4주차 TIL - 프로젝트의 끝...

# 연도별 결측치 비율 확인
missing_by_year = data_cleaned.groupby('Year').apply(lambda x: x.isnull().mean() * 100)
print("Missing by Year:\n", missing_by_year)

# 결측치 비율이 낮은 연도만 필터링
valid_years = missing_by_year[missing_by_year['Value'] < 20].index
data_cleaned = data_cleaned[data_cleaned['Year'].isin(valid_years)]

 

# 'Value' 열의 결측치를 평균값으로 대체
data_cleaned['Value'] = data_cleaned['Value'].fillna(data_cleaned['Value'].mean())