Patents_groupby机制

1.使用列名分组

df = pd.DataFrame({'key1':['a', 'a', 'b', 'b', 'a'],
     'key2':['one', 'two', 'one', 'two', 'one'],
     'data1':np.random.randn(5),
     'data2':np.random.randn(5)})
group_1=df.groupby(['key1','key2'])
print(group_1.sum())
'''
#由于key2中并不是数值，自动过滤了
              data1     data2
key1 key2                    
a    one   0.120658  1.776958
     two   0.708023 -0.334745
b    one   0.336527 -0.118483
     two  -1.195948 -1.084212
'''
#只需要统计一列,[['data1']]是为了返回DataDataFrame格式
group_2=df.groupby('key1')[['data1']]
print(group_2.sum())
'''
         data1
key1          
a    -3.510479
b     0.327874
'''

#禁用分组键作为索引
group_1=df.groupby('key1',as_index=False)
print(group_1.mean())
'''
  key1     data1     data2
0    a  0.215868  0.887776
1    b -0.013590 -2.059145
'''

2.使用字典分组

people=pd.DataFrame(np.random.randn(25).reshape(5,5),columns=['a','b','c','d','e']
                    ,index=['Joe','Steve','Wes','Jim','Travis'])
#添加几个NA值
people.loc[2:3,['b','c']]=np.nan
mapping={'a':'red','b':'red','c':'blue','d':'blue','e':'red','f':'orange'}
by_column=people.groupby(mapping,axis=1)
print(by_column.sum())

'''
            blue       red
Joe    -0.504558  2.111179
Steve  -1.658838  0.130956
Wes     1.004845  1.742293
Jim    -2.551048 -1.502194
Travis  1.854355  0.171491
'''

3.使用Series分组

people=pd.DataFrame(np.random.randn(25).reshape(5,5),columns=['a','b','c','d','e']
                    ,index=['Joe','Steve','Wes','Jim','Travis'])
map_series=pd.Series(list('abaab'),index=['a','b','c','d','e'])
by_column=people.groupby(map_series,axis=1)
print(by_column.count())

'''
        a  b
Joe     3  2
Steve   3  2
Wes     3  2
Jim     3  2
Travis  3  2
'''

4.使用函数分组

#不得不说pandas强大....
people=pd.DataFrame(np.random.randn(25).reshape(5,5),columns=['a','b','c','d','e']
                    ,index=['Joe','Steve','Wes','Jim','Travis'])
map_series=pd.Series(list('abaab'),index=['a','b','c','d','e'])
print(by_column.min())
'''
          a         b         c         d         e
J -1.005321 -0.718634  0.949499  0.121992  0.281395
S -0.331975  0.387535 -0.024841 -1.244947  0.228626
T -1.627892 -0.190549  2.365620 -1.013034 -0.907791
W  0.685558  0.569147 -0.485205  1.094103 -2.196524
'''

5.层级分组

'''
level：层次索引的层级。从0开始分别对应第一层等索引，默认为-1，则代表最里面一层索引。
'''
people=pd.DataFrame(np.random.randn(25).reshape(5,5),columns=[['Joe','Steve','Wes','Jim','Travis'],['boy','boy','girl','girl','boy']]
                    ,index=['Joe','Steve','Wes','Jim','Travis'])
people.columns.names=['name','sex']
print(people.groupby(level='sex',axis=1).min())
'''
sex          boy      girl
Joe     0.720471  0.097515
Steve  -0.811630  0.263458
Wes    -1.879113 -0.775714
Jim    -1.631855 -0.945603
Travis -1.221499 -1.234002
'''

6.遍历

'''
groupby支持迭代,生成的是元组序列
'''
df = pd.DataFrame({'key1':['a', 'a', 'b', 'b', 'a'],
     'key2':['one', 'two', 'one', 'two', 'one'],
     'data1':np.random.randn(5),
     'data2':np.random.randn(5)})
for i,n in df.groupby('key1'):
    print(i)
    print(n)
'''
a
  key1 key2     data1     data2
0    a  one -0.462239  2.618347
1    a  two -0.546438  1.615818
4    a  one  1.117225 -1.525680
b
  key1 key2     data1     data2
2    b  one  1.565555  0.813002
3    b  two -0.803730  1.082145
'''


pieces=dict(list(df.groupby('key1')))
print(pieces['a'])
'''
  key1 key2     data1     data2
0    a  one -0.579428 -0.870761
1    a  two  0.378817 -0.913764
4    a  one  0.546169  0.290938
'''

7.聚合

7.1优化的groupby方法

count：分组中非nan的个数
sum：非nan的累和
mean：非nan的均值
std，var：标准差与方差
min，max：非nan的最小值与最大值
prod：非nan的乘积
first，last：非nan的第一个值和最后一个值

7.2逐列与多函数应用

def PeakToPeak(arr):
    return arr.max() - arr.min()
#数据集：https://github.com/kojoidrissa/pydata-book
tips = pd.read_csv('tips.csv')
tips['tip_pct'] = tips['tip'] / tips['total_bill']
grouped = tips.groupby(['sex','smoker'])
grouped_pct = grouped['tip_pct'].agg(['mean','std',PeakToPeak])
print(grouped_pct)
'''
                   mean       std  PeakToPeak
sex    smoker                                
Female No      0.156921  0.036421    0.195876
       Yes     0.182150  0.071595    0.360233
Male   No      0.160669  0.041849    0.220186
       Yes     0.152771  0.090588    0.674707
'''


'''
计算多个列
'''
grouped_pct = grouped['tip_pct','total_bill'].agg(['mean','std','count'])
print(grouped_pct)
'''
                tip_pct                 total_bill                
                   mean       std count       mean       std count
sex    smoker                                                     
Female No      0.156921  0.036421    54  18.105185  7.286455    54
       Yes     0.182150  0.071595    33  17.977879  9.189751    33
Male   No      0.160669  0.041849    97  19.791237  8.726566    97
       Yes     0.152771  0.090588    60  22.284500  9.911845    60
'''