{"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."},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# Load 1000th rows of train.csv\ntrain = pd.read_csv('../input/train.csv',nrows=100000)\n# Look at the head of this sample\ntrain.head()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"#Get columns from train\ncolumns = train.columns\n# Analyze features size (if categorical or not)\nfor col in columns:\n    print(col)\n    print(len(set(train[col])))"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# Correlation each feature with hotel_cluster:\nfor col in columns:\n    if (train[col].dtype)!='object':\n        print(col)\n        print(train[col].corr(train['hotel_cluster']))"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"print(list(train['hotel_cluster'])[:10])"},{"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}