def f_getmodelen(model_path):
'''
依据模型路径 给出需要输入模型的变量个数
:param model_path: 模型路径
:param implen: 重要变量长度
:return:
'''
x = ModelUtil.load_bstmodel(model_path)
try:
# xgboost 获取变量的方法
x = x.feature_names
modellen = len(x)
except:
try:
# 随机森林的获取方法
modellen = x[0].n_features_
except:
try:
# gbm 获取入模变量的方法
modellen = len(x.feature_name())
except:
# 评分卡 获取入模变量的方法
modellen = len(x.params) - 1
return modellen
def f_getVarpctrf(model_path, implen):
'''
依据模型路径 给出需要输入模型的变量个数
:param model_path: 模型路径
:param implen: 重要变量长度
:return:
'''
x = ModelUtil.load_bstmodel(model_path)
try:
# 随机森林的获取方法
modellen = x.n_features_
except:
modellen = np.nan
return implen == modellen
def f_getVarpctgbm(model_path, implen):
'''
依据模型路径 给出需要输入模型的变量个数
:param model_path: 模型路径
:param implen: 重要变量长度
:return:
'''
x = ModelUtil.load_bstmodel(model_path)
try:
# gbm 获取入模变量的方法
modellen = len(x.feature_name())
except:
modellen = np.nan
return implen == modellen
def f_getVarpctboost(model_path, implen):
'''
依据模型路径 给出需要输入模型的变量个数
:param model_path: 模型路径
:param implen: 重要变量长度
:return:
'''
x = ModelUtil.load_bstmodel(model_path)
try:
# xgboost 获取变量的方法
x = x.feature_names
modellen = len(x)
except:
modellen = np.nan
return implen == modellen
def __init__(self, modelname, dummyList, Allcol, bstmodelpath):
self.modelname = modelname
self.dummyList = dummyList # 这个也会获取到
self.Allcol = Allcol # f_genAllcol(dummyAfterdf) 可以由这个函数获取到
self.bstmodelpath = bstmodelpath
self.bstmodel = ModelUtil.load_bstmodel(bstmodelpath)
for x in ls:
fill_dict[x] = 0
# print(fill_dict)
var = dummy2df.fillna(fill_dict)
return var
# dummyList = list(set(res[4]) - set(res[5]))
# dummyAfterdf = f_dummyOld(tr, dummyList)
# f_dummyNew(te.head(3), dummyList, f_genAllcol(dummyAfterdf))
if __name__ == '__main__':
# 测试一下 保存模型处理数据的类
modelpath = r'C:\Users\liyin\Desktop\CcxMLOGE\TestUnit\ccxboost\model20171211190055\modeltxt\model_ccxboost_2017-12-11.txt'
bst = ModelUtil.load_bstmodel(modelpath)
Allcol = bst.feature_names
import numpy as np
dd = pd.DataFrame(np.ones(len(Allcol))).T
dd.columns = Allcol
dd.index = ['All']
dummyList = list(set([i.split('_')[0] for i in Allcol if '_' in i]))
psd = processData('ccxboost', dummyList, dd, modelpath)
psd.modelname
psd.save('111', r'C:\Users\liyin\Desktop\CcxMLOGE\TestUnit')
path = 'C:/Users/liyin/Desktop/CcxMLOGE/TestUnit/predict/ccxboost111.model'
with open(path, 'rb') as f:
psd_1 = pickle.load(f)