{"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":"train = pd.read_csv('../input/train.csv',\n                    dtype={'is_booking':bool,'srch_destination_id':np.int32, 'hotel_cluster':np.int32},\n                    usecols=['srch_destination_id','is_booking','hotel_cluster'],)\ntest = pd.read_csv('../input/test.csv',\n                    dtype={'srch_destination_id':np.int32},\n                    usecols=['srch_destination_id'],)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"test.describe()\ntrain.describe()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"test.count()\n"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.count()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"test[0:2]"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train[0:2]"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train[-3:]"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"type(train[\"is_booking\"])"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.shape"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train[\"is_booking\"].hist()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.groupby(\"is_booking\").mean()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.groupby(\"is_booking\").count()"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":0}