{"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":"\ntrain = 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'],\n                    chunksize=1000000)\naggs = []\nprint('-'*38)\nfor chunk in train:\n    agg = chunk.groupby(['srch_destination_id',\n                         'hotel_cluster'])['is_booking'].agg(['sum','count'])\n    agg.reset_index(inplace=True)\n    aggs.append(agg)\n    print('.',end='')\nprint('')\naggs = pd.concat(aggs, axis=0)\naggs.head()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"d={ 'Group':[1,1,2,2],\n    'Eng':[3,6,5,7],\n    'Chem':[5,6,3,2],\n    'Phys':[4,5,2,1]\n}\n\ndf=pd.DataFrame(data=d, columns=['Group', 'Eng', 'Chem', 'Phys'])\n\nprint(df)\naggr=[]\naggr=df.groupby(['Group']).agg(['max'])\nprint(aggr)"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":0}