{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"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\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output.\n\ndf = pd.read_csv('../input/train.csv')\n"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# Get range, std dev, range of data\nfor col in df[df>0]:\n     print('col:', col, df[col].describe()[['mean','std','min','max']])"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"#Add place_id's to a dictionary, and figure out which is the most popular place.\nplaces = dict()\n\nfor col in df[df>0]:\n    place_id = col['place_id']\n    if place_id in places:\n        places[place_id] += 1\n    else:\n        places[place_id] = 1\n        \nprint(len(places))\n        \n    \n    "},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":""}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":0}