# Step 0: Import the necessary libraries
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
# Step 1: Dataset
X, y = make_classification(n_samples=100, n_features=2,
n_redundant=0, n_clusters_per_class=1, flip_y=0.1, random_state=0)
# Step 2: Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=42)
# Step 3: Preprocess the dataset by scaling the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
# Step 4: Initialize the linear SVM classifier
clf = SVC(kernel=’linear’, C=1.0)
# Step 5: Train the classifier with the training data
clf.fit(X_train_scaled, y_train)
# Step 6: Plot the decision boundary
plt.figure(figsize=(10,6))
# Plot the decision boundary
ax = plt.gca()
xlim = ax.get_xlim()
ylim = ax.get_ylim()
# Create grid to evaluate model
xx = np.linspace(xlim[0], xlim[1], 30)
yy = np.linspace(ylim[0], ylim[1], 30)
YY, XX = np.meshgrid(yy, xx)
xy = np.vstack([XX.ravel(), YY.ravel()]).T
Z = clf.decision_function(xy).reshape(XX.shape)
# Plot decision boundary and margins
ax.contour(XX, YY, Z, colors=’k’, levels=[-1, 0, 1],
alpha=0.5, linestyles=[‘–‘, ‘-‘, ‘–‘])
# Plot support vectors
ax.scatter(clf.support_vectors_[:, 0],
clf.support_vectors_[:, 1], s=100, linewidth=1, facecolors=’none’,
edgecolors=’k’)
# Plot data points
plt.scatter(X_train_scaled[:, 0], X_train_scaled[:, 1],
c=y_train, cmap=plt.cm.Paired, edgecolors=’k’)
plt.xlabel(‘Feature 1’)
plt.ylabel(‘Feature 2’)
plt.title(‘SVM Decision Boundary with Support Vectors’)
plt.show()
