DataFrame.groupby()聚合,分组级运算

import pandas as pd
df = pd.Data ({'key1':list('ababa'),
         'key2': ['one','two','one','two','one'],
         'data1': np.random.randn(5),
         'data2': np.random.randn(5)})
print(df)

   data1   data2 key1 key2
0 -1.313101 -0.453361  a one
1 0.791463 1.096693  b two
2 0.462611 1.150597  a one
3 -0.216121 1.381333  b two
4 0.077367 -0.282876  a one

#将df['data1']按照分组键为df['key1']进行分组
grouped=df['data1'].groupby(df['key1'])
print(grouped.mean())

key1
a  -0.257707
b  0.287671
Name: data1, dtype: float64

states=np.array(['Ohio','California','California','Ohio','Ohio'])
years=np.array([2005,2005,2006,2005,2006])
#states第一层索引，years第二层分层索引
print(df['data1'].groupby([states,years]).mean())
California 2005  0.791463
      2006  0.462611
Ohio    2005  -0.764611
      2006  0.077367
Name: data1, dtype: float64

#df根据‘key1'分组，然后对df剩余数值型的数据运算
df.groupby('key1').mean()
     data1   data2
key1          
a  -0.257707 0.138120
b   0.287671 1.239013
#可以看出没有key2列，因为df[‘key2']不是数值数据，所以被从结果中移除。默认情况下，所有数值列都会被聚合，虽然有时可能被过滤为一个子集。

#name就是groupby中的key1的值，group就是要输出的内容
for name, group in df.groupby('key1'):
    print (name,group)

a    data1   data2 key1 key2
0 -1.313101 -0.453361  a one
2 0.462611 1.150597  a one
4 0.077367 -0.282876  a one
b    data1   data2 key1 key2
1 0.791463 1.096693  b two
3 -0.216121 1.381333  b two

#转化为字典
piece=dict(list(df.groupby('key1')))

{'a':    data1   data2 key1 key2
 0 -1.313101 -0.453361  a one
 2 0.462611 1.150597  a one
 4 0.077367 -0.282876  a one, 'b':    data1   data2 key1 key2
 1 0.791463 1.096693  b two
 3 -0.216121 1.381333  b two}
#对字典取值
value = piece['a']

grouped=df.groupby(df.dtypes, axis=1)
value = dict(list(grouped))
print(value)

{dtype('float64'):    data1   data2
0 -1.313101 -0.453361
1 0.791463 1.096693
2 0.462611 1.150597
3 -0.216121 1.381333
4 0.077367 -0.282876, dtype('O'):  key1 key2
0  a one
1  b two
2  a one
3  b two
4  a one}

#对df进行'key1'，'key2'的两次分组，然后取data2的数据，对两次细分的分组数据取均值
value = df.groupby(['key1','key2'])[['data2']].mean()

       data2
key1 key2     
a  one  0.138120
b  two  1.239013
----------------------------------
df
Out[1]: 
   data1   data2 key1 key2
0 -1.313101 -0.453361  a one
1 0.791463 1.096693  b two
2 0.462611 1.150597  a one
3 -0.216121 1.381333  b two
4 0.077367 -0.282876  a one
----------------------------------

df['key2'].iloc[-1] ='two'

value = df.groupby(['key1','key2'])[['data2']].mean()

value
Out[2]: 
       data2
key1 key2     
a  one  0.348618
   two -0.282876
b  two  1.239013