一、逻辑回归模型建立
import pandas as pd
data=pd.read_excel(r'F:\BaiduNetdiskDownload\chapter5\demo\data\bankloan.xls')
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)
print('通过随机逻辑回归模型筛选特征结束')
print('有效特征:%s' % ','.join(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)
print('模型的平均正确率为:%s' % lr.score(x,y))
结果展示: