Rob Wiederstein
33d0fc31c7
End-to-end LightGBM fraud detection pipeline built as an R package, orchestrated by targets with data stored in MinIO via Apache Arrow. Includes 6-layer Lakehouse architecture, class imbalance tournament, formally tuned hyperparameters (PR-AUC 0.198), and Quarto RevealJS slides. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
140 lines
4.1 KiB
Plaintext
140 lines
4.1 KiB
Plaintext
# Generated by roxygen2: do not edit by hand
|
|
|
|
export(build_baf_recipe)
|
|
export(clean_baf_base)
|
|
export(compute_fraud_by_month)
|
|
export(connect_baf)
|
|
export(convert_to_parquet)
|
|
export(engineer_features)
|
|
export(evaluate_final_model)
|
|
export(format_class_imbalance_tourney_gt)
|
|
export(format_fraud_by_month_gt)
|
|
export(generate_model_inputs)
|
|
export(plot_conf_mat_heatmap)
|
|
export(plot_fraud_by_month)
|
|
export(plot_hexbin_interaction)
|
|
export(plot_missingness)
|
|
export(plot_num_cor)
|
|
export(plot_var_imp)
|
|
export(prepare_eda_recipe)
|
|
export(render_slides)
|
|
export(run_imbalance_tournament)
|
|
export(save_report_figure)
|
|
export(save_report_table)
|
|
export(train_diag_model)
|
|
export(train_production_model)
|
|
importFrom(arrow,S3FileSystem)
|
|
importFrom(arrow,open_dataset)
|
|
importFrom(arrow,read_csv_arrow)
|
|
importFrom(arrow,s3_bucket)
|
|
importFrom(arrow,to_duckdb)
|
|
importFrom(arrow,write_dataset)
|
|
importFrom(arrow,write_parquet)
|
|
importFrom(colorspace,qualitative_hcl)
|
|
importFrom(colorspace,scale_color_discrete_qualitative)
|
|
importFrom(colorspace,scale_fill_continuous_diverging)
|
|
importFrom(colorspace,scale_fill_continuous_sequential)
|
|
importFrom(corrr,correlate)
|
|
importFrom(corrr,rearrange)
|
|
importFrom(corrr,shave)
|
|
importFrom(corrr,stretch)
|
|
importFrom(cowplot,background_grid)
|
|
importFrom(cowplot,theme_cowplot)
|
|
importFrom(cowplot,theme_half_open)
|
|
importFrom(cowplot,theme_minimal_grid)
|
|
importFrom(cowplot,theme_minimal_vgrid)
|
|
importFrom(dplyr,`%>%`)
|
|
importFrom(dplyr,across)
|
|
importFrom(dplyr,any_of)
|
|
importFrom(dplyr,arrange)
|
|
importFrom(dplyr,bind_rows)
|
|
importFrom(dplyr,case_when)
|
|
importFrom(dplyr,collect)
|
|
importFrom(dplyr,desc)
|
|
importFrom(dplyr,everything)
|
|
importFrom(dplyr,filter)
|
|
importFrom(dplyr,group_by)
|
|
importFrom(dplyr,if_else)
|
|
importFrom(dplyr,mutate)
|
|
importFrom(dplyr,n)
|
|
importFrom(dplyr,pull)
|
|
importFrom(dplyr,rename)
|
|
importFrom(dplyr,select)
|
|
importFrom(dplyr,slice_max)
|
|
importFrom(dplyr,slice_sample)
|
|
importFrom(dplyr,summarise)
|
|
importFrom(dplyr,summarize)
|
|
importFrom(dplyr,tbl_vars)
|
|
importFrom(dplyr,ungroup)
|
|
importFrom(ggplot2,aes)
|
|
importFrom(ggplot2,autoplot)
|
|
importFrom(ggplot2,coord_flip)
|
|
importFrom(ggplot2,element_blank)
|
|
importFrom(ggplot2,element_text)
|
|
importFrom(ggplot2,expansion)
|
|
importFrom(ggplot2,geom_line)
|
|
importFrom(ggplot2,geom_linerange)
|
|
importFrom(ggplot2,geom_point)
|
|
importFrom(ggplot2,geom_segment)
|
|
importFrom(ggplot2,geom_text)
|
|
importFrom(ggplot2,geom_tile)
|
|
importFrom(ggplot2,ggplot)
|
|
importFrom(ggplot2,ggsave)
|
|
importFrom(ggplot2,labs)
|
|
importFrom(ggplot2,position_dodge)
|
|
importFrom(ggplot2,scale_color_manual)
|
|
importFrom(ggplot2,scale_fill_gradient)
|
|
importFrom(ggplot2,scale_y_continuous)
|
|
importFrom(ggplot2,scale_y_log10)
|
|
importFrom(ggplot2,stat_summary_hex)
|
|
importFrom(ggplot2,theme)
|
|
importFrom(ggplot2,theme_minimal)
|
|
importFrom(ggrepel,geom_text_repel)
|
|
importFrom(glue,glue)
|
|
importFrom(gt,cols_label)
|
|
importFrom(gt,data_color)
|
|
importFrom(gt,fmt_number)
|
|
importFrom(gt,gt)
|
|
importFrom(gt,tab_header)
|
|
importFrom(gt,tab_options)
|
|
importFrom(lightgbm,lgb.Dataset)
|
|
importFrom(lightgbm,lgb.importance)
|
|
importFrom(lightgbm,lgb.save)
|
|
importFrom(lightgbm,lgb.train)
|
|
importFrom(lubridate,"%m+%")
|
|
importFrom(parsnip,boost_tree)
|
|
importFrom(parsnip,set_engine)
|
|
importFrom(parsnip,set_mode)
|
|
importFrom(quarto,quarto_render)
|
|
importFrom(readr,write_rds)
|
|
importFrom(recipes,all_nominal_predictors)
|
|
importFrom(recipes,all_numeric_predictors)
|
|
importFrom(recipes,all_predictors)
|
|
importFrom(recipes,bake)
|
|
importFrom(recipes,prep)
|
|
importFrom(recipes,recipe)
|
|
importFrom(recipes,step_dummy)
|
|
importFrom(recipes,step_impute_median)
|
|
importFrom(recipes,step_indicate_na)
|
|
importFrom(recipes,step_novel)
|
|
importFrom(recipes,step_unknown)
|
|
importFrom(recipes,step_zv)
|
|
importFrom(recipes,update_role)
|
|
importFrom(scales,percent)
|
|
importFrom(stats,reorder)
|
|
importFrom(stats,sd)
|
|
importFrom(stats,t.test)
|
|
importFrom(stringr,str_remove)
|
|
importFrom(stringr,str_replace_all)
|
|
importFrom(themis,adasyn)
|
|
importFrom(themis,smote)
|
|
importFrom(themis,step_tomek)
|
|
importFrom(tidyr,pivot_longer)
|
|
importFrom(tidyselect,where)
|
|
importFrom(workflows,add_model)
|
|
importFrom(workflows,add_recipe)
|
|
importFrom(workflows,extract_fit_engine)
|
|
importFrom(workflows,fit)
|
|
importFrom(workflows,workflow)
|
|
importFrom(yardstick,pr_auc)
|