pyrandom.py 文件源码

def get_feature_importance(list_of_features):
    n_estimators=10000
    random_state=0
    n_jobs=4
    x_train=data_frame[list_of_features]
    y_train=data_frame.iloc[:,-1]
    feat_labels= data_frame.columns[1:]
    forest = BaggingRegressor(n_estimators=n_estimators,random_state=random_state,n_jobs=n_jobs) 
    forest.fit(x_train,y_train) 
    importances=forest.feature_importances_ 
    indices = np.argsort(importances)[::-1]


    for f in range(x_train.shape[1]):
        print("%2d) %-*s %f" % (f+1,30,feat_labels[indices[f]],
                                        importances[indices[f]]))


    plt.title("Feature Importance")
    plt.bar(range(x_train.shape[1]),importances[indices],color='lightblue',align='center')
    plt.xticks(range(x_train.shape[1]),feat_labels[indices],rotation=90)
    plt.xlim([-1,x_train.shape[1]])
    plt.tight_layout()
    plt.show()