#-*- coding: utf-8 -*-
import pandas as pd
filename = 'C:/Users/Administrator/Desktop/demo/data/bankloan.xls'
data = pd.read_excel(filename)
x = data.iloc[:,:8].as_matrix()
y = data.iloc[:,8].as_matrix()
from sklearn.linear_model import LogisticRegression as LR
from sklearn.linear_model import RandomizedLogisticRegression as RLR
rlr = RLR() #建立随机逻辑回归模型,筛选变量
rlr.fit(x, y) #训练
rlr.get_support() #获取特征结果
print(u'通过随机逻辑回归筛选特征结束')
print('有效特征为' +','.join(list(data.columns[rlr.get_support()])))
x = data[data.columns[rlr.get_support()]].as_matrix() #筛选好特征
lr = LR() #建立逻辑回归模型
lr.fit(x, y) #用筛选后的特征进行训练
print(u'通过逻辑回归训练结束')
print(u'模型的平均正确率:%s' % lr.score(x, y)) #
Python逻辑回归预测违约率
最新推荐文章于 2024-07-15 10:49:30 发布