def check_lil_diags(self):
assert_array_equal(lil_diags([[1,2,3],[4,5],[6]],
[0,1,2],(3,3)).todense(),
[[1,4,6],
[0,2,5],
[0,0,3]])
assert_array_equal(lil_diags([[6],[4,5],[1,2,3]],
[2,1,0],(3,3)).todense(),
[[1,4,6],
[0,2,5],
[0,0,3]])
assert_array_equal(lil_diags([[6,7,8],[4,5],[1,2,3]],
[2,1,0],(3,3)).todense(),
[[1,4,6],
[0,2,5],
[0,0,3]])
assert_array_equal(lil_diags([[1,2,3],[4,5],[6]],
[0,-1,-2],(3,3)).todense(),
[[1,0,0],
[4,2,0],
[6,5,3]])
assert_array_equal(lil_diags([[6,7,8],[4,5]],
[-2,-1],(3,3)).todense(),
[[0,0,0],
[4,0,0],
[6,5,0]])
def smooth(self,verts = None,alpha = 1.0): if self._adj is None : self._compute_neighbours() nverts = len(self.vertices) ns = lil_diags( [1./np.array(self._adj.sum(1)).flatten()],[0],(nverts,nverts) ) reg = ns*self._adj*np.matrix(self.vertices) if verts is None : self.vertices = np.array((1.-alpha)*self.vertices + alpha*reg) else : self.vertices[verts] = (1.-alpha)*self.vertices[verts] + alpha*np.array(reg)[verts]
def buildTransitionMatrix(self):
"""Build Markov transition matrix from the affinity matrix."""
start = time.time()
self._transition = np.dot(
self._affinity,
sparse.lil_diags([1 / np.array(self._affinity.sum(0)).flatten()], [0], [self._n_nodes, self._n_nodes]),
)
LOGGER.debug("Markov transition matrix was built in {0:.2f}s.".format(time.time() - start))
def smooth(self,verts = None,alpha = 1.0): if self._adj is None : self._compute_neighbours() nverts = len(self.vertices) ns = lil_diags( [1./np.array(self._adj.sum(1)).flatten()],[0],(nverts,nverts) ) reg = ns*self._adj*np.matrix(self.vertices) if verts is None : self.vertices = np.array((1.-alpha)*self.vertices + alpha*reg) else : self.vertices[verts] = (1.-alpha)*self.vertices[verts] + alpha*np.array(reg)[verts]
def __init__(self, model_graph, node_sizes, clqs, lattice=False):
"""
Initializes MRF object.
model_graph: Numpy array or Scipy.sparse matrix
A matrix defining the edges between nodes in the network. If
graph[i, j] = 1 there exists a undirected edge from node i to j.
node_sizes: List or Int
A list of the possible number of values a discrete
node can have. If node_sizes[i] = 2, then the discrete node i
can have one of 2 possible values, such as True or False. If
this parameter is passed as an integer, it indicates that all
nodes have the size indicated by the integer.
clqs: List of clique objects (cliques.py)
A list of the cliques in the MRF.
lattice: Bool
Lattice is true if this MRF has a lattice graph structure, and
false otherwise.
"""
"""Assign the input values to their respective internal data members"""
self.lattice = lattice
self.num_nodes = model_graph.shape[0]
self.cliques = clqs
self.node_sizes = node_sizes
"""Convert the graph to a sparse matrix"""
if ((type(model_graph) == type(np.matrix([0]))) or
(type(model_graph) == type(np.array([0])))):
model_graph = sparse.lil_matrix(model_graph)
"""In an MRF, all edges are bi-directional"""
self.model_graph = model_graph - \
sparse.lil_diags([sparse.extract_diagonal(\
model_graph)], [0], (model_graph.shape[0], \
model_graph.shape[0]))\
+ model_graph.T
"""
Obtain elimination order, which is just the input order in the case
of a lattice.
"""
if self.lattice == True:
self.order = range(0, self.model_graph.shape[0])
else:
self.order = graph.topological_sort(self.model_graph)