├── .gitignore ├── .project ├── .pydevproject ├── .settings └── org.eclipse.core.resources.prefs ├── LICENSE ├── README.md ├── cameleogrey_leaderboard_03_13_2023.png ├── requirements.txt └── src ├── classes ├── CatBoostBinaryClassifierMixup.py ├── CatBoostBinarySelfOptimized.py ├── CatBoostCVAverager.py ├── CatBoostMulticlassOptimal.py ├── DataCleaner.py ├── FeatureBuilder.py ├── GreyAutoencoder1d.py ├── GreyCategoricalEncoder.py ├── GreyFeatureSelector.py ├── GreyUrlEncoder.py ├── MLP_Network.py ├── UserFeatDictBuilder.py ├── __init__.py ├── danet │ ├── DANet.py │ ├── DANetClassifier.py │ └── sparsemax.py ├── gnn │ ├── BiasedRandomWalk.py │ ├── GraphFeatureBuilder.py │ ├── Node2VecEmbedder.py │ ├── RandomWalk.py │ ├── UniformRandomWalk.py │ └── WatchYourStepEmbedder.py ├── paths_config.py ├── scrapping │ ├── BERTVectorizer.py │ ├── GreyHtmlContentParser.py │ ├── SimpleDataPreprocessor.py │ ├── SiteHtmlScrapper.py │ ├── TfidfW2vVectorizer.py │ └── __init__.py └── utils.py ├── scripts_content_parsing ├── 0_check_ocr.py ├── 1_scrap_site_screenshots.py ├── 2_parse_content.py ├── 3_build_content_feat_dict.py └── __init__.py ├── scripts_gnn ├── 0_test.py ├── 1_fit_graph_embedder.py ├── 2_build_graph_features_dict.py ├── 3_0_build_embedding_dataset.py ├── 3_1_test_is_male_profit.py └── 3_2_test_age_profit.py └── scripts_main ├── 0_make_subsample.py ├── 1_eda.py ├── 2_1_build_base_features.py ├── 2_2_build_factor_features_dict.py ├── 2_2_build_w2v_features_dict.py ├── 3_build_dataset.py ├── 5_0_make_is_male_submission.py ├── 5_1_make_is_male_danet_submission.py ├── 6_0_make_age_submission.py ├── 6_1_make_age_danet_submission.py ├── 7_build_final_submission.py └── __init__.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/.gitignore -------------------------------------------------------------------------------- /.project: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/.project -------------------------------------------------------------------------------- /.pydevproject: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/.pydevproject -------------------------------------------------------------------------------- /.settings/org.eclipse.core.resources.prefs: -------------------------------------------------------------------------------- 1 | eclipse.preferences.version=1 2 | encoding/=UTF-8 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/README.md -------------------------------------------------------------------------------- /cameleogrey_leaderboard_03_13_2023.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/cameleogrey_leaderboard_03_13_2023.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/requirements.txt -------------------------------------------------------------------------------- /src/classes/CatBoostBinaryClassifierMixup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/CatBoostBinaryClassifierMixup.py -------------------------------------------------------------------------------- /src/classes/CatBoostBinarySelfOptimized.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/CatBoostBinarySelfOptimized.py -------------------------------------------------------------------------------- /src/classes/CatBoostCVAverager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/CatBoostCVAverager.py -------------------------------------------------------------------------------- /src/classes/CatBoostMulticlassOptimal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/CatBoostMulticlassOptimal.py -------------------------------------------------------------------------------- /src/classes/DataCleaner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/DataCleaner.py -------------------------------------------------------------------------------- /src/classes/FeatureBuilder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/FeatureBuilder.py -------------------------------------------------------------------------------- /src/classes/GreyAutoencoder1d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/GreyAutoencoder1d.py -------------------------------------------------------------------------------- /src/classes/GreyCategoricalEncoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/GreyCategoricalEncoder.py -------------------------------------------------------------------------------- /src/classes/GreyFeatureSelector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/GreyFeatureSelector.py -------------------------------------------------------------------------------- /src/classes/GreyUrlEncoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/GreyUrlEncoder.py -------------------------------------------------------------------------------- /src/classes/MLP_Network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/MLP_Network.py -------------------------------------------------------------------------------- /src/classes/UserFeatDictBuilder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/UserFeatDictBuilder.py -------------------------------------------------------------------------------- /src/classes/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/classes/danet/DANet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/danet/DANet.py -------------------------------------------------------------------------------- /src/classes/danet/DANetClassifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/danet/DANetClassifier.py -------------------------------------------------------------------------------- /src/classes/danet/sparsemax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/danet/sparsemax.py -------------------------------------------------------------------------------- /src/classes/gnn/BiasedRandomWalk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/gnn/BiasedRandomWalk.py -------------------------------------------------------------------------------- /src/classes/gnn/GraphFeatureBuilder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/gnn/GraphFeatureBuilder.py -------------------------------------------------------------------------------- /src/classes/gnn/Node2VecEmbedder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/gnn/Node2VecEmbedder.py -------------------------------------------------------------------------------- /src/classes/gnn/RandomWalk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/gnn/RandomWalk.py -------------------------------------------------------------------------------- /src/classes/gnn/UniformRandomWalk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/gnn/UniformRandomWalk.py -------------------------------------------------------------------------------- /src/classes/gnn/WatchYourStepEmbedder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/gnn/WatchYourStepEmbedder.py -------------------------------------------------------------------------------- /src/classes/paths_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/paths_config.py -------------------------------------------------------------------------------- /src/classes/scrapping/BERTVectorizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/scrapping/BERTVectorizer.py -------------------------------------------------------------------------------- /src/classes/scrapping/GreyHtmlContentParser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/scrapping/GreyHtmlContentParser.py -------------------------------------------------------------------------------- /src/classes/scrapping/SimpleDataPreprocessor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/scrapping/SimpleDataPreprocessor.py -------------------------------------------------------------------------------- /src/classes/scrapping/SiteHtmlScrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/scrapping/SiteHtmlScrapper.py -------------------------------------------------------------------------------- /src/classes/scrapping/TfidfW2vVectorizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/scrapping/TfidfW2vVectorizer.py -------------------------------------------------------------------------------- /src/classes/scrapping/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/classes/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/classes/utils.py -------------------------------------------------------------------------------- /src/scripts_content_parsing/0_check_ocr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_content_parsing/0_check_ocr.py -------------------------------------------------------------------------------- /src/scripts_content_parsing/1_scrap_site_screenshots.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_content_parsing/1_scrap_site_screenshots.py -------------------------------------------------------------------------------- /src/scripts_content_parsing/2_parse_content.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_content_parsing/2_parse_content.py -------------------------------------------------------------------------------- /src/scripts_content_parsing/3_build_content_feat_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_content_parsing/3_build_content_feat_dict.py -------------------------------------------------------------------------------- /src/scripts_content_parsing/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/scripts_gnn/0_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_gnn/0_test.py -------------------------------------------------------------------------------- /src/scripts_gnn/1_fit_graph_embedder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_gnn/1_fit_graph_embedder.py -------------------------------------------------------------------------------- /src/scripts_gnn/2_build_graph_features_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_gnn/2_build_graph_features_dict.py -------------------------------------------------------------------------------- /src/scripts_gnn/3_0_build_embedding_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_gnn/3_0_build_embedding_dataset.py -------------------------------------------------------------------------------- /src/scripts_gnn/3_1_test_is_male_profit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_gnn/3_1_test_is_male_profit.py -------------------------------------------------------------------------------- /src/scripts_gnn/3_2_test_age_profit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_gnn/3_2_test_age_profit.py -------------------------------------------------------------------------------- /src/scripts_main/0_make_subsample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/0_make_subsample.py -------------------------------------------------------------------------------- /src/scripts_main/1_eda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/1_eda.py -------------------------------------------------------------------------------- /src/scripts_main/2_1_build_base_features.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/2_1_build_base_features.py -------------------------------------------------------------------------------- /src/scripts_main/2_2_build_factor_features_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/2_2_build_factor_features_dict.py -------------------------------------------------------------------------------- /src/scripts_main/2_2_build_w2v_features_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/2_2_build_w2v_features_dict.py -------------------------------------------------------------------------------- /src/scripts_main/3_build_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/3_build_dataset.py -------------------------------------------------------------------------------- /src/scripts_main/5_0_make_is_male_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/5_0_make_is_male_submission.py -------------------------------------------------------------------------------- /src/scripts_main/5_1_make_is_male_danet_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/5_1_make_is_male_danet_submission.py -------------------------------------------------------------------------------- /src/scripts_main/6_0_make_age_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/6_0_make_age_submission.py -------------------------------------------------------------------------------- /src/scripts_main/6_1_make_age_danet_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/6_1_make_age_danet_submission.py -------------------------------------------------------------------------------- /src/scripts_main/7_build_final_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/CameleoGrey/cameleogrey_mtsmlcup/HEAD/src/scripts_main/7_build_final_submission.py -------------------------------------------------------------------------------- /src/scripts_main/__init__.py: -------------------------------------------------------------------------------- 1 | --------------------------------------------------------------------------------