def read_graph(graph_file, dataset_name, directed=False, weighted=False):
"""
Reads the input network in networkx.
:param graph_file: The directory where graph in EPGM format is stored
:param dataset_name: The name of the graph selected out of all the graph heads in EPGM file
:return: The graph in networkx format
"""
try: # assume args.input points to an EPGM graph
G_epgm = EPGM(graph_file)
graphs = G_epgm.G["graphs"]
if (
dataset_name is None
): # if dataset_name is not given, use the name of the 1st graph head
dataset_name = graphs[0]["meta"]["label"]
print(
"WARNING: dataset name not specified, using dataset '{}' in the 1st graph head"
.format(dataset_name))
graph_id = None
for g in graphs:
if g["meta"]["label"] == dataset_name:
graph_id = g["id"]
g = G_epgm.to_nx(graph_id, directed)
if weighted:
raise NotImplementedError
else:
# This is the correct way to set the edge weight in a MultiGraph.
edge_weights = {e: 1 for e in g.edges(keys=True)}
nx.set_edge_attributes(g, name="weight", values=edge_weights)
except: # otherwise, assume arg.input points to an edgelist file
if weighted:
g = nx.read_edgelist(
graph_file,
nodetype=int,
data=(("weight", float), ),
create_using=nx.DiGraph(),
)
else:
g = nx.read_edgelist(graph_file,
nodetype=int,
create_using=nx.DiGraph())
for edge in g.edges():
g[edge[0]][edge[1]]["weight"] = 1
if not directed:
g = g.to_undirected()
if not nx.is_connected(g):
print("Graph is not connected")
# take the largest connected component as the data
g_ccs = (g.subgraph(c).copy() for c in nx.connected_components(g))
g = max(g_ccs, key=len)
print("Largest subgraph statistics: {} nodes, {} edges".format(
g.number_of_nodes(), g.number_of_edges()))
print("Graph statistics: {} nodes, {} edges".format(
g.number_of_nodes(), g.number_of_edges()))
return g
def from_epgm(epgm_location, dataset_name=None, directed=False):
"""
Imports a graph stored in EPGM format to a NetworkX object
Args:
epgm_location (str): The directory containing the EPGM data
dataset_name (str), optional: The name of the dataset to import
directed (bool): If True, load as a directed graph, otherwise
load as an undirected graph
Returns:
A NetworkX graph containing the data for the EPGM-stored graph.
"""
G_epgm = EPGM(epgm_location)
graphs = G_epgm.G["graphs"]
# if dataset_name is not given, use the name of the 1st graph head
if not dataset_name:
dataset_name = graphs[0]["meta"]["label"]
warnings.warn(
"dataset name not specified, using dataset '{}' in the 1st graph head".format(
dataset_name
),
RuntimeWarning,
stacklevel=2,
)
# Select graph using dataset_name
for g in graphs:
if g["meta"]["label"] == dataset_name:
graph_id = g["id"]
# Convert to StellarGraph (via nx)
Gnx = G_epgm.to_nx(graph_id, directed=directed)
print(
"Graph statistics: {} nodes, {} edges".format(
Gnx.number_of_nodes(), Gnx.number_of_edges()
)
)
return Gnx
def read_graph(graph_file, dataset_name, is_directed=False, is_weighted=False):
"""
Reads the input network in networkx.
Args:
graph_file: The directory where graph in EPGM format is stored.
dataset_name: The name of the graph selected out of all the graph heads in EPGM file.
Returns:
The graph in networkx format
"""
if graph_file.split('.')[-1] == 'gpickle':
g = nx.read_gpickle(graph_file)
for edge in g.edges():
g[edge[0]][edge[1]]["weight"] = 1 # {'weight': 1}
if not is_directed:
g = g.to_undirected()
return g
try: # assume args.input points to an EPGM graph
G_epgm = EPGM(graph_file)
graphs = G_epgm.G["graphs"]
if (
dataset_name is None
): # if dataset_name is not given, use the name of the 1st graph head
dataset_name = graphs[0]["meta"]["label"]
print(
"WARNING: dataset name not specified, using dataset '{}' in the 1st graph head"
.format(dataset_name))
graph_id = None
for g in graphs:
if g["meta"]["label"] == dataset_name:
graph_id = g["id"]
g = G_epgm.to_nx(graph_id, is_directed)
if is_weighted:
raise NotImplementedError
else:
# This is the correct way to set the edge weight in a MultiGraph.
edge_weights = {e: 1 for e in g.edges(keys=True)}
nx.set_edge_attributes(g, name="weight", values=edge_weights)
except: # otherwise, assume arg.input points to an edgelist file
if is_weighted:
g = nx.read_edgelist(
graph_file,
nodetype=int,
data=(("weight", float), ),
create_using=nx.DiGraph(),
)
else:
g = nx.read_edgelist(graph_file,
nodetype=int,
create_using=nx.DiGraph())
for edge in g.edges():
g[edge[0]][edge[1]]["weight"] = 1 # {'weight': 1}
if not is_directed:
g = g.to_undirected()
print("Graph statistics: {} nodes, {} edges".format(
g.number_of_nodes(), g.number_of_edges()))
return g