{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"from sklearn.model_selection import KFold\nfrom sklearn.metrics import accuracy_score, roc_auc_score\nfrom sklearn.linear_model import Ridge\n\nimport pandas as pd\nimport numpy as np\n\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\nimport gc\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"In this kernels we'll use Ridge regression as our model. Ridge regression is actually a very good choice for **classification** problem when the evaluation metric is AUC - it often performs nearly as well, or even better, than Logistic Reression. "},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/multi-cat-encodings/X_train_te.csv')\ntest = pd.read_csv('../input/multi-cat-encodings/X_test_te.csv')\nsample_submission = pd.read_csv('../input/cat-in-the-dat-ii/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train['target'].values\ntrain = train.drop(['target','fold_column'], axis=1)\nX = train.values.copy()\ntest_np = test.values.copy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_oof = np.zeros((train.shape[0],))\ntest_preds = 0\ntrain_oof.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nn_splits = 5\nkf = KFold(n_splits=n_splits, random_state=17, shuffle=True)\nscores = []\n\nfor jj, (train_index, val_index) in enumerate(kf.split(X)):\n    print(\"Fitting fold\", jj+1)\n    X_train, X_test = X[train_index], X[val_index]\n    y_train, y_test = y[train_index], y[val_index]\n\n    #model = LinearRegression(use_gpu=True, regularizer = 1.0/5, dual=False)\n    model = Ridge(alpha = 5)\n    #model = LinearRegression(use_gpu=True, dual=False)\n    model.fit(X_train, y_train)\n    y_pred = model.predict(X_test)\n    train_oof[val_index] = y_pred\n    score = roc_auc_score(y_test, y_pred)\n    print(\"Fold AUC:\", score)\n    scores.append(score)\n    #test_preds += model.predict(test).values/n_splits\n    test_preds += model.predict(test_np)/n_splits\n    \nprint(\"Mean AUC:\", np.mean(scores))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission['target'] = test_preds\nsample_submission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.save('test_preds', test_preds)\nnp.save('train_oof', train_oof)","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}