Movatterモバイル変換

ubair

ubair is an R package for Statistical Investigationof the Impact of External Conditions on Air Quality: it uses thestatistical software R to analyze and visualize the impact of externalfactors, such as traffic restrictions, hazards, and political measures,on air quality. It aims to provide experts with a transparent comparisonof modeling approaches and to support data-driven evaluations for policyadvisory purposes.

Installation

Recommended option installfromcran

runinstall.packages("ubair") or via source code fromhttps://gitlab.opencode.de/uba-ki-lab/ubair

Sample Usage of package

For a more detailed explanation of the package, you can access thevignettes:

• View user_sample source code directly in thevignettes/ folder.
• Open vignette by functionvignette("user_sample_1", package = "ubair"), if thepackage was installed with vignettes

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

# Plot meteo dataplot_station_measurements(env_data, params$meteo_variables)

• split data into training, reference and effect time intervals

application_start<- lubridate::ymd("20191201")# This coincides with the start of the reference windowdate_effect_start<- lubridate::ymd_hm("20200323 00:00")# This splits the forecast into reference and effectapplication_end<- lubridate::ymd("20200504")# This coincides with the end of the effect windowbuffer<-24*14# 14 days bufferdt_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 0.001115 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$predictionplot_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

SHAP feature importances

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

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

Development

Prerequisites

1. R: Make sure you have R installed (recommendedversion 4.4.1). You can download it fromCRAN.
2. RStudio (optional but recommended): Download fromRStudio.

Setting Up the Environment

Install the development version of ubair:

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

Development

pip install pre-commit

renv::snapshot()

# update documentation and check package integritydevtools::check()# apply tidyverse style (also applied as precommit hook)usethis::use_tidy_style()# you can check for existing lintr warnings bydevtools::lint()# run testsdevtools::test()# build README.md if any changes have been made to README.Rmddevtools::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)