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

In [4]:

    

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


    

In [5]:

    

df = pd.read_csv("../data/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 [7]:

    

df.describe()


    

    
Out[7]:






  

    

      

      
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 [8]:

    

df.corr()


    

    
Out[8]:






  

    

      

      
Exposure
      
Mortality
    
  
  

    

      
Exposure
      
1.000000
      
0.926345
    
    

      
Mortality
      
0.926345
      
1.000000
    
  

In [10]:

    

lm = LogisticRegression()


    

In [13]:

    

df.std()


    

    
Out[13]:





Exposure      3.491192
Mortality    34.791346
dtype: float64

In [14]:

    

q1 = df['Exposure'].quantile(q=0.25)
q1


    

    
Out[14]:





2.4900000000000002

In [16]:

    

q3 = df['Exposure'].quantile(q=0.75)
q3


    

    
Out[16]:





6.4100000000000001

In [17]:

    

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


    

    
Out[17]:





<matplotlib.axes._subplots.AxesSubplot at 0x1147ef7b8>






    

In [25]:

    

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)
df.head()


    

    
Out[25]:






  

    

      

      
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
    
  

In [ ]:

    

## 和上面那个是一样的！

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


    

In [22]:

    

lm = LogisticRegression()


    

In [38]:

    

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


    

    
Out[38]:





(array([0, 0, 1, 0, 0, 1, 1, 1, 1]), array([1, 0, 0, 0, 0, 1, 1, 1, 1]))

In [39]:

    

lm = lm.fit(x,y)


    

    




/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)






    




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-39-0fc46e0387ae> in <module>()
----> 1 lm = lm.fit(x,y)

/usr/local/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)

/usr/local/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

/usr/local/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 [ ]:

    




    

In [ ]: