explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-29 01:13:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Auto-formatting

Browse Source
This commit is contained in:
Ines Montani 2019-02-14 19:56:38 +01:00
parent 2569339a98
commit 3d577b77c6
1 changed files with 33 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
spacy/tests/doc/test_doc_spilt.py
View File

@ -1,12 +1,11 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from ..util import get_doc
from ...vocab import Vocab
from ...tokens import Doc
from ...tokens import Span
import pytest import pytest
from spacy.vocab import Vocab
from spacy.tokens import Doc
from ..util import get_doc
def test_doc_split(en_tokenizer): def test_doc_split(en_tokenizer):
@ -17,35 +16,41 @@ def test_doc_split(en_tokenizer):
assert len(doc) == 3 assert len(doc) == 3
assert len(str(doc)) == 19 assert len(str(doc)) == 19
assert doc[0].head.text == 'start' assert doc[0].head.text == "start"
assert doc[1].head.text == '.' assert doc[1].head.text == "."
with doc.retokenize() as retokenizer: with doc.retokenize() as retokenizer:
retokenizer.split(doc[0], ["Los", "Angeles"], [1, 0], attrs={'tag':'NNP', 'lemma':'Los Angeles', 'ent_type':'GPE'}) retokenizer.split(
doc[0],
["Los", "Angeles"],
[1, 0],
attrs={"tag": "NNP", "lemma": "Los Angeles", "ent_type": "GPE"},
)
assert len(doc) == 4 assert len(doc) == 4
assert doc[0].text == 'Los' assert doc[0].text == "Los"
assert doc[0].head.text == 'Angeles' assert doc[0].head.text == "Angeles"
assert doc[0].idx == 0 assert doc[0].idx == 0
assert doc[1].idx == 3 assert doc[1].idx == 3
assert doc[1].text == 'Angeles' assert doc[1].text == "Angeles"
assert doc[1].head.text == 'start' assert doc[1].head.text == "start"
assert doc[2].text == 'start' assert doc[2].text == "start"
assert doc[2].head.text == '.' assert doc[2].head.text == "."
assert doc[3].text == '.' assert doc[3].text == "."
assert doc[3].head.text == '.' assert doc[3].head.text == "."
assert len(str(doc)) == 19 assert len(str(doc)) == 19
def test_split_dependencies(en_tokenizer): def test_split_dependencies(en_tokenizer):
text = "LosAngeles start." text = "LosAngeles start."
tokens = en_tokenizer(text) tokens = en_tokenizer(text)
doc = get_doc(tokens.vocab, [t.text for t in tokens]) doc = get_doc(tokens.vocab, [t.text for t in tokens])
dep1 = doc.vocab.strings.add('amod') dep1 = doc.vocab.strings.add("amod")
dep2 = doc.vocab.strings.add('subject') dep2 = doc.vocab.strings.add("subject")
with doc.retokenize() as retokenizer: with doc.retokenize() as retokenizer:
retokenizer.split(doc[0], ["Los", "Angeles"], [1, 0], [dep1, dep2]) retokenizer.split(doc[0], ["Los", "Angeles"], [1, 0], [dep1, dep2])
@ -53,27 +58,26 @@ def test_split_dependencies(en_tokenizer):
assert doc[1].dep == dep2 assert doc[1].dep == dep2
def test_split_heads_error(en_tokenizer): def test_split_heads_error(en_tokenizer):
text = "LosAngeles start." text = "LosAngeles start."
tokens = en_tokenizer(text) tokens = en_tokenizer(text)
doc = get_doc(tokens.vocab, [t.text for t in tokens]) doc = get_doc(tokens.vocab, [t.text for t in tokens])
#Not enough heads # Not enough heads
with pytest.raises(ValueError): with pytest.raises(ValueError):
with doc.retokenize() as retokenizer: with doc.retokenize() as retokenizer:
retokenizer.split(doc[0], ["Los", "Angeles"], [0]) retokenizer.split(doc[0], ["Los", "Angeles"], [0])
#Too many heads # Too many heads
with pytest.raises(ValueError): with pytest.raises(ValueError):
with doc.retokenize() as retokenizer: with doc.retokenize() as retokenizer:
retokenizer.split(doc[0], ["Los", "Angeles"], [1, 1, 0]) retokenizer.split(doc[0], ["Los", "Angeles"], [1, 1, 0])
#No token head # No token head
with pytest.raises(ValueError): with pytest.raises(ValueError):
with doc.retokenize() as retokenizer: with doc.retokenize() as retokenizer:
retokenizer.split(doc[0], ["Los", "Angeles"], [1, 1]) retokenizer.split(doc[0], ["Los", "Angeles"], [1, 1])
#Several token heads # Several token heads
with pytest.raises(ValueError): with pytest.raises(ValueError):
with doc.retokenize() as retokenizer: with doc.retokenize() as retokenizer:
retokenizer.split(doc[0], ["Los", "Angeles"], [0, 0]) retokenizer.split(doc[0], ["Los", "Angeles"], [0, 0])
@ -83,7 +87,7 @@ def test_spans_entity_merge_iob():
# Test entity IOB stays consistent after merging # Test entity IOB stays consistent after merging
words = ["abc", "d", "e"] words = ["abc", "d", "e"]
doc = Doc(Vocab(), words=words) doc = Doc(Vocab(), words=words)
doc.ents = [(doc.vocab.strings.add('ent-abcd'), 0, 2)] doc.ents = [(doc.vocab.strings.add("ent-abcd"), 0, 2)]
assert doc[0].ent_iob_ == "B" assert doc[0].ent_iob_ == "B"
assert doc[1].ent_iob_ == "I" assert doc[1].ent_iob_ == "I"
@ -94,12 +98,14 @@ def test_spans_entity_merge_iob():
assert doc[2].ent_iob_ == "I" assert doc[2].ent_iob_ == "I"
assert doc[3].ent_iob_ == "I" assert doc[3].ent_iob_ == "I"
def test_spans_sentence_update_after_merge(en_tokenizer): def test_spans_sentence_update_after_merge(en_tokenizer):
# fmt: off
text = "StewartLee is a stand up comedian. He lives in England and loves JoePasquale." text = "StewartLee is a stand up comedian. He lives in England and loves JoePasquale."
heads = [1, 0, 1, 2, -1, -4, -5, 1, 0, -1, -1, -3, -4, 1, -2] heads = [1, 0, 1, 2, -1, -4, -5, 1, 0, -1, -1, -3, -4, 1, -2]
deps = ['nsubj', 'ROOT', 'det', 'amod', 'prt', 'attr', deps = ["nsubj", "ROOT", "det", "amod", "prt", "attr", "punct", "nsubj",
'punct', 'nsubj', 'ROOT', 'prep', 'pobj', 'cc', 'conj', "ROOT", "prep", "pobj", "cc", "conj", "compound", "punct"]
'compound', 'punct'] # fmt: on
tokens = en_tokenizer(text) tokens = en_tokenizer(text)
doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps) doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps)