prepare_data.py 文件源码

def greedy_elim(df):

    # do feature selection using boruta
    X = df[[x for x in df.columns if x!='SalePrice']]
    y = df['SalePrice']
    #model = RandomForestRegressor(n_estimators=50)
    model = GradientBoostingRegressor(n_estimators=50, learning_rate=0.05)
    # 150 features seems to be the best at the moment. Why this is is unclear.
    feat_selector = RFE(estimator=model, step=1, n_features_to_select=150)

    # 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