[pandas] groupby mulicolumns

multi Column을 활용하여 Groupby하기

Github

'''
dataframe을 이용하여 group by 진행할때 multicalumn을 이용하는 방법

'''
def makeGroup_s002()->None:

    from numpy import ndarray
    import numpy as np

    from pandas import DataFrame
    import pandas as pd

    ## Data 준비
    datas = pd.DataFrame({'key1':['a', 'a', 'b', 'b', 'a'],
                          'key2':['one', 'two', 'one', 'two', 'one'],
                          'data1': np.random.rand(5),
                          'data2': np.random.rand(5)})

    print(datas)


    grouped:DataFrameGroupBy   = datas.groupby(['key1', 'key2'])

    print('-'*100)

    for key, group in grouped:
        print('group key: {0}'.format(key))
        print(group)
        print('-'*100)

 

group key: ('a', 'one')
  key1 key2     data1     data2
0    a  one  0.342689  0.819064
4    a  one  0.161171  0.175721
----------------------------------------------------------------------------------------------------
group key: ('a', 'two')
  key1 key2     data1     data2
1    a  two  0.976412  0.727764
----------------------------------------------------------------------------------------------------
group key: ('b', 'one')
  key1 key2     data1     data2
2    b  one  0.497101  0.287573
----------------------------------------------------------------------------------------------------
group key: ('b', 'two')
  key1 key2     data1     data2
3    b  two  0.758967  0.617483
----------------------------------------------------------------------------------------------------

Process finished with exit code 0