├── README.md ├── cases ├── adversarial_prompt_attacks.md ├── examples_im_for_embed_search.png ├── fit_transform_on_test.md ├── id_sort_leak.md ├── insufficient_stratification.md ├── metadata_predicts_target.md ├── ohe_target_as_feature.md ├── prod_frame_train_vid.md ├── recoverable_features_objs.md ├── test_based_evaluation.md ├── test_intersect_train_obvious.md ├── test_match_restore_embed_search.md ├── time_aviabilitiy_initial.md └── ts_val_leak.md └── src └── leakage_tests ├── group_strat.py ├── ohe_target_as_feature.py └── test_df_intersect_train_df.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/README.md -------------------------------------------------------------------------------- /cases/adversarial_prompt_attacks.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/adversarial_prompt_attacks.md -------------------------------------------------------------------------------- /cases/examples_im_for_embed_search.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/examples_im_for_embed_search.png -------------------------------------------------------------------------------- /cases/fit_transform_on_test.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/fit_transform_on_test.md -------------------------------------------------------------------------------- /cases/id_sort_leak.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/id_sort_leak.md -------------------------------------------------------------------------------- /cases/insufficient_stratification.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/insufficient_stratification.md -------------------------------------------------------------------------------- /cases/metadata_predicts_target.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/metadata_predicts_target.md -------------------------------------------------------------------------------- /cases/ohe_target_as_feature.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/ohe_target_as_feature.md -------------------------------------------------------------------------------- /cases/prod_frame_train_vid.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/prod_frame_train_vid.md -------------------------------------------------------------------------------- /cases/recoverable_features_objs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/recoverable_features_objs.md -------------------------------------------------------------------------------- /cases/test_based_evaluation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/test_based_evaluation.md -------------------------------------------------------------------------------- /cases/test_intersect_train_obvious.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/test_intersect_train_obvious.md -------------------------------------------------------------------------------- /cases/test_match_restore_embed_search.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/test_match_restore_embed_search.md -------------------------------------------------------------------------------- /cases/time_aviabilitiy_initial.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/time_aviabilitiy_initial.md -------------------------------------------------------------------------------- /cases/ts_val_leak.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/cases/ts_val_leak.md -------------------------------------------------------------------------------- /src/leakage_tests/group_strat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/src/leakage_tests/group_strat.py -------------------------------------------------------------------------------- /src/leakage_tests/ohe_target_as_feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/src/leakage_tests/ohe_target_as_feature.py -------------------------------------------------------------------------------- /src/leakage_tests/test_df_intersect_train_df.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/GrigoriiTarasov/Leaks-in-ML-DS-prevention/HEAD/src/leakage_tests/test_df_intersect_train_df.py --------------------------------------------------------------------------------