def replica_vs_original(seed=None, figpath=None, generator_func=None, G=None, params=None, num_replicas = 150, title_infix='', metrics=None, intermediates=False, n_jobs=-1):
#generate one or more replicas and compare them to the original graph
if seed==None:
seed = npr.randint(1E6)
print('rand seed: %d'%seed)
npr.seed(seed)
random.seed(seed)
if generator_func==None:
generator_func=algorithms.generate_graph
if G==None:
G = graphutils.load_graph(path='data-social/potterat_Hiv250.elist')
if metrics == None:
metrics = graphutils.default_metrics[:]
metrics = [m for m in metrics if m['optional'] < 2]
if 'metric_runningtime_bound' in params:
mrtb = params['metric_runningtime_bound']
metrics = [m for m in metrics if m['runningtime'] <= mrtb]
metrics = [m for m in metrics if m['name'] not in ['avg flow closeness']] #broken in NX 1.6
metrics.reverse()
if params == None:
params = {'verbose':False, 'node_edit_rate':[0.05, 0.04, 0.03, 0.02, 0.01],
'edge_edit_rate':[0.05, 0.04, 0.03, 0.02, 0.01], 'node_growth_rate':[0], 'locality_bias_correction':0., 'enforce_connected':True, 'accept_chance_edges':1.0,
'retain_intermediates':intermediates}
if intermediates:
params['retain_intermediates'] = True
print('Params:')
print(params)
print('Metrics:')
print([metric['name'] for metric in metrics])
replicas = replicate_graph(G=G, generator_func=generator_func, num_replicas=num_replicas, params=params, title_infix=title_infix, n_jobs=n_jobs)
jaccard_edges = evaluate_similarity(base_graphs=G, graphs=replicas, n_jobs=n_jobs) #this is actually a mean
vals_of_all = evaluate_metrics(graphs=[G]+replicas, metrics=metrics, n_jobs=n_jobs)
vals_of_graph = [metric_data[0] for metric_data in vals_of_all]
vals_of_replicas = [metric_data[1:] for metric_data in vals_of_all]
replica_statistics, figpath = plot_deviation(vals_of_replicas, vals_of_graph, metrics, figpath, jaccard_edges, title_infix, seed, getattr(G, 'name', ''))
#pylab.show()
data = {'metrics':[met['name'] for met in metrics], 'name':getattr(G, 'name', ''), 'params':params, 'num_replicas':num_replicas, 'figpath':figpath}
data[0] = replica_statistics
data[0].update({'vals_of_replicas':vals_of_replicas, 'val_of_models':vals_of_graph, 'avg_jaccard_edges':jaccard_edges})
if intermediates:
current_replicas = replicas
for level in range(1, max(len(params.get('node_edit_rate', [])), len(params.get('edge_edit_rate', [])), len(params.get('node_growth_rate', [])), len(params.get('edge_growth_rate', [])))):
print('LEVEL: %d'%level)
coarse_models = [r.coarser_graph.model_graph for r in current_replicas]
coarse_replicas = [r.coarser_graph for r in current_replicas]
vals_of_models = evaluate_metrics(graphs=coarse_models, metrics=metrics, n_jobs=n_jobs)
vals_of_replicas = evaluate_metrics(graphs=coarse_replicas, metrics=metrics, n_jobs=n_jobs)
jaccard_edges = evaluate_similarity(base_graphs=coarse_models, graphs=coarse_replicas, n_jobs=n_jobs)
replica_statistics, dummy \
= plot_deviation(vals_of_replicas=vals_of_replicas, vals_of_graph=vals_of_models,
metrics=metrics, figpath=figpath + 'level%d'%level, jaccard_edges=jaccard_edges)
current_replicas = coarse_replicas
data[level] = replica_statistics
data[level].update({'vals_of_replicas':vals_of_replicas, 'vals_of_models':vals_of_models, 'avg_jaccard_edges':jaccard_edges})
graphutils.safe_pickle(path=figpath+'.pkl', data=data)
save_param_set(params, seed, figpath)
save_stats_csv(path=figpath+'.csv', seed=seed, data=data)
return data
if verbose:
print('Writing graph image: %s ..' % image_path)
sys.stdout.flush()
retCode = os.system(visualizer_cmdl)
if verbose:
print(visualizer_cmdl)
if os.name == 'nt':
pdf_cmld = 'start %s' % image_path
if verbose:
print(pdf_cmld)
os.system(pdf_cmld)
elif os.name == 'posix':
#aside: file --mime-type -b my.pdf
open_in_unix(image_path, verbose=verbose, ext='pdf')
elif write_graph and visualizer != None:
if verbose:
print('Running visualizer: ' + str(visualizer))
sys.stdout.flush()
visualizer_cmdl = visualizer + ' ' + output_path
retCode = os.system(visualizer_cmdl)
if verbose:
print(visualizer_cmdl)
graphutils.safe_pickle(path=output_path + '.pkl',
data=new_G,
params=params)
if verbose:
print('Replica is referenced by variable: new_G')
def replica_vs_original(seed=None,
figpath=None,
generator_func=None,
G=None,
params=None,
num_replicas=150,
title_infix='',
metrics=None,
intermediates=False,
n_jobs=-1,
store_replicas=False):
"""generate one or more replicas and compare them to the original graph"""
if seed == None:
seed = npr.randint(1E6)
print('rand seed: %d' % seed)
npr.seed(seed)
random.seed(seed)
if generator_func == None:
generator_func = algorithms.generate_graph
if G == None:
G = graphutils.load_graph(path='data-social/potterat_Hiv250.elist')
if metrics == None:
metrics = graphutils.default_metrics[:]
metrics = [m for m in metrics if m['optional'] < 2]
if 'metric_runningtime_bound' in params:
mrtb = params['metric_runningtime_bound']
metrics = [m for m in metrics if m['runningtime'] <= mrtb]
metrics = [m for m in metrics
if m['name'] not in ['avg flow closeness']] #broken in NX 1.6
metrics.reverse()
if params == None:
params = {
'verbose': False,
'node_edit_rate': [0.05, 0.04, 0.03, 0.02, 0.01],
'edge_edit_rate': [0.05, 0.04, 0.03, 0.02, 0.01],
'node_growth_rate': [0],
'locality_bias_correction': 0.,
'enforce_connected': True,
'accept_chance_edges': 1.0,
'retain_intermediates': intermediates
}
if intermediates:
params['retain_intermediates'] = True
print('Params:')
print(params)
print('Metrics:')
print([metric['name'] for metric in metrics])
#if generator_func == algorithms.generate_graph:
#replicas = replicate_graph(G=G, generator_func=generator_func, num_replicas=num_replicas, params=params, title_infix=title_infix, n_jobs=n_jobs)
#else:
#replicas = replicate_graph(G=G, generator_func=generator_func, num_replicas=num_replicas, params=params,
# title_infix=title_infix, n_jobs=n_jobs)
replicas = read_all_files()
jaccard_edges = evaluate_similarity(
base_graphs=G, graphs=replicas,
n_jobs=n_jobs) #this is actually a mean
vals_of_all = evaluate_metrics(graphs=[G] + replicas,
metrics=metrics,
n_jobs=n_jobs)
vals_of_graph = [metric_data[0] for metric_data in vals_of_all]
vals_of_replicas = [metric_data[1:] for metric_data in vals_of_all]
replica_statistics, figpath = plot_deviation(vals_of_replicas,
vals_of_graph, metrics,
figpath, jaccard_edges,
title_infix, seed,
getattr(G, 'name', ''))
#pylab.show()
data = {
'metrics': [met['name'] for met in metrics],
'name': getattr(G, 'name', ''),
'params': params,
'num_replicas': num_replicas,
'figpath': figpath
}
data[0] = replica_statistics
data[0].update({
'vals_of_replicas': vals_of_replicas,
'val_of_models': vals_of_graph,
'avg_jaccard_edges': jaccard_edges
})
out_dir = "/home/varsha/Documents/final_results/Krongen/Boeing_normalized" + timeNow(
)
myfile = open(out_dir, 'w')
i = 0
for repl in vals_of_replicas:
for elem in repl:
nor_value = elem
if (vals_of_graph[i] != 0):
nor_value = float(elem) / vals_of_graph[i]
myfile.write(str(nor_value))
myfile.write('\t')
i += 1
myfile.write('\n')
myfile.close()
if intermediates:
current_replicas = replicas
for level in range(
1,
max(len(params.get('node_edit_rate', [])),
len(params.get('edge_edit_rate', [])),
len(params.get('node_growth_rate', [])),
len(params.get('edge_growth_rate', [])))):
print('LEVEL: %d' % level)
coarse_models = [
r.coarser_graph.model_graph for r in current_replicas
]
coarse_replicas = [r.coarser_graph for r in current_replicas]
vals_of_models = evaluate_metrics(graphs=coarse_models,
metrics=metrics,
n_jobs=n_jobs)
vals_of_replicas = evaluate_metrics(graphs=coarse_replicas,
metrics=metrics,
n_jobs=n_jobs)
jaccard_edges = evaluate_similarity(base_graphs=coarse_models,
graphs=coarse_replicas,
n_jobs=n_jobs)
replica_statistics, dummy \
= plot_deviation(vals_of_replicas=vals_of_replicas, vals_of_graph=vals_of_models,
metrics=metrics, figpath=figpath + 'level%d'%level, jaccard_edges=jaccard_edges)
current_replicas = coarse_replicas
data[level] = replica_statistics
data[level].update({
'vals_of_replicas': vals_of_replicas,
'vals_of_models': vals_of_models,
'avg_jaccard_edges': jaccard_edges
})
graphutils.safe_pickle(path=figpath + '.pkl', data=data)
save_param_set(params, seed, figpath)
save_stats_csv(path=figpath + '.csv', seed=seed, data=data)
# optionally store replica graphs in files
if store_replicas:
out_dir = "output/replicas_{0}_{1}".format(getattr(
G, "name", ""), timeNow()) # FIXME: add graph name
os.mkdir(out_dir)
for (G, replica_no) in zip(replicas, range(len(replicas))):
graphutils.write_graph(G,
path="{0}/{1}.gml".format(
out_dir, replica_no))
return data
visualizer_cmdl = sfdp_default_cmd + " -Tpdf %s > %s 2> %s " % (output_path, image_path, stderr_path)
if verbose:
print "Writing graph image: %s .." % image_path
sys.stdout.flush()
retCode = os.system(visualizer_cmdl)
if verbose:
print visualizer_cmdl
if os.name == "nt":
pdf_cmld = "start %s" % image_path
if verbose:
print pdf_cmld
os.system(pdf_cmld)
elif os.name == "posix":
# aside: file --mime-type -b my.pdf
open_in_unix(image_path, verbose=verbose, ext="pdf")
elif write_graph and visualizer != None:
if verbose:
print "Running visualizer: " + str(visualizer)
sys.stdout.flush()
visualizer_cmdl = visualizer + " " + output_path
retCode = os.system(visualizer_cmdl)
if verbose:
print visualizer_cmdl
graphutils.safe_pickle(path=output_path + ".pkl", data=new_G, params=params)
if verbose:
print "Replica is referenced by variable: new_G"
current_replicas = replicas
for level in xrange(1, max(len(params.get('node_edit_rate', [])), len(params.get('edge_edit_rate', [])), len(params.get('node_growth_rate', [])), len(params.get('edge_growth_rate', [])))):
print 'LEVEL: %d'%level
coarse_models = [r.coarser_graph.model_graph for r in current_replicas]
coarse_replicas = [r.coarser_graph for r in current_replicas]
vals_of_models = evaluate_metrics(graphs=coarse_models, metrics=metrics, n_jobs=n_jobs)
vals_of_replicas = evaluate_metrics(graphs=coarse_replicas, metrics=metrics, n_jobs=n_jobs)
jaccard_edges = evaluate_similarity(base_graphs=coarse_models, graphs=coarse_replicas, n_jobs=n_jobs)
replica_statistics, dummy \
= plot_deviation(vals_of_replicas=vals_of_replicas, vals_of_graph=vals_of_models,
metrics=metrics, figpath=figpath + 'level%d'%level, jaccard_edges=jaccard_edges)
current_replicas = coarse_replicas
data[level] = replica_statistics
data[level].update({'vals_of_replicas':vals_of_replicas, 'vals_of_models':vals_of_models, 'avg_jaccard_edges':jaccard_edges})
graphutils.safe_pickle(path=figpath+'.pkl', data=data)
save_param_set(params, seed, figpath)
save_stats_csv(path=figpath+'.csv', seed=seed, data=data)
return data
def safe_metrics(graph, metrics):
rets = []
for met_num,metric in enumerate(metrics):
try:
rets.append(metric['function'](graph))
except Exception, inst:
print 'error in computing: '+metric['name']
print inst
rets.append(graphutils.METRIC_ERROR)
def replica_vs_original(seed=None,
figpath=None,
generator_func=None,
G=None,
params=None,
num_replicas=150,
title_infix='',
metrics=None,
intermediates=False,
n_jobs=-1):
#generate one or more replicas and compare them to the original graph
if seed == None:
seed = npr.randint(1E6)
print 'rand seed: %d' % seed
npr.seed(seed)
random.seed(seed)
if generator_func == None:
generator_func = algorithms.generate_graph
if G == None:
G = graphutils.load_graph(path='data-social/potterat_Hiv250.elist')
if metrics == None:
metrics = graphutils.default_metrics[:]
metrics = filter(lambda m: m['optional'] < 2, metrics)
if 'metric_runningtime_bound' in params:
mrtb = params['metric_runningtime_bound']
metrics = filter(lambda m: m['runningtime'] <= mrtb, metrics)
metrics = filter(lambda m: m['name'] not in ['avg flow closeness'],
metrics) #broken in NX 1.6
metrics.reverse()
if params == None:
params = {
'verbose': False,
'node_edit_rate': [0.05, 0.04, 0.03, 0.02, 0.01],
'edge_edit_rate': [0.05, 0.04, 0.03, 0.02, 0.01],
'node_growth_rate': [0],
'locality_bias_correction': 0.,
'enforce_connected': True,
'accept_chance_edges': 1.0,
'retain_intermediates': intermediates
}
if intermediates:
params['retain_intermediates'] = True
print 'Params:'
print params
print 'Metrics:'
print[metric['name'] for metric in metrics]
replicas = replicate_graph(G=G,
generator_func=generator_func,
num_replicas=num_replicas,
params=params,
title_infix=title_infix,
n_jobs=n_jobs)
jaccard_edges = evaluate_similarity(
base_graphs=G, graphs=replicas,
n_jobs=n_jobs) #this is actually a mean
vals_of_all = evaluate_metrics(graphs=[G] + replicas,
metrics=metrics,
n_jobs=n_jobs)
vals_of_graph = [metric_data[0] for metric_data in vals_of_all]
vals_of_replicas = [metric_data[1:] for metric_data in vals_of_all]
replica_statistics, figpath = plot_deviation(vals_of_replicas,
vals_of_graph, metrics,
figpath, jaccard_edges,
title_infix, seed,
getattr(G, 'name', ''))
#pylab.show()
data = {
'metrics': [met['name'] for met in metrics],
'name': getattr(G, 'name', ''),
'params': params,
'num_replicas': num_replicas,
'figpath': figpath
}
data[0] = replica_statistics
data[0].update({
'vals_of_replicas': vals_of_replicas,
'val_of_models': vals_of_graph,
'avg_jaccard_edges': jaccard_edges
})
if intermediates:
current_replicas = replicas
for level in xrange(
1,
max(len(params.get('node_edit_rate', [])),
len(params.get('edge_edit_rate', [])),
len(params.get('node_growth_rate', [])),
len(params.get('edge_growth_rate', [])))):
print 'LEVEL: %d' % level
coarse_models = [
r.coarser_graph.model_graph for r in current_replicas
]
coarse_replicas = [r.coarser_graph for r in current_replicas]
vals_of_models = evaluate_metrics(graphs=coarse_models,
metrics=metrics,
n_jobs=n_jobs)
vals_of_replicas = evaluate_metrics(graphs=coarse_replicas,
metrics=metrics,
n_jobs=n_jobs)
jaccard_edges = evaluate_similarity(base_graphs=coarse_models,
graphs=coarse_replicas,
n_jobs=n_jobs)
replica_statistics, dummy \
= plot_deviation(vals_of_replicas=vals_of_replicas, vals_of_graph=vals_of_models,
metrics=metrics, figpath=figpath + 'level%d'%level, jaccard_edges=jaccard_edges)
current_replicas = coarse_replicas
data[level] = replica_statistics
data[level].update({
'vals_of_replicas': vals_of_replicas,
'vals_of_models': vals_of_models,
'avg_jaccard_edges': jaccard_edges
})
graphutils.safe_pickle(path=figpath + '.pkl', data=data)
save_param_set(params, seed, figpath)
save_stats_csv(path=figpath + '.csv', seed=seed, data=data)
return data