def calc_v1_matrix(self, v0):
from_list = []
to_list = []
value_list = []
max_id = 0
wds = WikipediaDataset()
for from_entity_id in v0:
link_to = wds.get_links_to(from_entity_id)
for v in link_to:
from_list.append(from_entity_id)
to_list.append(v)
value_list.append(1)
if v > max_id:
max_id = v
link_from = set(wds.get_links_to(from_entity_id))
for v in link_from:
from_list.append(v)
to_list.append(from_entity_id)
value_list.append(1)
mtx = sparse.coo_matrix((value_list, (from_list, to_list)), shape=(max_id + 1, max_id + 1))
full_set = set(to_list)
full_set.update(from_list)
return mtx, full_set
def calc_v1_matrix(self, entity_id_list):
# find links that are within the set of nodes we are passed, and
# all those in bound to them, and out bound from them
from_list = []
to_list = []
value_list = []
max_id = 0
wds = WikipediaDataset()
for from_entity_id in entity_id_list:
link_to = wds.get_links_to(from_entity_id)
for v in link_to:
from_list.append(from_entity_id)
to_list.append(v)
value_list.append(1)
if v > max_id:
max_id = v
link_from = set(wds.get_links_from(from_entity_id))
for v in link_from:
from_list.append(v)
to_list.append(from_entity_id)
value_list.append(1)
if v > max_id:
max_id = v
# TODO The following line threw a Value error (row index exceeds matrix dimentions) here on docid 579, and docid 105
try:
mtx = sparse.coo_matrix((value_list, (from_list, to_list)),
shape=(max_id + 1, max_id + 1))
pass
except ValueError as e:
self.logger.warning(
'An error occurred returning None rather that a V1 matrix. %s',
e)
return None
return mtx
def get_links_totally_within(self, entity_id_list):
from_list = []
to_list = []
value_list = []
v0_vertice_set = set(entity_id_list)
wds = WikipediaDataset()
for entity_id in v0_vertice_set:
links_to = wds.get_links_to(entity_id)
for link_to in links_to:
if link_to in v0_vertice_set:
to_list.append(entity_id)
from_list.append(link_to)
value_list.append(1)
return from_list, to_list, value_list