{"cells":[{"metadata":{},"cell_type":"markdown","source":"<h3><center>Introduction</center></h3>\n<div style=\"font-family:verdana; word-spacing:1.7px;\">\nIn this kernel we will be working with data from Google Cloud & NCAA® ML Competition 2019-Men's Challenge. We'll try to predict winners of NCAA based on previous tournaments! We have a lot of data, so let's start with EDA and then build a baseline model.\n\n</div>\n\n![image.png](attachment:image.png)","attachments":{"image.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"<h2><center>1. Importing Libraries</center></h2>"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore')\n\nimport numpy as np\nimport pandas as pd\nimport os\nfrom scipy import stats\n\nfrom tqdm import tqdm_notebook as tqdm\ntqdm().pandas()\n\n\nimport matplotlib.pylab as plt\nfrom matplotlib.patches import Circle, Rectangle, Arc\nimport seaborn as sns\n\nplt.style.use('seaborn-dark-palette')\nmypal = plt.rcParams['axes.prop_cycle'].by_key()['color'] # Grab the color pal\n\nimport gc\n\nimport eli5\n\nfrom sklearn.linear_model import LogisticRegression, LinearRegression\nfrom sklearn.preprocessing import StandardScaler, MinMaxScaler\nfrom sklearn.utils import shuffle\nfrom sklearn.model_selection import GridSearchCV, KFold, train_test_split, cross_val_score, \\\n                                        RepeatedStratifiedKFold, StratifiedKFold\nfrom sklearn import preprocessing\nfrom sklearn.metrics import confusion_matrix\n\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.dummy import DummyClassifier\n\n\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.svm import SVC\n\nimport lightgbm as lgb\nimport xgboost as xgb","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"PATH_MEN = '/kaggle/input/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/'","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h2><center>2. Exploring Data</center></h2>"},{"metadata":{},"cell_type":"markdown","source":"<h3>2.1. Teams Data</h3>"},{"metadata":{},"cell_type":"markdown","source":"<h3>Newbies</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"MTeams = pd.read_csv(PATH_MEN + '/MDataFiles_Stage1/MTeams.csv')\nMTeams.sort_values(by='FirstD1Season', ascending=False).head(10)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>Oldies</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"MTeams.sort_values(by='FirstD1Season').head(10)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>2.2. Seasons Data</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"MSeasons = pd.read_csv(PATH_MEN + 'MDataFiles_Stage1/MSeasons.csv')\n\nMSeasons.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>2.3. Seed Data</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"MNCAATourneySeeds = pd.read_csv(PATH_MEN + 'MDataFiles_Stage1/MNCAATourneySeeds.csv')\nMNCAATourneySeeds.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>2.4. Regular Season Results</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"MRegularSeasonCompactResults = pd.read_csv(PATH_MEN + 'MDataFiles_Stage1/MRegularSeasonCompactResults.csv')\nMRegularSeasonCompactResults.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>Winning & losing Teams</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Lets Add the winning and losing team names to the results\nMRegularSeasonCompactResults = \\\n    MRegularSeasonCompactResults \\\n    .merge(MTeams[['TeamName', 'TeamID']],\n           left_on='WTeamID',\n           right_on='TeamID',\n           validate='many_to_one') \\\n    .drop('TeamID', axis=1) \\\n    .rename(columns={'TeamName': 'WTeamName'}) \\\n    .merge(MTeams[['TeamName', 'TeamID']],\n           left_on='LTeamID',\n           right_on='TeamID') \\\n    .drop('TeamID', axis=1) \\\n    .rename(columns={'TeamName': 'LTeamName'})\n\nMRegularSeasonCompactResults.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"MRegularSeasonCompactResults['Score_Diff'] = MRegularSeasonCompactResults['WScore'] - MRegularSeasonCompactResults['LScore']\n\nplt.style.use('fivethirtyeight')\nMRegularSeasonCompactResults['Score_Diff'] \\\n    .plot(kind='hist',\n          bins=90,\n          figsize=(15, 5),\n          label='Mens',\n          alpha=0.5)\nplt.title('Score Differential')\nplt.xlim(0,60)\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"MRegularSeasonCompactResults","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.style.use('fivethirtyeight')\nfig, axs = plt.subplots(1, 2, figsize=(15, 5))\nMRegularSeasonCompactResults['counter'] = 1\nMRegularSeasonCompactResults.groupby('WTeamName')['counter'] \\\n    .count() \\\n    .sort_values() \\\n    .tail(20) \\\n    .plot(kind='barh',\n          title='⬆️ Most Regular Season Wins (Mens)',\n          figsize=(15, 8),\n          xlim=(600, 920),\n          color=mypal[2],\n         ax=axs[0])\nMRegularSeasonCompactResults.groupby('WTeamName')['counter'] \\\n    .count() \\\n    .sort_values(ascending=False) \\\n    .tail(20) \\\n    .plot(kind='barh',\n          title='⬇️ Least Regular Season Wins (Mens)',\n          figsize=(15, 8),\n          xlim=(0, 150),\n          color=mypal[3],\n          ax=axs[1])\naxs[1].set_ylabel('')\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>2.5. Event Data</h3>\n\nEach event is assigned to either a team or a single one of the team's players. Thus if a basket is made by one player and an assist is credited to a second player, that would show up as two separate records. The players are listed by PlayerID within the xPlayers.csv file."},{"metadata":{"trusted":true},"cell_type":"code","source":"mens_events = []\nfor year in [2015, 2016, 2017, 2018, 2019]:\n    mens_events.append(pd.read_csv(f'{PATH_MEN}MEvents{year}.csv'))\nMEvents = pd.concat(mens_events)\nprint(MEvents.shape)\nMEvents.head()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"del mens_events\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"plt.style.use('fivethirtyeight')\nMEvents['counter'] = 1\nMEvents.groupby('EventType')['counter'] \\\n    .sum() \\\n    .sort_values(ascending=False) \\\n    .plot(kind='bar',\n          figsize=(15, 5),\n         color=mypal[2],\n         title='Event Type Frequency (Mens)')\nplt.xticks(rotation=0)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>Area Event</h3>\n\n<div style=\"font-family:verdana; word-spacing:1.7px;\">\nWe are told that the Area feature describes the 13 \"areas\" of the court, as follows: 1=under basket; 2=in the paint; 3=inside right wing; 4=inside right; 5=inside center; 6=inside left; 7=inside left wing; 8=outside right wing; 9=outside right; 10=outside center; 11=outside left; 12=outside left wing; 13=backcourt.\n    </div>"},{"metadata":{"trusted":true},"cell_type":"code","source":"area_mapping = {0: np.nan,\n                1: 'under basket',\n                2: 'in the paint',\n                3: 'inside right wing',\n                4: 'inside right',\n                5: 'inside center',\n                6: 'inside left',\n                7: 'inside left wing',\n                8: 'outside right wing',\n                9: 'outside right',\n                10: 'outside center',\n                11: 'outside left',\n                12: 'outside left wing',\n                13: 'backcourt'}\n\nMEvents['Area_Name'] = MEvents['Area'].map(area_mapping)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"MEvents.groupby('Area_Name')['counter'].sum() \\\n    .sort_values() \\\n    .plot(kind='barh',\n          figsize=(15, 8),\n          title='Frequency of Event Area')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 8))\nfor i, d in MEvents.loc[~MEvents['Area_Name'].isna()].groupby('Area_Name'):\n    d.plot(x='X', y='Y', style='.', label=i, ax=ax, title='Visualizing Event Areas')\n    ax.legend()\nplt.legend(bbox_to_anchor=(1.04,1), loc=\"upper left\")\nax.set_xticks([])\nax.set_yticks([])\nax.set_xlabel('')\nax.set_xlim(0, 100)\nax.set_ylim(0, 100)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>2.6. PlayerIDs</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"MPlayers = pd.read_csv(PATH_MEN + 'MPlayers.csv', error_bad_lines=False)\n\nMPlayers.head()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"del MEvents\ndel MNCAATourneySeeds\ndel MPlayers\ndel MRegularSeasonCompactResults\ndel MSeasons\ndel MTeams\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3><center>3. Preparing Training & Validation Data</center></h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_result = pd.read_csv(PATH_MEN + 'MDataFiles_Stage1/MNCAATourneyCompactResults.csv')\ntourney_result = tourney_result[tourney_result['Season'] < 2015]\n\ntourney_seed = pd.read_csv(PATH_MEN + 'MDataFiles_Stage1/MNCAATourneySeeds.csv')\ntourney_seed = tourney_seed[tourney_seed['Season'] < 2015]\n\ntourney_result = tourney_result.drop(['DayNum', 'WScore', 'LScore', 'WLoc', 'NumOT'], axis=1)\ntourney_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)\n\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)\n\ntourney_result = tourney_result.drop('TeamID', axis=1)\n\n\ntourney_result['WSeed'] = tourney_result['WSeed'].apply(lambda x: int(x[1:3]))\ntourney_result['LSeed'] = tourney_result['LSeed'].apply(lambda x: int(x[1:3]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"season_result = pd.read_csv(PATH_MEN + 'MDataFiles_Stage1/MRegularSeasonCompactResults.csv')\nseason_result = season_result[season_result['Season'] < 2015]\n\nseason_win_result = season_result[['Season', 'WTeamID', 'WScore']]\nseason_lose_result = season_result[['Season', 'LTeamID', 'LScore']]\n\nseason_win_result.rename(columns={'WTeamID':'TeamID', 'WScore':'Score'}, inplace=True)\nseason_lose_result.rename(columns={'LTeamID':'TeamID', 'LScore':'Score'}, inplace=True)\n\nseason_result = pd.concat((season_win_result, season_lose_result)).reset_index(drop=True)\n\nseason_score = season_result.groupby(['Season', 'TeamID'])['Score'].sum().reset_index()\n\n\n\ntourney_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)\n\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)\n\n\n\ntourney_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)\n\ntourney_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']","execution_count":null,"outputs":[]},{"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":{},"cell_type":"markdown","source":"Training Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_win_result['result'] = 1\ntourney_lose_result['result'] = 0\ntrain_df = pd.concat((tourney_win_result, tourney_lose_result)).reset_index(drop=True)\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['result'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"season_result.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_result.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Testing Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.read_csv(PATH_MEN+'MSampleSubmissionStage1_2020.csv')\nsub = test_df.copy()\n\ntest_df.head()","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]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tourney_seed = pd.read_csv(PATH_MEN + 'MDataFiles_Stage1/MNCAATourneySeeds.csv')\ntourney_seed = tourney_seed[tourney_seed['Season'] > 2014]","execution_count":null,"outputs":[]},{"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')\nseason_result = season_result[season_result['Season'] > 2014]\nseason_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_score = season_result.groupby(['Season', 'TeamID'])['Score'].sum().reset_index()","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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['Seed1'] = test_df['Seed1'].map(lambda x: int(x[1:3]))\ntest_df['Seed2'] = test_df['Seed2'].map(lambda x: int(x[1:3]))\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.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train_df.drop('result', axis=1)\ny = train_df.result","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3><center>4. Model Test & Baseline result</center></h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"def evaluate_model(X, y, model):\n    cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)\n    \n    scores = cross_val_score(model, X, y, scoring='f1', cv=cv, n_jobs=-1)\n    return scores","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = DummyClassifier(strategy='uniform')\n\nscores = evaluate_model(X, y, model)\n\nprint('Mean Accuracy: %.3f (%.3f)' % (np.mean(scores), np.std(scores)))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3><center>5. Evaluate Machine Learning Algorithms</center></h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_models():\n    models, names = list(), list()\n    # LR \n    models.append(LogisticRegression(solver='lbfgs')) \n    names.append('LR')\n    # LDA\n    models.append(LinearDiscriminantAnalysis()) \n    names.append('LDA')\n    # NB\n    models.append(GaussianNB())\n    names.append('NB')\n    # SVM\n    models.append(SVC(gamma='scale'))\n    names.append('SVM')\n    return models, names","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"models, names = get_models()\n\nresults = list()\n\n\nfor i in range(len(models)):\n    \n    pipeline = Pipeline(steps=[('scale',MinMaxScaler()),('m',models[i])])\n    \n    scores = evaluate_model(X, y, pipeline)\n    \n    results.append(scores)\n\n    print('>%s %.3f (%.3f)' % (names[i], np.mean(scores), np.std(scores))) ","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10,5))\n_ = plt.boxplot(results, labels=names, showmeans=True) \n_ = plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# LGB\nlgb_num_leaves_max = 255\nlgb_in_leaf = 50\nlgb_lr = 0.0001\nlgb_bagging = 7\n\n# XGB\nxgb_max_depth = 20\nxgb_min_child_weight = 75\nxgb_lr = 0.0005\nxgb_num_boost_round_max = 4000\n# without early_stopping_rounds\n\n# Set weight of models\nw_lgb = 0.6\nw_xgb = 0.3\nw_logreg = 1 - w_lgb - w_xgb","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>6. LGB</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"params_lgb = {'num_leaves': lgb_num_leaves_max,\n              'min_data_in_leaf': lgb_in_leaf,\n              'objective': 'binary',\n              'max_depth': -1,\n              'learning_rate': lgb_lr,\n              \"boosting_type\": \"gbdt\",\n              \"bagging_seed\": lgb_bagging,\n              \"metric\": 'logloss',\n              \"verbosity\": -1,\n              'random_state': 42,\n             }","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"NFOLDS = 10\nfolds = KFold(n_splits=NFOLDS)\n#folds = StratifiedKFold(n_splits=10, shuffle=True, random_state=1)\n\ncolumns = X.columns\nsplits = folds.split(X, y)\ny_preds_lgb = np.zeros(test_df.shape[0])\ny_train_lgb = np.zeros(X.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_lgb, 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_train_lgb += clf.predict(X) / NFOLDS\n    y_preds_lgb += clf.predict(test_df) / NFOLDS\n    \n    del X_train, X_valid, y_train, y_valid\n    gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"def plot_cm(y_true, y_pred, title, figsize=(7,6)):\n    y_pred = y_pred.round().astype(int)\n    cm = confusion_matrix(y_true, y_pred, labels=np.unique(y_true))\n    cm_sum = np.sum(cm, axis=1, keepdims=True)\n    cm_perc = cm / cm_sum.astype(float) * 100\n    annot = np.empty_like(cm).astype(str)\n    nrows, ncols = cm.shape\n    for i in range(nrows):\n        for j in range(ncols):\n            c = cm[i, j]\n            p = cm_perc[i, j]\n            if i == j:\n                s = cm_sum[i]\n                annot[i, j] = '%.1f%%\\n%d/%d' % (p, c, s)\n            elif c == 0:\n                annot[i, j] = ''\n            else:\n                annot[i, j] = '%.1f%%\\n%d' % (p, c)\n    cm = pd.DataFrame(cm, index=np.unique(y_true), columns=np.unique(y_true))\n    cm.index.name = 'Actual'\n    cm.columns.name = 'Predicted'\n    fig, ax = plt.subplots(figsize=figsize)\n    plt.title(title)\n    sns.heatmap(cm, cmap= \"YlGnBu\", annot=annot, fmt='', ax=ax)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_cm(y, y_train_lgb, 'Confusion matrix for LGB model')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>7. XGB</h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"params_xgb = {'max_depth': xgb_max_depth,\n              'objective': 'binary:logistic',\n              'min_child_weight': xgb_min_child_weight,\n              'learning_rate': xgb_lr,\n              'eta'      : 0.3,\n              'subsample': 0.8,\n              'lambda '  : 4,\n              'eval_metric': 'logloss',\n              'colsample_bytree ': 0.9,\n              'colsample_bylevel': 1\n              }","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"NFOLDS = 10\nfolds = KFold(n_splits=NFOLDS)\n\ncolumns = X.columns\nsplits = folds.split(X, y)\n\ny_preds_xgb = np.zeros(test_df.shape[0])\ny_train_xgb = np.zeros(X.shape[0])\ny_oof_xgb = np.zeros(X.shape[0])\n\ntrain_df_set = xgb.DMatrix(X)\ntest_set = xgb.DMatrix(test_df)\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    train_set = xgb.DMatrix(X_train, y_train)\n    val_set = xgb.DMatrix(X_valid, y_valid)\n    \n    clf = xgb.train(params_xgb, train_set, num_boost_round=xgb_num_boost_round_max, evals=[(train_set, 'train'), (val_set, 'val')], verbose_eval=100)\n    \n    y_train_xgb += clf.predict(train_df_set) / NFOLDS\n    y_preds_xgb += clf.predict(test_set) / NFOLDS\n    \n    del X_train, X_valid, y_train, y_valid\n    gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_cm(y, y_train_xgb, 'Confusion matrix for XGB model')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3>8. Log Reg </h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"scale = MinMaxScaler()\nX_scaled = scale.fit_transform(X)\nX_test_scaled = scale.transform(test_df)\n\nmodel = LogisticRegression(solver='liblinear')\n\nmodel.fit(X_scaled, y)\n\ny_logreg_train = model.predict(X_scaled)\ny_logreg_pred = model.predict(X_test_scaled)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_cm(y, y_logreg_train, 'Confusion matrix for LogReg model')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h3><center>9. Merging Solutions</center></h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train_preds = 0.8*y_train_lgb + 0.1*y_train_xgb + 0.1*y_logreg_train\n\nplot_cm(y, y_train_preds, 'Confusion matrix for Merging solution')\n","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}