In [38]:

    

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd


    

In [39]:

    

dataset = pd.read_csv('Social_Network_Ads.csv')


    

In [40]:

    

X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values


    

In [41]:

    

from sklearn.model_selection import train_test_split


    

In [42]:

    

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)


    

In [43]:

    

from sklearn.preprocessing import StandardScaler


    

In [44]:

    

sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)


    

    




/usr/local/opt/pyenv/versions/3.6.0/Python.framework/Versions/3.6/lib/python3.6/site-packages/sklearn/utils/validation.py:429: DataConversionWarning: Data with input dtype int64 was converted to float64 by StandardScaler.
  warnings.warn(msg, _DataConversionWarning)

In [45]:

    

from sklearn.neighbors import KNeighborsClassifier


    

In [46]:

    

classifier = KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2)
classifier.fit(X_train, y_train)


    

    
Out[46]:





KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=5, p=2,
           weights='uniform')

In [47]:

    

y_pred = classifier.predict(X_test)
result = pd.DataFrame([y_test, y_pred]).transpose()
result.columns = ['observed', 'predicted']
result[result['observed'] != result['predicted']]


    

    
Out[47]:






  

    

      

      
observed
      
predicted
    
  
  

    

      
9
      
0
      
1
    
    

      
15
      
0
      
1
    
    

      
31
      
1
      
0
    
    

      
53
      
0
      
1
    
    

      
81
      
0
      
1
    
    

      
85
      
1
      
0
    
    

      
95
      
1
      
0
    
  

In [48]:

    

from sklearn.metrics import confusion_matrix


    

In [49]:

    

confusion_matrix(y_test, y_pred)


    

    
Out[49]:





array([[64,  4],
       [ 3, 29]])

In [50]:

    

from matplotlib.colors import ListedColormap


    

In [51]:

    

def draw(X_set, y_set, title):
    X1, X2 = np.meshgrid(np.arange(start=X_set[:, 0].min() - 1, stop=X_set[:, 0].max() + 1, step=0.01),
                         np.arange(start=X_set[:, 1].min() - 1, stop=X_set[:, 1].max() + 1, step=0.01))
    plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
                 alpha=0.5, cmap=ListedColormap(('red', 'green')))
    plt.xlim(X1.min(), X1.max())
    plt.ylim(X2.min(), X2.max())
    for i, j in enumerate(np.unique(y_set)):
        plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                    c=ListedColormap(('red', 'green'))(i), label=j)
    plt.title(title)
    plt.xlabel('Age')
    plt.ylabel('Estimated Salary')
    plt.legend()
    plt.show()


    

In [52]:

    

draw(X_train, y_train, 'K-NN (Train set)')


    

In [53]:

    

draw(X_test, y_test, 'K-NN (Train set)')