explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Auto-format

Browse Source
This commit is contained in:
Ines Montani 2019-11-20 13:15:24 +01:00
parent 235fe6fe3b
commit 6e303de717
7 changed files with 89 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/lang/char_classes.py
View File

@ -206,7 +206,15 @@ _upper = LATIN_UPPER + _russian_upper + _tatar_upper + _greek_upper + _ukrainian
_lower = LATIN_LOWER + _russian_lower + _tatar_lower + _greek_lower + _ukrainian_lower
_uncased = (
_bengali + _hebrew + _persian + _sinhala + _hindi + _kannada + _tamil + _telugu + _hangul
_bengali
+ _hebrew
+ _persian
+ _sinhala
+ _hindi
+ _kannada
+ _tamil
+ _telugu
+ _hangul
)
ALPHA = group_chars(LATIN + _russian + _tatar + _greek + _ukrainian + _uncased)

82
spacy/lang/ko/lex_attrs.py
View File

@ -5,47 +5,47 @@ from ...attrs import LIKE_NUM
_num_words = [
"영",
"공",
# Native Korean number system
"하나",
"둘",
"셋",
"넷",
"다섯",
"여섯",
"일곱",
"여덟",
"아홉",
"열",
"스물",
"서른",
"마흔",
"쉰",
"예순",
"일흔",
"여든",
"아흔",
# Sino-Korean number system
"일",
"이",
"삼",
"사",
"오",
"육",
"칠",
"팔",
"구",
"십",
"백",
"천",
"만",
"십만",
"백만",
"천만",
"일억",
"십억",
"백억"
"영",
"공",
# Native Korean number system
"하나",
"둘",
"셋",
"넷",
"다섯",
"여섯",
"일곱",
"여덟",
"아홉",
"열",
"스물",
"서른",
"마흔",
"쉰",
"예순",
"일흔",
"여든",
"아흔",
# Sino-Korean number system
"일",
"이",
"삼",
"사",
"오",
"육",
"칠",
"팔",
"구",
"십",
"백",
"천",
"만",
"십만",
"백만",
"천만",
"일억",
"십억",
"백억",
]

4
spacy/lang/lb/tokenizer_exceptions.py
View File

@ -6,9 +6,7 @@ from ...symbols import ORTH, LEMMA, NORM
# TODO
# treat other apostrophes within words as part of the word: [op d'mannst], [fir d'éischt] (= exceptions)
_exc = {
}
_exc = {}
# translate / delete what is not necessary
for exc_data in [

5
spacy/lang/zh/__init__.py
View File

@ -14,6 +14,7 @@ from .tag_map import TAG_MAP
def try_jieba_import(use_jieba):
try:
import jieba
return jieba
except ImportError:
if use_jieba:
@ -34,7 +35,9 @@ class ChineseTokenizer(DummyTokenizer):
def __call__(self, text):
# use jieba
if self.use_jieba:
jieba_words = list([x for x in self.jieba_seg.cut(text, cut_all=False) if x])
jieba_words = list(
[x for x in self.jieba_seg.cut(text, cut_all=False) if x]
)
words = [jieba_words[0]]
spaces = [False]
for i in range(1, len(jieba_words)):

8
spacy/scorer.py
View File

@ -271,7 +271,9 @@ class Scorer(object):
self.labelled_per_dep[token.dep_.lower()] = PRFScore()
if token.dep_.lower() not in cand_deps_per_dep:
cand_deps_per_dep[token.dep_.lower()] = set()
cand_deps_per_dep[token.dep_.lower()].add((gold_i, gold_head, token.dep_.lower()))
cand_deps_per_dep[token.dep_.lower()].add(
(gold_i, gold_head, token.dep_.lower())
)
if "-" not in [token[-1] for token in gold.orig_annot]:
# Find all NER labels in gold and doc
ent_labels = set([x[0] for x in gold_ents] + [k.label_ for k in doc.ents])
@ -304,7 +306,9 @@ class Scorer(object):
self.tags.score_set(cand_tags, gold_tags)
self.labelled.score_set(cand_deps, gold_deps)
for dep in self.labelled_per_dep:
self.labelled_per_dep[dep].score_set(cand_deps_per_dep.get(dep, set()), gold_deps_per_dep.get(dep, set()))
self.labelled_per_dep[dep].score_set(
cand_deps_per_dep.get(dep, set()), gold_deps_per_dep.get(dep, set())
)
self.unlabelled.score_set(
set(item[:2] for item in cand_deps), set(item[:2] for item in gold_deps)
)

17
spacy/tests/regression/test_issue4590.py
View File

@ -11,8 +11,14 @@ def test_issue4590(en_vocab):
"""Test that matches param in on_match method are the same as matches run with no on_match method"""
pattern = [
{"SPEC": {"NODE_NAME": "jumped"}, "PATTERN": {"ORTH": "jumped"}},
{"SPEC": {"NODE_NAME": "fox", "NBOR_RELOP": ">", "NBOR_NAME": "jumped"}, "PATTERN": {"ORTH": "fox"}},
{"SPEC": {"NODE_NAME": "quick", "NBOR_RELOP": ".", "NBOR_NAME": "jumped"}, "PATTERN": {"ORTH": "fox"}},
{
"SPEC": {"NODE_NAME": "fox", "NBOR_RELOP": ">", "NBOR_NAME": "jumped"},
"PATTERN": {"ORTH": "fox"},
},
{
"SPEC": {"NODE_NAME": "quick", "NBOR_RELOP": ".", "NBOR_NAME": "jumped"},
"PATTERN": {"ORTH": "fox"},
},
]
on_match = Mock()
@ -23,12 +29,11 @@ def test_issue4590(en_vocab):
text = "The quick brown fox jumped over the lazy fox"
heads = [3, 2, 1, 1, 0, -1, 2, 1, -3]
deps = ["det", "amod", "amod", "nsubj", "prep", "pobj", "det", "amod"]
doc = get_doc(en_vocab, text.split(), heads=heads, deps=deps)
matches = matcher(doc)
on_match_args = on_match.call_args
assert on_match_args[0][3] == matches

20
spacy/tests/test_scorer.py
View File

@ -12,8 +12,22 @@ from .util import get_doc
test_las_apple = [
[
"Apple is looking at buying U.K. startup for $ 1 billion",
{"heads": [2, 2, 2, 2, 3, 6, 4, 4, 10, 10, 7],
"deps": ['nsubj', 'aux', 'ROOT', 'prep', 'pcomp', 'compound', 'dobj', 'prep', 'quantmod', 'compound', 'pobj']},
{
"heads": [2, 2, 2, 2, 3, 6, 4, 4, 10, 10, 7],
"deps": [
"nsubj",
"aux",
"ROOT",
"prep",
"pcomp",
"compound",
"dobj",
"prep",
"quantmod",
"compound",
"pobj",
],
},
]
]
@ -59,7 +73,7 @@ def test_las_per_type(en_vocab):
en_vocab,
words=input_.split(" "),
heads=([h - i for i, h in enumerate(annot["heads"])]),
deps=annot["deps"]
deps=annot["deps"],
)
gold = GoldParse(doc, heads=annot["heads"], deps=annot["deps"])
doc[0].dep_ = "compound"