• shape, info()로 정보 확인하기

import pandas as pd
import numpy as np
from pandas import Series
from pandas import DataFrame

school_id_list = [{'name': 'John', 'job': "teacher", 'age': 40},
                {'name': 'Nate', 'job': "teacher", 'age': 35},
                {'name': 'Yuna', 'job': "teacher", 'age': 37},
                {'name': 'Abraham', 'job': "student", 'age': 10},
                {'name': 'Brian', 'job': "student", 'age': 12},
                {'name': 'Janny', 'job': "student", 'age': 11},
                {'name': 'Nate', 'job': "teacher", 'age': None},
                {'name': 'John', 'job': "student", 'age': None}
         ]

df = pd.DataFrame(school_id_list, columns = ['name', 'job', 'age'])

df
      name      job   age
0     John  teacher  40.0
1     Nate  teacher  35.0
2     Yuna  teacher  37.0
3  Abraham  student  10.0
4    Brian  student  12.0
5    Janny  student  11.0
6     Nate  teacher   NaN
7     John  student   NaN

#행, 열의 갯수 출력하기
df.shape
(8, 3)

df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8 entries, 0 to 7
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   name    8 non-null      object 
 1   job     8 non-null      object 
 2   age     6 non-null      float64
dtypes: float64(1), object(2)
memory usage: 320.0+ bytes

#age의 2개가 NaN값인 것을 알 수 있다.

• df.isna() / df.isnull() 활용하기

df.isna()
    name    job    age
0  False  False  False
1  False  False  False
2  False  False  False
3  False  False  False
4  False  False  False
5  False  False  False
6  False  False   True
7  False  False   True

df.isnull()
    name    job    age
0  False  False  False
1  False  False  False
2  False  False  False
3  False  False  False
4  False  False  False
5  False  False  False
6  False  False   True
7  False  False   True

Null 또는 NaN 값을 확인할 수 있다.

값 변경하기

• fillna(0) : 널 값을 0으로 바꾸기

df.age = df.age.fillna(0)
df
      name      job   age
0     John  teacher  40.0
1     Nate  teacher  35.0
2     Yuna  teacher  37.0
3  Abraham  student  10.0
4    Brian  student  12.0
5    Janny  student  11.0
6     Nate  teacher   0.0
7     John  student   0.0

• 직업으로 그룹을 나눠 중간 값으로 널 값을 채우기

df['age'].fillna(df.groupby('job')['age'].transform('median'), inplace=True)
df
      name      job   age
0     John  teacher  40.0
1     Nate  teacher  35.0
2     Yuna  teacher  37.0
3  Abraham  student  10.0
4    Brian  student  12.0
5    Janny  student  11.0
6     Nate  teacher  37.0
7     John  student  11.0

👍