pandas分组运算（groupby）

1. groupby()

import pandas as pd
df = pd.DataFrame([[1, 1, 2], [1, 2, 3], [2, 3, 4]], columns=["A", "B", "C"])
print(df)

g = df.groupby('A').mean()   # 按A列分组(groupby)，获取其他列的均值
print(g)

# 方法1
b = df['B'].groupby(df['A']).mean()    # 按A列分组，获取B列的均值
print(b)

# 方法2
b = df.ix[:,1].groupby(df.ix[:, 0]).mean()    # 按A列分组（0对应A列，1对应B列），获取B列的均值
print(b)

# 方法3
m = df.groupby('A')
b = m['B'].mean()
print(b)

2. 聚合方法size()和count()

size跟count的区别： size计数时包含NaN值，而count不包含NaN值

import pandas as pd
import numpy as np

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)

count()

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

size()

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

来自：https://blog.csdn.net/m0_37870649/article/details/80979809