def gen_er(dicProperties):
np.random.seed()
# initialize graph
graphER = Graph()
nNodes = 0
nEdges = 0
rDens = 0.0
if "Nodes" in dicProperties.keys():
nNodes = dicProperties["Nodes"]
graphER.add_vertex(nNodes)
if "Edges" in dicProperties.keys():
nEdges = dicProperties["Edges"]
rDens = nEdges / float(nNodes**2)
dicProperties["Density"] = rDens
else:
rDens = dicProperties["Density"]
nEdges = int(np.floor(rDens*nNodes**2))
dicProperties["Edges"] = nEdges
else:
nEdges = dicProperties["Edges"]
rDens = dicProperties["Density"]
nNodes = int(np.floor(np.sqrt(nEdges/rDens)))
graphER.add_vertex(nNodes)
dicProperties["Nodes"] = nNodes
# generate edges
numTest,numCurrentEdges = 0,0
while numCurrentEdges != nEdges and numTest < n_MAXTESTS:
lstEdges = np.random.randint(0,nNodes,(nEdges-numCurrentEdges,2))
graphER.add_edge_list(lstEdges)
# remove loops and duplicate edges
remove_self_loops(graphER)
remove_parallel_edges(graphER)
numCurrentEdges = graphER.num_edges()
numTest += 1
graphER.reindex_edges()
nEdges = graphER.num_edges()
rDens = nEdges / float(nNodes**2)
# generate types
rInhibFrac = dicProperties["InhibFrac"]
lstTypesGen = np.random.uniform(0,1,nEdges)
lstTypeLimit = np.full(nEdges,rInhibFrac)
lstIsExcitatory = np.greater(lstTypesGen,lstTypeLimit)
nExc = np.count_nonzero(lstIsExcitatory)
epropType = graphER.new_edge_property("int",np.multiply(2,lstIsExcitatory)-np.repeat(1,nEdges)) # excitatory (True) or inhibitory (False)
graphER.edge_properties["type"] = epropType
# and weights
if dicProperties["Weighted"]:
lstWeights = dicGenWeights[dicProperties["Distribution"]](graphER,dicProperties,nEdges,nExc) # generate the weights
epropW = graphER.new_edge_property("double",lstWeights) # crée la propriété pour stocker les poids
graphER.edge_properties["weight"] = epropW
return graphER
def examine_graph(graph: Graph,
experiment: str,
graphname: str,
real: bool,
directed: bool = True) -> Properties:
vertices = graph.num_vertices()
edges = graph.num_edges()
total_degrees = graph.get_total_degrees(np.arange(vertices))
min_degree = np.min(total_degrees)
max_degree = np.max(total_degrees)
avg_degree = vertex_average(graph, "total")[0]
largest_component = extract_largest_component(
graph, directed=False).num_vertices()
num_islands = np.sum(total_degrees == 0)
cc = global_clustering(graph)[0]
# _degrees, _counts = np.unique(total_degrees, return_counts=True)
# log_degrees = np.log(_degrees)
# log_counts = np.log(_counts)
# regressor = LinearRegression()
# regressor.fit(log_degrees.reshape(-1, 1), log_counts)
# exponent = regressor.coef_[0]
result = powerlaw.Fit(total_degrees,
xmin=1,
discrete=True,
xmax=max_degree)
exponent = -result.alpha
percentile = np.percentile(total_degrees, 95)
# print("Exponent for this graph is: ", exponent)
# print("Using powerlaw package: e = {} xmin = {} xmax = {}".format(
# exponent2, result.xmin, result.xmax))
# print("degrees: {}\ncounts: {}".format(_degrees[:20], _counts[:20]))
return Properties(experiment, graphname, real, vertices, edges, min_degree,
max_degree, avg_degree, largest_component, num_islands,
cc, directed, exponent, percentile)
def create_dict(g: gt.Graph, n_att_name, e_att_name):
node_dict = {n_att_name: {'size': g.num_vertices()}}
# find all the total values
unique_keys = np.unique([g.vp[n_att_name][n] for n in g.vertices()])
for k in unique_keys:
node_dict[n_att_name][k] = set(
[n for n in g.vertices() if (g.vp[n_att_name][n] == k)])
edge_dict = {e_att_name: {'size': int(g.num_edges())}}
# find all the total values
unique_keys = np.unique([g.ep[e_att_name][e] for e in g.edges()])
for k in unique_keys:
edge_dict[e_att_name][k] = set([(e.source(), e.target())
for e in g.edges()
if g.ep[e_att_name][e] == k])
edge_dict[e_att_name][k].update(
set([(e.target(), e.source()) for e in g.edges()
if g.ep[e_att_name][e] == k]))
# mirror_edges = []
# for e in edge_dict[e_att_name][k]:
# mirror_edges.append((e[1], e[0]))
# edge_dict[e_att_name][k].update(mirror_edges)
return node_dict, edge_dict
def main():
"""
Visualizes the research network of KTH as a graph.
"""
start_time = time()
# Create our undirected graph to return.
g = Graph(directed=False)
# The edge properties measuring collaboration.
e_times = g.new_edge_property("float")
# Grouping value for the verticies, verticies are in the same group if the
# have the same value.
v_groups = g.new_vertex_property("int")
# Color the verticies based on their faculties colors.
v_colors = g.new_vertex_property("vector<double>")
db_path = '/home/_/kth/kexet/db/kex.db'
query = """SELECT *
FROM final
WHERE (
name LIKE '%kth%' and
name LIKE '%;%' and
keywords is not null and
year >= 2013 and
ContentType = 'Refereegranskat' and
PublicationType = 'Artikel i tidskrift'
);"""
rows = load.rows(db_path, query)
for row in rows:
nobjs = parse.names(row['name'].split(';'))
graph.add_relation(g, nobjs, e_times, v_colors, v_groups)
g.edge_properties["times"] = e_times
g.vertex_properties["colors"] = v_colors
g.vertex_properties["groups"] = v_groups
log.info(g.num_vertices())
log.info(g.num_edges())
g.save('a.gt')
log.info('graph saved: a.gt')
log.info("db & parse %ss" % round(time() - start_time, 2))
# start_time = time()
# g = load_graph('a.gt')
# log.info("loading %ss" % round(time() - start_time, 2))
draw.largest(g.copy())
draw.radial_highest(g.copy())
draw.sfdp(g.copy())
draw.grouped_sfdp(g.copy())
draw.min_tree(g.copy())
draw.radial_random(g.copy())
draw.hierarchy(g.copy())
draw.minimize_blockmodel(g.copy())
draw.netscience(g.copy())
draw.fruchterman(g.copy())
def largest_strongly_connected_component(self, graph):
from graph_tool import Graph
import graph_tool.all as gt
largest_connected_component = Graph(directed=True)
if not self.is_relationship:
edge_prop_time = largest_connected_component.new_edge_property(
"int")
edge_prop_type = largest_connected_component.new_edge_property(
"string")
for edge in tqdm(graph.edges(data=True)):
e = tuple(edge[:2])
largest_connected_component.add_edge(e[0], e[1])
if not self.is_relationship:
edge_prop_time[e] = edge[-1]["time"]
edge_prop_type[e] = edge[-1]["type"]
largest_connected_component_view = gt.label_largest_component(
largest_connected_component)
largest_connected_component = gt.GraphView(
largest_connected_component,
vfilt=largest_connected_component_view)
print(
"Total nodes {0} in largest strongly connected component.".format(
largest_connected_component.num_vertices()))
print(
"Total edges {0} in largest strongly connected component.".format(
largest_connected_component.num_edges()))
with open(self.output, "w+") as output_file:
for edge in tqdm(largest_connected_component.edges()):
if not self.is_relationship:
output_file.write("{0} {1} {2} {3}\n".format(
edge.source(), edge.target(), edge_prop_time[edge],
edge_prop_type[edge]))
else:
output_file.write("{0} {1}\n".format(
edge.source(), edge.target()))
def mssp(g: graph_tool.Graph, weight_prop: graph_tool.EdgePropertyMap, L,
known_labels):
n = g.num_vertices()
dist_map = np.ones((n, n)) * np.inf
for i, j in itertools.combinations(L, 2):
if known_labels[i] != known_labels[j]:
dist_map[i, j] = graph_tool.topology.shortest_distance(
g, i, j, weight_prop)
i, j = np.unravel_index(dist_map.argmin(), dist_map.shape)
if weight_prop is None:
total_weight = g.num_edges() + 1
else:
total_weight = np.sum(weight_prop.a) + 1
if dist_map[i, j] < total_weight:
path, _ = graph_tool.topology.shortest_path(g, i, j, weight_prop)
mid_point = path[len(path) // 2]
return mid_point
else:
return None
class GraphClass:
#------------#
# Initialize #
#------------#
def __init__ (self, dicProp={"Name": "Graph", "Type": "None", "Weighted": False}, graph=None):
''' init from properties '''
self.dicProperties = deepcopy(dicProp)
self.dicGetProp = { "Reciprocity": get_reciprocity, "Clustering": get_clustering, "Assortativity": get_assortativity,
"Diameter": get_diameter, "SCC": get_num_scc, #"Spectral radius": get_spectral_radius,
"WCC": get_num_wcc, "InhibFrac": get_inhib_frac }
self.dicGenGraph = { "Erdos-Renyi": gen_er, "Free-scale": gen_fs, "EDR": gen_edr }
# create a graph
if graph != None:
# use the one furnished
self.__graph = graph
self.update_prop()
self.bPropToDate = True
elif dicProp["Type"] == "None":
# create an empty graph
self.__graph = Graph()
self.bPropToDate = False
else:
# generate a graph of the requested type
self.__graph = self.dicGenGraph[dicProp["Type"]](self.dicProperties)
self.update_prop()
self.set_name()
self.bPropToDate = True
@classmethod
def from_graph_class(cls, graphToCopy):
''' create new GraphClass instance as a deepcopy of another '''
dicProperties = deepcopy(graphToCopy.get_dict_properties())
gtGraph = graphToCopy.get_graph().copy()
# create
graphClass = cls(dicProperties, gtGraph)
# set state of properties
bPropToDate = deepcopy(graphToCopy.bPropToDate)
bBetwToDate = deepcopy(graphToCopy.bBetwToDate)
graphClass.bPropToDate = bPropToDate
graphClass.bBetwToDate = bBetwToDate
return graphClass
def copy(self):
''' returns a deepcopy of the graphClass instance '''
graphCopy = GraphClass()
graphCopy.set_graph(self.__graph.copy())
graphCopy.update_prop()
graphCopy.set_name(self.dicProperties["Name"]+'_copy')
return graphCopy
#---------------------------#
# Manipulating the gt graph #
#---------------------------#
def set_graph(self, gtGraph):
''' acquire a graph_tool graph as its own '''
if gtGraph.__class__ == Graph:
self.__graph = gtGraph
else:
raise TypeError("The object passed to 'copy_gt_graph' is not a < class 'graph_tool.Graph' > but a {}".format(gtGraph.__class__))
def inhibitory_subgraph(self):
''' create a GraphClass instance which graph contains only
the inhibitory connections of the current instance's graph '''
graph = self.graph.copy()
epropType = graph.new_edge_property("bool",-graph.edge_properties["type"].a+1)
graph.set_edge_filter(epropType)
inhibGraph = GraphClass()
inhibGraph.set_graph(Graph(graph,prune=True))
inhibGraph.set_prop("Weighted", True)
return inhibGraph
def excitatory_subgraph(self):
''' create a GraphClass instance which graph contains only
the excitatory connections of the current instance's graph '''
graph = self.graph.copy()
epropType = graph.new_edge_property("bool",graph.edge_properties["type"].a+1)
graph.set_edge_filter(epropType)
excGraph = GraphClass()
excGraph.set_graph(Graph(graph,prune=True))
excGraph.set_prop("Weighted", True)
return excGraph
#-------------------------#
# Set or update functions #
#-------------------------#
def set_name(self,name=""):
''' set graph name '''
if name != "":
self.dicProperties["Name"] = name
else:
strName = self.dicProperties["Type"]
tplUse = ("Nodes", "Edges", "Distribution")
for key,value in self.dicProperties.items():
if key in tplUse and (value.__class__ != dict):
strName += '_' + key[0] + str(value)
if key == "Clustering":
strName += '_' + key[0] + str(around(value,4))
self.dicProperties["Name"] = strName
print(self.dicProperties["Name"])
def update_prop(self, lstProp=[]):
''' update part or all of the graph properties '''
if lstProp:
for strPropName in lstProp:
if strPropName in self.dicGetProp.keys():
self.dicProperties[strPropName] = self.dicGetProp[strPropName](self.__graph)
else:
print("Ignoring unknown property '{}'".format(strPropName))
else:
self.dicProperties.update({ strPropName: self.dicGetProp[strPropName](self.__graph) for strPropName in self.dicGetProp.keys() })
self.bPropToDate = True
#---------------#
# Get functions #
#---------------#
## basic properties
def get_name(self):
return self.dicProperties["Name"]
def num_vertices(self):
return self.__graph.num_vertices()
def num_edges(self):
return self.__graph.num_edges()
def get_density(self):
return self.__graph.num_edges()/float(self.__graph.num_vertices()**2)
def is_weighted(self):
return self.dicProperties["Weighted"]
## graph and adjacency matrix
def get_graph(self):
self.bPropToDate = False
self.bBetwToDate = False
self.wBetweeness = False
return self.__graph
def get_mat_adjacency(self):
return adjacency(self.__graph, self.get_weights())
## complex properties
def get_prop(self, strPropName):
if strPropName in self.dicProperties.keys():
if not self.bPropToDate:
self.dicProperties[strPropName] = self.dicGetProp[strPropName](self.__graph)
return self.dicProperties[strPropName]
else:
print("Ignoring request for unknown property '{}'".format(strPropName))
def get_dict_properties(self):
return self.dicProperties
def get_degrees(self, strType="total", bWeights=True):
lstValidTypes = ["in", "out", "total"]
if strType in lstValidTypes:
return degree_list(self.__graph, strType, bWeights)
else:
print("Ignoring invalid degree type '{}'".format(strType))
return None
def get_betweenness(self, bWeights=True):
if bWeights:
if not self.bWBetwToDate:
self.wBetweeness = betweenness_list(self.__graph, bWeights)
self.wBetweeness = True
return self.wBetweeness
if not self.bBetwToDate and not bWeights:
self.betweenness = betweenness_list(self.__graph, bWeights)
self.bBetwToDate = True
return self.betweenness
def get_types(self):
if "type" in self.graph.edge_properties.keys():
return self.__graph.edge_properties["type"].a
else:
return repeat(1, self.__graph.num_edges())
def get_weights(self):
if self.dicProperties["Weighted"]:
epropW = self.__graph.edge_properties["weight"].copy()
epropW.a = multiply(epropW.a, self.__graph.edge_properties["type"].a)
return epropW
else:
return self.__graph.edge_properties["type"].copy()
def prepare_hierarchies_neighborhood(
experiments_path: ExperimentPaths,
conceptnet_graph_path: Union[str, Path],
filter_graphs_to_intersected_vertices: bool = True,
) -> pd.DataFrame:
conceptnet_hierarchy_neighborhood_df_path = (
experiments_path.experiment_path /
f"shortest-paths-pairs-{conceptnet_graph_path.stem}-df.pkl")
logger.info("Prepare graphs")
conceptnet_graph, vertices_conceptnet = prepare_conceptnet(
conceptnet_graph_path)
mlflow.log_metric("conceptnet_graph_nodes",
conceptnet_graph.num_vertices())
mlflow.log_metric("conceptnet_graph_edges", conceptnet_graph.num_edges())
aspect_graph, experiment_paths = prepare_aspect_graph(experiments_path)
mlflow.log_metric("aspect_graph_nodes", aspect_graph.num_vertices())
mlflow.log_metric("aspect_graph_edges", aspect_graph.num_edges())
aspect_graph_intersected = Graph(aspect_graph)
conceptnet_graph_intersected = Graph(conceptnet_graph)
aspect_graph_intersected, conceptnet_graph_intersected = intersected_nodes(
aspect_graph=aspect_graph_intersected,
conceptnet_graph=conceptnet_graph_intersected,
filter_graphs_to_intersected_vertices=
filter_graphs_to_intersected_vertices,
property_name="aspect_name",
)
mlflow.log_param("filter_graphs_to_intersected_vertices",
filter_graphs_to_intersected_vertices)
mlflow.log_metric(
"conceptnet_graph_intersected_nodes",
conceptnet_graph_intersected.num_vertices(),
)
mlflow.log_metric("aspect_graph_intersected_nodes",
aspect_graph_intersected.num_vertices())
mlflow.log_metric("conceptnet_graph_intersected_edges",
conceptnet_graph_intersected.num_edges())
mlflow.log_metric("aspect_graph_intersected_edges",
aspect_graph_intersected.num_edges())
aspect_names_intersected = list(
aspect_graph_intersected.vertex_properties["aspect_name"])
vertices_name_to_aspect_vertex = dict(
zip(aspect_graph.vertex_properties["aspect_name"],
aspect_graph.vertices()))
aspect_graph_vertices_intersected = [
vertices_name_to_aspect_vertex[a] for a in aspect_names_intersected
]
shortest_distances_aspect_graph = np.array([
shortest_distance(
g=aspect_graph,
source=v,
target=aspect_graph_vertices_intersected,
directed=True,
) for v in tqdm(aspect_graph_vertices_intersected,
desc="Aspect graph shortest paths...")
])
conceptnet_vertices_intersected = [
vertices_conceptnet[a] for a in aspect_names_intersected
]
mlflow.log_metric("conceptnet_vertices_intersected len",
len(conceptnet_vertices_intersected))
mlflow.log_metric("aspect_graph_vertices_intersected len",
len(aspect_graph_vertices_intersected))
assert len(conceptnet_vertices_intersected) == len(
aspect_graph_vertices_intersected
), "Wrong sequence of vertices in both graphs"
shortest_distances_conceptnet = np.array([
shortest_distance(
g=conceptnet_graph,
source=v,
target=conceptnet_vertices_intersected,
directed=True,
) for v in tqdm(conceptnet_vertices_intersected,
desc="Conceptnet shortest paths...")
])
pairs = []
for aspect_1_idx, aspect_1 in tqdm(enumerate(aspect_names_intersected),
desc="Pairs distances..."):
for aspect_2_idx, aspect_2 in enumerate(aspect_names_intersected):
pairs.append((
aspect_1,
aspect_2,
shortest_distances_aspect_graph[aspect_1_idx][aspect_2_idx],
shortest_distances_conceptnet[aspect_1_idx][aspect_2_idx],
))
pairs_df = pd.DataFrame(
pairs,
columns=[
"aspect_1",
"aspect_2",
"shortest_distance_aspect_graph",
"shortest_distance_conceptnet",
],
)
logger.info("Dump DataFrame with pairs")
pairs_df.to_pickle(conceptnet_hierarchy_neighborhood_df_path.as_posix())
mlflow.log_artifact(conceptnet_hierarchy_neighborhood_df_path.as_posix())
mlflow.log_metric("conceptnet_hierarchy_neighborhood_df_len",
len(pairs_df))
logger.info(
f"DataFrame with pairs dumped in: {experiment_paths.conceptnet_hierarchy_neighborhood.as_posix()}"
)
return pairs_df
class SegmentationGraph(object):
"""
Class defining the abstract SegmentationGraph object, its attributes and
implements methods common to all derived graph classes.
The constructor requires the following parameters of the underlying
segmentation that will be used to build the graph.
"""
def __init__(self):
"""
Constructor of the abstract SegmentationGraph object.
Returns:
None
"""
self.graph = Graph(directed=False)
"""graph_tool.Graph: a graph object storing the segmentation graph
topology, geometry and properties (initially empty).
"""
# Add "internal property maps" to the graph.
# vertex property for storing the xyz coordinates of the corresponding
# vertex:
self.graph.vp.xyz = self.graph.new_vertex_property("vector<float>")
# edge property for storing the distance between the connected vertices:
self.graph.ep.distance = self.graph.new_edge_property("float")
self.coordinates_to_vertex_index = {}
"""dict: a dictionary mapping the vertex coordinates (x, y, z) to the
vertex index.
"""
self.coordinates_pair_connected = set()
"""set: a set storing pairs of vertex coordinates that are
connected by an edge in a tuple form ((x1, y1, z1), (x2, y2, z2)).
"""
@staticmethod
def distance_between_voxels(voxel1, voxel2):
"""
Calculates and returns the Euclidean distance between two voxels.
Args:
voxel1 (tuple): first voxel coordinates in form of a tuple of
floats of length 3 (x1, y1, z1)
voxel2 (tuple): second voxel coordinates in form of a tuple of
floats of length 3 (x2, y2, z2)
Returns:
the Euclidean distance between two voxels (float)
"""
if (isinstance(voxel1, tuple) and (len(voxel1) == 3)
and isinstance(voxel2, tuple) and (len(voxel2) == 3)):
sum_of_squared_differences = 0
for i in range(3): # for each dimension
sum_of_squared_differences += (voxel1[i] - voxel2[i])**2
return math.sqrt(sum_of_squared_differences)
else:
raise pexceptions.PySegInputError(
expr='distance_between_voxels (SegmentationGraph)',
msg=('Tuples of integers of length 3 required as first and '
'second input.'))
def update_coordinates_to_vertex_index(self):
"""
Updates graph's dictionary coordinates_to_vertex_index.
The dictionary maps the vertex coordinates (x, y, z) to the vertex
index. It has to be updated after purging the graph, because vertices
are renumbered, as well as after reading a graph from a file (e.g.
before density calculation).
Returns:
None
"""
self.coordinates_to_vertex_index = {}
for vd in self.graph.vertices():
[x, y, z] = self.graph.vp.xyz[vd]
self.coordinates_to_vertex_index[(x, y,
z)] = self.graph.vertex_index[vd]
def calculate_density(self,
size,
scale,
mask=None,
target_coordinates=None,
verbose=False):
"""
Calculates ribosome density for each membrane graph vertex.
Calculates shortest geodesic distances (d) for each vertex in the graph
to each reachable ribosome center mapped on the membrane given by a
binary mask with coordinates in pixels or an array of coordinates in
given units.
Then, calculates a density measure of ribosomes at each vertex or
membrane voxel: D = sum {over all reachable ribosomes} (1 / (d + 1)).
Adds the density as vertex PropertyMap to the graph. Returns an array
with the same shape as the underlying segmentation with the densities
plus 1, in order to distinguish membrane voxels with 0 density from the
background.
Args:
size (tuple): size in voxels (X, Y, Z) of the original segmentation
scale (tuple): pixel size (X, Y, Z) in given units of the original
segmentation
mask (numpy.ndarray, optional): a binary mask of the ribosome
centers as 3D array where indices are coordinates in pixels
(default None)
target_coordinates (numpy.ndarray, optional): the ribosome centers
coordinates in given units as 2D array in format
[[x1, y1, z1], [x2, y2, z2], ...] (default None)
verbose (boolean, optional): if True (default False), some extra
information will be printed out
Returns:
a 3D numpy ndarray with the densities + 1
Note:
One of the two parameters, mask or target_coordinates, has to be
given.
"""
from . import ribosome_density as rd
# If a mask is given, find the set of voxels of ribosome centers mapped
# on the membrane, 'target_voxels', and rescale them to units,
# 'target_coordinates':
if mask is not None:
if mask.shape != size:
raise pexceptions.PySegInputError(
expr='calculate_density (SegmentationGraph)',
msg=("Size of the input 'mask' have to be equal to those "
"set during the generation of the graph."))
# output as a list of tuples [(x1,y1,z1), (x2,y2,z2), ...] in pixels
target_voxels = rd.get_foreground_voxels_from_mask(mask)
# for rescaling have to convert to an ndarray
target_ndarray_voxels = rd.tupel_list_to_ndarray_voxels(
target_voxels)
# rescale to units, output an ndarray [[x1,y1,z1], [x2,y2,z2], ...]
target_ndarray_coordinates = (target_ndarray_voxels *
np.asarray(scale))
# convert to a list of tuples, which are in units now
target_coordinates = rd.ndarray_voxels_to_tupel_list(
target_ndarray_coordinates)
# If target_coordinates are given (in units), convert them from a numpy
# ndarray to a list of tuples:
elif target_coordinates is not None:
target_coordinates = rd.ndarray_voxels_to_tupel_list(
target_coordinates)
# Exit if the target_voxels list is empty:
if len(target_coordinates) == 0:
raise pexceptions.PySegInputError(
expr='calculate_density (SegmentationGraph)',
msg="No target voxels were found! Check your input ('mask' or "
"'target_coordinates').")
print('{} target voxels'.format(len(target_coordinates)))
if verbose:
print(target_coordinates)
# Pre-filter the target coordinates to those existing in the graph
# (should already all be in the graph, but just in case):
target_coordinates_in_graph = []
for target_xyz in target_coordinates:
if target_xyz in self.coordinates_to_vertex_index:
target_coordinates_in_graph.append(target_xyz)
else:
raise pexceptions.PySegInputWarning(
expr='calculate_density (SegmentationGraph)',
msg=('Target ({}, {}, {}) not inside the membrane!'.format(
target_xyz[0], target_xyz[1], target_xyz[2])))
print('{} target coordinates in graph'.format(
len(target_coordinates_in_graph)))
if verbose:
print(target_coordinates_in_graph)
# Get all indices of the target coordinates:
target_vertices_indices = []
for target_xyz in target_coordinates_in_graph:
v_target_index = self.coordinates_to_vertex_index[target_xyz]
target_vertices_indices.append(v_target_index)
# Density calculation
# Add a new vertex property to the graph, density:
self.graph.vp.density = self.graph.new_vertex_property("float")
# Dictionary mapping voxel coordinates (for the volume returned later)
# to a list of density values falling within that voxel:
voxel_to_densities = {}
# For each vertex in the graph:
for v_membrane in self.graph.vertices():
# Get its coordinates:
membrane_xyz = self.graph.vp.xyz[v_membrane]
if verbose:
print('Membrane vertex ({}, {}, {})'.format(
membrane_xyz[0], membrane_xyz[1], membrane_xyz[2]))
# Get a distance map with all pairs of distances between current
# graph vertex (membrane_xyz) and target vertices (ribosome
# coordinates):
dist_map = shortest_distance(self.graph,
source=v_membrane,
target=target_vertices_indices,
weights=self.graph.ep.distance)
# Iterate over all shortest distances from the membrane vertex to
# the target vertices, while calculating the density:
# Initializing: membrane coordinates with no reachable ribosomes
# will have a value of 0, those with reachable ribosomes > 0.
density = 0
# If there is only one target voxel, dist_map is a single value -
# wrap it into a list.
if len(target_coordinates_in_graph) == 1:
dist_map = [dist_map]
for d in dist_map:
if verbose:
print('\tTarget vertex ...')
# if unreachable, the maximum float64 is stored
if d == np.finfo(np.float64).max:
if verbose:
print('\t\tunreachable')
else:
if verbose:
print('\t\td = {}'.format(d))
density += 1 / (d + 1)
# Add the density of the membrane vertex as a property of the
# current vertex in the graph:
self.graph.vp.density[v_membrane] = density
# Calculate the corresponding voxel of the vertex and add the
# density to the list keyed by the voxel in the dictionary:
# Scaling the coordinates back from units to voxels. (Without round
# float coordinates are truncated to the next lowest integer.)
voxel_x = int(round(membrane_xyz[0] / scale[0]))
voxel_y = int(round(membrane_xyz[1] / scale[1]))
voxel_z = int(round(membrane_xyz[2] / scale[2]))
voxel = (voxel_x, voxel_y, voxel_z)
if voxel in voxel_to_densities:
voxel_to_densities[voxel].append(density)
else:
voxel_to_densities[voxel] = [density]
if verbose:
print('\tdensity = {}'.format(density))
if (self.graph.vertex_index[v_membrane] + 1) % 1000 == 0:
now = datetime.now()
print('{} membrane vertices processed on: {}-{}-{} {}:{}:{}'.
format(self.graph.vertex_index[v_membrane] + 1, now.year,
now.month, now.day, now.hour, now.minute,
now.second))
# Initialize an array scaled like the original segmentation, which will
# hold in each membrane voxel the maximal density among the
# corresponding vertex coordinates in the graph plus 1 and 0 in each
# background (non-membrane) voxel:
densities = np.zeros(size, dtype=np.float16)
# The densities array membrane voxels are initialized with 1 in order to
# distinguish membrane voxels from the background.
for voxel in voxel_to_densities:
densities[voxel[0], voxel[1],
voxel[2]] = 1 + max(voxel_to_densities[voxel])
if verbose:
print('densities:\n{}'.format(densities))
return densities
def graph_to_points_and_lines_polys(self,
vertices=True,
edges=True,
verbose=False):
"""
Generates a VTK PolyData object from the graph with vertices as
vertex-cells (containing 1 point) and edges as line-cells (containing 2
points).
Args:
vertices (boolean, optional): if True (default) vertices are stored
a VTK PolyData object as vertex-cells
edges (boolean, optional): if True (default) edges are stored a VTK
PolyData object as line-cells
verbose (boolean, optional): if True (default False), some extra
information will be printed out
Returns:
- vtk.vtkPolyData with vertex-cells
- vtk.vtkPolyData with edges as line-cells
"""
# Initialization
poly_verts = vtk.vtkPolyData()
poly_lines = vtk.vtkPolyData()
points = vtk.vtkPoints()
vertex_arrays = list()
edge_arrays = list()
# Vertex property arrays
for prop_key in list(self.graph.vp.keys()):
data_type = self.graph.vp[prop_key].value_type()
if (data_type != 'string' and data_type != 'python::object'
and prop_key != 'xyz'):
if verbose:
print('\nvertex property key: {}'.format(prop_key))
print('value type: {}'.format(data_type))
if data_type[0:6] != 'vector': # scalar
num_components = 1
else: # vector
num_components = len(
self.graph.vp[prop_key][self.graph.vertex(0)])
array = TypesConverter().gt_to_vtk(data_type)
array.SetName(prop_key)
if verbose:
print('number of components: {}'.format(num_components))
array.SetNumberOfComponents(num_components)
vertex_arrays.append(array)
# Edge property arrays
for prop_key in list(self.graph.ep.keys()):
data_type = self.graph.ep[prop_key].value_type()
if data_type != 'string' and data_type != 'python::object':
if verbose:
print('\nedge property key: {}'.format(prop_key))
print('value type: {}'.format(data_type))
if data_type[0:6] != 'vector': # scalar
num_components = 1
else: # vector (all edge properties so far are scalars)
# num_components = len(
# self.graph.ep[prop_key][self.graph.edge(0, 1)])
num_components = 3
if verbose:
print('Sorry, not implemented yet, assuming a vector '
'with 3 components.')
array = TypesConverter().gt_to_vtk(data_type)
array.SetName(prop_key)
if verbose:
print('number of components: {}'.format(num_components))
array.SetNumberOfComponents(num_components)
edge_arrays.append(array)
if verbose:
print('\nvertex arrays length: {}'.format(len(vertex_arrays)))
print('edge arrays length: {}'.format(len(edge_arrays)))
# Geometry
lut = np.zeros(shape=self.graph.num_vertices(), dtype=np.int)
for i, vd in enumerate(self.graph.vertices()):
[x, y, z] = self.graph.vp.xyz[vd]
points.InsertPoint(i, x, y, z)
lut[self.graph.vertex_index[vd]] = i
if verbose:
print('number of points: {}'.format(points.GetNumberOfPoints()))
# Topology
# Vertices
verts = vtk.vtkCellArray()
if vertices:
for vd in self.graph.vertices(): # vd = vertex descriptor
verts.InsertNextCell(1)
verts.InsertCellPoint(lut[self.graph.vertex_index[vd]])
for array in vertex_arrays:
prop_key = array.GetName()
n_comp = array.GetNumberOfComponents()
data_type = self.graph.vp[prop_key].value_type()
data_type = TypesConverter().gt_to_numpy(data_type)
array.InsertNextTuple(
self.get_vertex_prop_entry(prop_key, vd, n_comp,
data_type))
if verbose:
print('number of vertex cells: {}'.format(
verts.GetNumberOfCells()))
# Edges
lines = vtk.vtkCellArray()
if edges:
for ed in self.graph.edges(): # ed = edge descriptor
lines.InsertNextCell(2)
lines.InsertCellPoint(
lut[self.graph.vertex_index[ed.source()]])
lines.InsertCellPoint(
lut[self.graph.vertex_index[ed.target()]])
for array in edge_arrays:
prop_key = array.GetName()
n_comp = array.GetNumberOfComponents()
data_type = self.graph.ep[prop_key].value_type()
data_type = TypesConverter().gt_to_numpy(data_type)
array.InsertNextTuple(
self.get_edge_prop_entry(prop_key, ed, n_comp,
data_type))
if verbose:
print('number of line cells: {}'.format(
lines.GetNumberOfCells()))
# vtkPolyData construction
poly_verts.SetPoints(points)
poly_lines.SetPoints(points)
if vertices:
poly_verts.SetVerts(verts)
if edges:
poly_lines.SetLines(lines)
for array in vertex_arrays:
poly_verts.GetCellData().AddArray(array)
for array in edge_arrays:
poly_lines.GetCellData().AddArray(array)
return poly_verts, poly_lines
def get_vertex_prop_entry(self, prop_key, vertex_descriptor, n_comp,
data_type):
"""
Gets a property value of a vertex for inserting into a VTK vtkDataArray
object.
This function is used by the methods graph_to_points_and_lines_polys and
graph_to_triangle_poly (the latter of the derived classes PointGraph and
TriangleGraph (in surface_graphs).
Args:
prop_key (str): name of the desired vertex property
vertex_descriptor (graph_tool.Vertex): vertex descriptor of the
current vertex
n_comp (int): number of components of the array (length of the
output tuple)
data_type: numpy data type converted from a graph-tool property
value type by TypesConverter().gt_to_numpy
Returns:
a tuple (with length like n_comp) with the property value of the
vertex converted to a numpy data type
"""
prop = list()
if n_comp == 1:
prop.append(data_type(self.graph.vp[prop_key][vertex_descriptor]))
else:
for i in range(n_comp):
prop.append(
data_type(self.graph.vp[prop_key][vertex_descriptor][i]))
return tuple(prop)
def get_edge_prop_entry(self, prop_key, edge_descriptor, n_comp,
data_type):
"""
Gets a property value of an edge for inserting into a VTK vtkDataArray
object.
This private function is used by the method
graph_to_points_and_lines_polys.
Args:
prop_key (str): name of the desired vertex property
edge_descriptor (graph_tool.Edge): edge descriptor of the current
edge
n_comp (int): number of components of the array (length of the
output tuple)
data_type: numpy data type converted from a graph-tool property
value type by TypesConverter().gt_to_numpy
Returns:
a tuple (with length like n_comp) with the property value of the
edge converted to a numpy data type
"""
prop = list()
if n_comp == 1:
prop.append(data_type(self.graph.ep[prop_key][edge_descriptor]))
else:
for i in range(n_comp):
prop.append(
data_type(self.graph.ep[prop_key][edge_descriptor][i]))
return tuple(prop)
# * The following SegmentationGraph methods are needed for the normal vector
# voting algorithm. *
def calculate_average_edge_length(self,
prop_e=None,
value=1,
verbose=False):
"""
Calculates the average edge length in the graph.
If a special edge property is specified, includes only the edges where
this property equals the given value. If there are no edges in the
graph, the given property does not exist or there are no edges with the
given property equaling the given value, None is returned.
Args:
prop_e (str, optional): edge property, if specified only edges where
this property equals the given value will be considered
value (int, optional): value of the specified edge property an edge
has to have in order to be considered (default 1)
verbose (boolean, optional): if True (default False), some extra
information will be printed out
Returns:
the average edge length in the graph (float) or None
"""
total_edge_length = 0
average_edge_length = None
if prop_e is None:
if verbose:
print("Considering all edges:")
if self.graph.num_edges() > 0:
if verbose:
print("{} edges".format(self.graph.num_edges()))
average_edge_length = np.mean(self.graph.ep.distance.a)
else:
print("There are no edges in the graph!")
elif prop_e in self.graph.edge_properties:
if verbose:
print("Considering only edges with property {} equaling value "
"{}!".format(prop_e, value))
num_special_edges = 0
for ed in self.graph.edges():
if self.graph.edge_properties[prop_e][ed] == value:
num_special_edges += 1
total_edge_length += self.graph.ep.distance[ed]
if num_special_edges > 0:
if verbose:
print("{} such edges".format(num_special_edges))
average_edge_length = total_edge_length / num_special_edges
else:
print("There are no edges with the property {} equaling value "
"{}!".format(prop_e, value))
if verbose:
print("Average length: {}".format(average_edge_length))
return average_edge_length
def find_geodesic_neighbors(self,
v,
g_max,
full_dist_map=None,
only_surface=False,
verbose=False):
"""
Finds geodesic neighbor vertices of a given vertex v in the graph that
are within a given maximal geodesic distance g_max from it.
Also finds the corresponding geodesic distances. All edges are
considered. The distances are calculated with Dijkstra's algorithm.
Args:
v (graph_tool.Vertex): the source vertex
g_max: maximal geodesic distance (in the units of the graph)
full_dist_map (graph_tool.PropertyMap, optional): the full distance
map for the whole graph; if None, a local distance map is
calculated for each vertex (default)
only_surface (boolean, optional): if True (default False), only
neighbors classified as surface patch (class 1) are considered
verbose (boolean, optional): if True (default False), some extra
information will be printed out
Returns:
a dictionary mapping a neighbor vertex index to the geodesic
distance from vertex v
"""
if full_dist_map is not None:
dist_v = full_dist_map[v].get_array()
else:
dist_v = shortest_distance(self.graph,
source=v,
target=None,
weights=self.graph.ep.distance,
max_dist=g_max)
dist_v = dist_v.get_array()
# numpy array of distances from v to all vertices, in vertex index order
vertex = self.graph.vertex
orientation_class = self.graph.vp.orientation_class
neighbor_id_to_dist = dict()
idxs = np.where(dist_v <= g_max)[0] # others are INF
for idx in idxs:
dist = dist_v[idx]
if dist != 0: # ignore the source vertex itself
v_i = vertex(idx)
if (not only_surface) or orientation_class[v_i] == 1:
neighbor_id_to_dist[idx] = dist
if verbose:
print("{} neighbors".format(len(neighbor_id_to_dist)))
return neighbor_id_to_dist
def find_geodesic_neighbors_exact(self,
o,
g_max,
only_surface=False,
verbose=False,
debug=False):
"""
Finds geodesic neighbor vertices of the origin vertex o in the graph
that are within a given maximal geodesic distance g_max from it.
Also finds the corresponding geodesic distances. All edges and faces are
considered. The distances are calculated with Sun's and Abidi's
algorithm, a simplification of Kimmels' and Sethian's fast marching
algorithm.
Args:
o (graph_tool.Vertex): the source vertex
g_max: maximal geodesic distance (in the units of the graph)
only_surface (boolean, optional): if True (default False), only
neighbors classified as surface patch (class 1) are considered
verbose (boolean, optional): if True (default False), some extra
information will be printed out
debug (boolean, optional): if True (default False), some more extra
information will be printed out
Returns:
a dictionary mapping a neighbor vertex index to the geodesic
distance from vertex o
"""
# Shortcuts
xyz = self.graph.vp.xyz
vertex = self.graph.vertex
orientation_class = self.graph.vp.orientation_class
distance_between_voxels = self.distance_between_voxels
calculate_geodesic_distance = self._calculate_geodesic_distance
insert_geo_dist_vertex_id = self._insert_geo_dist_vertex_id
# Initialization
geo_dist_heap = [] # heap has the smallest geodesic distance first
# dictionaries to keep track which geodesic distance belongs to which
# vertex or vertices and vice versa
geo_dist_to_vertex_ids = {}
vertex_id_to_geo_dist = {}
neighbor_id_to_dist = {} # output dictionary
# Tag the center point (o) as Alive:
self.graph.vp.tag = self.graph.new_vertex_property("string")
tag = self.graph.vp.tag # shortcut
tag[o] = "Alive"
if debug:
print("Vertex o={}: Alive".format(int(o)))
vertex_id_to_geo_dist[int(o)] = 0 # need it for geo. dist. calculation
xyz_o = tuple(xyz[o])
for n in o.all_neighbours():
# Tag all neighboring points of the center point (n) as Close
tag[n] = "Close"
# Geodesic distance in this case = Euclidean between o and n
xyz_n = tuple(xyz[n])
on = distance_between_voxels(xyz_o, xyz_n)
if debug:
print("Vertex n={}: Close with distance {}".format(int(n), on))
heappush(geo_dist_heap, on)
insert_geo_dist_vertex_id(geo_dist_to_vertex_ids, on, int(n))
vertex_id_to_geo_dist[int(n)] = on
# Repeat while the smallest distance is <= g_max
while len(geo_dist_heap) >= 1 and geo_dist_heap[0] <= g_max:
if debug:
print("\n{} distances in heap, first={}".format(
len(geo_dist_heap), geo_dist_heap[0]))
# 1. Change the tag of the point in Close with the smallest
# geodesic distance (a) from Close to Alive
smallest_geo_dist = heappop(geo_dist_heap)
closest_vertices_ids = geo_dist_to_vertex_ids[smallest_geo_dist]
a = vertex(closest_vertices_ids[0])
if len(closest_vertices_ids) > 1: # move the first one (a) to the
# back, so it's not taken again next time
closest_vertices_ids.pop(0)
closest_vertices_ids.append(int(a))
tag[a] = "Alive"
# only proceed if a is a surface patch:
if only_surface and orientation_class[a] != 1:
continue
neighbor_id_to_dist[int(a)] = smallest_geo_dist # add a to output
if debug:
print("Vertex a={}: Alive".format(int(a)))
neighbors_a = set(a.all_neighbours()) # actually don't have
# duplicates, but like this can use fast sets' intersection method
for c in neighbors_a:
# 2. Tag all neighboring points (c) of this point as Close,
# but skip those which are Alive already
if tag[c] == "Alive":
if debug:
print("Skipping Alive neighbor {}".format(int(c)))
continue
tag[c] = "Close"
if debug:
print("Vertex c={}: Close".format(int(c)))
# 3. Recompute the geodesic distance of these neighboring
# points, using only values of points that are Alive, and renew
# it only if the recomputed result is smaller
# Find Alive point b, belonging to the same triangle as a and c:
# iterate over an intersection of the neighbors of a and c
neighbors_c = set(c.all_neighbours())
common_neighbors_a_c = neighbors_a.intersection(neighbors_c)
for b in common_neighbors_a_c:
# check if b is tagged Alive
if tag[b] == "Alive":
if debug:
print("\tUsing vertex b={}".format(int(b)))
new_geo_dist_c = calculate_geodesic_distance(
a,
b,
xyz[c].a,
vertex_id_to_geo_dist,
verbose=verbose)
if int(c) not in vertex_id_to_geo_dist: # add c
if debug:
print("\tadding new distance {}".format(
new_geo_dist_c))
vertex_id_to_geo_dist[int(c)] = new_geo_dist_c
heappush(geo_dist_heap, new_geo_dist_c)
insert_geo_dist_vertex_id(geo_dist_to_vertex_ids,
new_geo_dist_c, int(c))
else:
old_geo_dist_c = vertex_id_to_geo_dist[int(c)]
if new_geo_dist_c < old_geo_dist_c: # update c
if debug:
print(
"\tupdating distance {} to {}".format(
old_geo_dist_c, new_geo_dist_c))
vertex_id_to_geo_dist[int(c)] = new_geo_dist_c
if old_geo_dist_c in geo_dist_heap:
# check because it is sometimes not there
geo_dist_heap.remove(old_geo_dist_c)
heappush(geo_dist_heap, new_geo_dist_c)
old_geo_dist_vertex_ids = geo_dist_to_vertex_ids[
old_geo_dist_c]
if len(old_geo_dist_vertex_ids) == 1:
del geo_dist_to_vertex_ids[old_geo_dist_c]
else:
old_geo_dist_vertex_ids.remove(int(c))
insert_geo_dist_vertex_id(
geo_dist_to_vertex_ids, new_geo_dist_c,
int(c))
elif debug:
print("\tkeeping the old distance={}, because "
"it's <= the new={}".format(
old_geo_dist_c, new_geo_dist_c))
# if debug:
# print(geo_dist_heap)
# print(geo_dist_to_vertex_ids)
# print(vertex_id_to_geo_dist)
# print(neighbor_id_to_dist)
break # one Alive b is expected, stop iteration
else:
if debug:
print("\tNo common neighbors of a and c are Alive")
del self.graph.vertex_properties["tag"]
if debug:
print("Vertex o={} has {} geodesic neighbors".format(
int(o), len(neighbor_id_to_dist)))
if verbose:
print("{} neighbors".format(len(neighbor_id_to_dist)))
return neighbor_id_to_dist
def _calculate_geodesic_distance(self,
a,
b,
xyz_c,
vertex_id_to_geo_dist,
verbose=False):
geo_dist_a = vertex_id_to_geo_dist[int(a)]
geo_dist_b = vertex_id_to_geo_dist[int(b)]
xyz_a = self.graph.vp.xyz[a].a
xyz_b = self.graph.vp.xyz[b].a
ab = euclidean_distance(xyz_a, xyz_b)
ac = euclidean_distance(xyz_a, xyz_c)
bc = euclidean_distance(xyz_b, xyz_c)
# maybe faster to use linalg.euclidean_distance directly on np.ndarrays
alpha = nice_acos((ab**2 + ac**2 - bc**2) / (2 * ab * ac))
beta = nice_acos((ab**2 + bc**2 - ac**2) / (2 * ab * bc))
if alpha < (math.pi / 2) and beta < (math.pi / 2):
if verbose:
print("\ttriangle abc is acute")
theta = nice_acos((geo_dist_a**2 + ab**2 - geo_dist_b**2) /
(2 * ab * geo_dist_a))
geo_dist_c = math.sqrt(ac**2 + geo_dist_a**2 - 2 * ac *
geo_dist_a * math.cos(alpha + theta))
else:
if verbose:
print("\ttriangle abc is obtuse")
geo_dist_c = min(geo_dist_a + ac, geo_dist_b + bc)
return geo_dist_c
@staticmethod
def _insert_geo_dist_vertex_id(geo_dist_to_vertices, geo_dist, vertex_ind):
if geo_dist in geo_dist_to_vertices:
geo_dist_to_vertices[geo_dist].append(vertex_ind)
else:
geo_dist_to_vertices[geo_dist] = [vertex_ind]
def get_vertex_property_array(self, property_name):
"""
Gets a numpy array with all values of a vertex property of the graph,
printing out the number of values, the minimal and the maximal value.
Args:
property_name (str): vertex property name
Returns:
an array (numpy.ndarray) with all values of the vertex property
"""
if (isinstance(property_name, str)
and property_name in self.graph.vertex_properties):
values = np.array(
self.graph.vertex_properties[property_name].get_array())
print('{} "{}" values'.format(len(values), property_name))
print('min = {}, max = {}, mean = {}'.format(
min(values), max(values), np.mean(values)))
return values
else:
raise pexceptions.PySegInputError(
expr='get_vertex_property_array (SegmentationGraph)',
msg=('The input "{}" is not a str object or is not found in '
'vertex properties of the graph.'.format(property_name)))
def build_graph(df_list, sens='ST', top=410, min_sens=0.01, edge_cutoff=0.0):
"""
Initializes and constructs a graph where vertices are the parameters
selected from the first dataframe in 'df_list', subject to the
constraints set by 'sens', 'top', and 'min_sens'. Edges are the second
order sensitivities of the interactions between those vertices,
with sensitivities greater than 'edge_cutoff'.
Parameters
-----------
df_list : list
A list of two dataframes. The first dataframe should be
the first/total order sensitivities collected by the
function data_processing.get_sa_data().
sens : str, optional
A string with the name of the sensitivity that you would
like to use for the vertices ('ST' or 'S1').
top : int, optional
An integer specifying the number of vertices to display (
the top sensitivity values).
min_sens : float, optional
A float with the minimum sensitivity to allow in the graph.
edge_cutoff : float, optional
A float specifying the minimum second order sensitivity to
show as an edge in the graph.
Returns
--------
g : graph-tool object
a graph-tool graph object of the network described above. Each
vertex has properties 'param', 'sensitivity', and 'confidence'
corresponding to the name of the parameter, value of the sensitivity
index, and it's confidence interval. The only edge property is
'second_sens', the second order sensitivity index for the
interaction between the two vertices it connects.
"""
# get the first/total index dataframe and second order dataframe
df = df_list[0]
df2 = df_list[1]
# Make sure sens is ST or S1
if sens not in set(['ST', 'S1']):
raise ValueError('sens must be ST or S1')
# Make sure that there is a second order index dataframe
try:
if not df2:
raise Exception('Missing second order dataframe!')
except:
pass
# slice the dataframes so the resulting graph will only include the top
# 'top' values of 'sens' greater than 'min_sens'.
df = df.sort_values(sens, ascending=False)
df = df.ix[df[sens] > min_sens, :].head(top)
df = df.reset_index()
# initialize a graph
g = Graph()
vprop_sens = g.new_vertex_property('double')
vprop_conf = g.new_vertex_property('double')
vprop_name = g.new_vertex_property('string')
eprop_sens = g.new_edge_property('double')
g.vertex_properties['param'] = vprop_name
g.vertex_properties['sensitivity'] = vprop_sens
g.vertex_properties['confidence'] = vprop_conf
g.edge_properties['second_sens'] = eprop_sens
# keep a list of all the vertices
v_list = []
# Add the vertices to the graph
for i, param in enumerate(df['Parameter']):
v = g.add_vertex()
vprop_sens[v] = df.ix[i, sens]
vprop_conf[v] = 1 + df.ix[i, '%s_conf' % sens] / df.ix[i, sens]
vprop_name[v] = param
v_list.append(v)
# Make two new columns in second order dataframe that point to the vertices
# connected on each row.
df2['vertex1'] = -999
df2['vertex2'] = -999
for vertex in v_list:
param = g.vp.param[vertex]
df2.ix[df2['Parameter_1'] == param, 'vertex1'] = vertex
df2.ix[df2['Parameter_2'] == param, 'vertex2'] = vertex
# Only allow edges for vertices that we've defined
df_edges = df2[(df2['vertex1'] != -999) & (df2['vertex2'] != -999)]
# eliminate edges below a certain cutoff value
pruned = df_edges[df_edges['S2'] > edge_cutoff]
pruned.reset_index(inplace=True)
# Add the edges for the graph
for i, sensitivity in enumerate(pruned['S2']):
v1 = pruned.ix[i, 'vertex1']
v2 = pruned.ix[i, 'vertex2']
e = g.add_edge(v1, v2)
# multiply by a number to make the lines visible on the plot
eprop_sens[e] = sensitivity * 150
# These are ways you can reference properties of vertices or edges
# g.vp.param[g.vertex(77)]
# g.vp.param[v_list[0]]
print('Created a graph with %s vertices and %s edges.\nVertices are the '
'top %s %s values greater than %s.\nOnly S2 values (edges) '
'greater than %s are included.' %
(g.num_vertices(), g.num_edges(), top, sens, min_sens, edge_cutoff))
return g
def build_graph(df_list, sens='ST', top=410, min_sens=0.01,
edge_cutoff=0.0):
"""
Initializes and constructs a graph where vertices are the parameters
selected from the first dataframe in 'df_list', subject to the
constraints set by 'sens', 'top', and 'min_sens'. Edges are the second
order sensitivities of the interactions between those vertices,
with sensitivities greater than 'edge_cutoff'.
Parameters
-----------
df_list : list
A list of two dataframes. The first dataframe should be
the first/total order sensitivities collected by the
function data_processing.get_sa_data().
sens : str, optional
A string with the name of the sensitivity that you would
like to use for the vertices ('ST' or 'S1').
top : int, optional
An integer specifying the number of vertices to display (
the top sensitivity values).
min_sens : float, optional
A float with the minimum sensitivity to allow in the graph.
edge_cutoff : float, optional
A float specifying the minimum second order sensitivity to
show as an edge in the graph.
Returns
--------
g : graph-tool object
a graph-tool graph object of the network described above. Each
vertex has properties 'param', 'sensitivity', and 'confidence'
corresponding to the name of the parameter, value of the sensitivity
index, and it's confidence interval. The only edge property is
'second_sens', the second order sensitivity index for the
interaction between the two vertices it connects.
"""
# get the first/total index dataframe and second order dataframe
df = df_list[0]
df2 = df_list[1]
# Make sure sens is ST or S1
if sens not in set(['ST', 'S1']):
raise ValueError('sens must be ST or S1')
# Make sure that there is a second order index dataframe
try:
if not df2:
raise Exception('Missing second order dataframe!')
except:
pass
# slice the dataframes so the resulting graph will only include the top
# 'top' values of 'sens' greater than 'min_sens'.
df = df.sort_values(sens, ascending=False)
df = df.ix[df[sens] > min_sens, :].head(top)
df = df.reset_index()
# initialize a graph
g = Graph()
vprop_sens = g.new_vertex_property('double')
vprop_conf = g.new_vertex_property('double')
vprop_name = g.new_vertex_property('string')
eprop_sens = g.new_edge_property('double')
g.vertex_properties['param'] = vprop_name
g.vertex_properties['sensitivity'] = vprop_sens
g.vertex_properties['confidence'] = vprop_conf
g.edge_properties['second_sens'] = eprop_sens
# keep a list of all the vertices
v_list = []
# Add the vertices to the graph
for i, param in enumerate(df['Parameter']):
v = g.add_vertex()
vprop_sens[v] = df.ix[i, sens]
vprop_conf[v] = 1 + df.ix[i, '%s_conf' % sens] / df.ix[i, sens]
vprop_name[v] = param
v_list.append(v)
# Make two new columns in second order dataframe that point to the vertices
# connected on each row.
df2['vertex1'] = -999
df2['vertex2'] = -999
for vertex in v_list:
param = g.vp.param[vertex]
df2.ix[df2['Parameter_1'] == param, 'vertex1'] = vertex
df2.ix[df2['Parameter_2'] == param, 'vertex2'] = vertex
# Only allow edges for vertices that we've defined
df_edges = df2[(df2['vertex1'] != -999) & (df2['vertex2'] != -999)]
# eliminate edges below a certain cutoff value
pruned = df_edges[df_edges['S2'] > edge_cutoff]
pruned.reset_index(inplace=True)
# Add the edges for the graph
for i, sensitivity in enumerate(pruned['S2']):
v1 = pruned.ix[i, 'vertex1']
v2 = pruned.ix[i, 'vertex2']
e = g.add_edge(v1, v2)
# multiply by a number to make the lines visible on the plot
eprop_sens[e] = sensitivity * 150
# These are ways you can reference properties of vertices or edges
# g.vp.param[g.vertex(77)]
# g.vp.param[v_list[0]]
print ('Created a graph with %s vertices and %s edges.\nVertices are the '
'top %s %s values greater than %s.\nOnly S2 values (edges) '
'greater than %s are included.' %
(g.num_vertices(), g.num_edges(), top, sens, min_sens, edge_cutoff))
return g
def evaluate_sampling(self, full_graph: Graph, sampled_graph: Graph,
full_partition: BlockState,
sampled_graph_partition: BlockState,
block_mapping: Dict[int, int],
vertex_mapping: Dict[int,
int], assignment: np.ndarray):
"""Evaluates the goodness of the samples.
Parameters
----------
full_graph : Graph
the full, unsampled Graph object
sampled_graph : Graph
the sampled graph
full_partition : Partition
the partitioning results on the full graph
sampled_graph_partition : Partition
the partitioning results on the sampled graph
block_mapping : Dict[int, int]
the mapping of blocks from the full graph to the sampled graph
vertex_mapping : Dict[int, int]
the mapping of vertices from the full graph to the sampled graph
assignment : np.ndarray[int]
the true vertex-to-community mapping
"""
#####
# General
#####
self.sampled_graph_num_vertices = sampled_graph.num_vertices()
self.sampled_graph_num_edges = sampled_graph.num_edges()
self.blocks_retained = sampled_graph_partition.get_B(
) / full_partition.get_B()
# pseudo_diameter returns a tuple: (diameter, (start_vertex, end_vertex))
self.sampled_graph_diameter = pseudo_diameter(sampled_graph)[0]
self.full_graph_diameter = pseudo_diameter(full_graph)[0]
for vertex in sampled_graph.vertices():
if (vertex.in_degree() + vertex.out_degree()) == 0:
self.sampled_graph_island_vertices += 1
self.sampled_graph_largest_component = extract_largest_component(
sampled_graph, directed=False).num_vertices()
self.full_graph_largest_component = extract_largest_component(
full_graph, directed=False).num_vertices()
######
# Expansion quality (http://portal.acm.org/citation.cfm?doid=1772690.1772762)
######
# Expansion factor = Neighbors of sample / size of sample
# Maximum expansion factor = (size of graph - size of sample) / size of sample
# Expansion quality = Neighbors of sample / (size of graph - size of sample)
# Expansion quality = 1 means sample is at most 1 edge away from entire graph
sampled_graph_vertices = set(vertex_mapping.keys())
neighbors = set()
for vertex in sampled_graph_vertices:
for neighbor in full_graph.get_out_neighbors(vertex):
neighbors.add(neighbor)
neighbors = neighbors - sampled_graph_vertices
self.expansion_quality = len(neighbors) / (
full_graph.num_vertices() - sampled_graph.num_vertices())
######
# Clustering coefficient
######
self.sampled_graph_clustering_coefficient = global_clustering(
sampled_graph)[0]
self.full_graph_clustering_coefficient = global_clustering(
full_graph)[0]
######
# Info on communities
######
self.get_community_details(
assignment,
full_partition.get_blocks().get_array(),
sampled_graph_partition.get_blocks().get_array(), vertex_mapping)
if np.unique(
assignment
).size == 1: # Cannot compute below metrics if no true partition is provided
return
#####
# % difference in ratio of within-block to between-block edges
#####
sample_assignment = assignment[np.fromiter(vertex_mapping.keys(),
dtype=np.int32)]
true_sampled_graph_partition = partition_from_truth(
sampled_graph, sample_assignment)
sampled_graph_blockmatrix = true_sampled_graph_partition.get_matrix()
self.sampled_graph_edge_ratio = sampled_graph_blockmatrix.diagonal(
).sum() / sampled_graph_blockmatrix.sum()
true_full_partition = partition_from_truth(full_graph, assignment)
full_blockmatrix = true_full_partition.get_matrix()
self.graph_edge_ratio = full_blockmatrix.diagonal().sum(
) / full_blockmatrix.sum()
#####
# Normalized difference from ideal-block membership
#####
membership_size = max(np.max(assignment),
np.max(sample_assignment)) + 1
full_graph_membership_nums = np.zeros(membership_size)
for block_membership in assignment:
full_graph_membership_nums[block_membership] += 1
sampled_graph_membership_nums = np.zeros(membership_size)
for block_membership in sample_assignment:
sampled_graph_membership_nums[block_membership] += 1
ideal_block_membership_nums = full_graph_membership_nums * \
(sampled_graph.num_vertices() / full_graph.num_vertices())
difference_from_ideal_block_membership_nums = np.abs(
ideal_block_membership_nums - sampled_graph_membership_nums)
self.difference_from_ideal_sample = np.sum(
difference_from_ideal_block_membership_nums /
sampled_graph.num_vertices())
class SegmentationGraph(object):
"""
Class defining the abstract SegmentationGraph object, its attributes and
implements methods common to all derived graph classes.
The constructor requires the following parameters of the underlying
segmentation that will be used to build the graph.
Args:
scale_factor_to_nm (float): pixel size in nanometers for scaling the
graph
scale_x (int): x axis length in pixels of the segmentation
scale_y (int): y axis length in pixels of the segmentation
scale_z (int): z axis length in pixels of the segmentation
"""
def __init__(self, scale_factor_to_nm, scale_x, scale_y, scale_z):
"""
Constructor.
Args:
scale_factor_to_nm (float): pixel size in nanometers for scaling the
graph
scale_x (int): x axis length in pixels of the segmentation
scale_y (int): y axis length in pixels of the segmentation
scale_z (int): z axis length in pixels of the segmentation
Returns:
None
"""
self.graph = Graph(directed=False)
"""graph_tool.Graph: a graph object storing the segmentation graph
topology, geometry and properties.
"""
self.scale_factor_to_nm = scale_factor_to_nm
"""float: pixel size in nanometers for scaling the coordinates and
distances in the graph
"""
self.scale_x = scale_x
"""int: x axis length in pixels of the segmentation"""
self.scale_y = scale_y
"""int: y axis length in pixels of the segmentation"""
self.scale_z = scale_z
"""int: z axis length in pixels of the segmentation"""
# Add "internal property maps" to the graph.
# vertex property for storing the xyz coordinates in nanometers of the
# corresponding vertex:
self.graph.vp.xyz = self.graph.new_vertex_property("vector<float>")
# edge property for storing the distance in nanometers between the
# connected vertices:
self.graph.ep.distance = self.graph.new_edge_property("float")
self.coordinates_to_vertex_index = {}
"""dist: a dictionary mapping the vertex coordinates in nanometers
(x, y, z) to the vertex index.
"""
self.coordinates_pair_connected = {}
"""dict: a dictionary storing pairs of vertex coordinates in nanometers
that are connected by an edge as a key in a tuple form
((x1, y1, z1), (x2, y2, z2)) with value True.
"""
@staticmethod
def distance_between_voxels(voxel1, voxel2):
"""
Calculates and returns the Euclidean distance between two voxels.
Args:
voxel1 (tuple): first voxel coordinates in form of a tuple of
integers of length 3 (x1, y1, z1)
voxel2 (tuple): second voxel coordinates in form of a tuple of
integers of length 3 (x2, y2, z2)
Returns:
the Euclidean distance between two voxels (float)
"""
if (isinstance(voxel1, tuple) and (len(voxel1) == 3) and
isinstance(voxel2, tuple) and (len(voxel2) == 3)):
sum_of_squared_differences = 0
for i in range(3): # for each dimension
sum_of_squared_differences += (voxel1[i] - voxel2[i]) ** 2
return math.sqrt(sum_of_squared_differences)
else:
error_msg = ('Tuples of integers of length 3 required as first and '
'second input.')
raise pexceptions.PySegInputError(
expr='distance_between_voxels (SegmentationGraph)',
msg=error_msg
)
def update_coordinates_to_vertex_index(self):
"""
Updates graph's dictionary coordinates_to_vertex_index.
The dictionary maps the vertex coordinates (x, y, z) scaled in
nanometers to the vertex index. It has to be updated after purging the
graph, because vertices are renumbered, as well as after reading a graph
from a file (e.g. before density calculation).
Returns:
None
"""
self.coordinates_to_vertex_index = {}
for vd in self.graph.vertices():
[x, y, z] = self.graph.vp.xyz[vd]
self.coordinates_to_vertex_index[
(x, y, z)] = self.graph.vertex_index[vd]
def calculate_density(self, mask=None, target_coordinates=None,
verbose=False):
"""
Calculates ribosome density for each membrane graph vertex.
Calculates shortest geodesic distances (d) for each vertex in the graph
to each reachable ribosome center mapped on the membrane given by a
binary mask with coordinates in pixels or an array of coordinates in nm.
Then, calculates a density measure of ribosomes at each vertex or
membrane voxel: D = sum {over all reachable ribosomes} (1 / (d + 1)).
Adds the density as vertex PropertyMap to the graph. Returns an array
with the same shape as the underlying segmentation with the densities
plus 1, in order to distinguish membrane voxels with 0 density from the
background.
Args:
mask (numpy.ndarray, optional): a binary mask of the ribosome
centers as 3D array where indices are coordinates in pixels
(default None)
target_coordinates (numpy.ndarray, optional): the ribosome centers
coordinates in nm as 2D array in format
[[x1, y1, z1], [x2, y2, z2], ...] (default None)
verbose (boolean, optional): if True (default False), some extra
information will be printed out
Returns:
a 3D numpy ndarray with the densities + 1
Note:
One of the first two parameters, mask or target_coordinates, has to
be given.
"""
import ribosome_density as rd
# If a mask is given, find the set of voxels of ribosome centers mapped
# on the membrane, 'target_voxels', and rescale them to nm,
# 'target_coordinates':
if mask is not None:
if mask.shape != (self.scale_x, self.scale_y, self.scale_z):
error_msg = ("Scales of the input 'mask' have to be equal to "
"those set during the generation of the graph.")
raise pexceptions.PySegInputError(
expr='calculate_density (SegmentationGraph)', msg=error_msg
)
# output as a list of tuples [(x1,y1,z1), (x2,y2,z2), ...] in pixels
target_voxels = rd.get_foreground_voxels_from_mask(mask)
# for rescaling have to convert to an ndarray
target_ndarray_voxels = rd.tupel_list_to_ndarray_voxels(
target_voxels
)
# rescale to nm, output an ndarray [[x1,y1,z1], [x2,y2,z2], ...]
target_ndarray_coordinates = (target_ndarray_voxels
* self.scale_factor_to_nm)
# convert to a list of tuples, which are in nm now
target_coordinates = rd.ndarray_voxels_to_tupel_list(
target_ndarray_coordinates
)
# If target_coordinates are given (in nm), convert them from a numpy
# ndarray to a list of tuples:
elif target_coordinates is not None:
target_coordinates = rd.ndarray_voxels_to_tupel_list(
target_coordinates
)
# Exit if the target_voxels list is empty:
if len(target_coordinates) == 0:
error_msg = ("No target voxels were found! Check your input "
"('mask' or 'target_coordinates').")
raise pexceptions.PySegInputError(
expr='calculate_density (SegmentationGraph)', msg=error_msg
)
print '%s target voxels' % len(target_coordinates)
if verbose:
print target_coordinates
# Pre-filter the target coordinates to those existing in the graph
# (should already all be in the graph, but just in case):
target_coordinates_in_graph = []
for target_xyz in target_coordinates:
if target_xyz in self.coordinates_to_vertex_index:
target_coordinates_in_graph.append(target_xyz)
else:
error_msg = ('Target (%s, %s, %s) not inside the membrane!'
% (target_xyz[0], target_xyz[1], target_xyz[2]))
raise pexceptions.PySegInputWarning(
expr='calculate_density (SegmentationGraph)', msg=error_msg
)
print '%s target coordinates in graph' % len(
target_coordinates_in_graph)
if verbose:
print target_coordinates_in_graph
# Get all indices of the target coordinates:
target_vertices_indices = []
for target_xyz in target_coordinates_in_graph:
v_target_index = self.coordinates_to_vertex_index[target_xyz]
target_vertices_indices.append(v_target_index)
# Density calculation
# Add a new vertex property to the graph, density:
self.graph.vp.density = self.graph.new_vertex_property("float")
# Dictionary mapping voxel coordinates (for the volume returned later)
# to a list of density values falling within that voxel:
voxel_to_densities = {}
# For each vertex in the graph:
for v_membrane in self.graph.vertices():
# Get its coordinates:
membrane_xyz = self.graph.vp.xyz[v_membrane]
if verbose:
print ('Membrane vertex (%s, %s, %s)'
% (membrane_xyz[0], membrane_xyz[1], membrane_xyz[2]))
# Get a distance map with all pairs of distances between current
# graph vertex (membrane_xyz) and target vertices (ribosome
# coordinates):
dist_map = shortest_distance(self.graph, source=v_membrane,
target=target_vertices_indices,
weights=self.graph.ep.distance)
# Iterate over all shortest distances from the membrane vertex to
# the target vertices, while calculating the density:
# Initializing: membrane coordinates with no reachable ribosomes
# will have a value of 0, those with reachable ribosomes > 0.
density = 0
# If there is only one target voxel, dist_map is a single value -
# wrap it into a list.
if len(target_coordinates_in_graph) == 1:
dist_map = [dist_map]
for d in dist_map:
if verbose:
print '\tTarget vertex ...'
# if unreachable, the maximum float64 is stored
if d == np.finfo(np.float64).max:
if verbose:
print '\t\tunreachable'
else:
if verbose:
print '\t\td = %s' % d
density += 1 / (d + 1)
# Add the density of the membrane vertex as a property of the
# current vertex in the graph:
self.graph.vp.density[v_membrane] = density
# Calculate the corresponding voxel of the vertex and add the
# density to the list keyed by the voxel in the dictionary:
# Scaling the coordinates back from nm to voxels. (Without round
# float coordinates are truncated to the next lowest integer.)
voxel_x = int(round(membrane_xyz[0] / self.scale_factor_to_nm))
voxel_y = int(round(membrane_xyz[1] / self.scale_factor_to_nm))
voxel_z = int(round(membrane_xyz[2] / self.scale_factor_to_nm))
voxel = (voxel_x, voxel_y, voxel_z)
if voxel in voxel_to_densities:
voxel_to_densities[voxel].append(density)
else:
voxel_to_densities[voxel] = [density]
if verbose:
print '\tdensity = %s' % density
if (self.graph.vertex_index[v_membrane] + 1) % 1000 == 0:
now = datetime.now()
print ('%s membrane vertices processed on: %s-%s-%s %s:%s:%s'
% (self.graph.vertex_index[v_membrane] + 1, now.year,
now.month, now.day, now.hour, now.minute, now.second))
# Initialize an array scaled like the original segmentation, which will
# hold in each membrane voxel the maximal density among the
# corresponding vertex coordinates in the graph plus 1 and 0 in each
# background (non-membrane) voxel:
densities = np.zeros((self.scale_x, self.scale_y, self.scale_z),
dtype=np.float16)
# The densities array membrane voxels are initialized with 1 in order to
# distinguish membrane voxels from the background.
for voxel in voxel_to_densities:
densities[voxel[0], voxel[1], voxel[2]] = 1 + max(
voxel_to_densities[voxel])
if verbose:
print 'densities:\n%s' % densities
return densities
def graph_to_points_and_lines_polys(self, vertices=True, edges=True,
verbose=False):
"""
Generates a VTK PolyData object from the graph with vertices as
vertex-cells (containing 1 point) and edges as line-cells (containing 2
points).
Args:
vertices (boolean, optional): if True (default) vertices are stored
a VTK PolyData object as vertex-cells
edges (boolean, optional): if True (default) edges are stored a VTK
PolyData object as line-cells
verbose (boolean, optional): if True (default False), some extra
information will be printed out
Returns:
- vtk.vtkPolyData with vertex-cells
- vtk.vtkPolyData with edges as line-cells
"""
# Initialization
poly_verts = vtk.vtkPolyData()
poly_lines = vtk.vtkPolyData()
points = vtk.vtkPoints()
vertex_arrays = list()
edge_arrays = list()
# Vertex property arrays
for prop_key in self.graph.vp.keys():
data_type = self.graph.vp[prop_key].value_type()
if (data_type != 'string' and data_type != 'python::object' and
prop_key != 'xyz'):
if verbose:
print '\nvertex property key: %s' % prop_key
print 'value type: %s' % data_type
if data_type[0:6] != 'vector': # scalar
num_components = 1
else: # vector
num_components = len(
self.graph.vp[prop_key][self.graph.vertex(0)]
)
array = TypesConverter().gt_to_vtk(data_type)
array.SetName(prop_key)
if verbose:
print 'number of components: %s' % num_components
array.SetNumberOfComponents(num_components)
vertex_arrays.append(array)
# Edge property arrays
for prop_key in self.graph.ep.keys():
data_type = self.graph.ep[prop_key].value_type()
if data_type != 'string' and data_type != 'python::object':
if verbose:
print '\nedge property key: %s' % prop_key
print 'value type: %s' % data_type
if data_type[0:6] != 'vector': # scalar
num_components = 1
else: # vector (all edge properties so far are scalars)
# num_components = len(
# self.graph.ep[prop_key][self.graph.edge(0, 1)]
# )
num_components = 3
if verbose:
print ('Sorry, not implemented yet, assuming a vector '
'with 3 components.')
array = TypesConverter().gt_to_vtk(data_type)
array.SetName(prop_key)
if verbose:
print 'number of components: %s' % num_components
array.SetNumberOfComponents(num_components)
edge_arrays.append(array)
if verbose:
print '\nvertex arrays length: %s' % len(vertex_arrays)
print 'edge arrays length: %s' % len(edge_arrays)
# Geometry
lut = np.zeros(shape=self.graph.num_vertices(), dtype=np.int)
for i, vd in enumerate(self.graph.vertices()):
[x, y, z] = self.graph.vp.xyz[vd]
points.InsertPoint(i, x, y, z)
lut[self.graph.vertex_index[vd]] = i
if verbose:
print 'number of points: %s' % points.GetNumberOfPoints()
# Topology
# Vertices
verts = vtk.vtkCellArray()
if vertices:
for vd in self.graph.vertices(): # vd = vertex descriptor
verts.InsertNextCell(1)
verts.InsertCellPoint(lut[self.graph.vertex_index[vd]])
for array in vertex_arrays:
prop_key = array.GetName()
n_comp = array.GetNumberOfComponents()
data_type = self.graph.vp[prop_key].value_type()
data_type = TypesConverter().gt_to_numpy(data_type)
array.InsertNextTuple(self.get_vertex_prop_entry(
prop_key, vd, n_comp, data_type))
if verbose:
print 'number of vertex cells: %s' % verts.GetNumberOfCells()
# Edges
lines = vtk.vtkCellArray()
if edges:
for ed in self.graph.edges(): # ed = edge descriptor
lines.InsertNextCell(2)
lines.InsertCellPoint(lut[self.graph.vertex_index[ed.source()]])
lines.InsertCellPoint(lut[self.graph.vertex_index[ed.target()]])
for array in edge_arrays:
prop_key = array.GetName()
n_comp = array.GetNumberOfComponents()
data_type = self.graph.ep[prop_key].value_type()
data_type = TypesConverter().gt_to_numpy(data_type)
array.InsertNextTuple(self.get_edge_prop_entry(
prop_key, ed, n_comp, data_type))
if verbose:
print 'number of line cells: %s' % lines.GetNumberOfCells()
# vtkPolyData construction
poly_verts.SetPoints(points)
poly_lines.SetPoints(points)
if vertices:
poly_verts.SetVerts(verts)
if edges:
poly_lines.SetLines(lines)
for array in vertex_arrays:
poly_verts.GetCellData().AddArray(array)
for array in edge_arrays:
poly_lines.GetCellData().AddArray(array)
return poly_verts, poly_lines
def get_vertex_prop_entry(self, prop_key, vertex_descriptor, n_comp,
data_type):
"""
Gets a property value of a vertex for inserting into a VTK vtkDataArray
object.
This private function is used by the methods
graph_to_points_and_lines_polys and graph_to_triangle_poly (the latter
of the derived class surface_graphs.TriangleGraph).
Args:
prop_key (str): name of the desired vertex property
vertex_descriptor (graph_tool.Vertex): vertex descriptor of the
current vertex
n_comp (int): number of components of the array (length of the
output tuple)
data_type: numpy data type converted from a graph-tool property
value type by TypesConverter().gt_to_numpy
Returns:
a tuple (with length like n_comp) with the property value of the
vertex converted to a numpy data type
"""
prop = list()
if n_comp == 1:
prop.append(data_type(self.graph.vp[prop_key][vertex_descriptor]))
else:
for i in range(n_comp):
prop.append(data_type(
self.graph.vp[prop_key][vertex_descriptor][i]))
return tuple(prop)
def get_edge_prop_entry(self, prop_key, edge_descriptor, n_comp, data_type):
"""
Gets a property value of an edge for inserting into a VTK vtkDataArray
object.
This private function is used by the method
graph_to_points_and_lines_polys.
Args:
prop_key (str): name of the desired vertex property
edge_descriptor (graph_tool.Edge): edge descriptor of the current
edge
n_comp (int): number of components of the array (length of the
output tuple)
data_type: numpy data type converted from a graph-tool property
value type by TypesConverter().gt_to_numpy
Returns:
a tuple (with length like n_comp) with the property value of the
edge converted to a numpy data type
"""
prop = list()
if n_comp == 1:
prop.append(data_type(self.graph.ep[prop_key][edge_descriptor]))
else:
for i in range(n_comp):
prop.append(data_type(
self.graph.ep[prop_key][edge_descriptor][i]))
return tuple(prop)
# * The following SegmentationGraph methods are needed for the normal vector
# voting algorithm. *
def calculate_average_edge_length(self, prop_e=None, value=1):
"""
Calculates the average edge length in the graph.
If a special edge property is specified, includes only the edges where
this property equals the given value. If there are no edges in the
graph, the given property does not exist or there are no edges with the
given property equaling the given value, None is returned.
Args:
prop_e (str, optional): edge property, if specified only edges where
this property equals the given value will be considered
value (int, optional): value of the specified edge property an edge
has to have in order to be considered (default 1)
Returns:
the average edge length in the graph (float) or None
"""
total_edge_length = 0
average_edge_length = None
if prop_e is None:
print "Considering all edges:"
for ed in self.graph.edges():
total_edge_length += self.graph.ep.distance[ed]
if self.graph.num_edges() > 0:
average_edge_length = total_edge_length / self.graph.num_edges()
else:
print "There are no edges in the graph!"
elif prop_e in self.graph.edge_properties:
print ("Considering only edges with property %s equaling value %s "
% (prop_e, value))
num_special_edges = 0
for ed in self.graph.edges():
if self.graph.edge_properties[prop_e][ed] == value:
num_special_edges += 1
total_edge_length += self.graph.ep.distance[ed]
if num_special_edges > 0:
average_edge_length = total_edge_length / num_special_edges
else:
print ("There are no edges with the property %s equaling value "
"%s!" % (prop_e, value))
print "Average length: %s" % average_edge_length
return average_edge_length
def find_geodesic_neighbors(self, v, g_max, verbose=False):
"""
Finds geodesic neighbor vertices of a given vertex v in the graph that
are within a given maximal geodesic distance g_max from it.
Also finds the corresponding geodesic distances. All edges are
considered.
Args:
v (graph_tool.Vertex): the source vertex
g_max: maximal geodesic distance (in nanometers, if the graph was
scaled)
verbose (boolean, optional): if True (default False), some extra
information will be printed out
Returns:
a dictionary mapping a neighbor vertex index to the geodesic
distance from vertex v
"""
dist_v = shortest_distance(self.graph, source=v, target=None,
weights=self.graph.ep.distance,
max_dist=g_max)
dist_v = dist_v.get_array()
neighbor_id_to_dist = dict()
idxs = np.where(dist_v <= g_max)[0]
for idx in idxs:
dist = dist_v[idx]
if dist != 0: # ignore the source vertex itself
neighbor_id_to_dist[idx] = dist
if verbose:
print "%s neighbors" % len(neighbor_id_to_dist)
return neighbor_id_to_dist
def get_vertex_property_array(self, property_name):
"""
Gets a numpy array with all values of a vertex property of the graph,
printing out the number of values, the minimal and the maximal value.
Args:
property_name (str): vertex property name
Returns:
an array (numpy.ndarray) with all values of the vertex property
"""
if (isinstance(property_name, str) and
property_name in self.graph.vertex_properties):
values = self.graph.vertex_properties[property_name].get_array()
print '%s "%s" values' % (len(values), property_name)
print 'min = %s, max = %s' % (min(values), max(values))
return values
else:
error_msg = ('The input "%s" is not a str object or is not found '
'in vertex properties of the graph.' % property_name)
raise pexceptions.PySegInputError(
expr='get_vertex_property_array (SegmentationGraph)',
msg=error_msg)
class BaseGraph(object):
"""
Class representing a graph. We do not use pure graph_tool.Graph for we want
to be able to easily change this library. Neither we use inheritance
as graph_tool has inconvenient licence.
"""
def __init__(self):
self._g = None
self._node_dict = {}
self._syn_to_vertex_map = None
self._lemma_to_nodes_dict = None
self._lu_on_vertex_dict = None
def use_graph_tool(self):
"""
Returns underlying graph_tool.Graph. It should be avoided at all costs.
"""
return self._g
def get_node_for_synset_id(self, syn_id):
"""
Lazy function to makes the map of synset identifiers to nodes into
the graph. The building of map is made only on the first funcion call.
The first and the next calls of this function will return the built map.
"""
if not self._syn_to_vertex_map:
self._syn_to_vertex_map = {}
for node in self.all_nodes():
if node.synset:
synset_id = node.synset.synset_id
self._syn_to_vertex_map[synset_id] = node
return self._syn_to_vertex_map.get(syn_id, None)
def pickle(self, filename):
self._g.save(filename)
def unpickle(self, filename):
self._g = load_graph(filename)
def init_graph(self, drctd=False):
self._g = Graph(directed=drctd)
def copy_graph_from(self, g):
self._g = g._g.copy()
def set_directed(self, drctd):
self._g.set_directed(drctd)
def is_directed(self):
return self._g.is_directed()
def merge_graphs(self, g1, g2):
self._g = graph_union(g1._g, g2._g, internal_props=True)
# Node operations:
def all_nodes(self):
for node in self._g.vertices():
yield BaseNode(self._g, node)
def create_node_attribute(self, name, kind, value=None):
if not self.has_node_attribute(name):
node_attr = self._g.new_vertex_property(kind, value)
self._g.vertex_properties[name] = node_attr
def create_node_attributes(self, node_attributes_list):
for attr in node_attributes_list:
if not self.has_node_attribute(attr[0]):
node_attr = self._g.new_vertex_property(attr[1])
self._g.vertex_properties[attr[0]] = node_attr
def has_node_attribute(self, name):
""" Checks if a node attribute already exists """
return name in self._g.vertex_properties
def delete_node_attribute(self, name):
""" Delete node attribute """
del self._g.vertex_properties[name]
def add_node(self, name, node_attributes_list=None):
if node_attributes_list is None:
node_attributes_list = []
if name not in self._node_dict:
new_node = self._g.add_vertex()
self._node_dict[name] = BaseNode(self._g, new_node)
for attr in node_attributes_list:
self._g.vertex_properties[attr[0]][new_node] = attr[1]
return self._node_dict[name]
def get_node(self, name):
return self._node_dict[name]
def remove_node(self, name):
self._g.remove_vertex(self._node_dict[name]._node)
del self._node_dict[name]
def nodes_filter(self,
nodes_to_filter_set,
inverted=False,
replace=False,
soft=False):
"""
Filters out nodes from set
Args:
nodes_to_filter_set (Iterable): Nodes which fill be filtered out.
inverted (bool): If True, nodes NOT in set will be filtered out.
Defaults to False.
replace (bool): Replace current filter instead of combining the two.
Defaults to False.
soft (bool): Hide nodes without removing them so they can be restored
with reset_nodes_filter. Defaults to False.
"""
predicate = lambda node: node not in nodes_to_filter_set
self.nodes_filter_conditional(predicate, inverted, replace, soft)
def nodes_filter_conditional(self,
predicate,
inverted=False,
replace=False,
soft=False):
"""
Filters node based on a predicate
Args:
predicate (Callable): Predicate returning False for nodes that should be
filtered out.
inverted (bool): Invert condition. Defaults to False.
replace (bool): Replace current filter instead of combining the two.
Defaults to False.
soft (bool): Hide nodes without removing them so they can be restored
with reset_nodes_filter. Defaults to False.
"""
(old_filter, old_inverted) = self._g.get_vertex_filter()
new_filter = self._g.new_vertex_property("bool")
for node in self.all_nodes():
kept = predicate(node) != inverted
if not replace and old_filter:
old_kept = bool(old_filter[node._node]) != old_inverted
kept = kept and old_kept
new_filter[node._node] = kept
self._g.set_vertex_filter(new_filter, False)
if not soft:
self.apply_nodes_filter()
def apply_nodes_filter(self):
""" Removes nodes that are currently filtered out """
self._g.purge_vertices()
def reset_nodes_filter(self):
""" Clears node filter """
self._g.set_vertex_filter(None)
# Edge operations:
def num_edges(self):
return self._g.num_edges()
def all_edges(self):
for e in self._g.edges():
yield BaseEdge(self._g, e)
def get_edges_between(self, source, target):
"""
Return all edges between source and target. Source and target can be either
BaseNode or integer.
"""
if isinstance(source, BaseNode):
source = source._node
if isinstance(target, BaseNode):
target = target._node
for e in self._g.edge(source, target, all_edges=True):
yield BaseEdge(self._g, e)
def get_edge(self, source, target, add_missing=False):
"""
Return some edge between source and target. Source and target can be either
BaseNode or integer.
"""
if isinstance(source, BaseNode):
source = source._node
if isinstance(target, BaseNode):
target = target._node
e = self._g.edge(source, target, add_missing)
if e is not None:
return BaseEdge(self._g, e)
else:
return None
def create_edge_attribute(self, name, kind, value=None):
if not self.has_edge_attribute(name):
edge_attr = self._g.new_edge_property(kind, value)
self._g.edge_properties[name] = edge_attr
def alias_edge_attribute(self, name, alias):
self._g.edge_properties[alias] = self._g.edge_properties[name]
def create_edge_attributes(self, edge_attributes_list):
for attr in edge_attributes_list:
if not self.has_edge_attribute(attr[0]):
edge_attr = self._g.new_edge_property(attr[1])
self._g.edge_properties[attr[0]] = edge_attr
def has_edge_attribute(self, name):
""" Checks if an edge attribute already existst """
return name in self._g.edge_properties
def delete_edge_attribute(self, name):
""" Delete edge attribute """
del self._g.edge_properties[name]
def add_edge(self, parent, child, edge_attributes_list=None):
if edge_attributes_list is None:
edge_attributes_list = []
new_edge = self._g.add_edge(parent._node, child._node)
for attr in edge_attributes_list:
self._g.edge_properties[attr[0]][new_edge] = attr[1]
return BaseEdge(self._g, new_edge)
def edges_filter(self, edges_to_filter_set):
edge_filter = self._g.new_edge_property("bool")
for e in self.all_edges():
if e in edges_to_filter_set:
edge_filter[e._edge] = False
else:
edge_filter[e._edge] = True
self._g.set_edge_filter(edge_filter)
self._g.purge_edges()
def ungraph_tool(self, thingy, lemma_on_only_synset_node_dict):
"""
Converts given data structure so that it no longer have any graph_tool dependencies.
"""
logger = logging.getLogger(__name__)
if type(thingy) == dict:
return {
self.ungraph_tool(k, lemma_on_only_synset_node_dict):
self.ungraph_tool(thingy[k], lemma_on_only_synset_node_dict)
for k in thingy
}
nodes_to_translate = set()
for vset in lemma_on_only_synset_node_dict.values():
for v in vset:
nodes_to_translate.add(v)
if type(thingy) == gt.PropertyMap:
dct = {}
if thingy.key_type() == 'v':
for node in nodes_to_translate:
dct[node] = thingy[node.use_graph_tool()]
elif thingy.key_type() == 'e':
for edge in self.all_edges():
dct[edge] = thingy[edge.use_graph_tool()]
else:
logger.error('Unknown property type %s', thingy.key_type())
raise NotImplemented
return dct
def generate_lemma_to_nodes_dict_synsets(self):
"""
This method generates a utility dictionary, which maps lemmas to
corresponding node objects. It is expensive in menas of time
needed to generate the dictionary. It should therefore be executed
at the beginning of the runtime and later its results should be reused
as many times as needed without re-executing the function.
"""
lemma_to_nodes_dict = defaultdict(set)
for node in self.all_nodes():
try:
lu_set = node.synset.lu_set
except KeyError:
continue
for lu in lu_set:
lemma = lu.lemma.lower()
lemma_to_nodes_dict[lemma].add(node)
self._lemma_to_nodes_dict = lemma_to_nodes_dict
def generate_lemma_to_nodes_dict_lexical_units(self):
"""
This method generates a utility dictionary, which maps lemmas to
corresponding node objects. It is expensive in menas of time
needed to generate the dictionary. It should therefore be executed
at the beginning of the runtime and later its results should be reused
as many times as needed without re-executing the function.
"""
lemma_to_nodes_dict = defaultdict(set)
for node in self.all_nodes():
try:
lemma = node.lu.lemma.lower()
lemma_to_nodes_dict[lemma].add(node)
except:
continue
self._lemma_to_nodes_dict = lemma_to_nodes_dict
@property
def lemma_to_nodes_dict(self):
return self._lemma_to_nodes_dict
def _make_lu_on_v_dict(self):
"""
Makes dictionary lu on vertex
"""
lu_on_vertex_dict = defaultdict(set)
for node in self.all_nodes():
try:
nl = node.lu
except Exception:
continue
if nl:
lu_on_vertex_dict[node.lu.lu_id] = node
self._lu_on_vertex_dict = lu_on_vertex_dict
class BoardGraphGraphtool(BoardGraphBase):
def __init__(self, number_of_vertices, graph_type):
super().__init__(number_of_vertices, graph_type)
# Graph tool creates directed multigraph by default.
self._graph = Graph()
self._graph.add_vertex(number_of_vertices)
self._graph.vertex_properties["cell"] = self._graph.new_vertex_property(
"object", number_of_vertices * [BoardCell()]
)
self._graph.edge_properties["direction"
] = self._graph.new_edge_property("object")
self._graph.edge_properties["weight"
] = self._graph.new_edge_property("int")
def __getitem__(self, position):
return self._graph.vp.cell[self._graph.vertex(position)]
def __setitem__(self, position, board_cell):
self._graph.vp.cell[self._graph.vertex(position)] = board_cell
def __contains__(self, position):
return position in range(0, self.vertices_count())
def vertices_count(self):
return self._graph.num_vertices()
def edges_count(self):
return self._graph.num_edges()
def has_edge(self, source_vertice, target_vertice, direction):
for e in self._graph.vertex(source_vertice).out_edges():
if (
int(e.target()) == target_vertice and
self._graph.ep.direction[e] == direction
):
return True
return False
def out_edges_count(self, source_vertice, target_vertice):
return len([
1 for e in self._graph.vertex(source_vertice).out_edges()
if int(e.target()) == target_vertice
])
def reconfigure_edges(self, width, height, tessellation):
"""
Uses tessellation object to create all edges in graph.
"""
self._graph.clear_edges()
for source_vertice in self._graph.vertices():
for direction in tessellation.legal_directions:
neighbor_vertice = tessellation.neighbor_position(
int(source_vertice),
direction,
board_width=width,
board_height=height
)
if neighbor_vertice is not None:
e = self._graph.add_edge(
source_vertice, neighbor_vertice, add_missing=False
)
self._graph.ep.direction[e] = direction
# TODO: Faster version?
# def reconfigure_edges(self, width, height, tessellation):
# """
# Uses tessellation object to create all edges in graph.
# """
# self._graph.clear_edges()
# edges_to_add = []
# directions_to_add = dict()
# for source_vertice in self._graph.vertices():
# for direction in tessellation.legal_directions:
# neighbor_vertice = tessellation.neighbor_position(
# int(source_vertice), direction,
# board_width=width, board_height=height
# )
# if neighbor_vertice is not None:
# edge = (int(source_vertice), neighbor_vertice,)
# edges_to_add.append(edge)
# if edge not in directions_to_add:
# directions_to_add[edge] = deque()
# directions_to_add[edge].append(direction)
# self._graph.add_edge_list(edges_to_add) if edges_to_add else None
# for e in edges_to_add:
# e_descriptors = self._graph.edge(
# s = self._graph.vertex(e[0]),
# t = self._graph.vertex(e[1]),
# all_edges = True
# )
# for e_descriptor in e_descriptors:
# if len(directions_to_add[e]) > 0:
# self._graph.ep.direction[e_descriptor] = directions_to_add[e][0]
# directions_to_add[e].popleft()
def calculate_edge_weights(self):
for e in self._graph.edges():
self._graph.ep.weight[e] = self.out_edge_weight(int(e.target()))
def neighbor(self, from_position, direction):
try:
for e in self._graph.vertex(from_position).out_edges():
if self._graph.ep.direction[e] == direction:
return int(e.target())
except ValueError as e:
raise IndexError(e.args)
return None
def wall_neighbors(self, from_position):
return [
int(n) for n in self._graph.vertex(from_position).out_neighbours()
if self[int(n)].is_wall
]
def all_neighbors(self, from_position):
return [
int(n) for n in self._graph.vertex(from_position).out_neighbours()
]
def shortest_path(self, start_position, end_position):
try:
return [
int(v)
for v in shortest_path(
g=self._graph,
source=self._graph.vertex(start_position),
target=self._graph.vertex(end_position),
)[0]
]
except ValueError:
return []
def dijkstra_path(self, start_position, end_position):
try:
self.calculate_edge_weights()
return [
int(v)
for v in shortest_path(
g=self._graph,
source=self._graph.vertex(start_position),
target=self._graph.vertex(end_position),
weights=self._graph.ep.weight,
)[0]
]
except ValueError:
return []
def position_path_to_direction_path(self, position_path):
retv = []
src_vertice_index = 0
for target_vertice in position_path[1:]:
source_vertice = position_path[src_vertice_index]
src_vertice_index += 1
for out_edge in self._graph.vertex(source_vertice).out_edges():
if int(out_edge.target()) == target_vertice:
retv.append(self._graph.ep.direction[out_edge])
return {
'source_position': position_path[0] if position_path else None,
'path': retv
}
def gen_fs(dicProperties):
np.random.seed()
graphFS = Graph()
# on définit la fraction des arcs à utiliser la réciprocité
f = dicProperties["Reciprocity"]
rFracRecip = f/(2.0-f)
# on définit toutes les grandeurs de base
rInDeg = dicProperties["InDeg"]
rOutDeg = dicProperties["OutDeg"]
nNodes = 0
nEdges = 0
rDens = 0.0
if "Nodes" in dicProperties.keys():
nNodes = dicProperties["Nodes"]
graphFS.add_vertex(nNodes)
if "Edges" in dicProperties.keys():
nEdges = dicProperties["Edges"]
rDens = nEdges / float(nNodes**2)
dicProperties["Density"] = rDens
else:
rDens = dicProperties["Density"]
nEdges = int(np.floor(rDens*nNodes**2))
dicProperties["Edges"] = nEdges
else:
nEdges = dicProperties["Edges"]
rDens = dicProperties["Density"]
nNodes = int(np.floor(np.sqrt(nEdges/rDens)))
graphFS.add_vertex(nNodes)
dicProperties["Nodes"] = nNodes
# on définit le nombre d'arcs à créer
nArcs = int(np.floor(rDens*nNodes**2)/(1+rFracRecip))
# on définit les paramètres fonctions de probabilité associées F(x) = A x^{-tau}
Ai = nArcs*(rInDeg-1)/(nNodes)
Ao = nArcs*(rOutDeg-1)/(nNodes)
# on définit les moyennes des distributions de pareto 2 = lomax
rMi = 1/(rInDeg-2.)
rMo = 1/(rOutDeg-2.)
# on définit les trois listes contenant les degrés sortant/entrant/bidirectionnels associés aux noeuds i in range(nNodes)
lstInDeg = np.random.pareto(rInDeg,nNodes)+1
lstOutDeg = np.random.pareto(rOutDeg,nNodes)+1
lstInDeg = np.floor(np.multiply(Ai/np.mean(lstInDeg), lstInDeg)).astype(int)
lstOutDeg = np.floor(np.multiply(Ao/np.mean(lstOutDeg), lstOutDeg)).astype(int)
# on génère les stubs qui vont être nécessaires et on les compte
nInStubs = int(np.sum(lstInDeg))
nOutStubs = int(np.sum(lstOutDeg))
lstInStubs = np.zeros(np.sum(lstInDeg))
lstOutStubs = np.zeros(np.sum(lstOutDeg))
nStartIn = 0
nStartOut = 0
for vert in range(nNodes):
nInDegVert = lstInDeg[vert]
nOutDegVert = lstOutDeg[vert]
for j in range(np.max([nInDegVert,nOutDegVert])):
if j < nInDegVert:
lstInStubs[nStartIn+j] += vert
if j < nOutDegVert:
lstOutStubs[nStartOut+j] += vert
nStartOut+=nOutDegVert
nStartIn+=nInDegVert
# on vérifie qu'on a à peu près le nombre voulu d'edges
while nInStubs*(1+rFracRecip)/float(nArcs) < 0.95 :
vert = np.random.randint(0,nNodes)
nAddInStubs = int(np.floor(Ai/rMi*(np.random.pareto(rInDeg)+1)))
lstInStubs = np.append(lstInStubs,np.repeat(vert,nAddInStubs)).astype(int)
nInStubs+=nAddInStubs
while nOutStubs*(1+rFracRecip)/float(nArcs) < 0.95 :
nAddOutStubs = int(np.floor(Ao/rMo*(np.random.pareto(rOutDeg)+1)))
lstOutStubs = np.append(lstOutStubs,np.repeat(vert,nAddOutStubs)).astype(int)
nOutStubs+=nAddOutStubs
# on s'assure d'avoir le même nombre de in et out stubs (1.13 is an experimental correction)
nMaxStubs = int(1.13*(2.0*nArcs)/(2*(1+rFracRecip)))
if nInStubs > nMaxStubs and nOutStubs > nMaxStubs:
np.random.shuffle(lstInStubs)
np.random.shuffle(lstOutStubs)
lstOutStubs.resize(nMaxStubs)
lstInStubs.resize(nMaxStubs)
nOutStubs = nInStubs = nMaxStubs
elif nInStubs < nOutStubs:
np.random.shuffle(lstOutStubs)
lstOutStubs.resize(nInStubs)
nOutStubs = nInStubs
else:
np.random.shuffle(lstInStubs)
lstInStubs.resize(nOutStubs)
nInStubs = nOutStubs
# on crée le graphe, les noeuds et les stubs
nRecip = int(np.floor(nInStubs*rFracRecip))
nEdges = nInStubs + nRecip +1
# les stubs réciproques
np.random.shuffle(lstInStubs)
np.random.shuffle(lstOutStubs)
lstInRecip = lstInStubs[0:nRecip]
lstOutRecip = lstOutStubs[0:nRecip]
lstEdges = np.array([np.concatenate((lstOutStubs,lstInRecip)),np.concatenate((lstInStubs,lstOutRecip))]).astype(int)
# add edges
graphFS.add_edge_list(np.transpose(lstEdges))
remove_self_loops(graphFS)
remove_parallel_edges(graphFS)
lstIsolatedVert = find_vertex(graphFS, graphFS.degree_property_map("total"), 0)
graphFS.remove_vertex(lstIsolatedVert)
graphFS.reindex_edges()
nNodes = graphFS.num_vertices()
nEdges = graphFS.num_edges()
rDens = nEdges / float(nNodes**2)
# generate types
rInhibFrac = dicProperties["InhibFrac"]
lstTypesGen = np.random.uniform(0,1,nEdges)
lstTypeLimit = np.full(nEdges,rInhibFrac)
lstIsExcitatory = np.greater(lstTypesGen,lstTypeLimit)
nExc = np.count_nonzero(lstIsExcitatory)
epropType = graphFS.new_edge_property("int",np.multiply(2,lstIsExcitatory)-np.repeat(1,nEdges)) # excitatory (True) or inhibitory (False)
graphFS.edge_properties["type"] = epropType
# and weights
if dicProperties["Weighted"]:
lstWeights = dicGenWeights[dicProperties["Distribution"]](graphFS,dicProperties,nEdges,nExc) # generate the weights
epropW = graphFS.new_edge_property("double",lstWeights) # crée la propriété pour stocker les poids
graphFS.edge_properties["weight"] = epropW
return graphFS
def reduce_space(q: gt.Graph,
a_graph: gt.Graph,
min_score,
delta,
method='MDST'):
num_edges_a = []
num_nodes_a = []
used_edges = set()
# delta = 0 # set to non-zero for corruption experiments - njp
# Hash
print('Hashing...')
start = time.time()
n_idx, e_idx = create_dict(a_graph, 'nValue',
'eValue') # Create an attribute index
# print_weights(n_idx,e_idx)
print('Done at ' + str(time.time() - start))
alg_start = time.time()
num_edges_a.append(a_graph.num_edges())
num_nodes_a.append(a_graph.num_vertices())
print('Calculating MDST')
start = time.time()
t_score = None
t_graph = None
if method == 'MDST' and len(used_edges) < 2 * q.num_edges():
t_graph, t_score = calculate_mdst_v2(q,
n_idx,
e_idx,
used_stuff=used_edges)
if method == 'Normal' or len(used_edges) >= 2 * q.num_edges():
if method == 'MDST':
# stop_here = 1
pass
t_graph = calc_random_spanning_tree(q)
print('Printing t_graph')
print_graph(t_graph)
print('t_score', t_score)
print('Done at ' + str(time.time() - start))
# print('Further the code for "graph_tool" is not translated. Further calculations are not considered valid.')
# Add used stuff to used.
# edges_used = t_graph.edges()
# used_edges.update(edges_used)
# used_edges.update([tuple([e2, e1]) for e1, e2 in edges_used]) #???WHAT FOR???
# also figure out what is unused.
tau = q.num_edges() - t_graph.num_edges() # Dumb way of calculating tau
print('Matching')
start = time.time()
mg = sgm_match(t_graph, a_graph, delta, tau, n_idx, e_idx)
print('Matching done at ' + str(time.time() - start))
print('Printing mg:')
root = None
for v in mg.vertices():
if v.in_degree() == 0:
root = v
break
print(root)
print_graph(mg)
a_prime = subsample_archive_from_matching(a_graph, mg, t_graph, e_idx)
# print 'Printing a_prime'
# PrintGraph(a_prime)
# gt.draw.graph_draw(a_prime, vertex_text=a_prime.vp['old'], vertex_font_size=18, output_size=(300, 300),
# output='a_prime.png')
# Score the solutions
print('Scoring solutions:')
start = time.time()
scores = []
threshold_matches = []
roots = [n for n in mg.vertices() if n.in_degree() == 0]
path_list_vp = vp_map(mg, 'path_list', 'object')
for root in roots:
sol = path_list_vp[root]
for _sol in sol:
origin_nodes = []
for _d in _sol:
d = []
for i in _d:
d.append(a_graph.vp['old'][a_graph.vertex(i)])
origin_nodes.append(tuple(d))
print('trying solutions', origin_nodes)
match, score = score_solution(q, a_prime, _sol)
origin_match = match_to_original_nodes(a_graph, match)
print('Got match with score: ', score)
print(origin_match)
if score >= min_score:
threshold_matches.append(origin_match)
scores.append(score)
for key, val in origin_match.items():
print('key {} val {}'.format(key, val))
num_edges_a.append(a_prime.num_edges())
num_nodes_a.append(a_prime.num_vertices())
print('Algorithm Post-hash Stages Done at ' + str(time.time() - start))
print('Algorithm Post-hash Stages Done at ' + str(time.time() - alg_start))
# print('Threshold matches: {}'.format(len(threshold_matches)))
return num_nodes_a, num_edges_a, threshold_matches, scores
def __init__(self, args: Namespace, graph: Graph) -> None:
"""Creates a new Evaluation object.
Parameters
----------
args : Namespace
the command-line arguments
graph : Graph
the loaded graph to be partitioned
"""
# CSV file into which to write the results
self.args = args
self.csv_file = args.csv + ".csv"
self.csv_details_file = args.csv + "_details.csv"
# Dataset parameters
self.block_size_variation = args.blockSizeVar
self.block_overlap = args.overlap
self.streaming_type = args.type
self.num_nodes = graph.num_vertices()
self.num_edges = graph.num_edges()
# Sampling evaluation
self.blocks_retained = 0.0
self.graph_edge_ratio = 0.0
self.difference_from_ideal_sample = 0.0
self.expansion_quality = 0.0
self.sampled_graph_clustering_coefficient = 0.0
self.full_graph_clustering_coefficient = 0.0
self.sampled_graph_diameter = 0
self.full_graph_diameter = 0
self.sampled_graph_largest_component = 0
self.full_graph_largest_component = 0
self.sampled_graph_island_vertices = 0
self.sampled_graph_num_vertices = 0
self.sampled_graph_num_edges = 0
self.sampled_graph_edge_ratio = 0.0
self.sampled_graph_num_blocks_algorithm = 0
self.sampled_graph_num_blocks_truth = 0
self.sampled_graph_accuracy = 0.0
self.sampled_graph_rand_index = 0.0
self.sampled_graph_adjusted_rand_index = 0.0
self.sampled_graph_pairwise_recall = 0.0
self.sampled_graph_pairwise_precision = 0.0
self.sampled_graph_entropy_algorithm = 0.0
self.sampled_graph_entropy_truth = 0.0
self.sampled_graph_entropy_algorithm_given_truth = 0.0
self.sampled_graph_entropy_truth_given_algorithm = 0.0
self.sampled_graph_mutual_info = 0.0
self.sampled_graph_missed_info = 0.0
self.sampled_graph_erroneous_info = 0.0
# Algorithm parameters
self.num_block_proposals = args.blockProposals
self.beta = args.beta
self.sample_size = args.sample_size
self.sampling_iterations = args.sample_iterations
self.sampling_algorithm = args.sample_type
self.delta_entropy_threshold = args.threshold
self.nodal_update_threshold_strategy = args.nodal_update_strategy
self.nodal_update_threshold_factor = args.factor
self.nodal_update_threshold_direction = args.direction
# Goodness of partition measures
self.num_blocks_algorithm = 0
self.num_blocks_truth = 0
self.accuracy = 0.0
self.rand_index = 0.0
self.adjusted_rand_index = 0.0
self.pairwise_recall = 0.0
self.pairwise_precision = 0.0
self.entropy_algorithm = 0.0
self.entropy_truth = 0.0
self.entropy_algorithm_given_truth = 0.0
self.entropy_truth_given_algorithm = 0.0
self.mutual_info = 0.0
self.missed_info = 0.0
self.erroneous_info = 0.0
self.sampled_graph_description_length = 0.0
self.max_sampled_graph_description_length = 0.0
self.full_graph_description_length = 0.0
self.max_full_graph_description_length = 0.0
self.sampled_graph_modularity = 0.0
self.full_graph_modularity = 0.0
# Algorithm runtime measures
self.loading = 0.0
self.sampling = 0.0
self.sampled_graph_partition_time = 0.0
self.total_partition_time = 0.0
self.merge_sample = 0.0
self.propagate_membership = 0.0
self.finetune_membership = 0.0
self.prepare_next_partitions = list() # type: List[float]
# self.finetuning_details = None
# Community details
self.real_communities = dict() # type: Dict[int, int]
self.algorithm_communities = dict() # type: Dict[int, int]
self.sampled_graph_real_communities = dict() # type: Dict[int, int]
self.sampled_graph_algorithm_communities = dict(
) # type: Dict[int, int]
self.contingency_table = None # type: np.ndarray
self.sampled_graph_contingency_table = None # type: np.ndarray