def kmeans_toy():
x, y = toy_dataset(4)
fig = Figure()
fig.ax.scatter(x[:, 0], x[:, 1], c=y)
fig.savefig('plots/toy_dataset_real_labels.png')
fig.ax.scatter(x[:, 0], x[:, 1])
fig.savefig('plots/toy_dataset.png')
n_cluster = 4
k_means = KMeans(n_cluster=n_cluster, max_iter=100, e=1e-8)
centroids, membership, i = k_means.fit(x)
assert centroids.shape == (n_cluster, 2), \
('centroids for toy dataset should be numpy array of size {} X 2'
.format(n_cluster))
assert membership.shape == (50 * n_cluster,), \
'membership for toy dataset should be a vector of size 200'
assert type(i) == int and i > 0, \
'Number of updates for toy datasets should be integer and positive'
print('[success] : kmeans clustering done on toy dataset')
print('Toy dataset K means clustering converged in {} steps'.format(i))
fig = Figure()
fig.ax.scatter(x[:, 0], x[:, 1], c=membership)
fig.ax.scatter(centroids[:, 0], centroids[:, 1], c='red')
fig.savefig('plots/toy_dataset_predicted_labels.png')
np.savez('results/k_means_toy.npz',
centroids=centroids,
step=i,
membership=membership,
y=y)
def kmeans_builder(centroid_func):
samples_per_cluster = 50
n_cluster = 9
x, y = toy_dataset(n_cluster, samples_per_cluster)
fig = Figure()
fig.ax.scatter(x[:, 0], x[:, 1], c=y)
fig.savefig('plots/toy_dataset_real_labels.png')
fig.ax.scatter(x[:, 0], x[:, 1])
fig.savefig('plots/toy_dataset.png')
k_means = KMeans(n_cluster=n_cluster, max_iter=100, e=1e-8)
centroids, membership, i = k_means.fit(x, centroid_func)
assert centroids.shape == (n_cluster, 2), \
('centroids for toy dataset should be numpy array of size {} X 2'
.format(n_cluster))
assert membership.shape == (samples_per_cluster * n_cluster,), \
'membership for toy dataset should be a vector of size {}'.format(len(membership))
assert type(i) == int and i > 0, \
'Number of updates for toy datasets should be integer and positive'
print('[success] : kmeans clustering done on toy dataset')
print('Toy dataset K means clustering converged in {} steps'.format(i))
fig = Figure()
fig.ax.scatter(x[:, 0], x[:, 1], c=membership)
fig.ax.scatter(centroids[:, 0], centroids[:, 1], c='red')
fig.savefig('plots/toy_dataset_predicted_labels.png')
def kmeans_builder(centroid_func):
samples_per_cluster = 50
n_cluster = 9
x, y = toy_dataset(n_cluster, samples_per_cluster)
# print("x: ", x)
# print("y: ", y)
# plot the scatter plot with color coded by cluster index
fig = Figure()
fig.ax.scatter(x[:, 0], x[:, 1], c=y)
fig.savefig('plots/toy_dataset_real_labels.png')
fig.ax.scatter(x[:, 0], x[:, 1])
fig.savefig('plots/toy_dataset.png')
# create a class kmeans
k_means = KMeans(n_cluster=n_cluster, max_iter=100, e=1e-8)
# fit the kmeans to data x using centroid_func to initialize
centroids, membership, i = k_means.fit(x, centroid_func)
assert centroids.shape == (n_cluster, 2), \
('centroids for toy dataset should be numpy array of size {} X 2'
.format(n_cluster))
assert membership.shape == (samples_per_cluster * n_cluster,), \
'membership for toy dataset should be a vector of size {}'.format(len(membership))
assert type(i) == int and i > 0, \
'Number of updates for toy datasets should be integer and positive'
print('[success] : kmeans clustering done on toy dataset')
print('Toy dataset K means clustering converged in {} steps'.format(i))
# plot toy dataset labelling using OUR method
fig = Figure()
fig.ax.scatter(x[:, 0], x[:, 1], c=membership)
fig.ax.scatter(centroids[:, 0], centroids[:, 1], c='red')
# plt.show()
fig.savefig('plots/toy_dataset_predicted_labels.png')
lambda1, lambda2 = eig
else:
lambda2, lambda1 = eig
angle = np.arctan(b / (a - c)) / 2
return np.sqrt(1 / lambda1), np.sqrt(1 / lambda2), angle
################################################################################
# GMM on 2D toy dataset
# The dataset is generated from N gaussian distributions equally spaced on N radius circle.
# Here, N=4
# You should be able to visualize the learnt gaussian distribution in plots folder
# Complete implementation of fit function for GMM class in gmm.py
################################################################################
x, y = toy_dataset(4, 100)
init = ['k_means', 'random']
for i in init:
n_cluster = 4
gmm = GMM(n_cluster=n_cluster, max_iter=1000, init=i, e=1e-6)
iterations = gmm.fit(x)
ll = gmm.compute_log_likelihood(x)
assert gmm.means.shape == (
n_cluster, 2), 'means should be numpy array with {}X2 shape'.format(n_cluster)
assert gmm.variances.shape == (
n_cluster, 2, 2), 'variances should be numpy array with {}X2X2 shape'.format(n_cluster)
assert gmm.pi_k.shape == (
