{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"4b22fab2-0db9-8aa2-e8a7-cef1786465f8"},"outputs":[],"source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n\ndef explore_data_set(data_set_name):\n    # need to display general info about this data set\n    # to make this faster we can read first row with all columns, all rows with one column\n    print(\"============= Exploring %s Data Set ==============\" % data_set_name)\n    cols = pd.read_csv(\"../input/%s\" % data_set_name, nrows=1)\n    if \"Response\" in cols.columns.tolist():\n        rows = pd.read_csv(data_set_name, usecols=[\"Response\"])\n        print(\"Data Size: Rows: %s - Cols: %s\" % (rows.shape[0], cols.shape[1]))\n        failure_rate = rows[rows.Response == 1].size / float(rows[rows.Response == 0].size)\n        print(\"Failure Rate: %s\" % failure_rate)\n    else:\n        rows = pandas.read_csv(data_set_name, usecols=[\"Id\"])\n        print(\"No Response column in this data set!\")\n        print(\"Data Size: Rows: %s - Cols: %s\" % (rows.shape[0], cols.shape[1]))\n\n\nexplore_data_set(\"train_numeric.csv\")\nexplore_data_set(\"train_date.csv\")\nexplore_data_set(\"train_categorical.csv\")\nexplore_data_set(\"test_numeric.csv\")\nexplore_data_set(\"test_date.csv\")\nexplore_data_set(\"test_categorical.csv\")"}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.5.2"}},"nbformat":4,"nbformat_minor":0}