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

In [51]:

    

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


    

In [2]:

    

df=pd.read_csv('../data/hanford.csv')


    

In [3]:

    

df.describe()


    

    
Out[3]:






  

    

      

      
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 [79]:

    

# find first and third quartiles
first_qtr=df['Exposure'].quantile(q=0.25)
third_qtr=df['Exposure'].quantile(q=0.75)


    

In [80]:

    

# calculate interquartile range
iqr = third_qtr - first_qtr


    

In [81]:

    

# define outliers
lower = first_qtr - 1.5*iqr


    

In [82]:

    

upper = third_qtr + 1.5*iqr


    

In [83]:

    

print(outlier1)


    

    




-3.39

In [84]:

    

print(outlier2) #  if exposure gt 12.29 then exposure is high? #this doesnt make sense bc no value of exposure is 12.29


    

    




12.29

In [99]:

    

# the line of code below returns true/false
# df['Exposure_High'] = df['Exposure']>=3.41 
# choose the median value instead
df['Exposure_High']=df['Exposure'].apply(lambda x:1 if x>=3.41 else 0)


    

In [100]:

    

df


    

    
Out[100]:






  

    

      

      
County
      
Exposure
      
Mortality
      
Exposure_High
    
  
  

    

      
0
      
Umatilla
      
2.49
      
147.1
      
0
    
    

      
1
      
Morrow
      
2.57
      
130.1
      
0
    
    

      
2
      
Gilliam
      
3.41
      
129.9
      
1
    
    

      
3
      
Sherman
      
1.25
      
113.5
      
0
    
    

      
4
      
Wasco
      
1.62
      
137.5
      
0
    
    

      
5
      
HoodRiver
      
3.83
      
162.3
      
1
    
    

      
6
      
Portland
      
11.64
      
207.5
      
1
    
    

      
7
      
Columbia
      
6.41
      
177.9
      
1
    
    

      
8
      
Clatsop
      
8.34
      
210.3
      
1
    
  

In [101]:

    

lm = LogisticRegression()


    

In [102]:

    

x = np.asarray(df['Mortality'])
y = np.asarray(df['Exposure_High'])


    

In [103]:

    

lm = lm.fit(x,y)


    

    




/Users/mercyemelike/.virtualenvs/data_analysis/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)






    




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-103-0fc46e0387ae> in <module>()
----> 1 lm = lm.fit(x,y)

/Users/mercyemelike/.virtualenvs/data_analysis/lib/python3.5/site-packages/sklearn/linear_model/logistic.py in fit(self, X, y, sample_weight)
   1140 
   1141         X, y = check_X_y(X, y, accept_sparse='csr', dtype=np.float64, 
-> 1142                          order="C")
   1143         check_classification_targets(y)
   1144         self.classes_ = np.unique(y)

/Users/mercyemelike/.virtualenvs/data_analysis/lib/python3.5/site-packages/sklearn/utils/validation.py in check_X_y(X, y, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)
    518         y = y.astype(np.float64)
    519 
--> 520     check_consistent_length(X, y)
    521 
    522     return X, y

/Users/mercyemelike/.virtualenvs/data_analysis/lib/python3.5/site-packages/sklearn/utils/validation.py in check_consistent_length(*arrays)
    174     if len(uniques) > 1:
    175         raise ValueError("Found arrays with inconsistent numbers of samples: "
--> 176                          "%s" % str(uniques))
    177 
    178 

ValueError: Found arrays with inconsistent numbers of samples: [1 9]

In [104]:

    

lm.predict([0])


    

    




---------------------------------------------------------------------------
NotFittedError                            Traceback (most recent call last)
<ipython-input-104-b7d9a29325c9> in <module>()
----> 1 lm.predict([0])

/Users/mercyemelike/.virtualenvs/data_analysis/lib/python3.5/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)

/Users/mercyemelike/.virtualenvs/data_analysis/lib/python3.5/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 [ ]: