Python groupby函数图文详解

DataFrame.groupby(by=None, axis=0, level=None, as_index=True, group_keys=True, squeeze=False,  observed=False, **kwargs)

import numpy as np
import pandas as pd
 
data = pd.DataFrame({
    'name': ['Tom', 'Kaggle', 'Litter', 'Sam', 'Sam', 'Sam'],
    'race': ['B', 'C', 'D', 'E', 'B', 'C'],
    'age': [37.0, 61.0, 56.0, 87.0, 58.0, 34.0],
    'signs_of_mental_illness': [True, True, False, False, False, False]
})
 
data.groupby('race')

# mean()
data.groupby('name')['age'].mean()
# count()
data.groupby('name')['age'].count()
data.groupby('age').count()

# 单键多列聚合
data.groupby('name')[['race','age',]].count()

print(data.groupby('name')['age'].agg(['mean']))
 
print(data.groupby('name')['age'].agg(['mean','count']))

print(data.groupby('race').agg({'age': np.median, 'signs_of_mental_illness': np.mean}))

print('apply之前')
grouped = data.groupby('name')
for name, group in grouped:
    print(name)
    print(group)
print('\n')
print('apply之后')
print(data.groupby('name').apply(lambda x: x.head(2)))

import numpy as np
import pandas as pd
 
 
data = pd.read_excel('订购时间预测2.xlsx')
def cut_m_d(x):
	return round(x.month + x.day / 30, 2)
 
data['m_d'] = data['Time'].apply(cut_m_d)
grouped = data.groupby('ID')
# 这一步是去重(ID),不去重会出现错误
result = grouped['m_d'].unique()
result2 = result.reset_index()
print(result2)