Ò»ÈÕÒ»¼¼£ºpandas»ñÈ¡groupby·Ö×éÀï×î´óÖµËùÔÚµÄÐÐ

import pandas as pd
 
df = pd.DataFrame({'Sp':['a','b','c','d','e','f'], 'Mt':['s1', 's1', 's2','s2','s2','s3'], 'Value':[1,2,3,4,5,6], 'Count':[3,2,5,10,10,6]})

 

df.groupby('Mt').apply(lambda t: t[t.Count==t.Count.max()])

print df.groupby(['Mt'])['Count'].agg(max)
 


 
idx=df.groupby(['Mt'])['Count'].transform(max)
 
print idx
 
idx1 =  idx == df['Count']
 
print idx1
 


 
df[idx1]
 

Mt
 
s1     3
 
s2    10
 
s3     6
 
Name: Count, dtype: int64
 
0 3
 
1 3
 
2 10
 
3 10
 
4 10
 
5 6
 
dtype: int64
 
0     True
 
1    False
 
2    False
 
3     True
 
4     True
 
5     True
 
dtype: bool
 

idx = df.groupby('Mt')['Count'].idxmax()
 
print idx
 


 
df.iloc[idx]
 

Mt
 
s1    0
 
s2    3
 
s3    5
 
Name: Count, dtype: int64
 

df.iloc[df.groupby(['Mt']).apply(lambda x: x['Count'].idxmax())]

def using_apply(df):
 
return (df.groupby('Mt').apply(lambda subf: subf['Value'][subf['Count'].idxmax()]))
 


 
def using_idxmax_loc(df):
 
idx = df.groupby('Mt')['Count'].idxmax()
 
return df.loc[idx, ['Mt', 'Value']]
 


 
print using_apply(df)
 


 
using_idxmax_loc(df)

Mt
 
s1    1
 
s2    4
 
s3    6
 
dtype: int64
 

df.sort('Count', ascending=False).groupby('Mt', as_index=False).first()