{"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\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split, GridSearchCV\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":{},"cell_type":"markdown","source":"1. Import files"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","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\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.drop(\"target\", axis=1)\ny= train[\"target\"]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"2. Feature engineering"},{"metadata":{"trusted":true},"cell_type":"code","source":"numeric_features = X.select_dtypes(include=['float64']).columns\nnumeric_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='median')),\n    ('scaler', StandardScaler())])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"integer_features = X.select_dtypes(include=['int64']).columns\ninteger_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='median')),\n    ('scaler', StandardScaler())])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"categorical_features = X.select_dtypes(include=['object']).columns\ncategorical_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),\n    ('onehot', OneHotEncoder(handle_unknown='ignore'))])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preprocessor = ColumnTransformer(\n    transformers=[\n        ('num', numeric_transformer, numeric_features),\n        ('int', integer_transformer, integer_features),\n        ('cat', categorical_transformer, categorical_features)])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"3. Apply Logistic Regression Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Append classifier to preprocessing pipeline.\n# Now we have a full prediction pipeline.\nclf = Pipeline(steps=[('preprocessor', preprocessor),\n                      ('classifier', LogisticRegression())])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n\nclf.fit(X_train, y_train)\nprint(\"model score: %.3f\" % clf.score(X_test, y_test))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"4. Probability of prediction"},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = clf.predict_proba(test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"5. Load to csv"},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.DataFrame({'id': test['id'], 'target':y_pred[:,1]})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv('/kaggle/working/submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"> #### Public score : 0.77752"}],"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}