Pandas dataframe由一些值组成

Question

I have this data

import numpy as np
import pandas as pd
group = {'gender': ['male', 'female', 'female', 'male', 'female', 'male', 'male'],
        'height': [175, 168, np.nan, 170, 167, np.nan, 190],
        }
labels = ['a', 'b', 'c', 'd', 'e', 'f', 'g']
df = pd.DataFrame(group, index=labels)
df2 = df.groupby('gender')['height'].mean()

and i want to fill nan with mean value from df2

Answer 1

code

import pandas as pd
import numpy as np

group = {'gender': ['male', 'female', 'female', 'male', 'female', 'male', 'male'],
        'height': [175, 168, np.nan, 170, 167, np.nan, 190],
        }
labels = ['a', 'b', 'c', 'd', 'e', 'f', 'g']
df = pd.DataFrame(group, index=labels)
df2 = df.groupby('gender')['height'].mean()
df['height'].fillna(df['gender'].map(df2), inplace=True)
# print(df2)
print(df)

output

   gender      height
a    male  175.000000
b  female  168.000000
c  female  167.500000
d    male  170.000000
e  female  167.000000
f    male  178.333333
g    male  190.000000

Answer 2

You can use groupby + transform with mean . Then fillna with the resulting series.

means = df.groupby('gender')['height'].transform('mean')
df['height'] = df['height'].fillna(means)

print(df)

   gender      height
a    male  175.000000
b  female  168.000000
c  female  167.500000
d    male  170.000000
e  female  167.000000
f    male  178.333333
g    male  190.000000