{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport category_encoders as ce\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import StratifiedKFold\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/cat-in-the-dat-ii/train.csv')\ntest = pd.read_csv('../input/cat-in-the-dat-ii/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.sort_index(inplace=True)\ntrain_y = train['target']; test_id = test['id']\ntrain.drop(['target', 'id'], axis=1, inplace=True); test.drop('id', axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"folds = 20\nsmoothing=100\ncat_feat_to_encode = train.columns[:].tolist()\n\noof = np.zeros(train.shape)\ntest_oof = np.zeros(test.shape)\nfrom sklearn.model_selection import StratifiedKFold\nfor tr_idx, oof_idx in StratifiedKFold(n_splits=folds, random_state= 1032, shuffle=True).split(train, train_y):\n    ce_target_encoder = ce.TargetEncoder(cols = cat_feat_to_encode, smoothing=smoothing)\n    ce_target_encoder.fit(train.iloc[tr_idx, :], train_y.iloc[tr_idx])\n    oof[oof_idx,:] = ce_target_encoder.transform(train.iloc[oof_idx, :]).values\n    test_oof[:,:] += ce_target_encoder.transform(test).values\ntest_oof /= folds\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.DataFrame(data=oof,columns=cat_feat_to_encode,index=train.index.values)\ntest = pd.DataFrame(data=test_oof,columns=cat_feat_to_encode,index=test.index.values)   \n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"glm =LogisticRegression( random_state=2, solver='lbfgs', max_iter=20600, fit_intercept=True, penalty='l2', verbose=0)\nglm.fit(train, train_y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"roc_auc_score(train_y,glm.predict_proba(train)[:,1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.DataFrame({'id': test_id, 'target': glm.predict_proba(test)[:,1]}).to_csv('submission.csv', index=False)","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":1}