def swiss_roll_test():
import matplotlib.pyplot as plt
plt.style.use('ggplot')
from time import time
from sklearn import manifold, datasets
from sklearn.manifold import SpectralEmbedding
from lpproj import LocalityPreservingProjection
n_points = 1000
X, color = datasets.samples_generator.make_s_curve(n_points,
random_state=0)
n_neighbors = 20
n_components = 2
# original lE algorithm
t0 = time()
ml_model = SpectralEmbedding(n_neighbors=n_neighbors,
n_components=n_components)
Y = ml_model.fit_transform(X)
t1 = time()
# 2d projection
fig, ax = plt.subplots(nrows=3, ncols=1, figsize=(5, 10))
ax[0].scatter(Y[:, 0], Y[:, 1], c=color, label='scikit')
ax[0].set_title('Sklearn-LE: {t:.2g}'.format(t=t1 - t0))
# Jakes LPP Algorithm
t0 = time()
ml_model = LocalityPreservingProjection(n_components=n_components)
ml_model.fit(X)
Y = ml_model.transform(X)
t1 = time()
ax[1].scatter(Y[:, 0], Y[:, 1], c=color, label='Jakes Algorithm')
ax[1].set_title('Jakes LPP: {t:.2g}'.format(t=t1 - t0))
# my SSSE algorith,
t0 = time()
ml_model = LocalityPreservingProjections(weight='angle',
n_components=n_components,
n_neighbors=n_neighbors,
sparse=True,
eig_solver='dense')
ml_model.fit(X)
Y = ml_model.transform(X)
t1 = time()
ax[2].scatter(Y[:, 0], Y[:, 1], c=color, label='My LPP Algorithm')
ax[2].set_title('My LPP: {t:.2g}'.format(t=t1 - t0))
plt.show()
def swiss_roll_test():
n_points = 1000
X, color = datasets.samples_generator.make_s_curve(n_points,
random_state=0)
n_neighbors=20
n_components=2
# original lE algorithm
t0 = time()
ml_model = SpectralEmbedding(n_neighbors=n_neighbors,
n_components=n_components)
Y = ml_model.fit_transform(X)
t1 = time()
# 2d projection
fig, ax = plt.subplots(nrows=3, ncols=1, figsize=(5,10))
ax[0].scatter(Y[:,0], Y[:,1], c=color, label='scikit')
ax[0].set_title('Sklearn-LE: {t:.2g}'.format(t=t1-t0))
# Jakes LPP Algorithm
t0 = time()
ml_model = LocalityPreservingProjection(n_components=n_components)
ml_model.fit(X)
Y = ml_model.transform(X)
t1 = time()
ax[1].scatter(Y[:,0], Y[:,1], c=color, label='Jakes Algorithm')
ax[1].set_title('Jakes LPP: {t:.2g}'.format(t=t1-t0))
# my SSSE algorith,
t0 = time()
ml_model = LocalityPreservingProjections(weight='angle',
n_components=n_components,
n_neighbors=n_neighbors,
sparse=True,
eig_solver='dense')
ml_model.fit(X)
Y = ml_model.transform(X)
t1 = time()
ax[2].scatter(Y[:,0], Y[:,1], c=color, label='My LPP Algorithm')
ax[2].set_title('My LPP: {t:.2g}'.format(t=t1-t0))
plt.show()
def test(g=dataset_generator.Generator(), mode='show'):
alpha_channel = 0.7
spectre1 = np.array([
np.array([1, 0, 0, alpha_channel]),
np.array([1, 1, 0, alpha_channel])
])
spectre2 = np.array([
np.array([0, 0, 1, alpha_channel]),
np.array([0, 1, 0, alpha_channel])
])
spectre3 = np.array([
np.array([1, 0, 1, alpha_channel]),
np.array([0, 1, 1, alpha_channel])
])
n_neighbors = 10
n_components = 2
fig = plt.figure(figsize=(15, 8))
se = SpectralEmbedding(n_components=n_components, n_neighbors=n_neighbors)
'''--------------------------------------------------------------------------------------------------------------'''
dataset, dataset_colors = g.generate_manifold(f, color_data=spectre1)
ax = fig.add_subplot(241, projection='3d')
ax.scatter(dataset[:, 0],
dataset[:, 1],
dataset[:, 2],
c=dataset_colors,
marker='s',
edgecolors='none')
dataset_embedding = se.fit_transform(dataset)
ax = fig.add_subplot(245)
ax.scatter(dataset_embedding[:, 0],
dataset_embedding[:, 1],
c=dataset_colors,
cmap=plt.cm.Spectral,
marker='s',
edgecolors='none')
'''--------------------------------------------------------------------------------------------------------------'''
new_points, new_colors = g.generate_manifold(f, spectre2)
new_points_embedding = np.array(
list(se.transform(point.reshape(1, -1))[0] for point in new_points))
ax = fig.add_subplot(242, projection='3d')
ax.scatter(dataset[:, 0],
dataset[:, 1],
dataset[:, 2],
c=dataset_colors,
marker='s',
edgecolors='none')
ax.scatter(new_points[:, 0],
new_points[:, 1],
new_points[:, 2],
c=new_colors,
marker='s',
edgecolors='none')
ax = fig.add_subplot(246)
ax.scatter(dataset_embedding[:, 0],
dataset_embedding[:, 1],
c=dataset_colors,
marker='s',
edgecolor='none')
ax.scatter(new_points_embedding[:, 0],
new_points_embedding[:, 1],
c=new_colors,
marker='s',
edgecolors='none')
'''--------------------------------------------------------------------------------------------------------------'''
re_colors = dataset_generator.Generator.generate_colors(
None, dataset.shape[0], spectre3)
re_embedding = np.array(
list(se.transform(point.reshape(1, -1))[0] for point in dataset))
ax = fig.add_subplot(243, projection='3d')
ax.scatter(dataset[:, 0],
dataset[:, 1],
dataset[:, 2],
c=dataset_colors,
marker='s',
edgecolors='none')
ax.scatter(dataset[:, 0],
dataset[:, 1],
dataset[:, 2],
c=re_colors,
marker='s',
edgecolors='none')
ax = fig.add_subplot(247)
ax.scatter(dataset_embedding[:, 0],
dataset_embedding[:, 1],
c=dataset_colors,
marker='s',
edgecolor='none')
ax.scatter(re_embedding[:, 0],
re_embedding[:, 1],
c=re_colors,
marker='s',
edgecolors='none')
'''--------------------------------------------------------------------------------------------------------------'''
dataset_reconstruction = np.array(
list(
se.inverse_transform(point.reshape(1, -1))[0]
for point in dataset_embedding))
ax = fig.add_subplot(244)
ax.scatter(dataset_embedding[:, 0],
dataset_embedding[:, 1],
c=dataset_colors,
marker='s',
edgecolor='none')
ax = fig.add_subplot(248, projection='3d')
ax.scatter(dataset_reconstruction[:, 0],
dataset_reconstruction[:, 1],
dataset_reconstruction[:, 2],
c=dataset_colors,
marker='s',
edgecolors='none')
ax.scatter(dataset[:, 0],
dataset[:, 1],
dataset[:, 2],
c=re_colors,
marker='s',
edgecolors='none')
'''--------------------------------------------------------------------------------------------------------------'''
plt.axis('tight')
if mode == 'show':
plt.show()
if f == 1000 or input('save? y/N') != 'y':
pass
else:
save(fig, dataset, dataset_embedding, new_points,
new_points_embedding)
else:
save(fig, dataset, dataset_embedding, new_points, new_points_embedding)
