In [19]:

    

import os

import pandas as pd
import numpy as np

import seaborn as sns; sns.set()

from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import confusion_matrix

from statsmodels.discrete.discrete_model import Logit, LogitResults


    

In [5]:

    

pd.set_option('max_columns', 200)
pd.set_option('max_rows', 200)
pd.set_option('display.float_format', '{:.2f}'.format)


    

In [7]:

    

df = pd.read_pickle('../Chapter 7 - Data Preparation and Visualization/claims_df')


    

In [32]:

    

df.shape


    

    
Out[32]:





(4700, 38)

In [9]:

    

disease = ['SP_ALZHDMTA','SP_CHF', 'SP_CHRNKIDN', 'SP_CNCR', 'SP_COPD', 'SP_DEPRESSN','SP_DIABETES', 'SP_ISCHMCHT', 'SP_OSTEOPRS', 'SP_RA_OA', 'SP_STRKETIA']
gender = ['gender_2']
ESRD = ['ESRD_Y']


    

In [10]:

    

X = df[disease+gender+ESRD]
y = df.HIGH_COST


    

In [11]:

    

lab_enc = LabelEncoder()


    

In [12]:

    

lab_enc.fit_transform(y)


    

    
Out[12]:





array([0, 0, 0, ..., 0, 0, 0])

In [110]:

    

lm = LogisticRegression()


    

In [111]:

    

lm.fit(X, y)


    

    
Out[111]:





LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

In [112]:

    

lm.score(X, y)


    

    
Out[112]:





0.9027659574468085

In [113]:

    

def generate_conf_mat(model, X, y):
    conf_mat = confusion_matrix(model.predict(X), y)
    conf_mat = pd.DataFrame(conf_mat/conf_mat.sum())
    conf_mat.columns = ['0_pred', '1_pred']
    conf_mat.index=['0_actual', '1_actual']
    return conf_mat


    

In [114]:

    

conf_mat = generate_conf_mat(lm, X, y)


    

In [115]:

    

conf_mat


    

    
Out[115]:







  

    

      

      
0_pred
      
1_pred
    
  
  

    

      
0_actual
      
0.88
      
0.08
    
    

      
1_actual
      
0.02
      
0.02
    
  

In [116]:

    

lm2 = Logit(y, X)


    

In [117]:

    

results = lm2.fit()


    

    




Optimization terminated successfully.
         Current function value: 0.421470
         Iterations 7

In [118]:

    

results.summary()


    

    
Out[118]:





Logit Regression Results

  
Dep. Variable:
     
HIGH_COST
    
  No. Observations:  
  
  4700
 


  
Model:
               
Logit
      
  Df Residuals:      
  
  4687
 


  
Method:
               
MLE
       
  Df Model:          
  
    12
 


  
Date:
          
Thu, 21 Jun 2018
 
  Pseudo R-squ.:     
  
-0.2946


  
Time:
              
11:27:17
     
  Log-Likelihood:    
 
 -1980.9


  
converged:
           
True
       
  LL-Null:           
 
 -1530.1


  
 
                      
 
        
  LLR p-value:       
  
 1.000
 




       
          
coef
     
std err
      
z
      
P>|z|
  
[0.025
    
0.975]
  


  
SP_ALZHDMTA
 
   -0.0405
 
    0.101
 
   -0.401
 
 0.688
 
   -0.238
 
    0.157


  
SP_CHF
      
   -0.2308
 
    0.097
 
   -2.370
 
 0.018
 
   -0.422
 
   -0.040


  
SP_CHRNKIDN
 
    1.4570
 
    0.121
 
   12.066
 
 0.000
 
    1.220
 
    1.694


  
SP_CNCR
     
    0.1308
 
    0.148
 
    0.882
 
 0.378
 
   -0.160
 
    0.421


  
SP_COPD
     
    0.9319
 
    0.116
 
    8.040
 
 0.000
 
    0.705
 
    1.159


  
SP_DEPRESSN
 
   -0.3392
 
    0.098
 
   -3.471
 
 0.001
 
   -0.531
 
   -0.148


  
SP_DIABETES
 
   -0.8365
 
    0.098
 
   -8.507
 
 0.000
 
   -1.029
 
   -0.644


  
SP_ISCHMCHT
 
   -1.1603
 
    0.093
 
  -12.432
 
 0.000
 
   -1.343
 
   -0.977


  
SP_OSTEOPRS
 
   -0.2756
 
    0.105
 
   -2.635
 
 0.008
 
   -0.481
 
   -0.071


  
SP_RA_OA
    
   -0.0401
 
    0.112
 
   -0.357
 
 0.721
 
   -0.260
 
    0.180


  
SP_STRKETIA
 
    1.0162
 
    0.166
 
    6.119
 
 0.000
 
    0.691
 
    1.342


  
gender_2
    
   -1.7737
 
    0.075
 
  -23.672
 
 0.000
 
   -1.921
 
   -1.627


  
ESRD_Y
      
    0.4462
 
    0.137
 
    3.265
 
 0.001
 
    0.178
 
    0.714

In [119]:

    

from sklearn.svm import LinearSVC


    

In [120]:

    

mod = svm.LinearSVC(class_weight='balanced')


    

In [121]:

    

mod.fit(X, y)


    

    
Out[121]:





LinearSVC(C=1.0, class_weight='balanced', dual=True, fit_intercept=True,
     intercept_scaling=1, loss='squared_hinge', max_iter=1000,
     multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,
     verbose=0)

In [122]:

    

conf_mat = generate_conf_mat(mod, X, y)


    

In [123]:

    

conf_mat


    

    
Out[123]:







  

    

      

      
0_pred
      
1_pred
    
  
  

    

      
0_actual
      
0.73
      
0.02
    
    

      
1_actual
      
0.17
      
0.08
    
  

In [ ]:

    




    

In [ ]: