随机森林特征选择

from sklearn.ensemble import RandomForestClassifier
import matplotlib.pyplot as plt

selected_feat_names=set()
for i in range(10):                           #这里我们进行十次循环取交集
    tmp = set()
    rfc = RandomForestClassifier(n_jobs=-1)
    rfc.fit(X, y)

    #print("training finished")

    importances = rfc.feature_importances_
    indices = np.argsort(importances)[::-1]   # 降序排列
    S={}
    for f in range(X.shape[1]):
        if  importances[indices[f]] >=0.0001:
            tmp.add(X.columns[indices[f]])
            S[X.columns[indices[f]]]=importances[indices[f]]
            #print("%2d) %-*s %f" % (f + 1, 30, X.columns[indices[f]], importances[indices[f]]))
    selected_feat_names |= tmp
    imp_fea=pd.Series(S)
print(len(selected_feat_names), "features are selected")