

In [ ]:

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

Data Preparation

Importing a dataset



In [ ]:

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



In [ ]:

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

Splitting the dataset into a Training set a Test set



In [ ]:

    
from sklearn.model_selection import train_test_split



In [ ]:

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

Feature Scaling



In [ ]:

    
from sklearn.preprocessing import StandardScaler



In [ ]:

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

Modeling

Fitting the Classifier to the Training set



In [ ]:

    
# from sklearn. import



In [ ]:

    
# classifier =
classifier.fit(X_train, y_train)

Predicting the Test set results



In [ ]:

    
y_pred = classifier.predict(X_test)

Making the Confusion Matrix



In [ ]:

    
from sklearn.metrics import confusion_matrix



In [ ]:

    
confusion_matrix(y_test, y_pred)

Visualising results



In [ ]:

    
from matplotlib.colors import ListedColormap



In [ ]:

    
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 [ ]:

    
draw(X_train, y_train, 'Classifier (Training set)')



In [ ]:

    
draw(X_test, y_test, 'Classifier (Test set)')