trainning.py 文件源码

def xgboost_feature_importance(model, train, return_df=False):


    features = train.columns
    create_feature_map(features)

    importance = model.get_fscore(fmap='xgb.fmap')
    importance = sorted(importance.items(), key=operator.itemgetter(1))

    df = pd.DataFrame(importance, columns=['feature', 'fscore'])
    df['fscore'] = df['fscore'] / df['fscore'].sum()

    sns.barplot(x="fscore", y="feature", data=df)
#    plt.xticks(range(len(df)), df.feature.tolist(), rotation=60)
    plt.title('Feature Importances')
    plt.ylabel('Relative Importance')

    print df

    if return_df is True:
        return df