逻辑回归模型

# -*- coding: utf-8 -*-
"""
Created on Thu Feb  1 13:33:50 2018

@author: Administrator
"""

import pandas as pd
path='F:/python/3python数据分析与挖掘实战/图书配套数据、代码/chapter5/demo/data/bankloan.xls'
df=pd.read_excel(path)
x=df.iloc[:,:8].as_matrix()
y=df.iloc[:,8].as_matrix()

from sklearn.linear_model import LogisticRegression as LR
from sklearn.linear_model import RandomizedLogisticRegression as RLR
rlr = RLR()#随机逻辑回归模型
rlr.fit(x,y)
rlr.get_support()#获取特征筛选结果
#rlr.scores_    各个特征的分数
print('通过随机逻辑回归模型筛选特征结束')
print('有效特征为:%s' % ','.join(df.columns[rlr.get_support()]))
x=df[df.columns[rlr.get_support()]].as_matrix()#筛选特征

lr=LR()#逻辑回归模型
lr.fit(x,y)
print('逻辑回归模型训练结束')
print('模型的平均正确率:%s' % lr.score(x,y))

lr.predict(x[0].reshape(1,-1))#预测


df
Out[26]: 
     年龄  教育  工龄  地址   收入   负债率      信用卡负债       其他负债  违约
0    41   3  17  12  176   9.3  11.359392   5.008608   1
1    27   1  10   6   31  17.3   1.362202   4.000798   0
2    40   1  15  14   55   5.5   0.856075   2.168925   0
3    41   1  15  14  120   2.9   2.658720   0.821280   0
4    24   2   2   0   28  17.3   1.787436   3.056564   1
5    41   2   5   5   25  10.2   0.392700   2.157300   0
6    39   1  20   9   67  30.6   3.833874  16.668126   0
7    43   1  12  11   38   3.6   0.128592   1.239408   0
8    24   1   3   4   19  24.4   1.358348   3.277652   1
9    36   1   0  13   25  19.7   2.777700   2.147300   0
10   27   1   0   1   16   1.7   0.182512   0.089488   0
11   25   1   4   0   23   5.2   0.252356   0.943644   0
12   52   1  24  14   64  10.0   3.929600   2.470400   0
13   37   1   6   9   29  16.3   1.715901   3.011099   0
14   48   1  22  15  100   9.1   3.703700   5.396300   0
15   36   2   9   6   49   8.6   0.817516   3.396484   1
16   36   2  13   6   41  16.4   2.918216   3.805784   1
17   43   1  23  19   72   7.6   1.181952   4.290048   0
18   39   1   6   9   61   5.7   0.563274   2.913726   0
19   41   3   0  21   26   1.7   0.099008   0.342992   0
20   39   1  22   3   52   3.2   1.154816   0.509184   0
21   47   1  17  21   43   5.6   0.587552   1.820448   0
22   28   1   3   6   26  10.0   0.431600   2.168400   0
23   29   1   8   6   27   9.8   0.402192   2.243808   0
24   21   2   1   2   16  18.0   0.241920   2.638080   1
25   25   4   0   2   32  17.6   2.140160   3.491840   0
26   45   2   9  26   69   6.7   0.707319   3.915681   0
27   43   1  25  21   64  16.7   0.951232   9.736768   0
28   33   2  12   8   58  18.4   3.084208   7.587792   0
29   26   3   2   1   37  14.2   0.204906   5.049094   0
..   ..  ..  ..  ..  ...   ...        ...        ...  ..
670  23   2   3   4   24   6.3   0.551880   0.960120   0
671  27   1   0   7   18  12.8   0.582912   1.721088   0
672  34   1   6   1   20   1.2   0.042480   0.197520   0
673  35   1   0   5   34  11.1   1.369962   2.404038   1
674  24   2   4   4   20   3.7   0.324120   0.415880   0
675  48   1  30   8  101   6.4   1.874560   4.589440   0
676  26   2   8   1   40  11.8   0.443680   4.276320   0
677  40   1   6   9   36   2.1   0.390852   0.365148   1
678  34   1   9   8   48   9.3   0.419616   4.044384   0
679  35   1  17   4   42   3.0   0.093240   1.166760   0
680  30   1   7   2   33  25.4   1.165098   7.216902   1
681  20   1   4   0   14   9.7   0.200984   1.157016   1
682  36   4   1  17   30  11.5   0.324300   3.125700   0
683  21   1   1   1   16   6.3   0.141120   0.866880   0
684  34   1  18  10   53  10.5   0.840315   4.724685   0
685  35   1   7   5   39  16.1   1.701609   4.577391   1
686  35   3   1   4   20   7.9   0.853200   0.726800   0
687  34   1  10   1   33  10.3   2.501664   0.897336   1
688  33   1  12  12   68  10.8   1.365984   5.978016   0
689  30   1   4   2   18  10.7   0.227268   1.698732   0
690  24   2   0   5   16   7.3   0.024528   1.143472   0
691  47   1  31   8  253   7.2   9.308376   8.907624   0
692  53   1   0  26   27  28.9   2.754459   5.048541   1
693  22   3   0   2   20   4.7   0.219020   0.720980   0
694  48   2   6   1   66  12.1   2.315940   5.670060   0
695  36   2   6  15   27   4.6   0.262062   0.979938   1
696  29   2   6   4   21  11.5   0.369495   2.045505   0
697  33   1  15   3   32   7.6   0.491264   1.940736   0
698  45   1  19  22   77   8.4   2.302608   4.165392   0
699  37   1  12  14   44  14.7   2.994684   3.473316   0

[700 rows x 9 columns]

runfile('C:/Users/Administrator/Desktop/87.py', wdir='C:/Users/Administrator/Desktop')
通过随机逻辑回归模型筛选特征结束
有效特征为:工龄,地址,负债率,信用卡负债
逻辑回归模型训练结束
模型的平均正确率:0.814285714286