{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport category_encoders as ce\nfrom sklearn.model_selection import train_test_split\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))","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)\ny_train = train['target']\nx_train = train.drop(['target', 'id'], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_id = test['id']\ntest.drop('id', axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for col in x_train.columns:\n    if x_train[col].isna().sum()>0:\n        x_train.loc[x_train[col].isna(),col] = x_train[col][-x_train[col].isna()].sample(n= x_train[col].isna().sum()).values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(x_train, y_train, test_size=0.3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"X_train.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"high_dim_cols=[]\nlow_dim_cols=[]\n\nfor col in X_train.columns:\n    if X_train[col].nunique()<20:\n        low_dim_cols.append(col)\n\nfor col in X_train.columns:\n    if X_train[col].nunique()>20:\n        high_dim_cols.append(col)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(low_dim_cols)\nprint(high_dim_cols)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ohEncoder = ce.OneHotEncoder(cols=low_dim_cols)\nX_train = ohEncoder.fit_transform(X_train)\nX_test = ohEncoder.transform(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"hashingEncoder = ce.HashingEncoder(cols=high_dim_cols)\nX_train = hashingEncoder.fit_transform(X_train)\nX_test = hashingEncoder.transform(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\nclf = LogisticRegression(random_state=0, solver='lbfgs', max_iter=2020, fit_intercept=True, penalty='none', verbose=0).fit(X_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = clf.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import accuracy_score\n\naccuracy_score(y_test, y_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = ohEncoder.transform(test)\ntest = hashingEncoder.transform(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.DataFrame({'id': test_id, 'target': clf.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}