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

In [19]:

    

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


    

In [25]:

    

df = pd.read_csv('hanford.csv')
df.columns


    

    
Out[25]:





Index(['County', 'Exposure', 'Mortality'], dtype='object')

In [26]:

    

df.head(2)


    

    
Out[26]:






  

    

      

      
County
      
Exposure
      
Mortality
    
  
  

    

      
0
      
Umatilla
      
2.49
      
147.1
    
    

      
1
      
Morrow
      
2.57
      
130.1
    
  

In [21]:

    

df.describe()


    

    
Out[21]:






  

    

      

      
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 [43]:

    

df['Mortality'].hist(bins=5)


    

    
Out[43]:





<matplotlib.axes._subplots.AxesSubplot at 0x109462400>






    

In [46]:

    

df['Mortality'].mean()


    

    
Out[46]:





157.34444444444446

In [50]:

    

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)
#lambda is a temporary function


    

In [51]:

    

df


    

    
Out[51]:






  

    

      

      
County
      
Exposure
      
Mortality
      
Exposure_low
      
Mort_high
      
Expo_high
    
  
  

    

      
0
      
Umatilla
      
2.49
      
147.1
      
1
      
1
      
0
    
    

      
1
      
Morrow
      
2.57
      
130.1
      
1
      
0
      
0
    
    

      
2
      
Gilliam
      
3.41
      
129.9
      
1
      
0
      
1
    
    

      
3
      
Sherman
      
1.25
      
113.5
      
1
      
0
      
0
    
    

      
4
      
Wasco
      
1.62
      
137.5
      
1
      
0
      
0
    
    

      
5
      
HoodRiver
      
3.83
      
162.3
      
0
      
1
      
1
    
    

      
6
      
Portland
      
11.64
      
207.5
      
0
      
1
      
1
    
    

      
7
      
Columbia
      
6.41
      
177.9
      
0
      
1
      
1
    
    

      
8
      
Clatsop
      
8.34
      
210.3
      
0
      
1
      
1
    
  

In [54]:

    

lm = LogisticRegression()


    

In [64]:

    

x = np.asarray(df[['Expo_high']])
y = np.asarray(df['Mort_high'])


    

In [65]:

    

lm = lm.fit(x,y)


    

In [66]:

    

lm.predict([50])


    

    




/usr/local/lib/python3.5/site-packages/sklearn/utils/validation.py:386: DeprecationWarning: Passing 1d arrays as data is deprecated in 0.17 and willraise ValueError in 0.19. Reshape your data either using X.reshape(-1, 1) if your data has a single feature or X.reshape(1, -1) if it contains a single sample.
  DeprecationWarning)






    
Out[66]:





array([1])