{"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\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 read-only \"../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%matplotlib inline\nfrom matplotlib import pyplot as plt\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"X_train = pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/train.csv\")\nX_test = pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = X_train['target']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":" print(X_train['target'].value_counts())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.drop(['id','target'], axis=1,inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_id = X_test['id']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.drop(['id'], axis=1,inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = pd.concat([X_train, X_test], axis=0, sort=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.dtypes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.isna().sum().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.isna().sum (axis = 0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for column in X.columns:\n    X[column].fillna(X[column].mode()[0], inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.isna().sum().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for col in ['bin_3', 'bin_4', 'nom_0', 'nom_1', 'nom_2', 'nom_3', 'nom_4', 'nom_5', 'nom_6', 'nom_7', 'nom_8', 'nom_9', \n            'ord_1', 'ord_2', 'ord_3', 'ord_4', 'ord_5']:\n    print(col)\n    print(X[col].value_counts())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nle = LabelEncoder()\nordinal_cols = ['bin_3','bin_4','ord_1','ord_2','ord_3','ord_4','ord_5','nom_5','nom_6','nom_7','nom_8','nom_9']\nfor col in ordinal_cols:\n    X[col] = le.fit_transform(X[col])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = pd.concat([X, pd.get_dummies(X['nom_0'], prefix='nom_0')], axis=1)\nX = pd.concat([X, pd.get_dummies(X['nom_1'], prefix='nom_1')], axis=1)\nX = pd.concat([X, pd.get_dummies(X['nom_2'], prefix='nom_2')], axis=1)\nX = pd.concat([X, pd.get_dummies(X['nom_3'], prefix='nom_3')], axis=1)\nX = pd.concat([X, pd.get_dummies(X['nom_4'], prefix='nom_4')], axis=1)\nX.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.drop(['nom_0','nom_1','nom_2','nom_3','nom_4'], axis=1,inplace=True)\nX.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train,X_test = X[:600000],X[600000:]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\nclf = LogisticRegression(solver='liblinear')\nclf.fit(X_train,y);\nprint('Score on train dataset:')\nclf.score(X_train,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import confusion_matrix\nconfusion_matrix (y,clf.predict(X_train))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import roc_curve\ny_pred = clf.predict_proba(X_train)[:,1]\nfpr, tpr, threshold = roc_curve (y, y_pred)\nplt.plot(fpr, tpr)\nplt.title('ROC curve')\nplt.xlabel('False Positive Rate')\nplt.ylabel('True Positive Rate')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test = clf.predict_proba(X_test)[:,1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"output = pd.DataFrame({\"id\": test_id, \"target\": y_test})\noutput.to_csv(\"output.csv\", index=False)\nprint(\"Your submission was successfully saved!\")\noutput.head(30)","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}