def converter_isomap_modular(data):
try:
from shogun.Features import RealFeatures
from shogun.Converter import Isomap
features = RealFeatures(data)
converter = Isomap()
converter.set_k(20)
converter.set_target_dim(1)
converter.apply(features)
return features
except ImportError:
print('No Eigen3 available')
def converter_isomap_modular(data):
try:
from shogun.Features import RealFeatures
from shogun.Converter import Isomap
features = RealFeatures(data)
converter = Isomap()
converter.set_k(20)
converter.set_target_dim(1)
converter.apply(features)
return features
except ImportError:
print("No Eigen3 available")
embedding = converter.embed(features)
X = embedding.get_feature_matrix()
#fig.add_subplot(3, 1, 2)
fig = pylab.figure()
pylab.plot(X[0, y1], X[1, y1], 'rx')
pylab.plot(X[0, y2], X[1, y2], 'go')
pylab.title('Stochastic Proximity Embedding with global strategy')
pylab.xlabel('x')
pylab.ylabel('y')
# Compute Isomap embedding (for comparison)
converter = Isomap()
converter.set_target_dim(2)
converter.set_k(6)
embedding = converter.embed(features)
X = embedding.get_feature_matrix()
#fig.add_subplot(3, 1, 3)
fig = pylab.figure()
pylab.plot(X[0, y1], X[1, y1], 'rx')
pylab.plot(X[0, y2], X[1, y2], 'go')
pylab.title('Isomap')
pylab.xlabel('x')
def converter_isomap_modular(data): from shogun.Features import RealFeatures from shogun.Converter import Isomap features = RealFeatures(data) converter = Isomap() converter.set_landmark(True) converter.set_landmark_number(5) converter.set_k(6) converter.set_target_dim(1) converter.apply(features) return features
lle = LocallyLinearEmbedding()
lle.set_k(9)
converters.append((lle, "LLE with k=%d" % lle.get_k()))
from shogun.Converter import MultidimensionalScaling
mds = MultidimensionalScaling()
converters.append((mds, "Classic MDS"))
lmds = MultidimensionalScaling()
lmds.set_landmark(True)
lmds.set_landmark_number(20)
converters.append(
(lmds, "Landmark MDS with %d landmarks" % lmds.get_landmark_number()))
from shogun.Converter import Isomap
cisomap = Isomap()
cisomap.set_k(9)
converters.append((cisomap, "Isomap with k=%d" % cisomap.get_k()))
from shogun.Converter import DiffusionMaps
from shogun.Kernel import GaussianKernel
dm = DiffusionMaps()
dm.set_t(2)
dm.set_width(1000.0)
converters.append(
(dm, "Diffusion Maps with t=%d, sigma=%f" % (dm.get_t(), dm.get_width())))
from shogun.Converter import HessianLocallyLinearEmbedding
hlle = HessianLocallyLinearEmbedding()
hlle.set_k(6)
converters.append((hlle, "Hessian LLE with k=%d" % (hlle.get_k())))
def converter_isomap_modular(data):
from shogun.Features import RealFeatures
from shogun.Converter import Isomap
features = RealFeatures(data)
converter = Isomap()
converter.set_landmark(True)
converter.set_landmark_number(5)
converter.set_k(6)
converter.set_target_dim(1)
converter.apply(features)
return features
from shogun.Converter import LocallyLinearEmbedding lle = LocallyLinearEmbedding() lle.set_k(9) converters.append((lle, "LLE with k=%d" % lle.get_k())) from shogun.Converter import MultidimensionalScaling mds = MultidimensionalScaling() converters.append((mds, "Classic MDS")) lmds = MultidimensionalScaling() lmds.set_landmark(True) lmds.set_landmark_number(20) converters.append((lmds,"Landmark MDS with %d landmarks" % lmds.get_landmark_number())) from shogun.Converter import Isomap cisomap = Isomap() cisomap.set_k(9) converters.append((cisomap,"Isomap with k=%d" % cisomap.get_k())) from shogun.Converter import DiffusionMaps from shogun.Kernel import GaussianKernel dm = DiffusionMaps() dm.set_t(20) kernel = GaussianKernel(100,1.0) dm.set_kernel(kernel) converters.append((dm,"Diffusion Maps with t=%d, sigma=%f" % (dm.get_t(),kernel.get_width()))) from shogun.Converter import HessianLocallyLinearEmbedding hlle = HessianLocallyLinearEmbedding() hlle.set_k(6) converters.append((hlle,"Hessian LLE with k=%d" % (hlle.get_k())))
