pandas_groupy的使用

参考链接：link

data = {
    
    
    'Id':[0,1,2,3,4,5,6,7],
    'Name':['Alen','Bob','Cidy','Daniel','Ellen','Frankie','Gate','Hebe'],
    'Gender':['Male','Male','Female','Male','Female','Male','Male','Female'],
    'Age':[18,19,18,20,17,21,20,22],
    'Score':[80,90,93,87,96,100,88,98],
    #'Timestamp':[1506959142820,1506959172820,1506959056066,1506959086066,1506959088613,1506959118613]
}
df = pd.DataFrame(data)
grouped = df.groupby('Gender')
print(type(grouped))
print(grouped)#<class 'pandas.core.groupby.groupby.DataFrameGroupBy'>
grouped = df.groupby('Gender')
grouped_muti = df.groupby(['Gender', 'Age'])#主要起的作用还是计数的作用，必定会有一列作为计数使用的。
print('===='*10)
print(grouped.size())
print('===='*10)
print(grouped_muti.size())
print('===='*10)
print(grouped.get_group('Female'))#获取指定的东西
print('===='*10)
print(grouped_muti.get_group(('Female', 17)))#使用过get_group之后，数据类型发生了改变。
df = grouped.get_group('Female').reset_index()#这个是索引重新定义
print('===='*10)
print(df)
print('===='*10)#如果使用过max()、count()、std()等，返回的结果是一个DataFrame对象。
print(grouped.count())#将gender作为主要的一列，ID，Name，Age，Score作为次要的列
print('===='*10)
print(grouped.max()[['Age', 'Score']])#只取特定的列
print('===='*10)
print(grouped.max())#默认取出来所有的列
print('===='*10)
print(grouped.mean()[['Age', 'Score']])

输出结果值：

   Id     Name  Gender  Age  Score
0   0     Alen    Male   18     80
1   1      Bob    Male   19     90
2   2     Cidy  Female   18     93
3   3   Daniel    Male   20     87
4   4    Ellen  Female   17     96
5   5  Frankie    Male   21    100
6   6     Gate    Male   20     88
7   7     Hebe  Female   22     98

<class 'pandas.core.groupby.generic.DataFrameGroupBy'>
<pandas.core.groupby.generic.DataFrameGroupBy object at 0x7fba4045a710>
========================================
Gender
Female    3
Male      5
dtype: int64
========================================
Gender  Age
Female  17     1
        18     1
        22     1
Male    18     1
        19     1
        20     2
        21     1
dtype: int64
========================================
   Id   Name  Gender  Age  Score
2   2   Cidy  Female   18     93
4   4  Ellen  Female   17     96
7   7   Hebe  Female   22     98
========================================
   Id   Name  Gender  Age  Score
4   4  Ellen  Female   17     96
========================================
   index  Id   Name  Gender  Age  Score
0      2   2   Cidy  Female   18     93
1      4   4  Ellen  Female   17     96
2      7   7   Hebe  Female   22     98
========================================
        Id  Name  Age  Score
Gender                      
Female   3     3    3      3
Male     5     5    5      5
========================================
        Age  Score
Gender            
Female   22     98
Male     21    100
========================================
        Id  Name  Age  Score
Gender                      
Female   7  Hebe   22     98
Male     6  Gate   21    100
========================================
         Age      Score
Gender                 
Female  19.0  95.666667
Male    19.6  89.000000

Process finished with exit code 0