def main_gaussian():
x_train, y_train, x_test, y_test = gaussians_dataset(2, [100, 150], [[1, 3], [-4, 8]], [[2, 3], [4, 1]])
svm_alg = SVM(n_epochs=100, lambDa=0.001, use_bias=False)
# train
svm_alg.fit_gd(x_train, y_train, verbose=True)
# test
predictions = svm_alg.predict(x_test)
accuracy = float(np.sum(predictions == y_test)) / y_test.shape[0]
print('Test accuracy: {}'.format(accuracy))
plot_pegasos_margin(x_test, y_test, svm_alg)
def main_svm():
"""
Main function to experiment with SVM on synthetic points.
"""
X_train, Y_train, X_test, Y_test = gaussians_dataset(2, [100, 150], [[1, 3], [-4, 8]], [[2, 3], [4, 1]])
# X_train, Y_train, X_test, Y_test = two_moon_dataset(n_samples=300, noise=0.2)
C = 100
kernel = 'rbf'
model = svm.SVC(C=C, kernel=kernel)
model.fit(X_train, Y_train)
# print result on train
plot_margin(X_train, Y_train, model, title='train data')
# print result on test
plot_margin(X_test, Y_test, model, title='test data')
def main_kmeans_gaussian():
"""
Main function to run kmeans the synthetic gaussian dataset.
"""
# generate the dataset
data, cl = gaussians_dataset(3, [100, 100, 70], [[1, 1], [-4, 6], [8, 8]],
[[1, 1], [3, 3], [1, 1]])
# visualize the dataset
fig, ax = plt.subplots(1, 2)
ax[0].scatter(data[:, 0], data[:, 1], c=cl, s=40)
plt.waitforbuttonpress()
# solve kmeans optimization
labels = kmeans(data, n_cl=3, verbose=True)
# visualize results
ax[1].scatter(data[:, 0], data[:, 1], c=labels, s=40)
plt.waitforbuttonpress()
def main_adaboost():
"""
Main function for fitting and testing Adaboost classifier.
"""
X_train, Y_train, X_test, Y_test = gaussians_dataset(2, [300, 400], [[1, 3], [-4, 8]], [[2, 3], [4, 1]])
# X_train, Y_train, X_test, Y_test = h_shaped_dataset()
# X_train, Y_train, X_test, Y_test = two_moon_dataset(n_samples=500, noise=0.2)
# Visualize dataset
plot_2d_dataset(X_train, Y_train, 'Training', blocking=False)
# Init model
model = AdaBoostClassifier(n_learners=100)
# Train
model.fit(X_train, Y_train, verbose=True)
# Predict
y_preds = model.predict(X_test)
print('Accuracy on test set: {}'.format(np.mean(y_preds == Y_test)))
# Visualize the predicted boundary
plot_boundary(X_train, Y_train, model)