├── .gitignore ├── README.md ├── charts ├── 2001-SEA-raw.png ├── 2002-oakland-as.png ├── 2017-cleveland-indians.png ├── 2017-newyork-yankees.png ├── 2018-boston-redsox.png ├── 2019-model-comparison.png ├── 2019-washington-nationals.png ├── Logit_Final_Model.png ├── eda-heatmap.png ├── eda-pct-2.png ├── eda-pct.png ├── feature-importances.png ├── lift-final-truncated.png ├── model-abbreviated-roc.png ├── model-full-roc.png ├── model-roc-double.png ├── post-2015-lift-aggregate.png ├── post-2015-lift.png └── thesis-latex-outputs.tex ├── elo-model └── elo-framework.ipynb ├── models ├── integrated-model-evaluation-finalrun.ipynb ├── ml-modeling.ipynb └── model-eval-draft_EDA.ipynb ├── output-data ├── COV_AGGREGATE.csv ├── EDA │ ├── W_L_DATA.csv │ └── YEARLY_HOME_WIN_RATE.csv ├── ELO_ratings.csv └── covariates.zip ├── preprocessing ├── covariate-gamelevel-import.ipynb ├── final-covariate-building.ipynb ├── gamelevel-data-preprocessing.ipynb ├── pitcher-hitter-integration.ipynb ├── processing_master_df.ipynb └── retrosheet_scraper.py └── visualization-data ├── WL_comparison.csv ├── brier_scores.csv ├── feature_importance.csv ├── final_model_test.csv ├── final_model_train.csv ├── scaled_brier_scores.csv ├── scaled_model_scores.csv ├── unscaled_brier_scores.csv ├── unscaled_model_monthly.csv └── unscaled_model_scores.csv /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/README.md -------------------------------------------------------------------------------- /charts/2001-SEA-raw.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/2001-SEA-raw.png -------------------------------------------------------------------------------- /charts/2002-oakland-as.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/2002-oakland-as.png -------------------------------------------------------------------------------- /charts/2017-cleveland-indians.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/2017-cleveland-indians.png -------------------------------------------------------------------------------- /charts/2017-newyork-yankees.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/2017-newyork-yankees.png -------------------------------------------------------------------------------- /charts/2018-boston-redsox.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/2018-boston-redsox.png -------------------------------------------------------------------------------- /charts/2019-model-comparison.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/2019-model-comparison.png -------------------------------------------------------------------------------- /charts/2019-washington-nationals.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/2019-washington-nationals.png -------------------------------------------------------------------------------- /charts/Logit_Final_Model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/Logit_Final_Model.png -------------------------------------------------------------------------------- /charts/eda-heatmap.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/eda-heatmap.png -------------------------------------------------------------------------------- /charts/eda-pct-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/eda-pct-2.png -------------------------------------------------------------------------------- /charts/eda-pct.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/eda-pct.png -------------------------------------------------------------------------------- /charts/feature-importances.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/feature-importances.png -------------------------------------------------------------------------------- /charts/lift-final-truncated.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/lift-final-truncated.png -------------------------------------------------------------------------------- /charts/model-abbreviated-roc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/model-abbreviated-roc.png -------------------------------------------------------------------------------- /charts/model-full-roc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/model-full-roc.png -------------------------------------------------------------------------------- /charts/model-roc-double.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/model-roc-double.png -------------------------------------------------------------------------------- /charts/post-2015-lift-aggregate.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/post-2015-lift-aggregate.png -------------------------------------------------------------------------------- /charts/post-2015-lift.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/post-2015-lift.png -------------------------------------------------------------------------------- /charts/thesis-latex-outputs.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/charts/thesis-latex-outputs.tex -------------------------------------------------------------------------------- /elo-model/elo-framework.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/elo-model/elo-framework.ipynb -------------------------------------------------------------------------------- /models/integrated-model-evaluation-finalrun.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/models/integrated-model-evaluation-finalrun.ipynb -------------------------------------------------------------------------------- /models/ml-modeling.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/models/ml-modeling.ipynb -------------------------------------------------------------------------------- /models/model-eval-draft_EDA.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/models/model-eval-draft_EDA.ipynb -------------------------------------------------------------------------------- /output-data/COV_AGGREGATE.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/output-data/COV_AGGREGATE.csv -------------------------------------------------------------------------------- /output-data/EDA/W_L_DATA.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/output-data/EDA/W_L_DATA.csv -------------------------------------------------------------------------------- /output-data/EDA/YEARLY_HOME_WIN_RATE.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/output-data/EDA/YEARLY_HOME_WIN_RATE.csv -------------------------------------------------------------------------------- /output-data/ELO_ratings.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/output-data/ELO_ratings.csv -------------------------------------------------------------------------------- /output-data/covariates.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/output-data/covariates.zip -------------------------------------------------------------------------------- /preprocessing/covariate-gamelevel-import.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/preprocessing/covariate-gamelevel-import.ipynb -------------------------------------------------------------------------------- /preprocessing/final-covariate-building.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/preprocessing/final-covariate-building.ipynb -------------------------------------------------------------------------------- /preprocessing/gamelevel-data-preprocessing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/preprocessing/gamelevel-data-preprocessing.ipynb -------------------------------------------------------------------------------- /preprocessing/pitcher-hitter-integration.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/preprocessing/pitcher-hitter-integration.ipynb -------------------------------------------------------------------------------- /preprocessing/processing_master_df.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/preprocessing/processing_master_df.ipynb -------------------------------------------------------------------------------- /preprocessing/retrosheet_scraper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/preprocessing/retrosheet_scraper.py -------------------------------------------------------------------------------- /visualization-data/WL_comparison.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/WL_comparison.csv -------------------------------------------------------------------------------- /visualization-data/brier_scores.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/brier_scores.csv -------------------------------------------------------------------------------- /visualization-data/feature_importance.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/feature_importance.csv -------------------------------------------------------------------------------- /visualization-data/final_model_test.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/final_model_test.csv -------------------------------------------------------------------------------- /visualization-data/final_model_train.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/final_model_train.csv -------------------------------------------------------------------------------- /visualization-data/scaled_brier_scores.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/scaled_brier_scores.csv -------------------------------------------------------------------------------- /visualization-data/scaled_model_scores.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/scaled_model_scores.csv -------------------------------------------------------------------------------- /visualization-data/unscaled_brier_scores.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/unscaled_brier_scores.csv -------------------------------------------------------------------------------- /visualization-data/unscaled_model_monthly.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/unscaled_model_monthly.csv -------------------------------------------------------------------------------- /visualization-data/unscaled_model_scores.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/andrew-cui/mlb-game-prediction/HEAD/visualization-data/unscaled_model_scores.csv --------------------------------------------------------------------------------