_pkgdown.yml

# Served from camilleross.org/taupatch/, not chross22.github.io: GitHub applies
# the user site's custom domain to every project page on the account. This must
# name where visitors actually land, or the canonical link, sitemap and og:url
# all point at a hostname nobody uses and search engines see two of each page.
url: https://camilleross.org/taupatch/

# NOT docs/. Several of these packages keep hand-written design notes and
# methods write-ups in docs/, tracked in git, and a pkgdown build would erase
# them. pkgdown refuses outright when it finds a docs/ it did not create; this
# names a directory that is unambiguously generated.
destination: pkgdown-site

template:
  bootstrap: 5
  light-switch: true

reference:
- title: Running a study
  desc: >
    A study is a config file plus data. Point-and-click through the Shiny
    app or drive the same pipeline from YAML; both take the same route.
  contents:
  - compare_runs
  - generate_config
  - load_config
  - pipeline_stages
  - run_taupatch
  - run_taupatch_app
  - save_config
  - single_stages

- title: Zooplankton data
  desc: >
    Reading plankton counts and getting them into one shape. A patch is
    defined by a species-and-stage abundance threshold, so which stages a
    column holds matters as much as the number in it.
  contents:
  - abundance_units
  - available_species
  - available_stages
  - default_species_catalog
  - format_zoop_data
  - is_raw_export
  - label_patch
  - load_zoop_data
  - measurement_columns
  - raw_abundance_suffix
  - species_catalog_from
  - split_dates
  - stage_suffix_pattern
  - station_summary
  - taxon_shorthand
  - validate_columns
  - zoop_taxa

- title: Covariates
  desc: >
    Fetching environmental fields and joining them to stations, including
    the derived layers that come from derivoce.
  contents:
  - add_derivoce_covariates
  - apply_prejoin_steps
  - attach_covariates
  - bathymetry_covariates
  - climate_index_covariates
  - copernicus_client
  - copernicus_covariates
  - covariate_grid
  - covariate_info
  - covariate_monthly_means
  - covariate_transforms
  - default_copernicus_datasets
  - derivoce_choices
  - derivoce_covariates
  - derivoce_required_inputs
  - derivoce_steps_for
  - fetch_covariates
  - generate_mock_covariates
  - plot_covariate_annual
  - plot_covariate_heatmap
  - plot_covariate_map
  - plot_covariate_seasonal
  - prejoin_steps

- title: Fitting and projecting
  desc: >
    The models themselves, single or ensembled, and the projection of a
    fitted model onto a new grid.
  contents:
  - ensemble_rules
  - ensemble_settings
  - fit_patch_ensemble
  - fit_patch_model
  - gam_bases
  - gam_methods
  - gam_smooth_terms
  - glm_coefficients
  - model_engine_fit
  - model_types
  - partial_effects
  - power_curve
  - print.taupatch_ensemble
  - project_patch_model

- title: Uncertainty and validation
  desc: >
    What the model does not know. Novelty and overlap surfaces say where a
    projection is extrapolating rather than interpolating.
  contents:
  - bootstrap_evaluation
  - jackknife_covariates
  - jackknife_dropped
  - jackknife_settings
  - novelty_surface
  - thin_covariates
  - uncertainty_settings

- title: Plots and output
  desc: >
    Figures for inspecting each stage, and the raster stack written at the
    end.
  contents:
  - plot_calibration
  - plot_gam_smooths
  - plot_glm_coefficients
  - plot_importance
  - plot_partial_effects
  - plot_pr_curve
  - plot_projection
  - plot_projection_uncertainty
  - plot_roc_curve
  - plot_station_map
  - plot_station_series
  - plot_threshold_performance
  - projection_map
  - write_suitability_stack

- title: Test fixtures
  desc: >
    Mock data, so an example or a test can run without a data extract.
  contents:
  - generate_mock_zoop_data