explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 09:57:26 +03:00
Code Issues Packages Projects Releases Wiki Activity

specify unicode strings for python 2.7

Browse Source
This commit is contained in:
svlandeg 2019-03-22 14:15:18 +01:00
parent 5318ce88fa
commit 9751312aff
1 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
spacy/tests/pipeline/test_el.py
View File

@ -15,13 +15,13 @@ def test_kb_valid_entities(nlp):
mykb = KnowledgeBase(nlp.vocab)
# adding entities
mykb.add_entity(entity_id="Q1", prob=0.9)
mykb.add_entity(entity_id="Q2", prob=0.2)
mykb.add_entity(entity_id="Q3", prob=0.5)
mykb.add_entity(entity_id=u'Q1', prob=0.9)
mykb.add_entity(entity_id=u'Q2', prob=0.2)
mykb.add_entity(entity_id=u'Q3', prob=0.5)
# adding aliases
mykb.add_alias(alias="douglas", entities=["Q2", "Q3"], probabilities=[0.8, 0.2])
mykb.add_alias(alias="adam", entities=["Q2"], probabilities=[0.9])
mykb.add_alias(alias=u'douglas', entities=[u'Q2', u'Q3'], probabilities=[0.8, 0.2])
mykb.add_alias(alias=u'adam', entities=[u'Q2'], probabilities=[0.9])
# test the size of the corresponding KB
assert(mykb.get_size_entities() == 3)
@ -33,13 +33,13 @@ def test_kb_invalid_entities(nlp):
mykb = KnowledgeBase(nlp.vocab)
# adding entities
mykb.add_entity(entity_id="Q1", prob=0.9)
mykb.add_entity(entity_id="Q2", prob=0.2)
mykb.add_entity(entity_id="Q3", prob=0.5)
mykb.add_entity(entity_id=u'Q1', prob=0.9)
mykb.add_entity(entity_id=u'Q2', prob=0.2)
mykb.add_entity(entity_id=u'Q3', prob=0.5)
# adding aliases - should fail because one of the given IDs is not valid
with pytest.raises(ValueError):
mykb.add_alias(alias="douglas", entities=["Q2", "Q342"], probabilities=[0.8, 0.2])
mykb.add_alias(alias=u'douglas', entities=[u'Q2', u'Q342'], probabilities=[0.8, 0.2])
def test_kb_invalid_probabilities(nlp):
@ -47,13 +47,13 @@ def test_kb_invalid_probabilities(nlp):
mykb = KnowledgeBase(nlp.vocab)
# adding entities
mykb.add_entity(entity_id="Q1", prob=0.9)
mykb.add_entity(entity_id="Q2", prob=0.2)
mykb.add_entity(entity_id="Q3", prob=0.5)
mykb.add_entity(entity_id=u'Q1', prob=0.9)
mykb.add_entity(entity_id=u'Q2', prob=0.2)
mykb.add_entity(entity_id=u'Q3', prob=0.5)
# adding aliases - should fail because the sum of the probabilities exceeds 1
with pytest.raises(ValueError):
mykb.add_alias(alias="douglassss", entities=["Q2", "Q3"], probabilities=[0.8, 0.4])
mykb.add_alias(alias=u'douglas', entities=[u'Q2', u'Q3'], probabilities=[0.8, 0.4])
def test_kb_invalid_combination(nlp):
@ -61,13 +61,13 @@ def test_kb_invalid_combination(nlp):
mykb = KnowledgeBase(nlp.vocab)
# adding entities
mykb.add_entity(entity_id="Q1", prob=0.9)
mykb.add_entity(entity_id="Q2", prob=0.2)
mykb.add_entity(entity_id="Q3", prob=0.5)
mykb.add_entity(entity_id=u'Q1', prob=0.9)
mykb.add_entity(entity_id=u'Q2', prob=0.2)
mykb.add_entity(entity_id=u'Q3', prob=0.5)
# adding aliases - should fail because the entities and probabilities vectors are not of equal length
with pytest.raises(ValueError):
mykb.add_alias(alias="douglassss", entities=["Q2", "Q3"], probabilities=[0.3, 0.4, 0.1])
mykb.add_alias(alias=u'douglas', entities=[u'Q2', u'Q3'], probabilities=[0.3, 0.4, 0.1])
def test_candidate_generation(nlp):
@ -75,15 +75,15 @@ def test_candidate_generation(nlp):
mykb = KnowledgeBase(nlp.vocab)
# adding entities
mykb.add_entity(entity_id="Q1", prob=0.9)
mykb.add_entity(entity_id="Q2", prob=0.2)
mykb.add_entity(entity_id="Q3", prob=0.5)
mykb.add_entity(entity_id=u'Q1', prob=0.9)
mykb.add_entity(entity_id=u'Q2', prob=0.2)
mykb.add_entity(entity_id=u'Q3', prob=0.5)
# adding aliases
mykb.add_alias(alias="douglas", entities=["Q2", "Q3"], probabilities=[0.8, 0.2])
mykb.add_alias(alias="adam", entities=["Q2"], probabilities=[0.9])
mykb.add_alias(alias=u'douglas', entities=[u'Q2', u'Q3'], probabilities=[0.8, 0.2])
mykb.add_alias(alias=u'adam', entities=[u'Q2'], probabilities=[0.9])
# test the size of the relevant candidates
assert(len(mykb.get_candidates("douglas")) == 2)
assert(len(mykb.get_candidates("adam")) == 1)
assert(len(mykb.get_candidates("shrubbery")) == 0)
assert(len(mykb.get_candidates(u'douglas')) == 2)
assert(len(mykb.get_candidates(u'adam')) == 1)
assert(len(mykb.get_candidates(u'shrubbery')) == 0)