @@
    • - +

    exportVisitToJson

    - + Source: R/exportToJson.R
    @@ -74,27 +80,29 @@

    exportVisitToJson

    Arguments

    -
    connectionDetails
    + + +
    connectionDetails

    An R object of type ConnectionDetail (details for the function that contains server info, database type, optionally username/password, port)

    -
    cdmDatabaseSchema
    +
    cdmDatabaseSchema

    Name of the database schema that contains the vocabulary files

    -
    resultsDatabaseSchema
    +
    resultsDatabaseSchema

    Name of the database schema that contains the Achilles analysis files. Default is cdmDatabaseSchema

    -
    outputPath
    +
    outputPath

    folder location to save the JSON files. Default is current working folder

    -
    vocabDatabaseSchema
    +
    vocabDatabaseSchema

    name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

    @@ -102,9 +110,7 @@

    Arguments

    Value

    - - -

    none

    +

    none

    Details

    @@ -113,13 +119,16 @@

    Details

    Examples

    - 
    if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
+    
    if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
 exportVisitToJson(connectionDetails,
-                  cdmDatabaseSchema = "cdm4_sim",
-                  outputPath = "your/output/path")
-}
+  cdmDatabaseSchema = "cdm4_sim",
+  outputPath = "your/output/path"
+)
+} # }
    @@ -134,15 +143,15 @@

    Examples

    -

    Site built with pkgdown 2.0.7.

    +

    Site built with pkgdown 2.1.3.

    - - + + diff --git a/docs/reference/generateDbSummary.html b/docs/reference/generateDbSummary.html index ac02078f..a52f5638 100644 --- a/docs/reference/generateDbSummary.html +++ b/docs/reference/generateDbSummary.html @@ -1,10 +1,10 @@ -generateDbSummary — generateDbSummary • AchillesgenerateDbSummary — generateDbSummary • Achilles - +
    @@ -29,7 +29,7 @@
    • -
      +
    • + Changelog +
      • +
      - +

      generateDbSummary

      - + Source: R/generateDbSummary.R
      -

      generateDbSummary can be run after the Achilles analyses are complete +

      generateDbSummary can be run after the Achilles analyses are complete to create a high-level database summary.

      - 
      generateDbSummary(
-  connectionDetails,
-  cdmDatabaseSchema,
-  resultsDatabaseSchema,
-  country,
-  provenance
-)
      + 
      generateDbSummary(
+  connectionDetails,
+  cdmDatabaseSchema,
+  resultsDatabaseSchema,
+  country,
+  provenance
+)

      Arguments

      -
      connectionDetails
      + + +
      connectionDetails

      An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

      -
      cdmDatabaseSchema
      + + +
      cdmDatabaseSchema

      Fully qualified name of database schema that contains OMOP CDM schema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_instance.dbo'.

      -
      resultsDatabaseSchema
      + + +
      resultsDatabaseSchema

      Fully qualified name of database schema that we can write final results to. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_results.dbo'.

      -
      country
      + + +
      country

      The country of origin of the database

      -
      provenance
      + + +
      provenance

      The provenance of the data (EHR, claims, registry, etc)

      +

      Value

      @@ -102,15 +125,18 @@

      Details

      Examples

      - 
      if (FALSE) {
-connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server",
-                                                                server = "yourserver")
-dbSummary <- generateDbSummary(connectionDetails,
-                               cdmDatabaseSchema = "cdm_schema",
-                               resultsDatabaseSchema = "results_schema",
-                               country = "Country of Origin",
-                               provenance = "Provenance of data")
-}
+    
      if (FALSE) { # \dontrun{
+connectionDetails <- DatabaseConnector::createConnectionDetails(
+  dbms = "sql server",
+  server = "yourserver"
+)
+dbSummary <- generateDbSummary(connectionDetails,
+  cdmDatabaseSchema = "cdm_schema",
+  resultsDatabaseSchema = "results_schema",
+  country = "Country of Origin",
+  provenance = "Provenance of data"
+)
+} # }
      @@ -125,15 +151,15 @@

      Examples

      -

      Site built with pkgdown 2.0.3.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/getAnalysisDetails.html b/docs/reference/getAnalysisDetails.html index 0f13d863..2fb4af19 100644 --- a/docs/reference/getAnalysisDetails.html +++ b/docs/reference/getAnalysisDetails.html @@ -1,9 +1,9 @@ -Get all analysis details — getAnalysisDetails • AchillesGet all analysis details — getAnalysisDetails • Achilles - +
      @@ -28,7 +28,7 @@
      • - +

      Get all analysis details

      - + Source: R/Achilles.R
      @@ -68,9 +74,7 @@

      Get all analysis details

      Value

      - - -

      A data.frame with the analysis details.

      +

      A data.frame with the analysis details.

      Details

      @@ -89,15 +93,15 @@

      Details

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/getSeasonalityScore.html b/docs/reference/getSeasonalityScore.html index b2a011f6..5f7309bc 100644 --- a/docs/reference/getSeasonalityScore.html +++ b/docs/reference/getSeasonalityScore.html @@ -1,9 +1,9 @@ -Get the seasonality score for a given monthly time series — getSeasonalityScore • AchillesGet the seasonality score for a given monthly time series — getSeasonalityScore • Achilles - +
      @@ -28,7 +28,7 @@
      • - +

      Get the seasonality score for a given monthly time series

      - + Source: R/getSeasonalityScore.r
      @@ -68,20 +74,20 @@

      Get the seasonality score for a given monthly time series

      Arguments

      -
      tsData
      + + +
      tsData

      A time series object.

      Value

      - - -

      A numeric value between 0 and 1 (inclusive) representing the seasonality of a time series.

      +

      A numeric value between 0 and 1 (inclusive) representing the seasonality of a time series.

      Details

      The degree of seasonality of a monthly time series is based on its departure from a uniform distribution. -If the number of cases for a given concept is uniformly distributed across all time periods (in this case, all months), +If the number of cases for a given concept is uniformly distributed across all time periods (in this case, all months), then its monthly proportion would be approximately constant. In this case, the time series would be considered "strictly non-seasonal" and its "seasonality score" would be zero. Similarly, if all cases recur at a single point in time (that is, in a single month), such a time series would be considered @@ -101,15 +107,15 @@

      Details

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/getTemporalData.html b/docs/reference/getTemporalData.html index 33910a16..559ffd1a 100644 --- a/docs/reference/getTemporalData.html +++ b/docs/reference/getTemporalData.html @@ -1,10 +1,10 @@ -getTemporalData — getTemporalData • AchillesgetTemporalData — getTemporalData • Achilles - +
      @@ -29,7 +29,7 @@
      • - +

      getTemporalData

      - + Source: R/getTemporalData.r
      @@ -76,33 +82,35 @@

      getTemporalData

      Arguments

      -
      connectionDetails
      + + +
      connectionDetails

      An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

      -
      cdmDatabaseSchema
      +
      cdmDatabaseSchema

      Fully qualified name of database schema that contains OMOP CDM schema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_instance.dbo'.

      -
      resultsDatabaseSchema
      +
      resultsDatabaseSchema

      Fully qualified name of database schema that we can write final results to. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_results.dbo'.

      -
      analysisIds
      +
      analysisIds

      (OPTIONAL) A vector containing the set of Achilles analysisIds for which results will be returned. The following are supported: 202,402,602,702,802,1802,2102. If not specified, data for all analysis will be returned. Ignored if conceptId is given.

      -
      conceptId
      +
      conceptId

      (OPTIONAL) A SNOMED concept_id from the CONCEPT table for which a monthly Achilles analysis exists. If not specified, all concepts for a given analysis will be returned.

      @@ -110,11 +118,7 @@

      Arguments

      Value

      - - -

      A data frame of query results from DatabaseConnector

      - - +

      A data frame of query results from DatabaseConnector

      Details

      @@ -126,13 +130,14 @@

      Details

      Examples

      - 
      if (FALSE) {
+    
      if (FALSE) { # \dontrun{
 pneumonia <- 255848
-monthlyResults <- getTemporalData(connectionDetails = connectionDetails,
-                                  cdmDatabaseSchema = "cdm",
-
-  resultsDatabaseSchema = "results", conceptId = pneumonia)
-}
+monthlyResults <- getTemporalData(
+  connectionDetails = connectionDetails,
+  cdmDatabaseSchema = "cdm",
+  resultsDatabaseSchema = "results", conceptId = pneumonia
+)
+} # }
      @@ -148,15 +153,15 @@

      Examples

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/index.html b/docs/reference/index.html index 5e2af3b1..db04320f 100644 --- a/docs/reference/index.html +++ b/docs/reference/index.html @@ -1,9 +1,9 @@ -Function reference • AchillesPackage index • Achilles - +
      @@ -28,7 +28,7 @@
      • - +
      @@ -152,6 +158,10 @@

      All functions exportVisitToJson()

      exportVisitToJson

      + +

      generateDbSummary()

      + +

      generateDbSummary

      getAnalysisDetails()

      @@ -209,15 +219,15 @@

      All functions
      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/isStationary.html b/docs/reference/isStationary.html index e0eb84f4..401a505d 100644 --- a/docs/reference/isStationary.html +++ b/docs/reference/isStationary.html @@ -1,9 +1,9 @@ -Determine whether or not a time series is stationary in the mean — isStationary • AchillesDetermine whether or not a time series is stationary in the mean — isStationary • Achilles - +
      @@ -28,7 +28,7 @@
      • - +

      Determine whether or not a time series is stationary in the mean

      - + Source: R/isStationary.r
      @@ -68,20 +74,20 @@

      Determine whether or not a time series is stationary in the mean

      Arguments

      -
      tsData
      + + +
      tsData

      A time series object.

      Value

      - - -

      A boolean indicating whether or not the given time series is stationary.

      +

      A boolean indicating whether or not the given time series is stationary.

      Details

      A time series must have a minimum of three complete years of data. -For details on the implementation of the Augmented Dickey-Fuller test, +For details on the implementation of the Augmented Dickey-Fuller test, see the tseries package on cran.

      @@ -97,15 +103,15 @@

      Details

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/listMissingAnalyses.html b/docs/reference/listMissingAnalyses.html index 78a80e0b..00d2a6b0 100644 --- a/docs/reference/listMissingAnalyses.html +++ b/docs/reference/listMissingAnalyses.html @@ -1,10 +1,10 @@ -listMissingAnalyses — listMissingAnalyses • AchilleslistMissingAnalyses — listMissingAnalyses • Achilles - +
      @@ -29,7 +29,7 @@
      • - +

      listMissingAnalyses

      - + Source: R/listMissingAnalyses.r
      @@ -70,32 +76,32 @@

      listMissingAnalyses

      Arguments

      -
      connectionDetails
      + + +
      connectionDetails

      An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

      -
      resultsDatabaseSchema
      +
      resultsDatabaseSchema

      Fully qualified name of database schema that contains achilles_results and achilles_results_dist tables.

      Value

      - - -

      A dataframe which is a subset of getAnalysisDetails

      - - +

      A dataframe which is a subset of getAnalysisDetails

      Examples

      - 
      if (FALSE) {
-Achilles::listMissingAnalyses(connectionDetails = connectionDetails,
-                              resultsDatabaseSchema = "results")
-}
+    
      if (FALSE) { # \dontrun{
+Achilles::listMissingAnalyses(
+  connectionDetails = connectionDetails,
+  resultsDatabaseSchema = "results"
+)
+} # }
      @@ -111,15 +117,15 @@

      Examples

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/optimizeAtlasCache.html b/docs/reference/optimizeAtlasCache.html index fe97f113..77cbec49 100644 --- a/docs/reference/optimizeAtlasCache.html +++ b/docs/reference/optimizeAtlasCache.html @@ -1,9 +1,9 @@ -Optimize atlas cache — optimizeAtlasCache • AchillesOptimize atlas cache — optimizeAtlasCache • Achilles - +
      @@ -28,7 +28,7 @@
      • - +

      Optimize atlas cache

      - + Source: R/Achilles.R
      @@ -76,49 +82,49 @@

      Optimize atlas cache

      Arguments

      -
      connectionDetails
      + + +
      connectionDetails

      An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

      -
      resultsDatabaseSchema
      +
      resultsDatabaseSchema

      Fully qualified name of database schema that we can write final results to. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_results.dbo'.

      -
      vocabDatabaseSchema
      +
      vocabDatabaseSchema

      String name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

      -
      outputFolder
      +
      outputFolder

      Path to store logs and SQL files

      -
      sqlOnly
      +
      sqlOnly

      TRUE = just generate SQL files, don't actually run, FALSE = run Achilles

      -
      verboseMode
      +
      verboseMode

      Boolean to determine if the console will show all execution steps. Default = TRUE

      -
      tempAchillesPrefix
      +
      tempAchillesPrefix

      The prefix to use for the "temporary" (but actually permanent) Achilles analyses tables. Default is "tmpach"

      Value

      - - -

      The SQL statement executed to update cache tables is returned.

      +

      The SQL statement executed to update cache tables is returned.

      Details

      @@ -137,15 +143,15 @@

      Details

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/performTemporalCharacterization.html b/docs/reference/performTemporalCharacterization.html index 47c6fb81..e244c8ae 100644 --- a/docs/reference/performTemporalCharacterization.html +++ b/docs/reference/performTemporalCharacterization.html @@ -1,9 +1,9 @@ -performTemporalCharacterization — performTemporalCharacterization • AchillesperformTemporalCharacterization — performTemporalCharacterization • Achilles - +
      @@ -28,7 +28,7 @@
      • - +

      performTemporalCharacterization

      - + Source: R/performTemporalCharacterization.r
      @@ -75,45 +81,45 @@

      performTemporalCharacterization

      Arguments

      -
      connectionDetails
      + + +
      connectionDetails

      An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

      -
      cdmDatabaseSchema
      +
      cdmDatabaseSchema

      Fully qualified name of database schema that contains OMOP CDM schema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_instance.dbo'.

      -
      resultsDatabaseSchema
      +
      resultsDatabaseSchema

      Fully qualified name of database schema that we can write final results to. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_results.dbo'.

      -
      analysisIds
      +
      analysisIds

      (OPTIONAL) A vector containing the set of Achilles analysisIds for which results will be returned. The following are supported: 202,402,602,702,802,1802,2102. If not specified, data for all analysis will be returned. Ignored if conceptId is given.

      -
      conceptId
      +
      conceptId

      (OPTIONAL) A SNOMED concept_id from the CONCEPT table for which a monthly Achilles analysis exists. If not specified, all concepts for a given analysis will be returned.

      -
      outputFile
      +
      outputFile

      CSV file where temporal characterization will be written. Default is temporal-characterization.csv.

      Value

      - - -

      A csv file with temporal analyses for each time series

      +

      A csv file with temporal analyses for each time series

      Details

      @@ -130,31 +136,34 @@

      Details

      Examples

      - 
      if (FALSE) {
+    
      if (FALSE) { # \dontrun{
 # Example 1:
 pneumonia <- 255848
 performTemporalCharacterization(
-  connectionDetails     = connectionDetails,
-  cdmDatabaseSchema     = "cdm",
+  connectionDetails = connectionDetails,
+  cdmDatabaseSchema = "cdm",
   resultsDatabaseSchema = "results",
-  conceptId             = pneumonia,
- outputFolder          = "output/pneumoniaTemporalChar.csv")
+  conceptId = pneumonia,
+  outputFolder = "output/pneumoniaTemporalChar.csv"
+)
 
 # Example 2:
 performTemporalCharacterization(
-  connectionDetails     = connectionDetails,
-  cdmDatabaseSchema     = "cdm",
+  connectionDetails = connectionDetails,
+  cdmDatabaseSchema = "cdm",
   resultsDatabaseSchema = "results",
-  analysisIds           = c(402,702),
- outputFolder          = "output/conditionAndDrugTemporalChar.csv")
+  analysisIds = c(402, 702),
+  outputFolder = "output/conditionAndDrugTemporalChar.csv"
+)
 
 # Example 3:
 performTemporalCharacterization(
-  connectionDetails     = connectionDetails,
-  cdmDatabaseSchema     = "cdm",
+  connectionDetails = connectionDetails,
+  cdmDatabaseSchema = "cdm",
   resultsDatabaseSchema = "results",
- outputFolder          = "output/CompleteTemporalChar.csv")
-}
+  outputFolder = "output/CompleteTemporalChar.csv"
+)
+} # }
      @@ -170,15 +179,15 @@

      Examples

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/runMissingAnalyses.html b/docs/reference/runMissingAnalyses.html index 3b9afb0b..9125c1fe 100644 --- a/docs/reference/runMissingAnalyses.html +++ b/docs/reference/runMissingAnalyses.html @@ -1,9 +1,9 @@ -runMissingAnalyses — runMissingAnalyses • AchillesrunMissingAnalyses — runMissingAnalyses • Achilles - +
      @@ -28,7 +28,7 @@
      • - +

      runMissingAnalyses

      - + Source: R/runMissingAnalyses.r
      @@ -77,26 +83,28 @@

      runMissingAnalyses

      Arguments

      -
      connectionDetails
      + + +
      connectionDetails

      An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package.

      -
      cdmDatabaseSchema
      +
      cdmDatabaseSchema

      Fully qualified name of database schema that contains OMOP CDM schema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_instance.dbo'.

      -
      resultsDatabaseSchema
      +
      resultsDatabaseSchema

      Fully qualified name of database schema that we can write final results to. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_results.dbo'.

      -
      scratchDatabaseSchema
      +
      scratchDatabaseSchema

      Fully qualified name of the database schema that will store all of the intermediate scratch tables, so for example, on SQL Server, 'cdm_scratch.dbo'. Must be accessible to/from the cdmDatabaseSchema @@ -105,24 +113,24 @@

      Arguments

      temporary tables instead of permanent tables.

      -
      vocabDatabaseSchema
      +
      vocabDatabaseSchema

      String name of database schema that contains OMOP Vocabulary. Default is cdmDatabaseSchema. On SQL Server, this should specifiy both the database and the schema, so for example 'results.dbo'.

      -
      tempEmulationSchema
      +
      tempEmulationSchema

      Formerly tempEmulationSchema. For databases like Oracle where you must specify the name of the database schema where you want all temporary tables to be managed. Requires create/insert permissions to this database.

      -
      outputFolder
      +
      outputFolder

      Path to store logs and SQL files

      -
      defaultAnalysesOnly
      +
      defaultAnalysesOnly

      Boolean to determine if only default analyses should be run. Including non-default analyses is substantially more resource intensive. Default = TRUE

      @@ -130,20 +138,19 @@

      Arguments

      Value

      - - -

      No return value. Run to execute analyses currently missing from results.

      +

      No return value. Run to execute analyses currently missing from results.

      Examples

      - 
      if (FALSE) {
-Achilles::runMissingAnalyses(connectionDetails = connectionDetails,
-                             cdmDatabaseSchema = "cdm",
-                             resultsDatabaseSchema = "results",
-
-  outputFolder = "/tmp")
-}
+    
      if (FALSE) { # \dontrun{
+Achilles::runMissingAnalyses(
+  connectionDetails = connectionDetails,
+  cdmDatabaseSchema = "cdm",
+  resultsDatabaseSchema = "results",
+  outputFolder = "/tmp"
+)
+} # }
      @@ -159,15 +166,15 @@

      Examples

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/showReportTypes.html b/docs/reference/showReportTypes.html index a569f5bb..01fae467 100644 --- a/docs/reference/showReportTypes.html +++ b/docs/reference/showReportTypes.html @@ -1,10 +1,10 @@ -showReportTypes — showReportTypes • AchillesshowReportTypes — showReportTypes • Achilles - +
      @@ -29,7 +29,7 @@
      • - +

      showReportTypes

      - + Source: R/exportToJson.R
      @@ -70,9 +76,7 @@

      showReportTypes

      Value

      - - -

      none (opens the allReports vector in a View() display)

      +

      none (opens the allReports vector in a View() display)

      Details

      @@ -83,9 +87,9 @@

      Details

      Examples

      - 
      if (FALSE) {
+    
      if (FALSE) { # \dontrun{
 showReportTypes()
-}
+} # }
      @@ -100,15 +104,15 @@

      Examples

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/sumAcrossYears.html b/docs/reference/sumAcrossYears.html index ca068612..388f3196 100644 --- a/docs/reference/sumAcrossYears.html +++ b/docs/reference/sumAcrossYears.html @@ -1,9 +1,9 @@ -For a monhtly time series, compute sum and proportion by month across all years — sumAcrossYears • AchillesFor a monhtly time series, compute sum and proportion by month across all years — sumAcrossYears • Achilles - +
      @@ -28,7 +28,7 @@
      • - +

      For a monhtly time series, compute sum and proportion by month across all years

      - + Source: R/sumAcrossYears.r
      @@ -68,15 +74,15 @@

      For a monhtly time series, compute sum and proportion by month across all ye

      Arguments

      -
      tsData
      + + +
      tsData

      A time series object

      Value

      - - -

      A data frame reporting the monthly sum across all years and the proportion this sum contributes to the total.

      +

      A data frame reporting the monthly sum across all years and the proportion this sum contributes to the total.

      @@ -91,15 +97,15 @@

      Value

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/reference/tsCompleteYears.html b/docs/reference/tsCompleteYears.html index 43a4ceea..5a988f50 100644 --- a/docs/reference/tsCompleteYears.html +++ b/docs/reference/tsCompleteYears.html @@ -1,9 +1,9 @@ -Trim a monthly time series object to so that partial years are removed — tsCompleteYears • AchillesTrim a monthly time series object to so that partial years are removed — tsCompleteYears • Achilles - +
      @@ -28,7 +28,7 @@
      • - +

      Trim a monthly time series object to so that partial years are removed

      - + Source: R/tsCompleteYears.r
      @@ -68,15 +74,15 @@

      Trim a monthly time series object to so that partial years are removed

      Arguments

      -
      tsData
      + + +
      tsData

      A time series object

      Value

      - - -

      A time series with partial years removed.

      +

      A time series with partial years removed.

      Details

      @@ -95,15 +101,15 @@

      Details

      -

      Site built with pkgdown 2.0.7.

      +

      Site built with pkgdown 2.1.3.

      - - + + diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 4a6b86d3..1b46fafe 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -1,159 +1,55 @@ - - - - /404.html - - - /articles/GettingStarted.html - - - /articles/index.html - - - /articles/RunningAchilles.html - - - /authors.html - - - /index.html - - - /ISSUE_TEMPLATE.html - - - /news/index.html - - - /reference/achilles.html - - - /reference/achillesHeel.html - - - /reference/addDataSource.html - - - /reference/createIndices.html - - - /reference/createTimeSeries.html - - - /reference/dropAllScratchTables.html - - - /reference/exportAO.html - - - /reference/exportConditionEraToJson.html - - - /reference/exportConditionToJson.html - - - /reference/exportDashboardToJson.html - - - /reference/exportDataDensityToJson.html - - - /reference/exportDeathToJson.html - - - /reference/exportDrugEraToJson.html - - - /reference/exportDrugToJson.html - - - /reference/exportHeelToJson.html - - - /reference/exportMeasurementToJson.html - - - /reference/exportMetaToJson.html - - - /reference/exportObservationPeriodToJson.html - - - /reference/exportObservationToJson.html - - - /reference/exportPerformanceToJson.html - - - /reference/exportPersonToJson.html - - - /reference/exportProcedureToJson.html - - - /reference/exportResultsToCSV.html - - - /reference/exportToAres.html - - - /reference/exportToJson.html - - - /reference/exportVisitDetailToJson.html - - - /reference/exportVisitToJson.html - - - /reference/fetchAchillesAnalysisResults.html - - - /reference/fetchAchillesHeelResults.html - - - /reference/generateDbSummary.html - - - /reference/getAnalysisDetails.html - - - /reference/getSeasonalityScore.html - - - /reference/getTemporalData.html - - - /reference/index.html - - - /reference/isStationary.html - - - /reference/launchHeelResultsViewer.html - - - /reference/listMissingAnalyses.html - - - /reference/optimizeAtlasCache.html - - - /reference/performTemporalCharacterization.html - - - /reference/runMissingAnalyses.html - - - /reference/showReportTypes.html - - - /reference/sumAcrossYears.html - - - /reference/tsCompleteYears.html - - - /reference/validateSchema.html - + +/404.html +/ISSUE_TEMPLATE.html +/articles/GettingStarted.html +/articles/RunningAchilles.html +/articles/index.html +/authors.html +/index.html +/news/index.html +/reference/achilles.html +/reference/achillesHeel.html +/reference/addDataSource.html +/reference/createIndices.html +/reference/createTimeSeries.html +/reference/dropAllScratchTables.html +/reference/exportAO.html +/reference/exportConditionEraToJson.html +/reference/exportConditionToJson.html +/reference/exportDashboardToJson.html +/reference/exportDataDensityToJson.html +/reference/exportDeathToJson.html +/reference/exportDrugEraToJson.html +/reference/exportDrugToJson.html +/reference/exportHeelToJson.html +/reference/exportMeasurementToJson.html +/reference/exportMetaToJson.html +/reference/exportObservationPeriodToJson.html +/reference/exportObservationToJson.html +/reference/exportPerformanceToJson.html +/reference/exportPersonToJson.html +/reference/exportProcedureToJson.html +/reference/exportResultsToCSV.html +/reference/exportToAres.html +/reference/exportToJson.html +/reference/exportVisitDetailToJson.html +/reference/exportVisitToJson.html +/reference/fetchAchillesAnalysisResults.html +/reference/fetchAchillesHeelResults.html +/reference/generateDbSummary.html +/reference/getAnalysisDetails.html +/reference/getSeasonalityScore.html +/reference/getTemporalData.html +/reference/index.html +/reference/isStationary.html +/reference/launchHeelResultsViewer.html +/reference/listMissingAnalyses.html +/reference/optimizeAtlasCache.html +/reference/performTemporalCharacterization.html +/reference/runMissingAnalyses.html +/reference/showReportTypes.html +/reference/sumAcrossYears.html +/reference/tsCompleteYears.html +/reference/validateSchema.html + diff --git a/extras/Achilles.pdf b/extras/Achilles.pdf deleted file mode 100644 index 6ac2e70a..00000000 Binary files a/extras/Achilles.pdf and /dev/null differ diff --git a/extras/GenerateDatabaseSummary.R b/extras/GenerateDatabaseSummary.R index ffd4cc83..082eb0aa 100644 --- a/extras/GenerateDatabaseSummary.R +++ b/extras/GenerateDatabaseSummary.R @@ -17,20 +17,22 @@ Achilles::achilles( cdmVersion = cdmVersion, connectionDetails = connectionDetails, cdmDatabaseSchema = cdmDatabaseSchema, - resultsDatabaseSchema = cdmDatabaseSchema, - smallCellCount = 0, - createTable = TRUE, - createIndices = FALSE, + resultsDatabaseSchema = cdmDatabaseSchema, smallCellCount = 0, createTable = TRUE, createIndices = FALSE, sqlOnly = FALSE ) -dbSummary <- Achilles::generateDbSummary(connectionDetails, cdmDatabaseSchema, resultsDatabaseSchema,demoCountry,demoProvenance) +dbSummary <- Achilles::generateDbSummary( + connectionDetails, + cdmDatabaseSchema, + resultsDatabaseSchema, + demoCountry, demoProvenance +) tableOutput <- dbSummary$summary -tableOutput$"Source Vocabularies" <- paste(dbSummary$sourceVocabs$VOCABULARY_ID, collapse="
      ") -tableOutput$"Visits" <- paste(dbSummary$visitDist$CONCEPT_NAME, collapse="
      ") +tableOutput$"Source Vocabularies" <- paste(dbSummary$sourceVocabs$VOCABULARY_ID, collapse = "
      ") +tableOutput$Visits <- paste(dbSummary$visitDist$CONCEPT_NAME, collapse = "
      ") # this will open results in the RStudio Viewer which can then be exported to image or html. -kbl(tableOutput,escape=F) %>% kableExtra::kable_styling() - +kbl(tableOutput, escape = F) %>% + kableExtra::kable_styling() diff --git a/extras/PackageMaintenance.R b/extras/PackageMaintenance.R index 4c6e99b3..f85e7a67 100755 --- a/extras/PackageMaintenance.R +++ b/extras/PackageMaintenance.R @@ -1,15 +1,15 @@ # @file PackageMaintenance # -# Copyright 2023 Observational Health Data Sciences and Informatics +# Copyright 2025 Observational Health Data Sciences and Informatics # # This file is part of Achilles -# +# # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at -# +# # http://www.apache.org/licenses/LICENSE-2.0 -# +# # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. @@ -25,29 +25,34 @@ unlink(folder, recursive = TRUE, force = TRUE) file.exists(folder) # Format and check code -------------------------------------------------------- -OhdsiRTools::formatRFolder() +styler::style_dir() + OhdsiRTools::checkUsagePackage("Achilles") OhdsiRTools::updateCopyrightYearFolder() devtools::spell_check() devtools::check() -# devtools::check(document = FALSE, args=c("--no-tests")) -# codetools::checkUsagePackage("Achilles") # Regenerate manual, vignette PDFs, and website -------------------------------- unlink("extras/Achilles.pdf") shell("R CMD Rd2pdf ./ --output=extras/Achilles.pdf") dir.create("inst/doc") + rmarkdown::render("vignettes/RunningAchilles.Rmd", output_file = "../inst/doc/RunningAchilles.pdf", - rmarkdown::pdf_document(latex_engine = "pdflatex", - toc = TRUE, number_sections = TRUE) + rmarkdown::pdf_document( + latex_engine = "pdflatex", + toc = TRUE, number_sections = TRUE + ) ) + rmarkdown::render("vignettes/GettingStarted.Rmd", output_file = "../inst/doc/GettingStarted.pdf", - rmarkdown::pdf_document(latex_engine = "pdflatex", - toc = TRUE, number_sections = TRUE) + rmarkdown::pdf_document( + latex_engine = "pdflatex", + toc = TRUE, number_sections = TRUE + ) ) devtools::document() @@ -61,4 +66,4 @@ devtools::check_rhub() devtools::release() -devtools::check(cran=TRUE) +devtools::check(cran = TRUE) diff --git a/extras/iterativeAchillesProcessing.r b/extras/iterativeAchillesProcessing.r index 3a47fa93..97bb796a 100644 --- a/extras/iterativeAchillesProcessing.r +++ b/extras/iterativeAchillesProcessing.r @@ -1,82 +1,73 @@ - # HOW TO: # # Achilles processing can be time consuming and since it functions # as an all-or-nothing process, end failure (or any single failure) will result in no analyses -# being recorded and the underlying results tables not created. The example below demonstrates -# how to run Achilles on smaller-to-larger tables, as an alternative to the default all-or-nothing approach. -# +# being recorded and the underlying results tables not created. The example below demonstrates +# how to run Achilles on smaller-to-larger tables, as an alternative to the default all-or-nothing approach. +# library(Achilles) analysisDetails <- Achilles::getAnalysisDetails() -# Suppose that you'd like to run Achilles for PERSON, OBSERVATION_PERIOD, VISIT_OCCURRENCE, CONDITION_OCCURRENCE, DRUG_EXPOSURE, and MEASUREMENT -# in that order. The PERSON table is the smallest in our above list and we'd like to run achilles just for PERSON. If achilles has failed -# in the past and the achilles results tables were not created, then when running achilles for PERSON, we allow createTable and -# updateGivenAnalysesOnly to assume their default values (ie, we don't specify them). +# Suppose that you'd like to run Achilles for PERSON, OBSERVATION_PERIOD, VISIT_OCCURRENCE, +# CONDITION_OCCURRENCE, DRUG_EXPOSURE, and MEASUREMENT in that order. The PERSON table is the +# smallest in our above list and we'd like to run achilles just for PERSON. If achilles has failed +# in the past and the achilles results tables were not created, then when running achilles for +# PERSON, we allow createTable and updateGivenAnalysesOnly to assume their default values (ie, we +# don't specify them). -personOnly <- analysisDetails[analysisDetails$category == "Person",]$analysis_id +personOnly <- analysisDetails[analysisDetails$category == "Person", ]$analysis_id Achilles::achilles( - connectionDetails = connectionDetails, - cdmDatabaseSchema = cdmDatabaseSchema, + connectionDetails = connectionDetails, + cdmDatabaseSchema = cdmDatabaseSchema, resultsDatabaseSchema = resultsDatabaseSchema, - outputFolder = "Your output folder", - analysisIds = personOnly) + outputFolder = "Your output folder", analysisIds = personOnly +) -# Once the above completes successfully, you can move on to your next smallest table, OBSERVATION_PERIOD. This time though, -# we need to call Achilles such that the prior PERSON analyses are NOT deleted. We do so by using createTable = F and -# updateGivenAnalysisOnly = T. +# Once the above completes successfully, you can move on to your next smallest table, +# OBSERVATION_PERIOD. This time though, we need to call Achilles such that the prior PERSON +# analyses are NOT deleted. We do so by using createTable = F and updateGivenAnalysisOnly = T. -opOnly <- analysisDetails[analysisDetails$category == "Observation Period",]$analysis_id +opOnly <- analysisDetails[analysisDetails$category == "Observation Period", ]$analysis_id Achilles::achilles( - connectionDetails = connectionDetails, - cdmDatabaseSchema = cdmDatabaseSchema, - resultsDatabaseSchema = resultsDatabaseSchema, - outputFolder = "Your output folder", - analysisIds = opOnly, - createTable = F, - updateGivenAnalysesOnly = T) + connectionDetails = connectionDetails, + cdmDatabaseSchema = cdmDatabaseSchema, + resultsDatabaseSchema = resultsDatabaseSchema, + outputFolder = "Your output folder", analysisIds = opOnly, createTable = F, updateGivenAnalysesOnly = T +) -# We continue to execute Achilles for VISIT_OCCURRENCE, CONDITION_OCCURRENCE, DRUG_EXPOSURE, and MEASUREMENT -# as we did for OBSERVATION_PERIOD. For example, for VISIT_OCCURRENCE: +# We continue to execute Achilles for VISIT_OCCURRENCE, CONDITION_OCCURRENCE, DRUG_EXPOSURE, and +# MEASUREMENT as we did for OBSERVATION_PERIOD. For example, for VISIT_OCCURRENCE: -voOnly <- analysisDetails[analysisDetails$category == "Visit Occurrence",]$analysis_id +voOnly <- analysisDetails[analysisDetails$category == "Visit Occurrence", ]$analysis_id Achilles::achilles( - connectionDetails = connectionDetails, - cdmDatabaseSchema = cdmDatabaseSchema, - resultsDatabaseSchema = resultsDatabaseSchema, - outputFolder = "Your output folder", - analysisIds = voOnly, - createTable = F, - updateGivenAnalysesOnly = T) + connectionDetails = connectionDetails, + cdmDatabaseSchema = cdmDatabaseSchema, + resultsDatabaseSchema = resultsDatabaseSchema, + outputFolder = "Your output folder", analysisIds = voOnly, createTable = F, updateGivenAnalysesOnly = T +) -# Alternatively, Since personOnly, opOnly, and voOnly, are just vectors analysis_ids, you can loop through these one by one. -# If your achilles_results table does not exist, you need to ensure that achilles is invoked correctly to create that table (see above). -# This is painfully slow, but may be helpful for debugging. Here's an example. +# Alternatively, Since personOnly, opOnly, and voOnly, are just vectors analysis_ids, you can loop +# through these one by one. If your achilles_results table does not exist, you need to ensure that +# achilles is invoked correctly to create that table (see above). This is painfully slow, but may +# be helpful for debugging. Here's an example. for (vo_id in voOnly) { - Achilles::achilles( - connectionDetails = connectionDetails, - cdmDatabaseSchema = cdmDatabaseSchema, - resultsDatabaseSchema = resultsDatabaseSchema, - outputFolder = "Your output folder", - analysisIds = vo_id, - createTable = F, - updateGivenAnalysesOnly = T) + connectionDetails = connectionDetails, cdmDatabaseSchema = cdmDatabaseSchema, + resultsDatabaseSchema = resultsDatabaseSchema, outputFolder = "Your output folder", analysisIds = vo_id, + createTable = F, updateGivenAnalysesOnly = T + ) } -# Finally, the column names and data types for achilles_results and achilles_results_dist are found here: -# https://github.com/OHDSI/Achilles/blob/master/inst/csv/schemas/schema_achilles_results.csv -# https://github.com/OHDSI/Achilles/blob/master/inst/csv/schemas/schema_achilles_results_dist.csv +# Finally, the column names and data types for achilles_results and achilles_results_dist are found +# here: https://github.com/OHDSI/Achilles/blob/master/inst/csv/schemas/schema_achilles_results.csv +# https://github.com/OHDSI/Achilles/blob/master/inst/csv/schemas/schema_achilles_results_dist.csv # so they can be created manually in SQL as well. - - - diff --git a/inst/csv/achilles/achilles_analysis_details.csv b/inst/csv/achilles/achilles_analysis_details.csv index 9fe1556d..3d5da58c 100644 --- a/inst/csv/achilles/achilles_analysis_details.csv +++ b/inst/csv/achilles/achilles_analysis_details.csv @@ -35,7 +35,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 202,0,,"Number of persons by visit occurrence start month, by visit_concept_id",visit_concept_id,calendar month,,,,1,Visit Occurrence 203,1,,Number of distinct visit occurrence concepts per person,,,,,,1,Visit Occurrence 204,0,,"Number of persons with at least one visit occurrence, by visit_concept_id by calendar year by gender by age decile",visit_concept_id,calendar year,gender_concept_id,age decile,,1,Visit Occurrence -206,1,,Distribution of age by visit_concept_id,visit_concept_id,gender_concept_id,,,,1,Visit Occurrence +206,1,,Distribution of age by visit_concept_id and gender,visit_concept_id,gender_concept_id,,,,1,Visit Occurrence 207,0,,Number of visit records with invalid person_id,,,,,,1,Visit Occurrence 209,0,,Number of visit records with invalid care_site_id,,,,,,1,Visit Occurrence 210,0,,Number of visit_occurrence records outside a valid observation period,,,,,,1,Observation Period @@ -45,7 +45,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 220,0,,Number of visit occurrence records by visit occurrence start month,calendar month,,,,,1,Visit Occurrence 221,0,,Number of persons by visit start year,calendar year,,,,,1,Visit Occurrence 225,0,,Number of visit_occurrence records by visit_source_concept_id,visit_source_concept_id,,,,,1,Visit Occurrence -226,0,,Number of records by domain by visit_concept_id,visit_source_concept_id,cdm_table_name,,,,1,Visit Occurrence +226,0,,Number of records by domain by visit_concept_id,visit_concept_id,cdm_table_name,,,,1,Visit Occurrence 230,0,,Number of visit_occurrence records inside valid observation period,,,,,,0,Observation Period 231,0,,Proportion of people with at least one visit_occurrence record outside a valid observation period,Proportion,Number of people with a visit_occurrence record outside a valid observation period,Number of people in visit_occurrence,,,0,Observation Period 232,0,,Proportion of visit_occurrence records outside a valid observation period,Proportion,Number of visit_occurrence records outside a valid observation period,Number of visit_occurrence records,,,0,Observation Period @@ -59,7 +59,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 403,1,,Number of distinct condition occurrence concepts per person,,,,,,1,Condition Occurrence 404,0,,"Number of persons with at least one condition occurrence, by condition_concept_id by calendar year by gender by age decile",condition_concept_id,calendar year,gender_concept_id,age decile,,1,Condition Occurrence 405,0,,"Number of condition occurrence records, by condition_concept_id by condition_type_concept_id",condition_concept_id,condition_type_concept_id,,,,1,Condition Occurrence -406,1,,Distribution of age by condition_concept_id,condition_concept_id,gender_concept_id,,,,1,Condition Occurrence +406,1,,Distribution of age by condition_concept_id and gender,condition_concept_id,gender_concept_id,,,,1,Condition Occurrence 409,0,,Number of condition occurrence records with invalid person_id,,,,,,0,Condition Occurrence 410,0,,Number of condition occurrence records outside valid observation period,,,,,,0,Observation Period 411,0,,Number of condition occurrence records with end date < start date,,,,,,0,Condition Occurrence @@ -97,7 +97,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 603,1,,Number of distinct procedure occurrence concepts per person,,,,,,1,Procedure Occurrence 604,0,,"Number of persons with at least one procedure occurrence, by procedure_concept_id by calendar year by gender by age decile",procedure_concept_id,calendar year,gender_concept_id,age decile,,1,Procedure Occurrence 605,0,,"Number of procedure occurrence records, by procedure_concept_id by procedure_type_concept_id",procedure_concept_id,procedure_type_concept_id,,,,1,Procedure Occurrence -606,1,,Distribution of age by procedure_concept_id,procedure_concept_id,gender_concept_id,,,,1,Procedure Occurrence +606,1,,Distribution of age by procedure_concept_id and gender,procedure_concept_id,gender_concept_id,,,,1,Procedure Occurrence 609,0,,Number of procedure occurrence records with invalid person_id,,,,,,0,Procedure Occurrence 610,0,,Number of procedure occurrence records outside valid observation period,,,,,,0,Observation Period 612,0,,Number of procedure occurrence records with invalid provider_id,,,,,,0,Procedure Occurrence @@ -115,7 +115,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 703,1,,Number of distinct drug exposure concepts per person,,,,,,1,Drug Exposure 704,0,,"Number of persons with at least one drug exposure, by drug_concept_id by calendar year by gender by age decile",drug_concept_id,calendar year,gender_concept_id,age decile,,1,Drug Exposure 705,0,,"Number of drug exposure records, by drug_concept_id by drug_type_concept_id",drug_concept_id,drug_type_concept_id,,,,1,Drug Exposure -706,1,,Distribution of age by drug_concept_id,drug_concept_id,gender_concept_id,,,,1,Drug Exposure +706,1,,Distribution of age by drug_concept_id and gender,drug_concept_id,gender_concept_id,,,,1,Drug Exposure 709,0,,Number of drug exposure records with invalid person_id,,,,,,0,Drug Exposure 710,0,,Number of drug exposure records outside valid observation period,,,,,,0,Observation Period 711,0,,Number of drug exposure records with end date < start date,,,,,,0,Drug Exposure @@ -137,7 +137,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 803,1,,Number of distinct observation occurrence concepts per person,,,,,,1,Observation 804,0,,"Number of persons with at least one observation occurrence, by observation_concept_id by calendar year by gender by age decile",observation_concept_id,calendar year,gender_concept_id,age decile,,1,Observation 805,0,,"Number of observation occurrence records, by observation_concept_id by observation_type_concept_id",observation_concept_id,observation_type_concept_id,,,,1,Observation -806,1,,Distribution of age by observation_concept_id,observation_concept_id,gender_concept_id,,,,1,Observation +806,1,,Distribution of age by observation_concept_id and gender,observation_concept_id,gender_concept_id,,,,1,Observation 807,0,,"Number of observation occurrence records, by observation_concept_id and unit_concept_id",observation_concept_id,unit_concept_id,,,,1,Observation 809,0,,Number of observation records with invalid person_id,,,,,,0,Observation 810,0,,Number of observation records outside valid observation period,,,,,,0,Observation Period @@ -151,7 +151,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 824,0,,Number of distinct people with co-occurring observation observation_concept_id pairs,observation_concept_id,observation_concept_id,ranking,num_people,num_cases,0,Observation 825,0,,Number of observation records by observation_source_concept_id,observation_source_concept_id,,,,,1,Observation 826,0,,Number of observation records by value_as_concept_id,value_as_concept_id,,,,,1,Observation -827,0,,Number of observation records by unit_concept_id,unit_as_concept_id,,,,,1,Observation +827,0,,Number of observation records by unit_concept_id,unit_concept_id,,,,,1,Observation 830,0,,Number of observation records inside a valid observation period,,,,,,0,Observation Period 831,0,,Proportion of people with at least one observation record outside a valid observation period,Proportion,Number of people with a observation record outside a valid observation period,Number of people in observation,,,0,Observation Period 832,0,,Proportion of observation records outside a valid observation period,Proportion,Number of records in observation outside a valid observation period,Number of observation records,,,0,Observation Period @@ -161,7 +161,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 902,0,,"Number of persons by drug era start month, by drug_concept_id",drug_concept_id,calendar month,,,,1,Drug Era 903,1,,Number of distinct drug era concepts per person,,,,,,1,Drug Era 904,0,,"Number of persons with at least one drug era, by drug_concept_id by calendar year by gender by age decile",drug_concept_id,calendar year,gender_concept_id,age decile,,1,Drug Era -906,1,,Distribution of age by drug_concept_id,drug_concept_id,gender_concept_id,,,,1,Drug Era +906,1,,Distribution of age by drug_concept_id and gender,drug_concept_id,gender_concept_id,,,,1,Drug Era 907,1,,"Distribution of drug era length, by drug_concept_id",drug_concept_id,,,,,1,Drug Era 908,0,,Number of drug eras without valid person,,,,,,0,Drug Era 910,0,,Number of drug_era records outside valid observation period,,,,,,0,Observation Period @@ -175,7 +175,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 1002,0,,"Number of persons by condition era start month, by condition_concept_id",condition_concept_id,calendar month,,,,1,Condition Era 1003,1,,Number of distinct condition era concepts per person,,,,,,1,Condition Era 1004,0,,"Number of persons with at least one condition era, by condition_concept_id by calendar year by gender by age decile",condition_concept_id,calendar year,gender_concept_id,age decile,,1,Condition Era -1006,1,,Distribution of age by condition_concept_id,condition_concept_id,gender_concept_id,,,,1,Condition Era +1006,1,,Distribution of age by condition_concept_id and gender,condition_concept_id,gender_concept_id,,,,1,Condition Era 1007,1,,"Distribution of condition era length, by condition_concept_id",condition_concept_id,,,,,1,Condition Era 1008,0,,Number of condition eras without valid person,,,,,,0,Condition Era 1010,0,,Number of condition_era records outside a valid observation period,,,,,,0,Observation Period @@ -197,7 +197,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 1302,0,,"Number of persons by visit detail start month, by visit_detail_concept_id",visit_detail_concept_id,calendar month,,,,1,Visit Detail 1303,1,,Number of distinct visit detail concepts per person,,,,,,1,Visit Detail 1304,0,,"Number of persons with at least one visit detail, by visit_detail_concept_id by calendar year by gender by age decile",visit_detail_concept_id,calendar year,gender_concept_id,age decile,,1,Visit Detail -1306,1,,Distribution of age by visit_detail_concept_id,visit_detail_concept_id,gender_concept_id,,,,1,Visit Detail +1306,1,,Distribution of age by visit_detail_concept_id and gender,visit_detail_concept_id,gender_concept_id,,,,1,Visit Detail 1307,0,,Number of visit records with invalid person_id,,,,,,0,Visit Detail 1309,0,,Number of visit_detail records with invalid care_site_id,,,,,,0,Visit Detail 1310,0,,Number of visit_detail records outside a valid observation period,,,,,,0,Observation Period @@ -246,7 +246,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 1803,1,,Number of distinct mesurement occurrence concepts per person,,,,,,1,Measurement 1804,0,,"Number of persons with at least one mesurement occurrence, by measurement_concept_id by calendar year by gender by age decile",measurement_concept_id,calendar year,gender_concept_id,age decile,,1,Measurement 1805,0,,"Number of measurement occurrence records, by measurement_concept_id by measurement_type_concept_id",measurement_concept_id,measurement_type_concept_id,,,,1,Measurement -1806,1,,Distribution of age by measurement_concept_id,measurement_concept_id,gender_concept_id,,,,1,Measurement +1806,1,,Distribution of age by measurement_concept_id and gender,measurement_concept_id,gender_concept_id,,,,1,Measurement 1807,0,,"Number of measurement occurrence records, by measurement_concept_id and unit_concept_id",measurement_concept_id,unit_concept_id,,,,1,Measurement 1809,0,,Number of measurement records with invalid person_id,,,,,,0,Measurement 1810,0,,Number of measurement records outside valid observation period,,,,,,0,Observation Period @@ -283,7 +283,7 @@ analysis_id,distribution,distributed_field,analysis_name,stratum_1_name,stratum_ 2102,0,,"Number of persons by device records start month, by device_concept_id",device_concept_id,calendar month,,,,1,Device Exposure 2104,0,,"Number of persons with at least one device exposure, by device_concept_id by calendar year by gender by age decile",device_concept_id,calendar year,gender_concept_id,age decile,,1,Device Exposure 2105,0,,"Number of device exposure records, by device_concept_id by device_type_concept_id",device_concept_id,device_type_concept_id,,,,1,Device Exposure -2106,1,,Distribution of age by device_concept_id,device_concept_id,gender_concept_id,,,,1,Device Exposure +2106,1,,Distribution of age by device_concept_id and gender,device_concept_id,gender_concept_id,,,,1,Device Exposure 2110,0,,Number of device_exposure records outside valid observation period,,,,,,0,Observation Period 2120,0,,Number of device_exposure records by device_exposure start month,calendar month,,,,,1,Device Exposure 2125,0,,Number of device_exposure records by device_source_concept_id,device_source_concept_id,,,,,1,Device Exposure diff --git a/inst/doc/GettingStarted.pdf b/inst/doc/GettingStarted.pdf new file mode 100644 index 00000000..526af0f1 Binary files /dev/null and b/inst/doc/GettingStarted.pdf differ diff --git a/inst/doc/RunningAchilles.pdf b/inst/doc/RunningAchilles.pdf new file mode 100644 index 00000000..31807dc5 Binary files /dev/null and b/inst/doc/RunningAchilles.pdf differ diff --git a/inst/sql/sql_server/analyses/1101.sql b/inst/sql/sql_server/analyses/1101.sql index b4ef9164..5aa6f0c5 100755 --- a/inst/sql/sql_server/analyses/1101.sql +++ b/inst/sql/sql_server/analyses/1101.sql @@ -15,4 +15,4 @@ INNER JOIN @cdmDatabaseSchema.location l1 ON p1.location_id = l1.location_id WHERE p1.location_id IS NOT NULL AND l1.state IS NOT NULL -GROUP BY l1.state, l1.location_id; \ No newline at end of file +GROUP BY l1.state, l1.location_id; diff --git a/inst/sql/sql_server/analyses/1103.sql b/inst/sql/sql_server/analyses/1103.sql index 7db4bd28..f2c52fb8 100755 --- a/inst/sql/sql_server/analyses/1103.sql +++ b/inst/sql/sql_server/analyses/1103.sql @@ -15,4 +15,4 @@ INNER JOIN @cdmDatabaseSchema.location l1 ON cs1.location_id = l1.location_id WHERE cs1.location_id IS NOT NULL AND l1.state IS NOT NULL -GROUP BY l1.state, cs1.location_id; \ No newline at end of file +GROUP BY l1.state, cs1.location_id; diff --git a/inst/sql/sql_server/analyses/1823.sql b/inst/sql/sql_server/analyses/1823.sql index eb6c55b9..10d7c0d8 100644 --- a/inst/sql/sql_server/analyses/1823.sql +++ b/inst/sql/sql_server/analyses/1823.sql @@ -1,27 +1,27 @@ - --- 1823 Number of measurement records, by measurement_concept_id and operator_concept_id - ---HINT DISTRIBUTE_ON_KEY(stratum_1) -SELECT - 1823 AS analysis_id, - CAST(m.measurement_concept_id AS VARCHAR(255)) AS stratum_1, - CAST(m.operator_concept_id AS VARCHAR(255)) AS stratum_2, - CAST(NULL AS VARCHAR(255)) AS stratum_3, - CAST(NULL AS VARCHAR(255)) AS stratum_4, - CAST(NULL AS VARCHAR(255)) AS stratum_5, - COUNT_BIG(*) AS count_value -INTO - @scratchDatabaseSchema@schemaDelim@tempAchillesPrefix_1823 -FROM - @cdmDatabaseSchema.measurement m -JOIN - @cdmDatabaseSchema.observation_period op -ON - m.person_id = op.person_id -AND - m.measurement_date >= op.observation_period_start_date -AND - m.measurement_date <= op.observation_period_end_date -GROUP BY - m.measurement_concept_id, - m.operator_concept_id; + +-- 1823 Number of measurement records, by measurement_concept_id and operator_concept_id + +--HINT DISTRIBUTE_ON_KEY(stratum_1) +SELECT + 1823 AS analysis_id, + CAST(m.measurement_concept_id AS VARCHAR(255)) AS stratum_1, + CAST(m.operator_concept_id AS VARCHAR(255)) AS stratum_2, + CAST(NULL AS VARCHAR(255)) AS stratum_3, + CAST(NULL AS VARCHAR(255)) AS stratum_4, + CAST(NULL AS VARCHAR(255)) AS stratum_5, + COUNT_BIG(*) AS count_value +INTO + @scratchDatabaseSchema@schemaDelim@tempAchillesPrefix_1823 +FROM + @cdmDatabaseSchema.measurement m +JOIN + @cdmDatabaseSchema.observation_period op +ON + m.person_id = op.person_id +AND + m.measurement_date >= op.observation_period_start_date +AND + m.measurement_date <= op.observation_period_end_date +GROUP BY + m.measurement_concept_id, + m.operator_concept_id; diff --git a/inst/sql/sql_server/analyses/achilles_performance_ddl.sql b/inst/sql/sql_server/analyses/achilles_performance_ddl.sql index 0fa13734..1403301d 100644 --- a/inst/sql/sql_server/analyses/achilles_performance_ddl.sql +++ b/inst/sql/sql_server/analyses/achilles_performance_ddl.sql @@ -9,4 +9,4 @@ CREATE TABLE @resultsDatabaseSchema.achilles_performance ( elapsed_seconds NUMERIC, start_time NUMERIC, end_time NUMERIC -); \ No newline at end of file +); diff --git a/inst/sql/sql_server/export/location/sqlLocationTable.sql b/inst/sql/sql_server/export/location/sqlLocationTable.sql index 609a91fd..0174fb55 100755 --- a/inst/sql/sql_server/export/location/sqlLocationTable.sql +++ b/inst/sql/sql_server/export/location/sqlLocationTable.sql @@ -16,4 +16,4 @@ FROM @results_database_schema.achilles_results c, denom WHERE - c.analysis_id BETWEEN 1100 AND 1103; \ No newline at end of file + c.analysis_id BETWEEN 1100 AND 1103; diff --git a/inst/sql/sql_server/export/measurement/sqlRecordsByUnit.sql b/inst/sql/sql_server/export/measurement/sqlRecordsByUnit.sql index de85c186..265ce7a0 100755 --- a/inst/sql/sql_server/export/measurement/sqlRecordsByUnit.sql +++ b/inst/sql/sql_server/export/measurement/sqlRecordsByUnit.sql @@ -11,4 +11,4 @@ from ( GROUP BY analysis_id, stratum_1, stratum_2, count_value ) ar1 inner join @vocab_database_schema.concept c1 on ar1.stratum_1 = c1.concept_id -inner join @vocab_database_schema.concept c2 on ar1.stratum_2 = c2.concept_id \ No newline at end of file +inner join @vocab_database_schema.concept c2 on ar1.stratum_2 = c2.concept_id diff --git a/man/achilles.Rd b/man/achilles.Rd index cdfe0055..6256081f 100644 --- a/man/achilles.Rd +++ b/man/achilles.Rd @@ -138,14 +138,16 @@ containing the results \examples{ \dontrun{ connectionDetails <- createConnectionDetails(dbms = "sql server", server = "some_server") -achillesResults <- achilles(connectionDetails = connectionDetails, +achillesResults <- achilles( + connectionDetails = connectionDetails, cdmDatabaseSchema = "cdm", resultsDatabaseSchema = "results", scratchDatabaseSchema = "scratch", sourceName = "Some Source", cdmVersion = "5.3", numThreads = 10, - outputFolder = "output") + outputFolder = "output" +) } } diff --git a/man/createTimeSeries.Rd b/man/createTimeSeries.Rd index f9e5633f..fb320362 100644 --- a/man/createTimeSeries.Rd +++ b/man/createTimeSeries.Rd @@ -26,9 +26,15 @@ correct column name (see example). \examples{ # Example 1: temporalData <- data.frame(START_DATE = seq.Date(as.Date("20210101", "\%Y\%m\%d"), - as.Date("20231201", - "\%Y\%m\%d"), by = "month"), COUNT_VALUE = round(runif(36, 1, 1000)), PREVALENCE = round(runif(36, - 0, 10), 2), PROPORTION_WITHIN_YEAR = round(runif(36, 0, 1), 2), stringsAsFactors = FALSE) + as.Date( + "20231201", + "\%Y\%m\%d" + ), + by = "month" +), COUNT_VALUE = round(runif(36, 1, 1000)), PREVALENCE = round(runif( + 36, + 0, 10 +), 2), PROPORTION_WITHIN_YEAR = round(runif(36, 0, 1), 2), stringsAsFactors = FALSE) dummyTs <- createTimeSeries(temporalData) dummyTs.cv <- dummyTs[, "COUNT_VALUE"] dummyTs.pv <- dummyTs[, "PREVALENCE"] @@ -37,8 +43,10 @@ dummyTs.pwy <- dummyTs[, "PROPORTION_WITHIN_YEAR"] \dontrun{ # Example 2: pneumonia <- 255848 -temporalData <- getTemporalData(connectionDetails = connectionDetails, cdmDatabaseSchema = "cdm", - resultsDatabaseSchema = "results", conceptId = pneumonia) +temporalData <- getTemporalData( + connectionDetails = connectionDetails, cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", conceptId = pneumonia +) pneumoniaTs <- createTimeSeries(temporalData) pneumoniaTs.cv <- pneumoniaTs[, "COUNT_VALUE"] pneumoniaTs.pv <- pneumoniaTs[, "PREVALENCE"] diff --git a/man/exportConditionEraToJson.Rd b/man/exportConditionEraToJson.Rd index ba478b61..6289464d 100755 --- a/man/exportConditionEraToJson.Rd +++ b/man/exportConditionEraToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Condition Era report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportConditionEraToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportConditionToJson.Rd b/man/exportConditionToJson.Rd index 2e2da20a..2fc24f84 100755 --- a/man/exportConditionToJson.Rd +++ b/man/exportConditionToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Condition report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportConditionToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportDashboardToJson.Rd b/man/exportDashboardToJson.Rd index 81f11e57..0ea242cb 100755 --- a/man/exportDashboardToJson.Rd +++ b/man/exportDashboardToJson.Rd @@ -42,10 +42,13 @@ genreated, this function will fail. } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportDashboardToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportDataDensityToJson.Rd b/man/exportDataDensityToJson.Rd index 177c2174..7d66cefb 100755 --- a/man/exportDataDensityToJson.Rd +++ b/man/exportDataDensityToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Data Density report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportDataDensityToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportDeathToJson.Rd b/man/exportDeathToJson.Rd index 2b54a704..82dff1ad 100755 --- a/man/exportDeathToJson.Rd +++ b/man/exportDeathToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Death report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportDeathToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportDrugEraToJson.Rd b/man/exportDrugEraToJson.Rd index 22a61b2f..796f1ff5 100755 --- a/man/exportDrugEraToJson.Rd +++ b/man/exportDrugEraToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Drug Era report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportDrugEraToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportDrugToJson.Rd b/man/exportDrugToJson.Rd index cc6d8105..4b47b9ab 100755 --- a/man/exportDrugToJson.Rd +++ b/man/exportDrugToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Drug report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportDrugToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportMeasurementToJson.Rd b/man/exportMeasurementToJson.Rd index b6692e6d..e7e95701 100755 --- a/man/exportMeasurementToJson.Rd +++ b/man/exportMeasurementToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Measurement report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportMeasurementToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportMetaToJson.Rd b/man/exportMetaToJson.Rd index 3dac1fc2..cda4abe6 100755 --- a/man/exportMetaToJson.Rd +++ b/man/exportMetaToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Achilles META report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportMetaToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportObservationPeriodToJson.Rd b/man/exportObservationPeriodToJson.Rd index 05c73b48..7479cced 100755 --- a/man/exportObservationPeriodToJson.Rd +++ b/man/exportObservationPeriodToJson.Rd @@ -41,10 +41,13 @@ Creates individual files for Observation Period report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportObservationPeriodToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportObservationToJson.Rd b/man/exportObservationToJson.Rd index 28faa0b7..848cb9cd 100755 --- a/man/exportObservationToJson.Rd +++ b/man/exportObservationToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Observation report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportObservationToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportPerformanceToJson.Rd b/man/exportPerformanceToJson.Rd index 0c92f1af..1aa629cd 100644 --- a/man/exportPerformanceToJson.Rd +++ b/man/exportPerformanceToJson.Rd @@ -40,10 +40,13 @@ Creates performance report including how long each Achilles result took to gener } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportPerformanceToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportPersonToJson.Rd b/man/exportPersonToJson.Rd index b0b6544f..a08fa97e 100755 --- a/man/exportPersonToJson.Rd +++ b/man/exportPersonToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Person report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportPersonToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportProcedureToJson.Rd b/man/exportProcedureToJson.Rd index 8ef8fa4f..43d9cde1 100755 --- a/man/exportProcedureToJson.Rd +++ b/man/exportProcedureToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Procedure report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportProcedureToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportToJson.Rd b/man/exportToJson.Rd index d00e0601..a008e2ea 100755 --- a/man/exportToJson.Rd +++ b/man/exportToJson.Rd @@ -52,8 +52,10 @@ Creates individual files for each report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportToJson(connectionDetails, cdmDatabaseSchema = "cdm4_sim", outputPath = "your/output/path") } } diff --git a/man/exportVisitDetailToJson.Rd b/man/exportVisitDetailToJson.Rd index 8082e1ba..44c9f27f 100644 --- a/man/exportVisitDetailToJson.Rd +++ b/man/exportVisitDetailToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for VISIT_DETAIL report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportVisitDetailToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/exportVisitToJson.Rd b/man/exportVisitToJson.Rd index 40cfb695..bad23b36 100755 --- a/man/exportVisitToJson.Rd +++ b/man/exportVisitToJson.Rd @@ -40,10 +40,13 @@ Creates individual files for Visit report found in Achilles.Web } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) exportVisitToJson(connectionDetails, - cdmDatabaseSchema = "cdm4_sim", - outputPath = "your/output/path") + cdmDatabaseSchema = "cdm4_sim", + outputPath = "your/output/path" +) } } diff --git a/man/generateDbSummary.Rd b/man/generateDbSummary.Rd index 596eb597..a55605a5 100644 --- a/man/generateDbSummary.Rd +++ b/man/generateDbSummary.Rd @@ -34,7 +34,7 @@ Server, 'cdm_results.dbo'.} none } \description{ -\code{generateDbSummary} can be run after the Achilles analyses are complete +\code{generateDbSummary} can be run after the Achilles analyses are complete to create a high-level database summary. } \details{ @@ -45,12 +45,15 @@ used in an analysis } \examples{ \dontrun{ -connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = "sql server", - server = "yourserver") +connectionDetails <- DatabaseConnector::createConnectionDetails( + dbms = "sql server", + server = "yourserver" +) dbSummary <- generateDbSummary(connectionDetails, - cdmDatabaseSchema = "cdm_schema", - resultsDatabaseSchema = "results_schema", - country = "Country of Origin", - provenance = "Provenance of data") + cdmDatabaseSchema = "cdm_schema", + resultsDatabaseSchema = "results_schema", + country = "Country of Origin", + provenance = "Provenance of data" +) } } diff --git a/man/getSeasonalityScore.Rd b/man/getSeasonalityScore.Rd index 28bf4c62..c65d561a 100644 --- a/man/getSeasonalityScore.Rd +++ b/man/getSeasonalityScore.Rd @@ -17,7 +17,7 @@ The seasonality score of a monthly time series is computed as its departure from } \details{ The degree of seasonality of a monthly time series is based on its departure from a uniform distribution. -If the number of cases for a given concept is uniformly distributed across all time periods (in this case, all months), +If the number of cases for a given concept is uniformly distributed across all time periods (in this case, all months), then its monthly proportion would be approximately constant. In this case, the time series would be considered "strictly non-seasonal" and its "seasonality score" would be zero. Similarly, if all cases recur at a single point in time (that is, in a single month), such a time series would be considered diff --git a/man/getTemporalData.Rd b/man/getTemporalData.Rd index abdc3a5d..544c2f1f 100644 --- a/man/getTemporalData.Rd +++ b/man/getTemporalData.Rd @@ -50,10 +50,11 @@ Occurrence 702 - Drug Exposure 802 - Observation 1802 - Measurement 2102 - Devic \examples{ \dontrun{ pneumonia <- 255848 -monthlyResults <- getTemporalData(connectionDetails = connectionDetails, - cdmDatabaseSchema = "cdm", - - resultsDatabaseSchema = "results", conceptId = pneumonia) +monthlyResults <- getTemporalData( + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", conceptId = pneumonia +) } } diff --git a/man/isStationary.Rd b/man/isStationary.Rd index a3fa1c94..60f10eaf 100644 --- a/man/isStationary.Rd +++ b/man/isStationary.Rd @@ -17,6 +17,6 @@ Uses the Augmented Dickey-Fuller test to determine when the time series has a un } \details{ A time series must have a minimum of three complete years of data. -For details on the implementation of the Augmented Dickey-Fuller test, +For details on the implementation of the Augmented Dickey-Fuller test, see the tseries package on cran. } diff --git a/man/listMissingAnalyses.Rd b/man/listMissingAnalyses.Rd index 4a303573..a796d2b0 100644 --- a/man/listMissingAnalyses.Rd +++ b/man/listMissingAnalyses.Rd @@ -23,8 +23,10 @@ not in achilles_results or achilles_results_dist } \examples{ \dontrun{ -Achilles::listMissingAnalyses(connectionDetails = connectionDetails, - resultsDatabaseSchema = "results") +Achilles::listMissingAnalyses( + connectionDetails = connectionDetails, + resultsDatabaseSchema = "results" +) } } diff --git a/man/performTemporalCharacterization.Rd b/man/performTemporalCharacterization.Rd index a5651fdf..af7786e9 100644 --- a/man/performTemporalCharacterization.Rd +++ b/man/performTemporalCharacterization.Rd @@ -58,26 +58,29 @@ A csv file with temporal analyses for each time series # Example 1: pneumonia <- 255848 performTemporalCharacterization( - connectionDetails = connectionDetails, - cdmDatabaseSchema = "cdm", - resultsDatabaseSchema = "results", - conceptId = pneumonia, - outputFolder = "output/pneumoniaTemporalChar.csv") + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", + conceptId = pneumonia, + outputFolder = "output/pneumoniaTemporalChar.csv" +) # Example 2: performTemporalCharacterization( - connectionDetails = connectionDetails, - cdmDatabaseSchema = "cdm", - resultsDatabaseSchema = "results", - analysisIds = c(402,702), - outputFolder = "output/conditionAndDrugTemporalChar.csv") + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", + analysisIds = c(402, 702), + outputFolder = "output/conditionAndDrugTemporalChar.csv" +) # Example 3: performTemporalCharacterization( - connectionDetails = connectionDetails, - cdmDatabaseSchema = "cdm", - resultsDatabaseSchema = "results", - outputFolder = "output/CompleteTemporalChar.csv") + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", + outputFolder = "output/CompleteTemporalChar.csv" +) } } diff --git a/man/runMissingAnalyses.Rd b/man/runMissingAnalyses.Rd index 69ea529a..8b15baac 100644 --- a/man/runMissingAnalyses.Rd +++ b/man/runMissingAnalyses.Rd @@ -59,11 +59,12 @@ No return value. Run to execute analyses currently missing from results. } \examples{ \dontrun{ -Achilles::runMissingAnalyses(connectionDetails = connectionDetails, - cdmDatabaseSchema = "cdm", - resultsDatabaseSchema = "results", - - outputFolder = "/tmp") +Achilles::runMissingAnalyses( + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", + outputFolder = "/tmp" +) } } diff --git a/tests/testthat.R b/tests/testthat.R index 5a56453a..ad5f7162 100644 --- a/tests/testthat.R +++ b/tests/testthat.R @@ -9,4 +9,4 @@ library(testthat) library(Achilles) -test_check("Achilles") \ No newline at end of file +test_check("Achilles") diff --git a/tests/testthat/setup.R b/tests/testthat/setup.R index f2b1908a..f0bda189 100644 --- a/tests/testthat/setup.R +++ b/tests/testthat/setup.R @@ -1,22 +1,25 @@ if (Sys.getenv("CDM5_REDSHIFT_SERVER") != "") { library(DatabaseConnector) - + if (dir.exists(Sys.getenv("DATABASECONNECTOR_JAR_FOLDER"))) { jdbcDriverFolder <- Sys.getenv("DATABASECONNECTOR_JAR_FOLDER") } else { jdbcDriverFolder <- file.path(tempdir(), "jdbcDrivers") dir.create(jdbcDriverFolder, showWarnings = FALSE) DatabaseConnector::downloadJdbcDrivers("all", pathToDriver = jdbcDriverFolder) - + Sys.setenv(DATABASECONNECTOR_JAR_FOLDER = jdbcDriverFolder) - - withr::defer({ - unlink(jdbcDriverFolder, - recursive = TRUE, - force = TRUE) - }, - testthat::teardown_env()) + + withr::defer( + { + unlink(jdbcDriverFolder, + recursive = TRUE, + force = TRUE + ) + }, + testthat::teardown_env() + ) } } else { message("Skipping driver setup because environmental variables not set") -} \ No newline at end of file +} diff --git a/tests/testthat/test-mssql.R b/tests/testthat/test-mssql.R index d758bfbe..330d0d01 100644 --- a/tests/testthat/test-mssql.R +++ b/tests/testthat/test-mssql.R @@ -2,22 +2,21 @@ test_that("Achilles MS SQL Execution", { if (Sys.getenv("CDM5_SQL_SERVER_USER") != "") { details <- createConnectionDetails( dbms = "sql server", - user = Sys.getenv("CDM5_SQL_SERVER_USER"), + user = Sys.getenv("CDM5_SQL_SERVER_USER"), password = URLdecode(Sys.getenv("CDM5_SQL_SERVER_PASSWORD")), server = Sys.getenv("CDM5_SQL_SERVER_SERVER") ) - + expect_no_error( Achilles::achilles( - connectionDetails = details, + connectionDetails = details, cdmDatabaseSchema = Sys.getenv("CDM5_SQL_SERVER_CDM54_SCHEMA"), resultsDatabaseSchema = Sys.getenv("CDM5_SQL_SERVER_OHDSI_SCHEMA"), cdmVersion = "5.4", createTable = T - ) + ) ) } else { message("Skipping MS SQL testing because environmental variables not set") } }) - diff --git a/tests/testthat/test-oracle.R b/tests/testthat/test-oracle.R deleted file mode 100644 index 601dc31b..00000000 --- a/tests/testthat/test-oracle.R +++ /dev/null @@ -1,22 +0,0 @@ -test_that("Achilles Oracle Execution", { - if (Sys.getenv("CDM5_ORACLE_SERVER") != "") { - details <- createConnectionDetails( - dbms = "oracle", - user = Sys.getenv("CDM5_ORACLE_USER"), - password = URLdecode(Sys.getenv("CDM5_ORACLE_PASSWORD")), - server = Sys.getenv("CDM5_ORACLE_SERVER") - ) - - expect_no_error( - Achilles::achilles( - connectionDetails = details, - cdmDatabaseSchema = Sys.getenv("CDM5_ORACLE_CDM54_SCHEMA"), - resultsDatabaseSchema = Sys.getenv("CDM5_ORACLE_OHDSI_SCHEMA"), - cdmVersion = "5.4", - createTable = T - ) - ) - } else { - message("Skipping Oracle testing because environmental variables not set") - } -}) diff --git a/tests/testthat/test-postgres.R b/tests/testthat/test-postgres.R index b1338761..239c8c18 100644 --- a/tests/testthat/test-postgres.R +++ b/tests/testthat/test-postgres.R @@ -6,7 +6,7 @@ test_that("Achilles Postgresql Execution", { password = URLdecode(Sys.getenv("CDM5_POSTGRESQL_PASSWORD")), server = Sys.getenv("CDM5_POSTGRESQL_SERVER") ) - + expect_no_error( Achilles::achilles( connectionDetails = details, @@ -19,4 +19,4 @@ test_that("Achilles Postgresql Execution", { } else { message("Skipping Postgres testing because environmental variables not set") } -}) \ No newline at end of file +}) diff --git a/tests/testthat/test-redshift.R b/tests/testthat/test-redshift.R index 0c880dda..d5161a3c 100644 --- a/tests/testthat/test-redshift.R +++ b/tests/testthat/test-redshift.R @@ -6,7 +6,7 @@ test_that("Achilles Redshift Execution", { password = URLdecode(Sys.getenv("CDM5_REDSHIFT_PASSWORD")), server = Sys.getenv("CDM5_REDSHIFT_SERVER") ) - + expect_no_error( Achilles::achilles( connectionDetails = details, diff --git a/vignettes/RunningAchilles.R b/vignettes/RunningAchilles.R index 941d0b69..efdc371b 100644 --- a/vignettes/RunningAchilles.R +++ b/vignettes/RunningAchilles.R @@ -4,14 +4,15 @@ knitr::opts_chunk$set( cache = FALSE, comment = "#>", error = FALSE, - tidy = FALSE) + tidy = FALSE +) ## ----tidy = FALSE, eval = FALSE----------------------------------------------- # connectionDetails <- createConnectionDetails(dbms = "postgresql", # server = "localhost/synpuf", # user = "cdm_user", # password = "cdm_password") -# +# # achilles(connectionDetails = connectionDetails, # cdmDatabaseSchema = "cdm", # resultsDatabaseSchema = "results", @@ -22,7 +23,7 @@ knitr::opts_chunk$set( # server = "localhost/synpuf", # user = "cdm_user", # password = "cdm_password") -# +# # achilles(connectionDetails = connectionDetails, # cdmDatabaseSchema = "cdm", # resultsDatabaseSchema = "results", @@ -35,7 +36,7 @@ knitr::opts_chunk$set( # server = "localhost/synpuf", # user = "cdm_user", # password = "cdm_password") -# +# # createIndices(connectionDetails = connectionDetails, # resultsDatabaseSchema = "results", # outputFolder = "output") @@ -45,10 +46,9 @@ knitr::opts_chunk$set( # server = "localhost/synpuf", # user = "cdm_user", # password = "cdm_password") -# +# # dropAllScratchTables(connectionDetails = connectionDetails, # scratchDatabaseSchema = "scratch", numThreads = 5) ## ----tidy = TRUE, eval = TRUE------------------------------------------------- citation("Achilles") - diff --git a/vignettes/RunningAchilles.Rmd b/vignettes/RunningAchilles.Rmd index 98ea22f9..a2ce5b45 100644 --- a/vignettes/RunningAchilles.Rmd +++ b/vignettes/RunningAchilles.Rmd @@ -20,7 +20,8 @@ knitr::opts_chunk$set( cache = FALSE, comment = "#>", error = FALSE, - tidy = FALSE) + tidy = FALSE +) ``` # Introduction @@ -114,15 +115,19 @@ When running **achilles**, the return value, if you assign a variable to the fun In single-threaded mode, there is no need to set a `scratchDatabaseSchema`, as temporary tables will be used. ```{r tidy = FALSE, eval = FALSE} -connectionDetails <- createConnectionDetails(dbms = "postgresql", - server = "localhost/synpuf", - user = "cdm_user", - password = "cdm_password") - -achilles(connectionDetails = connectionDetails, - cdmDatabaseSchema = "cdm", - resultsDatabaseSchema = "results", - outputFolder = "output") +connectionDetails <- createConnectionDetails( + dbms = "postgresql", + server = "localhost/synpuf", + user = "cdm_user", + password = "cdm_password" +) + +achilles( + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", + outputFolder = "output" +) ``` # Running Achilles: Multi-Threaded Mode @@ -130,17 +135,21 @@ achilles(connectionDetails = connectionDetails, In multi-threaded mode, you need to specify `scratchDatabaseSchema` and use > 1 for `numThreads`. ```{r tidy = FALSE, eval = FALSE} -connectionDetails <- createConnectionDetails(dbms = "postgresql", - server = "localhost/synpuf", - user = "cdm_user", - password = "cdm_password") - -achilles(connectionDetails = connectionDetails, - cdmDatabaseSchema = "cdm", - resultsDatabaseSchema = "results", - scratchDatabaseSchema = "scratch", - numThreads = 5, - outputFolder = "output") +connectionDetails <- createConnectionDetails( + dbms = "postgresql", + server = "localhost/synpuf", + user = "cdm_user", + password = "cdm_password" +) + +achilles( + connectionDetails = connectionDetails, + cdmDatabaseSchema = "cdm", + resultsDatabaseSchema = "results", + scratchDatabaseSchema = "scratch", + numThreads = 5, + outputFolder = "output" +) ``` # Post-Processing @@ -155,14 +164,18 @@ This section describes the usage of standalone functions for post-processing tha To improve query performance of the Achilles results tables, run the **createIndices** function. ```{r tidy = FALSE, eval = FALSE} -connectionDetails <- createConnectionDetails(dbms = "postgresql", - server = "localhost/synpuf", - user = "cdm_user", - password = "cdm_password") - -createIndices(connectionDetails = connectionDetails, - resultsDatabaseSchema = "results", - outputFolder = "output") +connectionDetails <- createConnectionDetails( + dbms = "postgresql", + server = "localhost/synpuf", + user = "cdm_user", + password = "cdm_password" +) + +createIndices( + connectionDetails = connectionDetails, + resultsDatabaseSchema = "results", + outputFolder = "output" +) ``` @@ -173,13 +186,17 @@ If the **achilles** execution has errors, or if you did not enable this step in The `tableTypes` parameter can be used to specify which batch of staging tables to drop ("achilles"). ```{r tidy = FALSE, eval = FALSE} -connectionDetails <- createConnectionDetails(dbms = "postgresql", - server = "localhost/synpuf", - user = "cdm_user", - password = "cdm_password") - -dropAllScratchTables(connectionDetails = connectionDetails, - scratchDatabaseSchema = "scratch", numThreads = 5) +connectionDetails <- createConnectionDetails( + dbms = "postgresql", + server = "localhost/synpuf", + user = "cdm_user", + password = "cdm_password" +) + +dropAllScratchTables( + connectionDetails = connectionDetails, + scratchDatabaseSchema = "scratch", numThreads = 5 +) ``` # Acknowledgments