def test_eigencalculation(self):
L = numpy.array([ [1., 0., 0., 0.],
[ 0, 1., 0., -4.],
[ 0, 0., 1., 0.],
[ 0, -4., 0., 1.]])
max_clusters = 2
v = SpectralTools.calculateUnnormalizedEigenvectors(L, max_clusters, False)
L = numpy.array([ [1., 0., 0., 0.],
[ 0, 1., 0., -4.],
[ 0, 0., 1., 0.],
[ 0, -4., 0., 1.]])
v = SpectralTools.calculateUnnormalizedEigenvectors(L, max_clusters, True)
D = [1.,2.,3.,4.]
L = numpy.array([ [1., 0., 0., 0.],
[ 0, 1., 0., -4.],
[ 0, 0., 1., 0.],
[ 0, -4., 0., 1.]])
v = SpectralTools.calculateNormalizedEigenvectors(L, D, max_clusters, False)
L = numpy.array([ [1., 0., 0., 0.],
[ 0, 1., 0., -4.],
[ 0, 0., 1., 0.],
[ 0, -4., 0., 1.]])
v = SpectralTools.calculateNormalizedEigenvectors(L, D, max_clusters, True)
self.fail("CHECK EIGENCALCULATIONS AGAIN, VALUES FOR THIS METHODS ARE DIFFERENT")
def __init__(self, condensed_matrix, **kwargs):
"""
Constructor. Calculates the eigenvectors given a dataset distance matrix. The eigenvector distances would be the
common part for clusterings with different k.
@param condensed_matrix: The distance matrix of the dataset.
@param sigma_sq: The squared value of sigma for the adjacency matrix calculation. If None, the value will be automatically
calculated.
@param max_clusters: Maximum number of clusters we will try with this algorithm (for instance with max_clusters = 10
we can try with ks in range [1..10]
@param laplacian_calculation_type: The type of calculation.
@param store_W: If True the object stores the adjacency matrix. Useful for testing.
@param verbose: If True some messages will be printed.
"""
self.handle_params(kwargs,
max_clusters_default=condensed_matrix.row_length -
1)
print "Initializing Spectral clustering. This may take some time ..."
# self.verbose = True
if self.sigma_sq is not None:
if self.verbose:
print "Calculating W with sigma = %f estimation..." % self.sigma_sq
W = SpectralTools.calculate_fully_connected_adjacency_matrix(
condensed_matrix, self.sigma_sq)
else:
if self.verbose: print "Calculating W with sigma estimation..."
sigmas = SpectralTools.local_sigma_estimation(condensed_matrix)
W = SpectralTools.calculate_fully_connected_adjacency_matrix_with_sigma_estimation(
condensed_matrix, sigmas)
self.sigma_sq = numpy.mean(sigmas)**2
if self.verbose:
print "Sigma^2 estimation (mean of local sigmas): ", self.sigma_sq
if self.force_sparse:
SpectralTools.force_sparsity(W)
if self.store_W:
if self.verbose: print "Storing W ..."
self.W = numpy.copy(W)
if self.verbose: print "Calculating Degree Matrix ..."
D = SpectralTools.calculate_degree_matrix(W)
if self.verbose: print "Calculating Laplacian ..."
L = SpectralTools.calculateUnnormalizedLaplacian(W, D)
if self.verbose: print "Calculating Eigenvectors ..."
if self.spectral_type == "UNNORMALIZED":
v = SpectralTools.calculateUnnormalizedEigenvectors(
L, self.max_clusters, self.force_sparse)
elif self.spectral_type == "NORMALIZED":
v = SpectralTools.calculateNormalizedEigenvectors(
L, D, self.max_clusters, self.force_sparse)
self.eigenvectors = v # eigenvectors in columns. We need the rows of this matrix for the clustering.
if self.verbose: print "Spectral initialization finished."
def __init__(self, condensed_matrix, **kwargs):
"""
Constructor. Calculates the eigenvectors given a dataset distance matrix. The eigenvector distances would be the
common part for clusterings with different k.
@param condensed_matrix: The distance matrix of the dataset.
@param sigma_sq: The squared value of sigma for the adjacency matrix calculation. If None, the value will be automatically
calculated.
@param max_clusters: Maximum number of clusters we will try with this algorithm (for instance with max_clusters = 10
we can try with ks in range [1..10]
@param laplacian_calculation_type: The type of calculation.
@param store_W: If True the object stores the adjacency matrix. Useful for testing.
@param verbose: If True some messages will be printed.
"""
self.handle_params(kwargs, max_clusters_default = condensed_matrix.row_length-1)
print "Initializing Spectral clustering. This may take some time ..."
# self.verbose = True
if self.sigma_sq is not None:
if self.verbose: print "Calculating W with sigma = %f estimation..."%self.sigma_sq
W = SpectralTools.calculate_fully_connected_adjacency_matrix(condensed_matrix, self.sigma_sq)
else:
if self.verbose: print "Calculating W with sigma estimation..."
sigmas = SpectralTools.local_sigma_estimation(condensed_matrix)
W = SpectralTools.calculate_fully_connected_adjacency_matrix_with_sigma_estimation(condensed_matrix, sigmas)
self.sigma_sq = numpy.mean(sigmas)**2
if self.verbose: print "Sigma^2 estimation (mean of local sigmas): ", self.sigma_sq
if self.force_sparse:
SpectralTools.force_sparsity(W)
if self.store_W:
if self.verbose: print "Storing W ..."
self.W = numpy.copy(W)
if self.verbose: print "Calculating Degree Matrix ..."
D = SpectralTools.calculate_degree_matrix(W)
if self.verbose: print "Calculating Laplacian ..."
L = SpectralTools.calculateUnnormalizedLaplacian(W, D)
if self.verbose: print "Calculating Eigenvectors ..."
if self.spectral_type == "UNNORMALIZED":
v = SpectralTools.calculateUnnormalizedEigenvectors(L, self.max_clusters, self.force_sparse)
elif self.spectral_type == "NORMALIZED":
v = SpectralTools.calculateNormalizedEigenvectors(L, D, self.max_clusters, self.force_sparse)
self.eigenvectors = v # eigenvectors in columns. We need the rows of this matrix for the clustering.
if self.verbose: print "Spectral initialization finished."