{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"import numpy as np \nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn\nfrom subprocess import check_output\ntrain = pd.read_csv('../input/train.csv')\n#print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n"},{"cell_type":"markdown","metadata":{},"source":"Show columns"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"print(train.columns)"},{"cell_type":"markdown","metadata":{},"source":"Try to estimate the location of each place by the average of the check-ins"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"print(\"Number of check-ins: \" + str(train[\"row_id\"].count()))\nplaceIds = train[\"place_id\"].as_matrix()\nunique = np.unique(placeIds)\nprint(\"Number of distinct places: \" + str(unique.shape[0]))\npositions = np.zeros([unique.shape[0], 2])"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"for p in placeIds:\n    idx = np.where(placeIds == p)\n    print(idx[0])\n    break"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":0}