{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport json\nfrom pandas.io.json import json_normalize\n\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","collapsed":true,"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":false},"cell_type":"markdown","source":"'device', 'geoNetwork', 'totals' and 'trafficSource' are in JSON format in training and test datasets. We'll use the function from Julian's great [kernel](https://www.kaggle.com/julian3833/1-quick-start-read-csv-and-flatten-json-fields/notebook) to flatten the format."},{"metadata":{"trusted":true,"_uuid":"60c50081b0a769efcc4ac406b1f33384917a4860"},"cell_type":"code","source":"def load_df(csv_path='../input/train.csv', nrows=None):\n    JSON_COLUMNS = ['device', 'geoNetwork', 'totals', 'trafficSource']\n    \n    df = pd.read_csv(csv_path, \n                     converters={column: json.loads for column in JSON_COLUMNS}, \n                     dtype={'fullVisitorId': 'str'}, # Important!!\n                     nrows=nrows)\n    \n    for column in JSON_COLUMNS:\n        column_as_df = json_normalize(df[column])\n        column_as_df.columns = [f\"{column}.{subcolumn}\" for subcolumn in column_as_df.columns]\n        df = df.drop(column, axis=1).merge(column_as_df, right_index=True, left_index=True)\n    print(f\"Loaded {os.path.basename(csv_path)}. Shape: {df.shape}\")\n    return df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"04b99cbbf886973f435eb5f4e66f36e15808ea94"},"cell_type":"code","source":"%%time\ndf_train = load_df()\ndf_test = load_df(\"../input/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"1451fcdf0d4238a7691c56114794f3eeec7e94f3"},"cell_type":"markdown","source":"19 columns have constant values. Removing them from the dataset."},{"metadata":{"trusted":true,"_uuid":"d5439c520d59d8f213105ad0e674740388b06cfa"},"cell_type":"code","source":"constant_columns = [col for col in df_train.columns if df_train[col].nunique(dropna=False)==1]\n\ndf_train.drop(columns=constant_columns,inplace=True)\ndf_test.drop(columns=constant_columns,inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2c23a622e24583af77d6f1b9b81494ecf30d86c8"},"cell_type":"code","source":"%%time\ndf_train.to_csv(\"df_train.csv\", index=False)\ndf_test.to_csv(\"df_test.csv\", index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}