Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ensure no candidates are returned for unknown aliases

This commit is contained in:
svlandeg 2019-03-21 15:24:40 +01:00
parent b6c3255a9f
commit c71123dd0c
3 changed files with 8 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/kb.pyx
View File

@ -149,5 +149,6 @@ cdef class KnowledgeBase:
entity_hash=self._entries[entry_index].entity_hash, entity_hash=self._entries[entry_index].entity_hash,
alias_hash=alias_hash, alias_hash=alias_hash,
prior_prob=prob) prior_prob=prob)
for (entry_index, prob) in zip(alias_entry.entry_indices, alias_entry.probs)] for (entry_index, prob) in zip(alias_entry.entry_indices, alias_entry.probs)
if entry_index != 0]

19
spacy/sandbox_test_sofie/testing_el.py
View File

@ -7,6 +7,7 @@ def create_kb():
mykb = KnowledgeBase() mykb = KnowledgeBase()
print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases()) print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases())
print()
# adding entities # adding entities
entity_0 = "Q0" # douglas adams entity_0 = "Q0" # douglas adams
@ -22,33 +23,23 @@ def create_kb():
mykb.add_entity(entity_id=entity_5301561, prob=0.5) mykb.add_entity(entity_id=entity_5301561, prob=0.5)
print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases()) print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases())
print()
# adding aliases # adding aliases
alias1 = "douglassss" alias1 = "douglassss"
print(" adding alias", alias1, "to Q42 and Q5301561") print(" adding alias", alias1, "to Q42 and Q5301561")
mykb.add_alias(alias=alias1, entities=["Q42", "Q5301561"], probabilities=[0.8, 0.2]) mykb.add_alias(alias=alias1, entities=["Q42", "Q5301561"], probabilities=[0.8, 0.2])
alias2 = "johny"
print(" adding alias", alias2, "to Q0, Q42 and Q5301561")
mykb.add_alias(alias=alias2, entities=["Q0", "Q42", "Q5301561"], probabilities=[0.3, 0.1, 0.4])
alias3 = "adam" alias3 = "adam"
print(" adding alias", alias3, "to Q42") print(" adding alias", alias3, "to Q42")
mykb.add_alias(alias=alias3, entities=["Q42"], probabilities=[0.9]) mykb.add_alias(alias=alias3, entities=["Q42"], probabilities=[0.9])
print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases()) print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases())
print()
for alias in [alias1, alias2, alias3]: for alias in [alias1, "rubbish", alias3]:
print()
print("candidates for", alias)
candidates = mykb.get_candidates(alias) candidates = mykb.get_candidates(alias)
for candidate in candidates: print(len(candidates), "candidates for", alias)
print(" candidate")
print(" kb_id", candidate.kb_id)
print(" kb_id_", candidate.kb_id_)
print(" alias", candidate.alias)
print(" alias_", candidate.alias_)
print(" prior_prob", candidate.prior_prob)
def add_el(): def add_el():

1
spacy/tests/pipeline/test_el.py
View File

@ -80,3 +80,4 @@ def test_candidate_generation():
# test the size of the relevant candidates # test the size of the relevant candidates
assert(len(mykb.get_candidates("douglas")) == 2) assert(len(mykb.get_candidates("douglas")) == 2)
assert(len(mykb.get_candidates("adam")) == 1) assert(len(mykb.get_candidates("adam")) == 1)
assert(len(mykb.get_candidates("shrubbery")) == 0)