groupby

import pandas as pd
import numpy as np


# 创建一个 DataFrame 对象
ipl_data = {'Team': ['Riders', 'Riders', 'Devils', 'Devils', 'Kings',
         'kings', 'Kings', 'Kings', 'Riders', 'Royals', 'Royals', 'Riders'],
         'Rank': [1, 2, 2, 3, 3,4 ,1 ,1,2 , 4,1,2],
         'Year': [2014,2015,2014,2015,2014,2015,2016,2017,2016,2014,2015,2017],
         'Points':[876,789,863,673,741,812,756,7988,64,701,804,690]}
df = pd.DataFrame(ipl_data)
print (df)

# 将数据拆分组
print (df.groupby('Team'))
# 查看分组
print (df.groupby('Team').groups)
# 多列分组
print (df.groupby(['Team','Year']).groups)

grouped = df.groupby('Year')
# 迭代遍历分组
for name,group in grouped:
    print (name)
    print (group)

# 获取一个分组
print('Get group 2014: ')
print (grouped.get_group(2014))

# 聚合
print('Group agg: test mean ')
print (grouped['Points'].agg(np.mean))
# 多个聚合函数
agg = grouped['Points'].agg([np.sum, np.mean, np.std])
print (agg)
# 过滤
filter = df.groupby('Team').filter(lambda x: len(x) >= 3)
print (filter)