📜 결측값 제거 후 상위 70프로 데이터 에서 Q1 값 구하기
import pandas as pd
from sklearn.datasets import load_boston
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.metrics import mean_squared_error
import sklearn.svm as svm
df = pd.read_csv('../notebook/housing.csv')
df.dropna()
df.iloc[:int(df.shape[0] * 0.7)]
result = np.percentile(dataset['housing_median_age'],25)
print(int(result))
📖 그룹별 평균 구해서 다루기
mean_dataset= dataset.groupby('ocean_proximity')[['housing_median_age']].mean()
over_mean = mean_dataset['housing_median_age'] > dataset['housing_median_age'].mean()
mean_dataset[over_mean].index