1# Basic syntax:
2df.groupby('column_name').mean()
3
4# Where this will return the mean of each group with the same values in
5# the column "column_name"
6
7# Example usage:
8import pandas as pd
9import numpy as np
10
11df = pd.DataFrame({'A': [1, 1, 2, 1, 2],
12 'B': [np.nan, 2, 3, 4, 5],
13 'C': [1, 2, 1, 1, 2]}, columns=['A', 'B', 'C'])
14
15print(df)
16 A B C
170 1 NaN 1
181 1 2.0 2
192 2 3.0 1
203 1 4.0 1
214 2 5.0 2
22
23# Calculate the mean of columns B and C grouped by the values in column A
24df.groupby('A').mean() # Returns:
25 B C
26A
271 3.0 1.333333
282 4.0 1.500000
29
30# Calculate the mean of column C grouped by the values in columns A and B
31df.groupby(['A', 'B']).mean() # Returns:
32 C
33A B
341 2.0 2
35 4.0 1
362 3.0 1
37 5.0 2