pyspark GBTRegressor 特征重要度 及排序

#打印特征索引及其重要度
features_important = model.featureImportances
print(features_important)

#获取各个特征在模型中的重要性并按照权重倒序打印
ks = list(features_important.indices)
vs = list(features_important.toArray())

features_important = tuple(features_important)
print(len(features_important))


name_index = train.schema["features"].metadata["ml_attr"]["attrs"]


index_im = zip(ks, vs)
names = []
idxs = []
 
fea_num = 0

for it in name_index[‘numeric‘]:
    names.append(it[‘name‘])
    idxs.append(it[‘idx‘])
    fea_num += 1
    
print (fea_num)

d = zip(names, idxs)
p = zip(index_im, d)
 
kv = {}
for fir, sec in p:
    kv[sec[0]] = fir[1]
    fea_num += 1
print(len(kv))
print (sorted(kv.items(), key=lambda el: el[1], reverse=True))