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 [5]:

    

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


    

    
Out[5]:






  

    

      

      
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
    
  

In [6]:

    

df.describe()


    

    
Out[6]:






  

    

      

      
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 [7]:

    

df.median()


    

    
Out[7]:





Exposure       3.41
Mortality    147.10
dtype: float64

In [8]:

    

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


    

    
Out[8]:





96.800000000000011

In [10]:

    

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


    

    
Out[10]:





47.800000000000011

In [11]:

    

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


    

    
Out[11]:





3.9199999999999999

In [12]:

    

UAL_m= (iqr_m*1.5) + df['Mortality'].quantile(q=0.75)
UAL_m


    

    
Out[12]:





249.60000000000002

In [17]:

    

UAL_e= (iqr_m*1.5) + df['Exposure'].quantile(q=0.75)
UAL_e


    

    
Out[17]:





78.110000000000014

In [13]:

    

LAL_m= df['Mortality'].quantile(q=0.25) - (iqr_e*1.5)  
LAL_m


    

    
Out[13]:





124.22

In [14]:

    

LAL_e= df['Exposure'].quantile(q=0.25) - (iqr_e*1.5)  
LAL_e


    

    
Out[14]:





-3.3899999999999997

In [15]:

    

len(df[df['Mortality']> UAL_m])


    

    
Out[15]:





0

In [18]:

    

len(df[df['Exposure']> UAL_e])


    

    
Out[18]:





0

In [19]:

    

len(df[df['Mortality']< LAL_m])


    

    
Out[19]:





1

In [20]:

    

len(df[df['Mortality'] > UAL_m])


    

    
Out[20]:





0

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [41]:

    

lm = LogisticRegression()


    

In [49]:

    

data = np.asarray(df[['Mortality','Exposure']])
x = data[:,1:]
y = data[:,0]


    

In [50]:

    

data


    

    
Out[50]:





array([[ 147.1 ,    2.49],
       [ 130.1 ,    2.57],
       [ 129.9 ,    3.41],
       [ 113.5 ,    1.25],
       [ 137.5 ,    1.62],
       [ 162.3 ,    3.83],
       [ 207.5 ,   11.64],
       [ 177.9 ,    6.41],
       [ 210.3 ,    8.34]])

In [44]:

    

x


    

    
Out[44]:





array([[  2.49],
       [  2.57],
       [  3.41],
       [  1.25],
       [  1.62],
       [  3.83],
       [ 11.64],
       [  6.41],
       [  8.34]])

In [45]:

    

y


    

    
Out[45]:





array([ 147.1,  130.1,  129.9,  113.5,  137.5,  162.3,  207.5,  177.9,
        210.3])

In [48]:

    

lm.fit(x,y)


    

    




---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-48-fead33db94e1> in <module>()
----> 1 lm.fit(x)

TypeError: fit() missing 1 required positional argument: 'y'

In [35]:

    

lm.coef_


    

    




---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-35-f029e8367547> in <module>()
----> 1 lm.coef_

AttributeError: 'LogisticRegression' object has no attribute 'coef_'

In [36]:

    

lm.score(x,y)


    

    




---------------------------------------------------------------------------
NotFittedError                            Traceback (most recent call last)
<ipython-input-36-366f7d2147ae> in <module>()
----> 1 lm.score(x,y)

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\sklearn\base.py in score(self, X, y, sample_weight)
    308         """
    309         from .metrics import accuracy_score
--> 310         return accuracy_score(y, self.predict(X), sample_weight=sample_weight)
    311 
    312 

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\sklearn\linear_model\base.py in predict(self, X)
    266             Predicted class label per sample.
    267         """
--> 268         scores = self.decision_function(X)
    269         if len(scores.shape) == 1:
    270             indices = (scores > 0).astype(np.int)

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\sklearn\linear_model\base.py in decision_function(self, X)
    240         if not hasattr(self, 'coef_') or self.coef_ is None:
    241             raise NotFittedError("This %(name)s instance is not fitted "
--> 242                                  "yet" % {'name': type(self).__name__})
    243 
    244         X = check_array(X, accept_sparse='csr')

NotFittedError: This LogisticRegression instance is not fitted yet

In [37]:

    

slope = lm.coef_[0]


    

    




---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-37-84e9eb32b1fa> in <module>()
----> 1 slope = lm.coef_[0]

AttributeError: 'LogisticRegression' object has no attribute 'coef_'

In [38]:

    

intercept = lm.intercept_


    

    




---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-38-0f828ae237a1> in <module>()
----> 1 intercept = lm.intercept_

AttributeError: 'LogisticRegression' object has no attribute 'intercept_'

In [40]:

    

lm.predict(50)


    

    




---------------------------------------------------------------------------
NotFittedError                            Traceback (most recent call last)
<ipython-input-40-abad1de0f282> in <module>()
----> 1 lm.predict(50)

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\sklearn\linear_model\base.py in predict(self, X)
    266             Predicted class label per sample.
    267         """
--> 268         scores = self.decision_function(X)
    269         if len(scores.shape) == 1:
    270             indices = (scores > 0).astype(np.int)

c:\users\radhika\appdata\local\programs\python\python35-32\lib\site-packages\sklearn\linear_model\base.py in decision_function(self, X)
    240         if not hasattr(self, 'coef_') or self.coef_ is None:
    241             raise NotFittedError("This %(name)s instance is not fitted "
--> 242                                  "yet" % {'name': type(self).__name__})
    243 
    244         X = check_array(X, accept_sparse='csr')

NotFittedError: This LogisticRegression instance is not fitted yet

In [ ]: