Apply logistic regression to categorize whether a county had high mortality rate due to contamination

In [1]:

    

import pandas as pd
%matplotlib inline
import numpy as np
from sklearn.linear_model import LogisticRegression


    

In [3]:

    

df=pd.read_csv("hanford.csv")


    

In [4]:

    

df.describe()


    

    
Out[4]:






  

    

      

      
Exposure
      
Mortality
    
  
  

    

      
count
      
9.000000
      
9.000000
    
    

      
mean
      
4.617778
      
157.344444
    
    

      
std
      
3.491192
      
34.791346
    
    

      
min
      
1.250000
      
113.500000
    
    

      
25%
      
2.490000
      
130.100000
    
    

      
50%
      
3.410000
      
147.100000
    
    

      
75%
      
6.410000
      
177.900000
    
    

      
max
      
11.640000
      
210.300000
    
  

In [5]:

    

df.corr()


    

    
Out[5]:






  

    

      

      
Exposure
      
Mortality
    
  
  

    

      
Exposure
      
1.000000
      
0.926345
    
    

      
Mortality
      
0.926345
      
1.000000
    
  

In [8]:

    

df['Mortality'].hist()


    

    
Out[8]:





<matplotlib.axes._subplots.AxesSubplot at 0x11715d2b0>






    

In [9]:

    

df['Mortality'].mean()


    

    
Out[9]:





157.34444444444446

In [13]:

    

#use the median as a threshold 
df['Mort_high']=df['Mortality'].apply(lambda x:1 if x>=147.1 else 0)
df['Expo_high']=df['Exposure'].apply(lambda x:1 if x>=3.41 else 0)


    

In [14]:

    

def exposure_high(x):
    if x>=3.41:
        return 1
    else:
        return 0


    

In [15]:

    

df


    

    
Out[15]:






  

    

      

      
County
      
Exposure
      
Mortality
      
Mort_high
      
Expo_high
    
  
  

    

      
0
      
Umatilla
      
2.49
      
147.1
      
1
      
0
    
    

      
1
      
Morrow
      
2.57
      
130.1
      
0
      
0
    
    

      
2
      
Gilliam
      
3.41
      
129.9
      
0
      
1
    
    

      
3
      
Sherman
      
1.25
      
113.5
      
0
      
0
    
    

      
4
      
Wasco
      
1.62
      
137.5
      
0
      
0
    
    

      
5
      
HoodRiver
      
3.83
      
162.3
      
1
      
1
    
    

      
6
      
Portland
      
11.64
      
207.5
      
1
      
1
    
    

      
7
      
Columbia
      
6.41
      
177.9
      
1
      
1
    
    

      
8
      
Clatsop
      
8.34
      
210.3
      
1
      
1
    
  

In [7]:

    

Q1=df['Exposure'].quantile(q=0.25)
Q1


    

    
Out[7]:





2.4900000000000002

In [ ]:

    

Q2=df['Exposure'].quantile(q=0.)


    

In [ ]:

    




    

In [ ]:

    




    

In [16]:

    

lm =


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-16-44d480e072fd> in <module>()
----> 1 lm = smf.ols(formula="Mortality~Exposure",data=df).fit()

NameError: name 'smf' is not defined

In [ ]:

    

lm=lm.fit(x.y)


    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: