{"cells":[{"metadata":{},"cell_type":"markdown","source":"## Import Library & Load Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.linear_model import LogisticRegression\nimport matplotlib.pyplot as plt\nfrom sklearn.utils import shuffle\nfrom sklearn.model_selection import GridSearchCV","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"tourney_result = pd.read_csv('../input/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/MDataFiles_Stage1/MNCAATourneyCompactResults.csv')\ntourney_seed = pd.read_csv('../input/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/MDataFiles_Stage1/MNCAATourneySeeds.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# deleting unnecessary columns\ntourney_result = tourney_result.drop(['DayNum', 'WScore', 'LScore', 'WLoc', 'NumOT'], axis=1)\ntourney_result","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Merge Seed"},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_result = pd.merge(tourney_result, tourney_seed, left_on=['Season', 'WTeamID'], right_on=['Season', 'TeamID'], how='left')\ntourney_result.rename(columns={'Seed':'WSeed'}, inplace=True)\ntourney_result = tourney_result.drop('TeamID', axis=1)\ntourney_result = pd.merge(tourney_result, tourney_seed, left_on=['Season', 'LTeamID'], right_on=['Season', 'TeamID'], how='left')\ntourney_result.rename(columns={'Seed':'LSeed'}, inplace=True)\ntourney_result = tourney_result.drop('TeamID', axis=1)\ntourney_result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_seed(x):\n    return int(x[1:3])\n\ntourney_result['WSeed'] = tourney_result['WSeed'].map(lambda x: get_seed(x))\ntourney_result['LSeed'] = tourney_result['LSeed'].map(lambda x: get_seed(x))\ntourney_result","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Merge Score"},{"metadata":{"trusted":true},"cell_type":"code","source":"season_result = pd.read_csv('../input/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/MDataFiles_Stage1/MRegularSeasonCompactResults.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"season_win_result = season_result[['Season', 'WTeamID', 'WScore']]\nseason_lose_result = season_result[['Season', 'LTeamID', 'LScore']]\nseason_win_result.rename(columns={'WTeamID':'TeamID', 'WScore':'Score'}, inplace=True)\nseason_lose_result.rename(columns={'LTeamID':'TeamID', 'LScore':'Score'}, inplace=True)\nseason_result = pd.concat((season_win_result, season_lose_result)).reset_index(drop=True)\nseason_result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"season_score = season_result.groupby(['Season', 'TeamID'])['Score'].sum().reset_index()\nseason_score","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_result = pd.merge(tourney_result, season_score, left_on=['Season', 'WTeamID'], right_on=['Season', 'TeamID'], how='left')\ntourney_result.rename(columns={'Score':'WScoreT'}, inplace=True)\ntourney_result = tourney_result.drop('TeamID', axis=1)\ntourney_result = pd.merge(tourney_result, season_score, left_on=['Season', 'LTeamID'], right_on=['Season', 'TeamID'], how='left')\ntourney_result.rename(columns={'Score':'LScoreT'}, inplace=True)\ntourney_result = tourney_result.drop('TeamID', axis=1)\ntourney_result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_win_result = tourney_result.drop(['Season', 'WTeamID', 'LTeamID'], axis=1)\ntourney_win_result.rename(columns={'WSeed':'Seed1', 'LSeed':'Seed2', 'WScoreT':'ScoreT1', 'LScoreT':'ScoreT2'}, inplace=True)\ntourney_win_result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_lose_result = tourney_win_result.copy()\ntourney_lose_result['Seed1'] = tourney_win_result['Seed2']\ntourney_lose_result['Seed2'] = tourney_win_result['Seed1']\ntourney_lose_result['ScoreT1'] = tourney_win_result['ScoreT2']\ntourney_lose_result['ScoreT2'] = tourney_win_result['ScoreT1']\ntourney_lose_result","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Prepare Training Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_win_result['Seed_diff'] = tourney_win_result['Seed1'] - tourney_win_result['Seed2']\ntourney_win_result['ScoreT_diff'] = tourney_win_result['ScoreT1'] - tourney_win_result['ScoreT2']\ntourney_lose_result['Seed_diff'] = tourney_lose_result['Seed1'] - tourney_lose_result['Seed2']\ntourney_lose_result['ScoreT_diff'] = tourney_lose_result['ScoreT1'] - tourney_lose_result['ScoreT2']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_win_result['result'] = 1\ntourney_lose_result['result'] = 0\ntourney_result = pd.concat((tourney_win_result, tourney_lose_result)).reset_index(drop=True)\ntourney_result","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Preparing testing data"},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.read_csv('../input/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/MSampleSubmissionStage1_2020.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['Season'] = test_df['ID'].map(lambda x: int(x[:4]))\ntest_df['WTeamID'] = test_df['ID'].map(lambda x: int(x[5:9]))\ntest_df['LTeamID'] = test_df['ID'].map(lambda x: int(x[10:14]))\ntest_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.merge(test_df, tourney_seed, left_on=['Season', 'WTeamID'], right_on=['Season', 'TeamID'], how='left')\ntest_df.rename(columns={'Seed':'Seed1'}, inplace=True)\ntest_df = test_df.drop('TeamID', axis=1)\ntest_df = pd.merge(test_df, tourney_seed, left_on=['Season', 'LTeamID'], right_on=['Season', 'TeamID'], how='left')\ntest_df.rename(columns={'Seed':'Seed2'}, inplace=True)\ntest_df = test_df.drop('TeamID', axis=1)\ntest_df = pd.merge(test_df, season_score, left_on=['Season', 'WTeamID'], right_on=['Season', 'TeamID'], how='left')\ntest_df.rename(columns={'Score':'ScoreT1'}, inplace=True)\ntest_df = test_df.drop('TeamID', axis=1)\ntest_df = pd.merge(test_df, season_score, left_on=['Season', 'LTeamID'], right_on=['Season', 'TeamID'], how='left')\ntest_df.rename(columns={'Score':'ScoreT2'}, inplace=True)\ntest_df = test_df.drop('TeamID', axis=1)\ntest_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['Seed1'] = test_df['Seed1'].map(lambda x: get_seed(x))\ntest_df['Seed2'] = test_df['Seed2'].map(lambda x: get_seed(x))\ntest_df['Seed_diff'] = test_df['Seed1'] - test_df['Seed2']\ntest_df['ScoreT_diff'] = test_df['ScoreT1'] - test_df['ScoreT2']\ntest_df = test_df.drop(['ID', 'Pred', 'Season', 'WTeamID', 'LTeamID'], axis=1)\ntest_df","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Train"},{"metadata":{"trusted":true},"cell_type":"code","source":"X = tourney_result.drop('result', axis=1)\ny = tourney_result.result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import KFold\nimport lightgbm as lgb\n\nparams = {'num_leaves': 570,\n          'min_child_weight': 0.034,\n          'feature_fraction': 0.379,\n          'bagging_fraction': 0.418,\n          'min_data_in_leaf': 106,\n          'objective': 'binary',\n          'max_depth': -1,\n          'learning_rate': 0.1,\n          \"boosting_type\": \"gbdt\",\n          \"bagging_seed\": 11,\n          \"metric\": 'logloss',\n          \"verbosity\": -1,\n          'reg_alpha': 0.3899,\n          'reg_lambda': 0.648,\n          'random_state': 47,\n         }","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import gc\nNFOLDS = 10\nfolds = KFold(n_splits=NFOLDS)\n\ncolumns = X.columns\nsplits = folds.split(X, y)\ny_preds = np.zeros(test_df.shape[0])\ny_oof = np.zeros(X.shape[0])\n\nfeature_importances = pd.DataFrame()\nfeature_importances['feature'] = columns\n  \nfor fold_n, (train_index, valid_index) in enumerate(splits):\n    print('Fold:',fold_n+1)\n    X_train, X_valid = X[columns].iloc[train_index], X[columns].iloc[valid_index]\n    y_train, y_valid = y.iloc[train_index], y.iloc[valid_index]\n    \n    dtrain = lgb.Dataset(X_train, label=y_train)\n    dvalid = lgb.Dataset(X_valid, label=y_valid)\n\n    clf = lgb.train(params, dtrain, 10000, valid_sets = [dtrain, dvalid], verbose_eval=200)\n    \n    feature_importances[f'fold_{fold_n + 1}'] = clf.feature_importance()\n    \n    y_pred_valid = clf.predict(X_valid)\n    y_oof[valid_index] = y_pred_valid\n    \n    y_preds += clf.predict(test_df) / NFOLDS\n    \n    del X_train, X_valid, y_train, y_valid\n    gc.collect()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Predict & Make Submission File"},{"metadata":{"trusted":true},"cell_type":"code","source":"\nsubmission_df = pd.read_csv('../input/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/MSampleSubmissionStage1_2020.csv')\nsubmission_df['Pred'] = y_preds\nsubmission_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df['Pred'].hist()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Feature Importances:"},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\nfeature_importances['average'] = feature_importances[[f'fold_{fold_n + 1}' for fold_n in range(folds.n_splits)]].mean(axis=1)\nfeature_importances.to_csv('feature_importances.csv')\n\nplt.figure(figsize=(10, 6))\nsns.barplot(data=feature_importances.sort_values(by='average', ascending=False).head(7), x='average', y='feature');\nplt.title('7 TOP feature importance over {} folds average'.format(folds.n_splits));","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}