import pandas as pd
filename=r'..\data\bankloan.xls' #导入数据路径
data=pd.read_excel(filename) #读取该excel文件
x=data.iloc[:,:8].as_matrix() #选取数据集中0-7行的数据，形成一个矩阵
y=data.iloc[:,8].as_matrix()
from sklearn.linear_model import LogisticRegression as LR
from sklearn.linear_model import RandomizedLogisticRegression as RLR
rlr=RLR()
rlr.fit(x,y) #训练模型
rlr.get_support() #获取特征筛选结果
print(u'通过逻辑回归模型筛选特征结束。')
print(u'有效特征为：%s'%','.join(data.columns[rlr.get_support()]))
x=data[data.columns[rlr.get_support()]].as_matrix() #筛选好的特征
lr=LR()
lr.fit(x,y)
print(u'逻辑回归模型训练结束')
print(u'模型的平均正确率：%s'%lr.score(x,y))

import pandas as pd
filename=r'..\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()
rlr.fit(x,y)
rlr.get_support()
print(u'通过逻辑回归模型筛选特征结束。')
data2=data.drop(u'违约',1)
print(u'有效特征为：%s'%','.join(data2.columns[rlr.get_support()]))
x=data[data2.columns[rlr.get_support()]].as_matrix()
lr=LR()
lr.fit(x,y)
print(u'逻辑回归模型训练结束')
print(u'模型的平均正确率：%s'%lr.score(x,y))