{"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":"from sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegressionCV\nfrom sklearn.metrics import roc_auc_score\nimport matplotlib.pyplot as plt\nfrom sklearn.preprocessing import OneHotEncoder\nimport pandas as pd\nimport numpy as np","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/train.csv')\ntest = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/test.csv')\n\n\nlabels = train.pop('target') \nlabels = labels.values\n\ntrain_id = train.pop(\"id\")\ntest_id = test.pop(\"id\")\n\ntrain.shape, test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = pd.concat([train, test])\ndata[\"ord_5a\"] = data[\"ord_5\"].str[0]\ndata[\"ord_5b\"] = data[\"ord_5\"].str[1]\ncolumns = [i for i in data.columns]\n\ndummies = pd.get_dummies(data,\n                         columns=columns,\n                         drop_first=True,\n                         sparse=True)\n\ndel data","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = dummies.iloc[:train.shape[0], :]\ntest = dummies.iloc[train.shape[0]:, :]\n\ndel dummies\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = train.sparse.to_coo().tocsr()\ntest = test.sparse.to_coo().tocsr()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr_cv = LogisticRegressionCV(Cs=7,\n                        solver=\"lbfgs\",\n                        tol=0.0001,\n                        max_iter=30000,\n                        cv=5)\n\nlr_cv.fit(train, labels)\n\nlr_cv_pred = lr_cv.predict_proba(train)[:, 1]\nscore = roc_auc_score(labels, lr_cv_pred)\n\nprint(\"score: \", score)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_pred = lr_cv.predict_proba(test)[:, 1]\nsubmiss = pd.DataFrame({\"id\": test_id, \"target\": test_pred})\nsubmiss.to_csv('Submission(LogisticRegression).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":4}