prepare_data.py 文件源码

 复制代码def fs_boruta(df):
    # do feature selection using boruta
    X = df[[x for x in df.columns if x!='SalePrice']]
    y = df['SalePrice']
    model = GradientBoostingRegressor()
    feat_selector = boruta_py.BorutaPy(model, n_estimators=100, verbose=12)

    # find all relevant features
    feat_selector.fit_transform(X.as_matrix(), y.as_matrix())

    # check selected features
    features_bool = np.array(feat_selector.support_)
    features = np.array(X.columns)
    result = features[features_bool]
    #print(result)

    # check ranking of features
    features_rank = feat_selector.ranking_
    #print(features_rank)
    rank = features_rank[features_bool]
    #print(rank)

    return result