def graph_to_vector(g, metric, all_tokens):
"""Create feature vector from a single graph.
The list of *all_tokens* is used as basis for the feature vector, and
value for each word in graph *g* according to *metric* is calculated.
"""
cents = graph.centralities(g, metric)
vector = [cents.get(token, 0.0) for token in all_tokens]
return vector
def graph_to_vector(g, metric, all_tokens):
"""Create feature vector from a single graph.
The list of *all_tokens* is used as basis for the feature vector, and
value for each word in graph *g* according to *metric* is calculated.
"""
cents = graph.centralities(g, metric)
vector = [cents.get(token, 0.0) for token in all_tokens]
return vector
def store_centralities(corpus, context):
print '> Calculating and storing centralities for', corpus
g = retrieve_corpus_network(corpus, context)
metrics = graph_representation.get_metrics(True, exclude_flow=True)
for metric in metrics:
m = metric.split()[0]
store_path = 'output/centralities/co-occurrence/'+corpus+'/'+context+'/'+m+'.cent'
if data.pickle_from_file(store_path, suppress_warning=True):
print ' already present, skipping:', metric
continue
else:
print ' calculating:', metric
try:
c = graph.centralities(g, metric)
data.pickle_to_file(c, store_path)
except MemoryError as e:
print 'MemoryError :('
data.write_to_file('MemoryError while claculating '+metric+' on '+corpus+':\n'+str(e)+'\n\n', 'output/log/errors')
def store_centralities(corpus, context):
print '> Calculating and storing centralities for', corpus
g = retrieve_corpus_network(corpus, context)
metrics = graph_representation.get_metrics(True, exclude_flow=True)
for metric in metrics:
m = metric.split()[0]
store_path = 'output/centralities/co-occurrence/' + corpus + '/' + context + '/' + m + '.cent'
if data.pickle_from_file(store_path, suppress_warning=True):
print ' already present, skipping:', metric
continue
else:
print ' calculating:', metric
try:
c = graph.centralities(g, metric)
data.pickle_to_file(c, store_path)
except MemoryError as e:
print 'MemoryError :('
data.write_to_file(
'MemoryError while claculating ' + metric + ' on ' + corpus +
':\n' + str(e) + '\n\n', 'output/log/errors')
def graph_to_dict(g, metric, icc=None):
"""Return node values as dictionary
If `icc` is provided, values are TC-ICC, otherwise TC is calculated.
"""
import pprint as pp
centralities = graph.centralities(g, metric)
if icc:
for term in centralities:
try:
centralities[term] = centralities[term] * icc[term]
except KeyError as ke:
# excepting for this to detect possible missmatch between icc and doc network
# TODO: should be cleaned up once tc-icc eval exp is done
if term not in centralities and term in icc:
print ' !', str(ke), 'found in icc but not in graph centralities'
else:
print ' !', str(ke), 'found in graph centralities but not in icc'
centralities[term] = 0.0
return centralities
def graph_to_dict(g, metric, icc=None):
"""Return node values as dictionary
If `icc` is provided, values are TC-ICC, otherwise TC is calculated.
"""
import pprint as pp
centralities = graph.centralities(g, metric)
if icc:
for term in centralities:
try:
centralities[term] = centralities[term] * icc[term]
except KeyError as ke:
# excepting for this to detect possible missmatch between icc and doc network
# TODO: should be cleaned up once tc-icc eval exp is done
if term not in centralities and term in icc:
print ' !', str(
ke), 'found in icc but not in graph centralities'
else:
print ' !', str(
ke), 'found in graph centralities but not in icc'
centralities[term] = 0.0
return centralities