kernel_support_vector_machine.py

import numpy as np
import pandas as pd
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.metrics import confusion_matrix
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

dataset = pd.read_csv('social_network_ads.csv')
X = dataset.iloc[:, [2, 3]].values
Y = dataset.iloc[:, 4].values

x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size = 0.25, random_state = 0)

sc = StandardScaler()
x_train = sc.fit_transform(x_train)
x_test = sc.transform(x_test)

classifier = SVC(kernel = 'rbf', random_state = 0)
classifier.fit(x_train, y_train)

y_pred = classifier.predict(x_test)
print(y_pred)

cm = confusion_matrix(y_test, y_pred)
print(cm)

x_set, y_set = x_test, y_test
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 = 0.75, 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('Kernel SVM (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()