words2 = self.words_around_symbol(candidate)
self.words2 += len(words1)
cm = CandidateMetrics()
cm.score = self.words_similarity(words1, words2, exclude)
cm.degree = ksyn.degree(self.hg, candidate)
logging.info('%s %s' % (candidate, cm))
if cm.better_than(best_cm):
best_cm = cm
best = candidate
self.best_sense_t += time.time() - start
return best, best_cm
if __name__ == '__main__':
hgr = hyperg.HyperGraph({
'backend': 'leveldb',
'hg': 'wordnet_wikidata.hg'
})
p = par.Parser()
d = Disambiguation(hgr, p)
r1 = ['stocks', 'stock']
text1 = "Chinese stocks end year with double-digit losses"
r2 = ['cambridge']
text2 = "Cambridge near Boston in the United States."
text3 = "Cambridge near London in England."
print(d.best_sense(r2, text2))
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with GraphBrain. If not, see <http://www.gnu.org/licenses/>.
import operator
import numpy as np
from sklearn.cluster import DBSCAN
import gb.tools.json as json_tools
import gb.hypergraph.edge as ed
import gb.nlp.parser as par
from gb.explore.similarity import edge_similarity
if __name__ == '__main__':
print('creating parser...')
par = par.Parser()
print('parser created.')
edge_data = json_tools.read('edges_similar_concepts.json')
extra_edges = {}
for item in edge_data:
edge = ed.str2edge(item['edge'])
matched = [ed.str2edge(match[1]) for match in item['matches']]
for part in edge[1:]:
if part not in matched:
key = ed.edge2str(part)
if key in extra_edges:
extra_edges[key] += 1
else:
extra_edges[key] = 1
def headlines_inference(hg, predicates_file):
parser = par.Parser()
Headlines(hg, parser, predicates_file).process()
self.entities[entity]['total_conflict_from'] = total
h, total = herfindhal_and_total(self.entities[entity]['conflict_to']
+ self.entities[entity]['conflict_from'])
self.entities[entity]['h_conflict'] = h
self.entities[entity]['total_conflict'] = total
h, total = herfindhal_and_total(self.entities[entity]['conflict_over'])
self.entities[entity]['h_conflict_over'] = h
self.entities[entity]['total_conflict_over'] = total
h, total = herfindhal_and_total(self.entities[entity]['conflict_for'])
self.entities[entity]['h_conflict_for'] = h
self.entities[entity]['total_conflict_for'] = total
self.write_metrics(entity)
i += 1
bar.update(i)
def process(self):
self.find_actors()
self.infer()
self.compute_metrics()
if __name__ == '__main__':
hgr = HyperGraph({'backend': 'leveldb', 'hg': 'infer.hg'})
parse = par.Parser()
Headlines(hgr, parse, 'predicate_patterns.csv').process()
def generate(hg):
print('starting parser...')
parser = par.Parser()
mer = Meronomy(hg, parser)
print('reading edges...')
total_edges = 0
total_beliefs = 0
total_verts = hg.symbol_count() + hg.edge_count()
i = 0
with progressbar.ProgressBar(max_value=total_verts) as bar:
for vertex in hg.all():
if sym.is_edge(vertex):
edge = vertex
total_edges += 1
if hg.is_belief(edge):
mer.add_edge(edge)
total_beliefs += 1
i += 1
if (i % 1000) == 0:
bar.update(i)
print('edges: %s; beliefs: %s' % (total_edges, total_beliefs))
print('post assignments...')
i = 0
with progressbar.ProgressBar(max_value=total_verts) as bar:
for vertex in hg.all():
if sym.is_edge(vertex):
edge = vertex
if hg.is_belief(edge):
mer.post_assignments(edge)
i += 1
if (i % 1000) == 0:
bar.update(i)
print('generating meronomy graph...')
mer.generate()
print('normalizing meronomy graph...')
mer.normalize_graph()
print('generating synonyms...')
mer.generate_synonyms()
print('writing synonyms...')
i = 0
with progressbar.ProgressBar(max_value=len(mer.synonym_sets)) as bar:
for syn_id in mer.synonym_sets:
edges = set()
for atom in mer.synonym_sets[syn_id]:
if atom in mer.edge_map:
edges |= mer.edge_map[atom]
best_count = -1
best_label_edge = None
for edge in edges:
if mer.edge_counts[edge] > best_count:
best_count = mer.edge_counts[edge]
best_label_edge = edge
label = hg.get_label(best_label_edge)
syn_symbol = sym.build(label, 'syn%s' % syn_id)
for edge in edges:
syn_edge = (cons.are_synonyms, edge, syn_symbol)
hg.add(syn_edge)
label_symbol = sym.build(label, cons.label_namespace)
label_edge = (cons.has_label, syn_symbol, label_symbol)
hg.add(label_edge)
i += 1
if i % 1000 == 0:
bar.update(i)
bar.update(i)
print('%s synonym sets created' % len(mer.synonym_sets))
print('done.')