{"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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport json\nfrom pandas.io.json import json_normalize","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"64d20a0cf973a55a5ca0ed8b60aee5e662ef5c82"},"cell_type":"code","source":"JSON_COLUMNS = ['device', 'geoNetwork', 'totals', 'trafficSource']\ndef load_df(csv_path='../input/train.csv'):\n\n    df = pd.read_csv(csv_path, \n                     converters={column: json.loads for column in JSON_COLUMNS}, \n                     dtype={'fullVisitorId': 'str'})\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\n    return df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1607b716e8b817c87ca6332e02a5d8e0e6292226"},"cell_type":"code","source":"train = load_df(\"../input/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"cf18a287841ac4b6d992618beaf599a886e555a7"},"cell_type":"code","source":"print(train.columns)","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}