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 [2]:

    

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


    

In [3]:

    

df


    

    
Out[3]:






  

    

      

      
County
      
Exposure
      
Mortality
    
  
  

    

      
0
      
Umatilla
      
2.49
      
147.1
    
    

      
1
      
Morrow
      
2.57
      
130.1
    
    

      
2
      
Gilliam
      
3.41
      
129.9
    
    

      
3
      
Sherman
      
1.25
      
113.5
    
    

      
4
      
Wasco
      
1.62
      
137.5
    
    

      
5
      
HoodRiver
      
3.83
      
162.3
    
    

      
6
      
Portland
      
11.64
      
207.5
    
    

      
7
      
Columbia
      
6.41
      
177.9
    
    

      
8
      
Clatsop
      
8.34
      
210.3
    
  

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 [10]:

    

df['Exposure'].max() - df['Exposure'].min()


    

    
Out[10]:





10.390000000000001

In [11]:

    

df['Mortality'].max() - df['Mortality'].min()


    

    
Out[11]:





96.800000000000011

In [12]:

    

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


    

    
Out[12]:





2.4900000000000002

In [ ]:

    

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


    

In [13]:

    

df['Exposure'].quantile(q=0.5)


    

    
Out[13]:





3.4100000000000001

In [14]:

    

df['Exposure'].quantile(q=0.75)


    

    
Out[14]:





6.4100000000000001

In [20]:

    

iqr_ex = df['Exposure'].quantile(q=0.75) - df['Exposure'].quantile(q=0.25)
iqr_ex


    

    
Out[20]:





3.9199999999999999

In [16]:

    

df['Mortality'].quantile(q=0.25)


    

    
Out[16]:





130.09999999999999

In [17]:

    

df['Mortality'].quantile(q=0.5)


    

    
Out[17]:





147.09999999999999

In [18]:

    

df['Mortality'].quantile(q=0.75)


    

    
Out[18]:





177.90000000000001

In [22]:

    

iqr_mort = df['Mortality'].quantile(q=0.75) - df['Mortality'].quantile(q=0.25)
iqr_mort


    

    
Out[22]:





47.800000000000011

In [23]:

    

df.std()


    

    
Out[23]:





Exposure      3.491192
Mortality    34.791346
dtype: float64

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: