def clique_percolation(G, data_prefix='snap_'):
'''
Parameters
-----------
G: An iGraph or edge list file
'''
snap_home, graph_file = snap.setup(G)
if graph_file is None:
return
path_cpm = os.path.join(snap_home, "examples", "cliques", "cliquesmain")
try:
FNULL = open(os.devnull, 'w')
out = subprocess.Popen([path_cpm,"-o:"+data_prefix,"-i:"+graph_file], stdout=FNULL).wait()
except TypeError as e:
print("Error occurred: {}".format(e))
return
os.remove(graph_file)
return snap.read_communities_by_community("cpm-" + data_prefix + ".txt", G, delete_file=True)
def cesna(G,
attributes_to_include,
data_prefix='snap_',
node_filepath='',
detect_comm=100,
min_comm=5,
max_comm=100,
trials=5,
threads=cpu_count(),
alpha=.3,
beta=0.3):
'''
Parameters
-----------
G: An iGraph or edge list file
f_attributes: Input node attribute file name (Required)
f_attribute_names: Input file name for node attribute names (Required)
nodes: Input file name for node names (Node ID, Node label)
detect_comm: The number of communities to detect (-1: detect automatically) (default:10)
min_comm: Minimum number of communities to try (default:3)
max_comm: Maximum number of communities to try (default:20)
trials: How many trials for the number of communities (default:5)
threads: Number of threads for parallelization (default:4)
aw: We maximize (1 - aw) P(Network) + aw * P(Attributes) (default:0.5)
lw: Weight for l-1 regularization on learning the logistic model parameters (default:1)
alpha: Alpha for backtracking line search (default:0.05)
beta: Beta for backtracking line search (default:0.3)
mf if the fraction of nodes with positive values for an attribute is smaller than this, we ignore that attribute (default:0)
'''
snap_home, graph_file = snap.setup(G)
f_attribute_names, f_attributes = snap.attribute_setup(
G, attributes_to_include)
if graph_file is None:
return
path_cesna = os.path.join(snap_home, "examples", "cesna", "cesna")
try:
FNULL = open(os.devnull, 'w')
out = subprocess.Popen([
path_cesna, "-o:" + data_prefix, "-i:" + graph_file,
"-l:" + node_filepath, "-c:" + str(detect_comm),
"-mc:" + str(min_comm), "-xc:" + str(max_comm),
"-nc:" + str(trials), "-nt:" + str(threads), "-sa:" + str(alpha),
"-sb:" + str(beta), "-a:" + f_attributes, "-n:" + f_attribute_names
],
stdout=FNULL).wait()
except TypeError as e:
print("Error occurred: {}".format(e))
return
os.remove(graph_file)
return snap.read_communities_by_community(data_prefix + "cmtyvv.txt",
G,
delete_file=True)
def bigclam(G,
data_prefix='snap_',
node_filepath='',
detect_comm=100,
min_comm=5,
max_comm=100,
trials=5,
threads=cpu_count(),
alpha=0.3,
beta=0.3):
'''
BigClam from Snap
Parameters
----------
G : A NetworkX graph or edge list file
data_prefix: Output file for communitities (data_prefix + cmtyvv.txt)
node_file_path: Input file name for node names (Node ID, Node label)
detect_comm: The number of communities to detect (-1: detect automatically) (Default: 100)
min_comm: Minimum number of communities to try (Default = 5)
max_comm: Maximum number of communities to try (Default = 100)
trials: How many trials for the number of communities (Default = 10)
threads: Number of threads for parallelization (Default = 4)
alpha: Alpha for backtracking line search (Default = 0.05)
beta: Beta for backtracking line search (Default = 0.3)
Returns: List of SubGraphs representing the communities. The SubGraphs are automatically serialized to disk as file data_prefix+'cmtyvv.txt'
'''
snap_home, graph_file = setup(G, include_header=False)
if graph_file is None:
return None
path_bigclam = os.path.join(snap_home, "examples", "bigclam", "bigclam")
try:
FNULL = open(os.devnull, 'w')
out = subprocess.Popen([
path_bigclam, "-o:" + data_prefix, "-i:" + graph_file, "-l:" +
node_filepath, "-c:" + str(detect_comm), "-mc:" + str(min_comm),
"-xc:" + str(max_comm), "-nc:" + str(trials),
"-nt:" + str(threads), "-sa:" + str(alpha), "-sb:" + str(beta)
],
stdout=FNULL).wait()
except TypeError as e:
print("Error occurred: {}".format(e))
return
os.remove(graph_file)
return read_communities_by_community(data_prefix + "cmtyvv.txt",
G,
delete_file=True)
def coda(G,
data_prefix='snap_',
node_filepath='',
graph_type=0,
detect_comm=100,
min_comm=5,
max_comm=100,
trials=10,
threads=4,
alpha=0.05,
beta=0.3):
'''
Coda from Snap
Parameters
----------
G : A NetworkX graph or edge list file
node_file_path: Input file name for node names (Node ID, Node label)
graph_type: 0=directed, 1=undirected (default: 0)
detect_comm: The number of communities to detect (-1: detect automatically) (Default: 100)
min_comm: Minimum number of communities to try (Default = 5)
max_comm: Maximum number of communities to try (Default = 100)
trials: How many trials for the number of communities (Default = 10)
threads: Number of threads for parallelization (Default = 4)
alpha: Alpha for backtracking line search (Default = 0.05)
beta: Beta for backtracking line search (Default = 0.3)
'''
snap_home, graph_file = setup(G)
path_coda = os.path.join(snap_home, "examples", "coda", "coda")
try:
FNULL = open(os.devnull, 'w')
out = subprocess.Popen([
path_coda, "-o:" + data_prefix, "-i:" + graph_file,
"-l:" + node_filepath, "-g:" + str(graph_type),
"-c:" + str(detect_comm), "-mc:" + str(min_comm),
"xc:" + str(max_comm), "-nc:" + str(trials), "-nt:" + str(threads),
"-sa:" + str(alpha), "-sb:" + str(beta)
],
stdout=FNULL).wait()
except TypeError as e:
print("Error occurred: {}".format(e))
return
os.remove(graph_file)
#CODE returns an "in" and an "out" file. Not sure why... so am just using out
return read_communities_by_community(data_prefix + "cmtyvv.out.txt", G)
def cesna(G, attributes_to_include, data_prefix='snap_', node_filepath='', detect_comm=100, min_comm=5, max_comm=100, trials=5, threads=cpu_count(), alpha=.3, beta=0.3):
'''
Parameters
-----------
G: An iGraph or edge list file
f_attributes: Input node attribute file name (Required)
f_attribute_names: Input file name for node attribute names (Required)
nodes: Input file name for node names (Node ID, Node label)
detect_comm: The number of communities to detect (-1: detect automatically) (default:10)
min_comm: Minimum number of communities to try (default:3)
max_comm: Maximum number of communities to try (default:20)
trials: How many trials for the number of communities (default:5)
threads: Number of threads for parallelization (default:4)
aw: We maximize (1 - aw) P(Network) + aw * P(Attributes) (default:0.5)
lw: Weight for l-1 regularization on learning the logistic model parameters (default:1)
alpha: Alpha for backtracking line search (default:0.05)
beta: Beta for backtracking line search (default:0.3)
mf if the fraction of nodes with positive values for an attribute is smaller than this, we ignore that attribute (default:0)
'''
snap_home, graph_file = snap.setup(G)
f_attribute_names, f_attributes = snap.attribute_setup(G, attributes_to_include)
if graph_file is None:
return
path_cesna = os.path.join(snap_home, "examples", "cesna", "cesna")
try:
FNULL = open(os.devnull, 'w')
out = subprocess.Popen([path_cesna,"-o:"+data_prefix,"-i:"+graph_file,"-l:"+node_filepath, "-c:" + str(detect_comm), "-mc:"+str(min_comm), "-xc:"+str(max_comm), "-nc:"+str(trials), "-nt:"+str(threads), "-sa:"+str(alpha), "-sb:"+str(beta), "-a:"+f_attributes, "-n:"+f_attribute_names],stdout=FNULL).wait()
except TypeError as e:
print("Error occurred: {}".format(e))
return
os.remove(graph_file)
return snap.read_communities_by_community(data_prefix + "cmtyvv.txt", G, delete_file=True)
def bigclam(G, data_prefix='snap_', node_filepath='', detect_comm=100, min_comm=5, max_comm=100, trials=10, threads=4, alpha=0.05, beta=0.3):
'''
BigClam from Snap
Parameters
----------
G : A NetworkX graph or edge list file
data_prefix: Output file for communitities (data_prefix + cmtyvv.txt)
node_file_path: Input file name for node names (Node ID, Node label)
detect_comm: The number of communities to detect (-1: detect automatically) (Default: 100)
min_comm: Minimum number of communities to try (Default = 5)
max_comm: Maximum number of communities to try (Default = 100)
trials: How many trials for the number of communities (Default = 10)
threads: Number of threads for parallelization (Default = 4)
alpha: Alpha for backtracking line search (Default = 0.05)
beta: Beta for backtracking line search (Default = 0.3)
Returns: List of SubGraphs representing the communities. The SubGraphs are automatically serialized to disk as file data_prefix+'cmtyvv.txt'
'''
snap_home, graph_file = setup(G)
if graph_file is None:
return None
path_bigclam = os.path.join(snap_home, "examples", "bigclam", "bigclam")
try:
out = subprocess.Popen([path_bigclam,"-o:"+data_prefix,"-i:"+graph_file,"-l:"+node_filepath,"-c:"+str(detect_comm), "-mc:"+str(min_comm), "-xc:"+str(max_comm), "-nc:"+str(trials), "-nt:"+str(threads), "-sa:"+str(alpha), "-sb:"+str(beta)]).wait()
except TypeError as e:
print("Error occurred: {}".format(e))
return
os.remove(graph_file)
return read_communities_by_community(data_prefix + "cmtyvv.txt", G)
def coda(
G,
data_prefix="snap_",
node_filepath="",
graph_type=0,
detect_comm=100,
min_comm=5,
max_comm=100,
trials=10,
threads=4,
alpha=0.05,
beta=0.3,
):
"""
Coda from Snap
Parameters
----------
G : A NetworkX graph or edge list file
node_file_path: Input file name for node names (Node ID, Node label)
graph_type: 0=directed, 1=undirected (default: 0)
detect_comm: The number of communities to detect (-1: detect automatically) (Default: 100)
min_comm: Minimum number of communities to try (Default = 5)
max_comm: Maximum number of communities to try (Default = 100)
trials: How many trials for the number of communities (Default = 10)
threads: Number of threads for parallelization (Default = 4)
alpha: Alpha for backtracking line search (Default = 0.05)
beta: Beta for backtracking line search (Default = 0.3)
"""
snap_home, graph_file = setup(G)
path_coda = os.path.join(snap_home, "examples", "coda", "coda")
try:
FNULL = open(os.devnull, "w")
out = subprocess.Popen(
[
path_coda,
"-o:" + data_prefix,
"-i:" + graph_file,
"-l:" + node_filepath,
"-g:" + str(graph_type),
"-c:" + str(detect_comm),
"-mc:" + str(min_comm),
"xc:" + str(max_comm),
"-nc:" + str(trials),
"-nt:" + str(threads),
"-sa:" + str(alpha),
"-sb:" + str(beta),
],
stdout=FNULL,
).wait()
except TypeError as e:
print("Error occurred: {}".format(e))
return
os.remove(graph_file)
# CODE returns an "in" and an "out" file. Not sure why... so am just using out
return read_communities_by_community(data_prefix + "cmtyvv.out.txt", G)