特征工程 —— 特征重要性排序（Random Forest）

樹模型天然會對特征進行重要性排序，以分裂數據集，構建分支；

1. 使用 Random Forest

from sklearn.datasets import load_boston
from sklearn.ensemble import RandomForestRegressor


boston_data = load_boston()
X = boston_data['data']
y = boston_data['target']
    # dir(boston_data) ⇒ 查看其支持的屬性為 ['DESCR', 'data', 'feature_names', 'target']
rf = RandomForestRegressor()
rf.fit(X, y)

print(sorted(zip(boston_data['feature_names'], map(lambda x: round(x, 4), 
                                                   rf.feature_importances_)),
             key=operator.itemgetter(1), reverse=True))