{"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 os\nimport json\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom pandas.io.json import json_normalize\n\n# print(os.listdir(\"../input\"))\n# print(os.listdir(\"../input/ga-customer-revenue-prediction\"))\n\ndef load_df(csv_path = '../input/ga-customer-revenue-prediction/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\n\n# Any results you write to the current directory are saved as output.\n\ndf_train = load_df()\ndf_train.head()\ntrain_data = df_train.copy()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df_train.describe()\ndf_train.info()\n#redundant columns\nconst_cols = []\nfor col in df_train.columns:\n     if df_train[col].nunique(dropna = False) == 1:\n            const_cols.append(col)\n\nprint(const_cols)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# type conversion for revenue column\ndf_train['totals.transactionRevenue'] = df_train['totals.transactionRevenue'].astype('float')\nsummary2 = df_train.groupby('fullVisitorId')['totals.transactionRevenue'].sum().reset_index()\nprint(summary2.head())\nplt.scatter(x=summary2.index, y=np.sort(np.log1p(summary2['totals.transactionRevenue'])))\nplt.xlabel('index', fontsize=12)\nplt.ylabel('TransactionRevenue', fontsize=12)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.pivot_table(df_train, index = , col = ['channelGrouping',], values = ['visitNumber',], aggfunc = np.sum)\nsummary3 = df_train.groupby('visitNumber')['totals.transactionRevenue'].sum().reset_index()\nprint(summary3.index)\nplt.scatter(x=summary3.index, y=np.log1p(summary3['totals.transactionRevenue']))\nplt.xlabel('visitnumber', fontsize=12)\nplt.ylabel('TransactionRevenue', fontsize=12)\nplt.show()","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":1}