Python Pandas分组聚合的实现方法

import numpy as np

from pandas import Series, DataFrame

 

frame = DataFrame(np.random.randn(4, 3),

         columns = list('bde'),

         index = ['Utah', 'Ohio', 'Texas', 'Oregon'])

print frame

print np.abs(frame)

print

 

f = lambda x: x.max() - x.min()

print frame.apply(f)

print frame.apply(f, axis = 1)

def f(x):

  return Series([x.min(), x.max()], index = ['min', 'max'])

print frame.apply(f)

print

 

print 'applymap和map'

_format = lambda x: '%.2f' % x

print frame.applymap(_format)

print frame['e'].map(_format) 

df = DataFrame({'key1': ['a', 'a', 'b', 'b', 'a'],

        'key2': ['one', 'two', 'one', 'two', 'one'],

        'data1': np.random.randn(5),

        'data2': np.random.randn(5)})

grouped = df.groupby(df['key1'])

print grouped.mean() 



df.groupby(lambda x:'even' if x%2==0 else 'odd').mean() #通过函数分组 

df = DataFrame({'key1': ['a', 'a', 'b', 'b', 'a'],

        'key2': ['one', 'two', 'one', 'two', 'one'],

        'data1': np.random.randn(5),

        'data2': np.random.randn(5)})

grouped = df.groupby('key1')

print grouped.agg('mean')

 

     data1   data2

key1          

a   0.749117 0.220249

b  -0.567971 -0.126922 

df = DataFrame({'key1': ['a', 'a', 'b', 'b', 'a'],

        'key2': ['one', 'two', 'one', 'two', 'one'],

        'data1': np.random.randn(5),

        'data2': np.random.randn(5)})

grouped = df.groupby('key1')

print grouped.agg(['sum','mean'])
print grouped.apply(np.sum)  #apply的在这里同样适用，只是不能传入多个,这两个函数基本是可以通用的。 

print grouped.apply(lambda x: x.describe())

 

        data1   data2

key1             

a  count 3.000000 3.000000

   mean -0.887893 -1.042878

   std  0.777515 1.551220

   min  -1.429440 -2.277311

   25%  -1.333350 -1.913495

   50%  -1.237260 -1.549679

   75%  -0.617119 -0.425661

   max  0.003021 0.698357

b  count 2.000000 2.000000

   mean -0.078983 0.106752

   std  0.723929 0.064191

   min  -0.590879 0.061362

   25%  -0.334931 0.084057

   50%  -0.078983 0.106752

   75%  0.176964 0.129447

   max  0.432912 0.152142