def g_one_main(n, md, model, to_pickle=True, data_dir='pkls'):
r = dict()
g = gt.price_network(N=n,
m=md,
gamma=1,
directed=False,
seed_graph=gt.complete_graph(N=md + 1))
if model == 'configuration':
gt.random_rewire(g, model='configuration')
r['N'] = n
r['md'] = md
r['model'] = model
try:
r.update(
dict(
n=g.num_vertices(),
m=g.num_edges(),
# l=average_path(g),
# cc=gt.global_clustering(g)
r_a=gt.assortativity(g, 'total'),
rho_a=rank_assortativity(g, method='spearman'),
tau_a=rank_assortativity(g, method='kendall')))
r.update(g_centrality_correlations(g))
except Exception as e:
logger.error(e)
if to_pickle is True:
filename = gen_filename(n, md, model, data_dir)
with open(filename, 'wb') as f:
pickle.dump(r, f, -1)
return r
def erdos_renyi_graph(n, e, directed=False, gcc=True):
g = Graph(directed=directed)
g.add_vertex(n)
rint = np.random.randint
edge_list = [[x, y]
for x, y in zip(rint(0, n, size=e), rint(0, n, size=e))]
g.add_edge_list(edge_list)
random_rewire(g, model="erdos")
g = make_simple_graph(g, undirected=1 - directed, gcc=gcc)
return g
def mcore_of_rewired(args_tuple):
t, g, model = args_tuple
pid = mp.current_process(),
rejected = gt.random_rewire(g, model=model)
print('Process id={}, number of rejected edges={}'.format(pid, rejected))
logger.info('PID=%s, number of rejected edges=%s', pid, rejected)
kshell = gt.kcore_decomposition(g)
s = pd.Series(kshell.a.copy())
k = s.max()
n = (s == k).sum()
logger.info('PID=%s, ts=%s, K=%s, N=%s', pid, t, k, n)
return (t, k, n)
def kcore_growing_shuffle(fn1='retweet.201710.claim.raw.csv',
fn2='graph.daily.csv',
ofn=None,
rewiring=None):
"""The growing of kcore by shuffling the edge list."""
if ofn is None:
ofn = 'kcore.growing.shuffle'
if rewiring:
ofn += '.' + rewiring
ofn += '.csv'
g = prepare_network_from_raw(fn1)
if rewiring is not None:
gt.random_rewire(g, model=rewiring)
evmap = pd.read_csv(fn2)
enum_list = evmap['enum'].tolist()
emap = pd.DataFrame(g.get_edges().copy(),
columns=['source', 'target', 'idx'])
emap = emap[['source', 'target']]
emap = emap.reindex(np.random.permutation(
emap.index)).reset_index(drop=True)
v_map = dict()
v_counter = -1
gp_counter = 0
g = gt.Graph()
mcore_k = []
mcore_s = []
mcore_idx = []
vnum = []
enum = []
largest_component_vnum = []
g = gt.Graph()
for i, s, t in emap.itertuples():
if s not in v_map:
v_counter += 1
v_map[s] = v_counter
if t not in v_map:
v_counter += 1
v_map[t] = v_counter
source = v_map.get(s)
target = v_map.get(t)
g.add_edge(source, target, add_missing=True)
if g.num_edges() >= enum_list[gp_counter]:
kcore = pd.Series(gt.kcore_decomposition(g).a.copy())
mcore = kcore.value_counts().sort_index(ascending=False)
mk = mcore.index[0]
ms = mcore.iloc[0]
mcore_k.append(mk)
mcore_s.append(ms)
mcore_idx.append(kcore.loc[kcore == mk].index.tolist())
lcv = gt.label_largest_component(g, directed=False)
vnum.append(g.num_vertices())
enum.append(g.num_edges())
largest_component_vnum.append(lcv.a.sum())
logger.info(g)
logger.info('gp counter: %s', gp_counter)
logger.info('Main core at enum=%s: k=%s, num=%s', g.num_edges(),
mk, ms)
gp_counter += 1
cdf = pd.DataFrame(
dict(mcore_k=mcore_k,
mcore_s=mcore_s,
mcore_idx=mcore_idx,
vnum=vnum,
enum=enum,
largest_commponent_vnum=largest_component_vnum))
cdf.to_csv(ofn, index=False)
def kcore_growing_daily_rewiring(fn,
ofn=None,
freq='D',
model='constrained-configuration'):
"""The growing of kcore by rewiring daily."""
if ofn is None:
ofn = 'kcore.growing.daily-rewiring.{}.csv'.format(model)
# load only necessary columns
df = pd.read_csv(fn, parse_dates=['tweet_created_at'], usecols=[2, 3, 4])
df = df.set_index('tweet_created_at')
# remove self-loop
df = df.loc[df.from_raw_id != df.to_raw_id]
df['row_id'] = np.arange(len(df))
df['gpf'] = False
gpf_rows = df.row_id.groupby(pd.Grouper(freq=freq)).last()
gpf_rows = gpf_rows.loc[gpf_rows.notnull()].astype('int')
df.loc[df.row_id.isin(gpf_rows.values), 'gpf'] = True
v_map = dict()
e_set = set()
v_counter = -1
g = gt.Graph()
mcore_k = []
mcore_s = []
mcore_idx = []
vnum = []
enum = []
largest_component_vnum = []
ts = []
for created_at, from_raw_id, to_raw_id, gpf in df[[
'from_raw_id', 'to_raw_id', 'gpf'
]].itertuples():
e = (from_raw_id, to_raw_id)
if e not in e_set:
if from_raw_id not in v_map:
v_counter += 1
v_map[from_raw_id] = v_counter
if to_raw_id not in v_map:
v_counter += 1
v_map[to_raw_id] = v_counter
source = v_map.get(from_raw_id)
target = v_map.get(to_raw_id)
g.add_edge(source, target, add_missing=True)
e_set.add(e)
if gpf:
g1 = g.copy()
rejected = gt.random_rewire(g1, model=model, edge_sweep=True)
logger.info('Number of rejected when rewiring: %s', rejected)
ts.append(created_at)
kcore = pd.Series(gt.kcore_decomposition(g1).a.copy())
mcore = kcore.value_counts().sort_index(ascending=False)
mk = mcore.index[0]
ms = mcore.iloc[0]
mcore_k.append(mk)
mcore_s.append(ms)
mcore_idx.append(kcore.loc[kcore == mk].index.tolist())
lcv = gt.label_largest_component(g1, directed=False)
vnum.append(g1.num_vertices())
enum.append(g1.num_edges())
largest_component_vnum.append(lcv.a.sum())
logger.info(g1)
logger.info('Main core at %s: k=%s, num=%s', created_at, mk, ms)
cdf = pd.DataFrame(
dict(timeline=ts,
mcore_k=mcore_k,
mcore_s=mcore_s,
mcore_idx=mcore_idx,
vnum=vnum,
enum=enum,
largest_commponent_vnum=largest_component_vnum))
cdf.to_csv(ofn, index=False)
#! /usr/bin/env python # -*- coding: utf-8 -*- """ @author: lockheed Information and Electronics Engineering Huazhong University of science and technology E-mail:[email protected] Created on: 4/30/14 9:58 AM Copyright (C) lockheedphoenix """ import graph_tool.all as gt g = gt.load_graph('RG.xml.gz') pos = g.vertex_properties['pos'] gt.graph_draw(g, pos=pos, output_size=[1024, 800], output='RG.png') gt.random_rewire(g, model='erdos') gt.graph_draw(g, pos=pos, output_size=[1024, 800], output='ER.png')
#! /usr/bin/env python # -*- coding: utf-8 -*- """ @author: lockheed Information and Electronics Engineering Huazhong University of science and technology E-mail:[email protected] Created on: 4/30/14 9:58 AM Copyright (C) lockheedphoenix """ import graph_tool.all as gt g = gt.load_graph('RG.xml.gz') pos = g.vertex_properties['pos'] gt.graph_draw(g, pos=pos,output_size=[1024,800],output='RG.png') gt.random_rewire(g,model='erdos') gt.graph_draw(g, pos=pos,output_size=[1024,800],output='ER.png')