explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-03-04 11:25:51 +03:00
Code Issues Packages Projects Releases Wiki Activity

minor changes

Browse Source
This commit is contained in:
India Kerle 2024-03-07 08:10:01 -03:00
parent 59d8ee4132
commit 8b64741502
2 changed files with 40 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
spacy/pipeline/coordinationruler.py
View File

@ -26,22 +26,36 @@ def _split_doc(doc: Doc) -> bool:
noun_modified = False
has_conjunction = False
noun_count = 0
modifiers = set()
for token in doc:
if token.pos_ == "NOUN":
noun_count += 1
if token.head.pos_ == "NOUN": ## check to see that the phrase is a noun phrase
has_modifier = any(
child.dep_ == "amod" for child in token.head.children
) # check to see if the noun has a modifier
if has_modifier:
for child in token.head.children:
if child.dep_ in ["amod", "advmod", "nmod"]:
modifiers.add(child.text)
noun_modified = True
for child in token.children:
if child.dep_ == "conj" and child.pos_ == "ADJ":
modifiers.add(child.text)
# check if there is a conjunction in the phrase
if token.pos_ == "CCONJ":
has_conjunction = True
return (
True if noun_modified and has_conjunction else False
) # and not all_nouns_modified else False
modifier_count = len(modifiers)
noun_modified = modifier_count > 0
all_nouns_modified = modifier_count == noun_count
if noun_modified and has_conjunction and not all_nouns_modified:
return True
else:
return False
def _collect_modifiers(token: Token) -> List[str]:
"""Collects adverbial modifiers for a given token.

27
spacy/tests/pipeline/test_coordinationruler.py
View File

@ -211,7 +211,7 @@ def noun_construction_case10(nlp):
words = ["fresh", "but", "quite", "sour", "apples", "and", "chicken", "wings"]
spaces = [True, True, True, True, True, True, True, False]
pos_tags = ["ADJ", "CCONJ", "ADV", "ADJ", "NOUN", "CCONJ", "NOUN", "NOUN"]
dep_relations = ["amod", "cc", "advmod", "conj", "ROOT", "cc", "conj", "compound"]
dep_relations = ["amod", "cc", "advmod", "amod", "ROOT", "cc", "compound", "conj"]
doc = Doc(nlp.vocab, words=words, spaces=spaces)
@ -220,13 +220,12 @@ def noun_construction_case10(nlp):
token.dep_ = dep
doc[0].head = doc[4]
doc[1].head = doc[3]
doc[1].head = doc[4]
doc[2].head = doc[3]
doc[3].head = doc[0]
doc[4].head = doc[4]
doc[5].head = doc[6]
doc[6].head = doc[4]
doc[7].head = doc[6]
doc[3].head = doc[4]
doc[5].head = doc[4]
doc[6].head = doc[7]
doc[7].head = doc[4]
return doc
@ -271,7 +270,7 @@ def test_split_noun_coordination(
noun_construction_case2,
noun_construction_case3,
noun_construction_case4,
# noun_construction_case5,
noun_construction_case5,
noun_construction_case6,
noun_construction_case7,
noun_construction_case8,
@ -309,9 +308,9 @@ def test_split_noun_coordination(
assert all(isinstance(phrase, str) for phrase in case4_split)
assert case4_split == ["hot chicken wings", "hot soup"]
# #test 5: multiple modifiers
# case5_split = split_noun_coordination(noun_construction_case5)
# assert case5_split == None
# #test 5: same # of modifiers as nouns
case5_split = split_noun_coordination(noun_construction_case5)
assert case5_split == None
# test 6: modifier phrases
case6_split = split_noun_coordination(noun_construction_case6)
@ -325,6 +324,7 @@ def test_split_noun_coordination(
# test 7:
case7_split = split_noun_coordination(noun_construction_case7)
print(case7_split)
assert case7_split == ["fresh apples", "juicy apples"]
# test 8:
@ -337,12 +337,11 @@ def test_split_noun_coordination(
# test 10:
case10_split = split_noun_coordination(noun_construction_case10)
assert case10_split == ["fresh apples", "quite sour apples", "chicken soup"]
assert case10_split == ['fresh apples', 'quite sour apples', 'fresh chicken wings', 'quite sour chicken wings']
# test 11:
case11_split = split_noun_coordination(noun_construction_case11)
assert case11_split == None
pass
################### test factory ##############################