Course2-1.Rmd

---
title: "Course2-1"
output: html_document
date: "2024-06-14"
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

## R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.

When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

```{r cars, echo=FALSE}
summary(cars)
```

## Including Plots

You can also embed plots, for example:

```{r pressure, echo=FALSE, fig.width=6, fig.height=3, fig.cap="Title of figure", fig.align='left'}
plot(pressure)

plot(cars$speed)
```

Note that the `echo = FALSE` parameter was added to the code chunk to prevent printing of the R code that generated the plot.

```{r, echo=FALSE, include=TRUE, eval=TRUE}
# create an object dataframe example `dfex` and assign to it the .sav file `sample.sav` that was introduced previously
### Adrian comments, June 18th 2024
### sample.sav is not available which means that I cannot reproduce your code
dfex<-haven::read_sav("sample.sav")

# create an object movies metadata `dfmv` and assign to it the .xlsx file `movies.xlsx`
# note the different paths to these files
# note that we specify which sheet to read too; here only sheet 1 is imported
dfmv<-readxl::read_excel("movies.xlsx",1)

# next, we check if the source material was imported successfully by observing the first lines in the tables
head(dfex)
```

```{r}
r <- getOption("repos")
r["CRAN"] <-"https://cloud.r-project.org/"
options(repos=r)
```

```{r}
pacman::p_load(tidyverse,readxl,haven,sjlabelled, kableExtra)
# note: this exact code chunk might end up looking differently in the short book
# this is becauase i'd install packages as needed
```

# Plain text vs. live text

This is an example of how automatization can be implemented in the work flow. My list of movies include `r nrow(dfmv)` entries. The title of those movies are `r dfmv$Movie`. Is there a movie that I actually don't like on that list, well, the answer is that I dislike exactly `r dfmv %>% filter(Like %in% c("No","no","NO")) %>% nrow()` movies on that list. Is there a movie that I actually like on that list, well, the answer is that I like exactly `r dfmv %>% filter(Like %in% c("Yes","yes","YES")) %>% nrow()` movies on that list.

```{r}
# we remove all the labels using the package sjlabelled and mutate
# as factors columns gen and res
# this step makes it easier later on to work with plots
# note that it is not a necessary step in general but only for the sake of 
# simplicity here
dfex<-dfex %>% sjlabelled::remove_all_labels() %>% 
  mutate(gen=factor(gen),
         res=factor(res))

# subsamples 15 study participants at random
tmpdf1<-sample_n(dfex,15)
# subsample 60 study participants at random
tmpdf2<-sample_n(dfex,60)
```

```{r}
haven::write_sav(tmpdf1,"tmpdf1.sav")
haven::write_sav(tmpdf2,"tmpdf2.sav")
```

```{r}
# import dataset into one object and then subject this object to the ggplot code

# 1 - imports dataset into object tempdf
tempdf<-haven::read_sav("tmpdf1.sav") %>% 
  sjlabelled::remove_all_labels() %>% 
  mutate(gen=factor(gen),
         res=factor(res))

# 2 - applies the ggplot to the dataset
ggplot(tempdf, aes(x=gen, y=wom_warm)) + 
  labs(x="Gender",
       y="Stereotype of warmth") +
  geom_boxplot() + 
  theme_light()

ggplot(tempdf, aes(x=gen, y=wom_comp)) + 
  labs(x="Gender",
       y="Stereotype of competence") + 
  geom_boxplot() + 
  theme_light()


# 3 - for illustration purposes, repeat step 1 with each 
# of the three datasets (tmpdf1,tmpdf2 and dfex) 
# making sure they are assigned into the same object tempdf. 
# As long as the ggplot code is applied to a dataset with the same structure
# and variable labels the output will be updated automatically.
```

```{r}
library(knitr)
dfmv %>% knitr::kable(caption="Simple table using knitr::kable()",format = "pipe")
```

```{r}
# does some data manipulation to retrieve the required information
tmptbl<-dfmv %>% 
  filter(Actor %in% c("Keanu Reeves", "Alec Baldwin", "Arnold Schwarzenegger"))

# creates an empty table holder that is our summary table that we'd
# want to include in the final output document
extbl<-tibble(
  
  like=tmptbl[ tmptbl$Grade >= 7 & tmptbl$Like %in% c("Yes","No"), ]$Like,
  name=tmptbl[ tmptbl$Grade >= 7 & tmptbl$Like %in% c("Yes","No"), ]$Actor,
  movie=tmptbl[ tmptbl$Grade >= 7 & tmptbl$Like %in% c("Yes","No"), ]$Movie,
  wiki=tmptbl[ tmptbl$Grade >= 7 & tmptbl$Like %in% c("Yes","No"), ]$Wikilink
  
)
```

```{r}
extbl %>% knitr::kable(caption="Movies graded 7 or more from liked and least like actors", format="pipe")
```

```{r}
# Search for the row containing "Emilia Clarke"
search_keyword <- "Emilia Clarke"
matched_row <- dfmv[apply(dfmv, 1, function(row) length(agrep(search_keyword, row["Actor"], ignore.case = TRUE)) > 0), ]

# Display the matched row using knitr::kable()
kable(matched_row)
```

```{r}
print(matched_row)
```