In [79]:

    

import pandas as pd
import matplotlib.pyplot as plt
import math


    

In [80]:

    

data = pd.read_csv('resources/data-logistic.csv', header=None)


    

In [81]:

    

data.head()


    

    
Out[81]:







  

    

      

      
0
      
1
      
2
    
  
  

    

      
0
      
-1
      
-0.663827
      
-0.138526
    
    

      
1
      
1
      
1.994596
      
2.468025
    
    

      
2
      
-1
      
-1.247395
      
0.749425
    
    

      
3
      
1
      
2.309374
      
1.899836
    
    

      
4
      
1
      
0.849143
      
2.407750
    
  

In [82]:

    

plt.scatter(data[1], data[2], c=data[0])


    

    
Out[82]:





<matplotlib.collections.PathCollection at 0x1167065d0>






    

In [88]:

    

def functionW1(w1, w2, y, X, k, C):
    l = len(y)
    S = 0
    for i in xrange(0, l):
        S += y[i] * X[1][i] * (1.0 - 1.0 / (1.0 + math.exp(-y[i] * (w1*X[1][i] + w2*X[2][i]))))

    return w1 + (k * (1.0 / l) * S) - k * C * w1

def functionW2(w1, w2, y, X, k, C):
    l = len(y)
    S = 0
    for i in xrange(0, l):
        S += y[i] * X[2][i] * (1.0 - 1.0 / (1.0 + math.exp(-y[i] * (w1*X[1][i] + w2*X[2][i]))))

    return w2 + (k * (1.0 / l) * S) - k * C * w2


    

In [84]:

    

def grad(y, X, C=0.0, w1=0.0, w2=0.0, k=0.1, err=1e-5):
    i = 0
    i_max = 10000
    w1_new, w2_new = w1, w2

    while True:
        i += 1
        w1_new, w2_new = functionW1(w1, w2, y, X, k, C), functionW2(w1, w2, y, X, k, C)
        e = math.sqrt((w1_new - w1) ** 2 + (w2_new - w2) ** 2)

        if i >= i_max or e <= err:
            break
        else:
            w1, w2 = w1_new, w2_new

    return [w1_new, w2_new]


    

In [89]:

    

w1, w2 = grad(data[0], data.loc[:, 1:])
rw1, rw2 = grad(data[0], data.loc[:, 1:], 10.0)


    

In [90]:

    

def auc_roc(X, w1, w2):
    return 1.0 / (1.0 + math.exp(-w1 * X[1] - w2 * X[2]))


    

In [91]:

    

y_score = data.loc[:,1:].apply(lambda x: a(x, w1, w2), axis=1)
y_rscore = data.loc[:,1:].apply(lambda x: a(x, rw1, rw2), axis=1)

auc = roc_auc_score(y, y_score)
rauc = roc_auc_score(y, y_rscore)

print("{:0.3f} {:0.3f}".format(auc, rauc))


    

    




0.927 0.936