{"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":{"trusted":true},"cell_type":"code","source":"import json\nimport os\nfrom pandas.io.json import json_normalize","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true,"collapsed":true},"cell_type":"code","source":"def read_data(path,nrows):\n    df = pd.read_csv(path,\n                converters = {column: json.loads for column in [\"device\",\"geoNetwork\",\"totals\",\"trafficSource\"]},\n                 dtype = {\"fullVisitorId\" : \"str\"},\n                 nrows=nrows)\n    for column in [\"device\",\"geoNetwork\",\"totals\",\"trafficSource\"]:\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    return df\n\ndf_small = pd.DataFrame(read_data(\"/kaggle/input/ga-customer-revenue-prediction/train.csv\",200000))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Vamos a quitar las columnas con \"not available in demo dataset\".\n\nTambién quitamos \"socialEngagementType\" y \"totals.visits\" por tener un único valor"},{"metadata":{"trusted":true},"cell_type":"code","source":"for column in df_small.columns:\n    if len(df_small[column].unique()) == 1:\n        df_small.drop(column,axis=1,inplace=True)\ndf_small.drop([\"device.isMobile\",\"geoNetwork.continent\",'geoNetwork.metro','visitId',\n               'sessionId','trafficSource.referralPath','trafficSource.adwordsClickInfo.gclId',\n               'trafficSource.campaignCode'],axis=1,inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mapeo=dict()\ncontinents = list()\nfor i,name in enumerate(df_small[\"geoNetwork.subContinent\"].unique()):\n    continents.append(pd.DataFrame(df_small.loc[df_small[\"geoNetwork.subContinent\"] == name, : ]))\n    mapeo[i] = name","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_small['trafficSource.adwordsClickInfo.slot'].value_counts()","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}