{"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":"df_train = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/train.csv', index_col='id')\ndf_test = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/test.csv', index_col='id')\nprint(df_train.shape, df_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train_AF = df_train[['nom_0', 'month', 'nom_5', 'day', 'ord_4', 'ord_2']]\ndf_test_AF = df_test[['nom_0', 'month', 'nom_5', 'day', 'ord_4', 'ord_2']]\ndf_train_AF.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"my_AD=pd.concat([df_train_AF,df_test_AF], sort=False)\nmy_AD.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def description(df):\n    print(f\"Dataset Shape: {df.shape}\")\n    summary = pd.DataFrame(df.dtypes,columns=['dtypes'])\n    summary = summary.reset_index()\n    summary['Name'] = summary['index']\n    summary = summary[['Name','dtypes']]\n    summary['Missing'] = df.isnull().sum().values    \n    summary['Uniques'] = df.nunique().values\n    summary['First Value'] = df.iloc[0].values\n    summary['Second Value'] = df.iloc[1].values\n    summary['Third Value'] = df.iloc[2].values\n    return summary\ndescription(my_AD)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"my_AD_CE=my_AD.copy()\ncolumns=['day','month']\nfor col in columns:\n    my_AD_CE[col+'_sin']=np.sin((2*np.pi*my_AD_CE[col])/max(my_AD_CE[col]))\n    my_AD_CE[col+'_cos']=np.cos((2*np.pi*my_AD_CE[col])/max(my_AD_CE[col]))\nmy_AD_CE=my_AD_CE.drop(columns,axis=1)\nmy_AD=my_AD_CE\nmy_AD.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"my_AD.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import missingno as msno","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"msno.matrix(my_AD)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"msno.matrix(my_AD, sort='ascending')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"my_AD=pd.get_dummies(my_AD, prefix=['Color'], columns=['nom_0'])\nmy_AD","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"map_ord2 = {'Freezing':1, \n            'Cold':2, \n            'Warm':3, \n            'Hot':4, \n            'Boiling Hot':5, \n            'Lava Hot':6}\nmy_AD.ord_2 = my_AD.ord_2.map(map_ord2)\nmy_AD","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import category_encoders as ce\nencoder = ce.BinaryEncoder(cols=['ord_4'])\ndf_bin = encoder.fit_transform(my_AD['ord_4'])\nmy_AD = pd.concat([my_AD,df_bin], axis=1)\nmy_AD","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import category_encoders as ce\nencoder = ce.BinaryEncoder(cols=['nom_5'])\ndf_bin = encoder.fit_transform(my_AD['nom_5'])\nmy_AD = pd.concat([my_AD,df_bin], axis=1)\nmy_AD","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}