svm_classifier_feature_scaling.ipynb

Kernel: Unknown Kernel

# SVM for binary classification in 2d
# Code is based on
# https://github.com/ageron/handson-ml2/blob/master/05_support_vector_machines.ipynb


import numpy as np
import matplotlib.pyplot as plt

try:
    from sklearn.svm import SVC
except ModuleNotFoundError:
    %pip install -qq scikit-learn
    from sklearn.svm import SVC
from sklearn import datasets
from sklearn.datasets import make_moons
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.preprocessing import StandardScaler
from sklearn.svm import LinearSVC

try:
    from probml_utils import savefig
except ModuleNotFoundError:
    %pip install -qq git+https://github.com/probml/probml-utils.git
    from probml_utils import savefig


def plot_svc_decision_boundary(svm_clf, xmin, xmax):
    w = svm_clf.coef_[0]
    b = svm_clf.intercept_[0]

    # At the decision boundary, w0*x0 + w1*x1 + b = 0
    # => x1 = -w0/w1 * x0 - b/w1
    x0 = np.linspace(xmin, xmax, 200)
    decision_boundary = -w[0] / w[1] * x0 - b / w[1]

    margin = 1 / w[1]
    gutter_up = decision_boundary + margin
    gutter_down = decision_boundary - margin

    svs = svm_clf.support_vectors_
    plt.scatter(svs[:, 0], svs[:, 1], s=180, facecolors="#FFAAAA")
    plt.plot(x0, decision_boundary, "k-", linewidth=2)
    plt.plot(x0, gutter_up, "k--", linewidth=2)
    plt.plot(x0, gutter_down, "k--", linewidth=2)


Xs = np.array([[1, 50], [5, 20], [3, 80], [5, 60]]).astype(np.float64)
ys = np.array([0, 0, 1, 1])
svm_clf = SVC(kernel="linear", C=100)
svm_clf.fit(Xs, ys)

plt.figure(figsize=(9, 2.7))
plt.subplot(121)
plt.plot(Xs[:, 0][ys == 1], Xs[:, 1][ys == 1], "bo")
plt.plot(Xs[:, 0][ys == 0], Xs[:, 1][ys == 0], "ms")
plot_svc_decision_boundary(svm_clf, 0, 6)
plt.xlabel("$x_0$", fontsize=20)
plt.ylabel("$x_1$    ", fontsize=20, rotation=0)
plt.title("Unscaled", fontsize=16)
plt.axis([0, 6, 0, 90])

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
X_scaled = scaler.fit_transform(Xs)
svm_clf.fit(X_scaled, ys)

plt.subplot(122)
plt.plot(X_scaled[:, 0][ys == 1], X_scaled[:, 1][ys == 1], "bo")
plt.plot(X_scaled[:, 0][ys == 0], X_scaled[:, 1][ys == 0], "ms")
plot_svc_decision_boundary(svm_clf, -2, 2)
plt.xlabel("$x_0$", fontsize=20)
plt.ylabel("$x'_1$  ", fontsize=20, rotation=0)
plt.title("Scaled", fontsize=16)
plt.axis([-2, 2, -2, 2])

savefig("svm_classifier_feature_scaling.pdf", dpi=300)