ubair

install.packages("<path-to-zip>/ubair-main.zip", repos = NULL, type = "source")

install.packages("remotes")
# requires a configures ssh-key
remotes::install_git("git@gitlab.opencode.de:uba-ki-lab/ubair.git")
# alternative via password
remotes::install_git("https://gitlab.opencode.de/uba-ki-lab/ubair.git")

library(ubair)
params <- load_params()
env_data <- sample_data_DESN025

# Plot meteo data
plot_station_measurements(env_data, params$meteo_variables)

application_start <- lubridate::ymd("20191201") # This coincides with the start of the reference window
date_effect_start <- lubridate::ymd_hm("20200323 00:00") # This splits the forecast into reference and effect
application_end <- lubridate::ymd("20200504") # This coincides with the end of the effect window

buffer <- 24 * 14 # 14 days buffer

dt_prepared <- prepare_data_for_modelling(env_data, params)
dt_prepared <- dt_prepared[complete.cases(dt_prepared)]
split_data <- split_data_counterfactual(
  dt_prepared, application_start,
  application_end
)
res <- run_counterfactual(split_data,
  params,
  detrending_function = "linear",
  model_type = "lightgbm",
  alpha = 0.9,
  log_transform = TRUE,
  calc_shaps = TRUE
)

#> [LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000509 seconds.
#> You can set `force_row_wise=true` to remove the overhead.
#> And if memory is not enough, you can set `force_col_wise=true`.
#> [LightGBM] [Info] Total Bins 1557
#> [LightGBM] [Info] Number of data points in the train set: 104486, number of used features: 9
#> [LightGBM] [Info] Start training from score -0.000000

predictions <- res$prediction

plot_counterfactual(predictions, params,
  window_size = 14,
  date_effect_start,
  buffer = buffer,
  plot_pred_interval = TRUE
)

round(calc_performance_metrics(predictions, date_effect_start, buffer = buffer), 2)

#>           RMSE            MSE            MAE           MAPE           Bias 
#>           7.38          54.48           5.38           0.18          -2.73 
#>             R2 Coverage lower Coverage upper       Coverage    Correlation 
#>           0.74           0.97           0.95           0.92           0.89 
#>            MFB            FGE 
#>          -0.05           0.19

round(calc_summary_statistics(predictions, date_effect_start, buffer = buffer), 2)

estimate_effect_size(predictions, date_effect_start, buffer = buffer, verbose = TRUE)

#> The external effect changed the target value on average by -6.294 compared to the reference time window. This is a -26.37% relative change.

#> $absolute_effect
#> [1] -6.294028
#> 
#> $relative_effect
#> [1] -0.2637

shapviz::sv_importance(res$importance, kind = "bee")

xvars <- c("TMP", "WIG", "GLO", "WIR")
shapviz::sv_dependence(res$importance, v = xvars)

install.packages("renv")
renv::restore()
devtools::build()
devtools::load_all()

pip install pre-commit

renv::snapshot()

# update documentation and check package integrity
devtools::check()
# apply tidyverse style (also applied as precommit hook)
usethis::use_tidy_style()
# you can check for existing lintr warnings by
devtools::lint()
# run tests
devtools::test()
# build README.md if any changes have been made to README.Rmd
devtools::build_readme()

cov <- covr::package_coverage(type = "all")
cov_list <- covr::coverage_to_list(cov)
data.table::data.table(
  part = c("Total", names(cov_list$filecoverage)),
  coverage = c(cov_list$totalcoverage, as.vector(cov_list$filecoverage))
)

covr::report(cov)