def plot_svm():
num_points = 10
(X, y, f) = random_linearly_separable_data(num_points, bounds)
(w_svm, vectors) = linsep_svm(X, y)
x_plot = X[:,0]
y_plot = X[:,1]
s = 20*np.ones(num_points)
s[vectors] = 60
pla = PLA(bounds=bounds)
pla.fit(X, y)
w_pla = pla.weights
# test values for b
print("Average b:", w_svm[0])
each_b = y[vectors] - np.dot(X[vectors], w_svm[1:])
print("Individual b's:", each_b)
(x_f, y_f) = weights_to_mxb_2D(f, bounds)
(x_w, y_w) = weights_to_mxb_2D(w_svm, bounds)
(x_p, y_p) = weights_to_mxb_2D(w_pla, bounds)
c = np.where(y==1, 'r', 'b')
plt.scatter(x_plot,y_plot, s, c=c)
plt.plot(x_f, y_f, 'k-.')
plt.plot(x_w, y_w, 'b')
plt.plot(x_p, y_p, 'r--')
plt.xlim([-1, 1])
plt.ylim([-1, 1])
plt.grid()
plt.show()
def simple_svm():
print("Solving problems 12 and 13")
X = np.array([[1, 0], [0, 1], [0, -1],
[-1, 0], [0, 2], [0, -2],
[-2, 0]])
y = np.array([-1, -1, -1, 1, 1, 1, 1])
def svm_transform(X):
return np.array([[x[1]**2-2*x[0]-1, x[0]**2-2*x[1]+1] for x in X])
X_t = svm_transform(X)
clf = svm.SVC(kernel='poly', gamma=1, degree=2, coef0=1, C=10**10)
clf.fit(X, y)
print("num vectors: ", sum(clf.n_support_))
w_test = np.array([-0.5, 1, 0])
# Plot
plt.scatter(X_t[:, 0], X_t[:, 1], c=np.where(y==1, 'r', 'b'))
ax = plt.gca()
bounds = np.concatenate([ax.get_xlim(), ax.get_ylim()])
(x_t, y_t) = weights_to_mxb_2D(w_test, bounds)
plt.grid()
plt.plot(x_t, y_t, 'r--')
plt.show()
