def generate_Erdos_Renyi(name,
n_node,
n_edge,
directed=False,
seed=None,
overide=False):
'''
Generates an Erdos-Renyi random graph of the specified GraphType.
'''
if not overide and local_exists(name):
raise Exception("graph {} exists".format(name))
else:
params = {
"name": "Erdos-Renyi",
'n_node': n_node,
"n_edge": n_edge,
"directed": directed
}
description = "Erdos_Renyi random graph"
weighted = False
gen = RandomGenerator(params=params)
edges, gt = gen.generate(seed)
from .dataset import Dataset
return Dataset(name, description=description, groundtruthObj=gt, edgesObj=edges, \
directed=directed, weighted=weighted, overide=overide, additional_meta={'genopts': params})
def generate_undirected_unweighted_hier_random_graph_LFR(name, N, k=None, maxk=None, mu1=None, mu2=None, t1=None, t2=None, minc=None, \
maxc=None, on=None, om=None, minC=None, maxC=None, seed=None, overide=False):
'''
Lancichinetti-Fortunato-Radicchi Benchmark geneartor. Original from https://sites.google.com/site/andrealancichinetti/files
Parameter
=========== ==========================================================
-N [number of nodes]
-k [average degree]
-maxk [maximum degree]
-t1 [minus exponent for the degree sequence]
-t2 [minus exponent for the community size distribution]
-minc [minimum for the micro community sizes]
-maxc [maximum for the micro community sizes]
-on [number of overlapping nodes]
-om [number of memberships of the overlapping nodes]
-minC [minimum for the macro community size]
-maxC [maximum for the macro community size]
-mu1 [mixing parameter for the macro communities (see Readme file)]
-mu2 [mixing parameter for the micro communities (see Readme file)]
=========== ==========================================================
-------------------- Examples ---------------------------
Example2:
./hbenchmark -f flags.dat
./hbenchmark -N 10000 -k 20 -maxk 50 -mu2 0.3 -minc 20 -maxc 50 -minC 100 -maxC 1000 -mu1 0.1
Reference
Lancichinetti, Andrea, and Santo Fortunato. "Benchmarks for testing community detection algorithms on directed and weighted graphs with overlapping communities." Physical Review E 80.1 (2009): 016118.
'''
if not overide and local_exists(name):
raise Exception("graph {} exists".format(name))
else:
params = locals()
del params['overide']
description = "LFR random graph"
directed = False
weighted = False
params['directed'] = directed
params['hier'] = True
params['weighted'] = weighted
params['name'] = 'LFR'
gen = RandomGenerator(params=params)
edges, gt = gen.generate(seed)
from .dataset import Dataset
return Dataset(name,
description=description,
groundtruthObj=gt,
edgesObj=edges,
directed=directed,
weighted=weighted,
overide=overide,
additional_meta={'genopts': params})
def load_sample_dataset(name, overide=False):
if not overide and local_exists(name):
return load_local(name)
else:
path = os.path.join(config.GCT_HOME, 'data', _DATASET_[name])
edges = pd.read_csv(path)
gt = pd.read_csv(path.replace("_edges", '_gt'))
description = ""
directed = False
return convert.from_edgelist(name,
edges,
groundtruth=gt,
directed=directed,
description=description,
overide=overide)
def load_snap_dataset(name, overide=False):
if not overide and local_exists(name):
return load_local(name)
else:
conf = _DATASET_[name]
edges = conf.get_edges()
gt = conf.get_ground_truth()
description = conf.description
weighted = conf.weighted
directed = conf.directed
return Dataset(name,
description=description,
groundtruthObj=gt,
edgesObj=edges,
directed=directed,
weighted=weighted,
overide=overide)
def setUp(self):
overide = False
def f(name):
overide = False
return random_dataset.generate_ovp_LFR(name,
N=128,
k=16,
maxk=16,
muw=0.1,
minc=32,
beta=1,
a=0,
overide=overide)
name = "test_LFR_unw_und"
self.graph_unweighted_undirect = self.get_dataset(name, f)
assert not self.graph_unweighted_undirect.is_directed()
assert not self.graph_unweighted_undirect.is_weighted()
def f2(name):
return random_dataset.generate_ovp_LFR("test_LFR_w_und",
N=128,
k=16,
maxk=16,
muw=0.1,
minc=32,
beta=1,
weighted=True,
a=0,
overide=overide)
name = "test_LFR_w_und"
self.graph_weighted_undirect = self.get_dataset(name, f)
assert not self.graph_weighted_undirect.is_directed()
assert self.graph_weighted_undirect.is_weighted()
name = "test_LFR_w_dir"
if dataset.local_exists(name):
self.graph_weighted_direct = dataset.load_local(name)
else:
self.graph_weighted_direct = random_dataset.generate_ovp_LFR(
name,
N=128,
k=16,
maxk=16,
muw=0.1,
minc=32,
beta=1,
weighted=True,
a=1,
overide=overide)
assert self.graph_weighted_direct.is_directed()
assert self.graph_weighted_direct.is_weighted()
name = "test_LFR_unw_dir"
if dataset.local_exists(name):
self.graph_unweighted_direct = dataset.load_local(name)
else:
self.graph_unweighted_direct = random_dataset.generate_ovp_LFR(
name,
N=128,
k=16,
maxk=16,
muw=0.1,
minc=32,
beta=1,
weighted=False,
a=1,
overide=overide)
assert self.graph_unweighted_direct.is_directed()
assert not self.graph_unweighted_direct.is_weighted()
self.graphs = [
self.graph_unweighted_undirect, self.graph_weighted_undirect,
self.graph_weighted_direct, self.graph_unweighted_direct
]
def get_dataset(self, name, fun):
if dataset.local_exists(name):
return dataset.load_local(name)
else:
return fun(name)
def generate_directed_weighted_random_graph_LFR(name, N, k=None, maxk=None, mut=None, muw=None, beta=None, t1=None, t2=None, \
minc=None, maxc=None, on=None, om=None, C=None, seed=None, overide=False):
'''
Lancichinetti-Fortunato-Radicchi Benchmark geneartor. Original from https://sites.google.com/site/andrealancichinetti/files
Parameter:
=========== ==========================================================
-N [number of nodes]
-k [average in-degree]
-maxk [maximum in-degree]
-mut [mixing parameter for the topology]
-muw [mixing parameter for the weights]
-beta [exponent for the weight distribution]
-t1 [minus exponent for the degree sequence]
-t2 [minus exponent for the community size distribution]
-minc [minimum for the community sizes]
-maxc [maximum for the community sizes]
-on [number of overlapping nodes]
-om [number of memberships of the overlapping nodes]
=========== ==========================================================
-N, -k, -maxk, -muw have to be specified. For the others, the program can use default values:
t1=2, t2=1, on=0, om=0, beta=1.5, mut=muw, minc and maxc will be chosen close to the degree sequence extremes.
If you set a parameter twice, the latter one will be taken.
-------------------- Other options ---------------------------
To have a random network use: -rand
Using this option will set muw=0, mut=0, and minc=maxc=N, i.e. there will be one only community.
Use option -sup (-inf) if you want to produce a benchmark whose distribution of the ratio of external in-degree/total in-degree is superiorly (inferiorly) bounded by the mixing parameter.
-------------------- Examples ---------------------------
Example1: ./benchmark -N 1000 -k 15 -maxk 50 -muw 0.1 -minc 20 -maxc 50
Example2: ./benchmark -f flags.dat -t1 3
Reference
Lancichinetti, Andrea, and Santo Fortunato. "Benchmarks for testing community detection algorithms on directed and weighted graphs with overlapping communities." Physical Review E 80.1 (2009): 016118.
'''
if not overide and local_exists(name):
raise Exception("graph {} exists".format(name))
else:
params = locals()
del params['overide']
description = "LFR random graph"
directed = True
weighted = True
params['directed'] = directed
params['weighted'] = weighted
params['name'] = 'LFR'
gen = RandomGenerator(params=params)
edges, gt = gen.generate(seed)
from .dataset import Dataset
return Dataset(name,
description=description,
groundtruthObj=gt,
edgesObj=edges,
directed=directed,
weighted=weighted,
overide=overide)
def generate_ovp_LFR(name,
N,
k=None,
maxk=None,
mut=None,
muw=None,
beta=None,
t1=None,
t2=None,
minc=None,
maxc=None,
on=None,
om=None,
C=None,
a=0,
weighted=False,
seed=None,
overide=False):
'''
Extended version of the Lancichinetti-Fortunato-Radicchi Benchmark for Weighted Overlapping networks
to evaluate clustering algorithms using generated ground-truth communities.
Refer https://github.com/eXascaleInfolab/LFR-Benchmark_UndirWeightOvp
Parameter
========== ===========================================================================
-N [number of nodes]
-k [average degree]
-maxk [maximum degree]
-mut [mixing parameter for the topology]
-muw [mixing parameter for the weights]
-beta [exponent for the weight distribution]
-t1 [minus exponent for the degree sequence]
-t2 [minus exponent for the community size distribution]
-minc [minimum for the community sizes]
-maxc [maximum for the community sizes]
-on [number of overlapping nodes]
-om [number of memberships of the overlapping nodes]
-C [Average clustering coefficient]
-cnl [output communities as strings of nodes (input format for NMI evaluation)]
-name [base name for the output files]. It is used for the network, communities and statistics; files extensions are added automatically:
.nsa - network, represented by space/tab separated arcs
.nse - network, represented by space/tab separated edges
{.cnl, .nmc} - communities, represented by nodes lists '.cnl' if '-cnl' is used, otherwise as a nodes membership in communities '.nmc')
.nst - network statistics
-seed [file name of the random seed, default: seed.txt]
-a [{0, 1} yield directed network (1 - arcs) rather than undirected (0 - edges), default: 0 - edges]
========== ===========================================================================
Reference
Lancichinetti, Andrea, and Santo Fortunato. "Benchmarks for testing community detection algorithms on directed and weighted graphs with overlapping communities." Physical Review E 80.1 (2009): 016118.
'''
if not overide and local_exists(name):
raise Exception("graph {} exists".format(name))
else:
params = locals()
del params['overide']
params['a'] = int(a)
params['name'] = 'ovp_LFR'
description = "overlap LFR random graph"
directed = (a > 0)
params['directed'] = directed
gen = RandomGenerator(params=params)
edges, gt = gen.generate(seed)
from .dataset import Dataset
return Dataset(name, description=description, groundtruthObj=gt, edgesObj=edges, \
directed=directed, weighted=weighted, overide=overide, additional_meta={'genopts': params})