{"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)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","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":"from sklearn.metrics import roc_auc_score\ncat_feat_to_encode = train.columns.tolist();  smoothing=0.20\nimport category_encoders as ce\noof = pd.DataFrame([])\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import StratifiedKFold","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for tr_idx, oof_idx in StratifiedKFold(n_splits=5, random_state=2600, 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.append(ce_target_encoder.transform(train.iloc[oof_idx, :]), ignore_index=False)\nce_target_encoder = ce.TargetEncoder(cols = cat_feat_to_encode, smoothing=smoothing)\nce_target_encoder.fit(train, train_y)\ntrain = oof.sort_index()\ntest = ce_target_encoder.transform(test)\nglm =LogisticRegression( random_state=2, solver='lbfgs', max_iter=20600, fit_intercept=True, penalty='l2', verbose=0)\nglm.fit(train, train_y)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\npd.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}