Python pandas中和groupby连用的聚合函数 size() count()的区别

df = pd.DataFrame({"Name":["Alice", "Bob", "Mallory", "Mallory", "Bob" , 
                           "Mallory"],"City":["Seattle", "Seattle", "Portland", "Seattle", "Seattle", "Portland"], 
                           "Val":[4,3,3,np.nan,np.nan,4]})

print(df)
df1 = df.groupby(["Name", "City"], as_index=False)['Val'].count()
print('--------------------------groupby(["Name", "City"], as_index=False)[Val].count()')
print(df1)

df1 = df.groupby(["City"], as_index=False).count()  # count把每一列的值都返回出现的次数
print('--------------------------groupby([City], as_index=False).count()')
print(df1)

df1 = df.groupby(["City"], as_index=False).size()  # size只返回分组字段的出现次数
print('--------------------------.groupby(["City"], as_index=False).size()')
print(df1)

df2=df.groupby(["Name", "City"], as_index=False).count()
print('--------------------------df.groupby(["Name", "City"], as_index=False).count()')
print(df2)

df3=df.groupby(["Name", "City"])['Val'].size().reset_index(name='Size')
print('--------------------------groupby(["Name", "City"])[Val].size().reset_index(name=Size)')

print(df3)

df4=df.groupby(["Name", "City"]).size()
print('--------------------------groupby(["Name", "City"]).size()')

print(df4)

结果如下：

 Name      City  Val
0    Alice   Seattle  4.0
1      Bob   Seattle  3.0
2  Mallory  Portland  3.0
3  Mallory   Seattle  NaN
4      Bob   Seattle  NaN
5  Mallory  Portland  4.0
--------------------------groupby(["Name", "City"], as_index=False)[Val].count()
      Name      City  Val
0    Alice   Seattle    1
1      Bob   Seattle    1
2  Mallory  Portland    2
3  Mallory   Seattle    0
--------------------------groupby([City], as_index=False).count()
       City  Name  Val
0  Portland     2    2
1   Seattle     4    2
--------------------------.groupby(["City"], as_index=False).size()
City
Portland    2
Seattle     4
dtype: int64
--------------------------df.groupby(["Name", "City"], as_index=False).count()
      Name      City  Val
0    Alice   Seattle    1
1      Bob   Seattle    1
2  Mallory  Portland    2
3  Mallory   Seattle    0
--------------------------groupby(["Name", "City"])[Val].size().reset_index(name=Size)
      Name      City  Size
0    Alice   Seattle     1
1      Bob   Seattle     2
2  Mallory  Portland     2
3  Mallory   Seattle     1
--------------------------groupby(["Name", "City"]).size()
Name     City    
Alice    Seattle     1
Bob      Seattle     2
Mallory  Portland    2
         Seattle     1
dtype: int64