explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-14 05:37:03 +03:00
Code Issues Packages Projects Releases Wiki Activity
db0d8c56d0
spaCy/spacy/tests/doc/test_retokenize_merge.py
Adriane Boyd 86d01e9229 Tidy up with flake8: imports, comparisons, etc.
2021-06-28 12:08:15 +02:00

495 lines
18 KiB
Python
Raw Blame History

import pytest
from spacy.attrs import LEMMA
from spacy.vocab import Vocab
from spacy.tokens import Doc, Token
def test_doc_retokenize_merge(en_tokenizer):
text = "WKRO played songs by the beach boys all night"
attrs = {
"tag": "NAMED",
"lemma": "LEMMA",
"ent_type": "TYPE",
"morph": "Number=Plur",
}
doc = en_tokenizer(text)
assert len(doc) == 9
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[4:7], attrs=attrs)
retokenizer.merge(doc[7:9], attrs=attrs)
assert len(doc) == 6
assert doc[4].text == "the beach boys"
assert doc[4].text_with_ws == "the beach boys "
assert doc[4].tag_ == "NAMED"
assert doc[4].lemma_ == "LEMMA"
assert str(doc[4].morph) == "Number=Plur"
assert doc[5].text == "all night"
assert doc[5].text_with_ws == "all night"
assert doc[5].tag_ == "NAMED"
assert str(doc[5].morph) == "Number=Plur"
assert doc[5].lemma_ == "LEMMA"
def test_doc_retokenize_merge_children(en_tokenizer):
"""Test that attachments work correctly after merging."""
text = "WKRO played songs by the beach boys all night"
attrs = {"tag": "NAMED", "lemma": "LEMMA", "ent_type": "TYPE"}
doc = en_tokenizer(text)
assert len(doc) == 9
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[4:7], attrs=attrs)
for word in doc:
if word.i < word.head.i:
assert word in list(word.head.lefts)
elif word.i > word.head.i:
assert word in list(word.head.rights)
def test_doc_retokenize_merge_hang(en_tokenizer):
text = "through North and South Carolina"
doc = en_tokenizer(text)
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[3:5], attrs={"lemma": "", "ent_type": "ORG"})
retokenizer.merge(doc[1:2], attrs={"lemma": "", "ent_type": "ORG"})
def test_doc_retokenize_retokenizer(en_tokenizer):
doc = en_tokenizer("WKRO played songs by the beach boys all night")
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[4:7])
assert len(doc) == 7
assert doc[4].text == "the beach boys"
def test_doc_retokenize_retokenizer_attrs(en_tokenizer):
doc = en_tokenizer("WKRO played songs by the beach boys all night")
# test both string and integer attributes and values
attrs = {LEMMA: "boys", "ENT_TYPE": doc.vocab.strings["ORG"]}
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[4:7], attrs=attrs)
assert len(doc) == 7
assert doc[4].text == "the beach boys"
assert doc[4].lemma_ == "boys"
assert doc[4].ent_type_ == "ORG"
def test_doc_retokenize_lex_attrs(en_tokenizer):
"""Test that lexical attributes can be changed (see #2390)."""
doc = en_tokenizer("WKRO played beach boys songs")
assert not any(token.is_stop for token in doc)
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[2:4], attrs={"LEMMA": "boys", "IS_STOP": True})
assert doc[2].text == "beach boys"
assert doc[2].lemma_ == "boys"
assert doc[2].is_stop
new_doc = Doc(doc.vocab, words=["beach boys"])
assert new_doc[0].is_stop
def test_doc_retokenize_spans_merge_tokens(en_tokenizer):
text = "Los Angeles start."
heads = [1, 2, 2, 2]
deps = ["dep"] * len(heads)
tokens = en_tokenizer(text)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
assert len(doc) == 4
assert doc[0].head.text == "Angeles"
assert doc[1].head.text == "start"
with doc.retokenize() as retokenizer:
attrs = {"tag": "NNP", "lemma": "Los Angeles", "ent_type": "GPE"}
retokenizer.merge(doc[0:2], attrs=attrs)
assert len(doc) == 3
assert doc[0].text == "Los Angeles"
assert doc[0].head.text == "start"
assert doc[0].ent_type_ == "GPE"
def test_doc_retokenize_spans_merge_tokens_default_attrs(en_vocab):
words = ["The", "players", "start", "."]
lemmas = [t.lower() for t in words]
heads = [1, 2, 2, 2]
deps = ["dep"] * len(heads)
tags = ["DT", "NN", "VBZ", "."]
pos = ["DET", "NOUN", "VERB", "PUNCT"]
doc = Doc(
en_vocab, words=words, tags=tags, pos=pos, heads=heads, deps=deps, lemmas=lemmas
)
assert len(doc) == 4
assert doc[0].text == "The"
assert doc[0].tag_ == "DT"
assert doc[0].pos_ == "DET"
assert doc[0].lemma_ == "the"
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:2])
assert len(doc) == 3
assert doc[0].text == "The players"
assert doc[0].tag_ == "NN"
assert doc[0].pos_ == "NOUN"
assert doc[0].lemma_ == "the players"
doc = Doc(
en_vocab, words=words, tags=tags, pos=pos, heads=heads, deps=deps, lemmas=lemmas
)
assert len(doc) == 4
assert doc[0].text == "The"
assert doc[0].tag_ == "DT"
assert doc[0].pos_ == "DET"
assert doc[0].lemma_ == "the"
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:2])
retokenizer.merge(doc[2:4])
assert len(doc) == 2
assert doc[0].text == "The players"
assert doc[0].tag_ == "NN"
assert doc[0].pos_ == "NOUN"
assert doc[0].lemma_ == "the players"
assert doc[1].text == "start ."
assert doc[1].tag_ == "VBZ"
assert doc[1].pos_ == "VERB"
assert doc[1].lemma_ == "start ."
def test_doc_retokenize_spans_merge_heads(en_vocab):
words = ["I", "found", "a", "pilates", "class", "near", "work", "."]
heads = [1, 1, 4, 6, 1, 4, 5, 1]
deps = ["dep"] * len(heads)
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
assert len(doc) == 8
with doc.retokenize() as retokenizer:
attrs = {"tag": doc[4].tag_, "lemma": "pilates class", "ent_type": "O"}
retokenizer.merge(doc[3:5], attrs=attrs)
assert len(doc) == 7
assert doc[0].head.i == 1
assert doc[1].head.i == 1
assert doc[2].head.i == 3
assert doc[3].head.i == 1
assert doc[4].head.i in [1, 3]
assert doc[5].head.i == 4
def test_doc_retokenize_spans_merge_non_disjoint(en_tokenizer):
text = "Los Angeles start."
doc = en_tokenizer(text)
with pytest.raises(ValueError):
with doc.retokenize() as retokenizer:
retokenizer.merge(
doc[0:2],
attrs={"tag": "NNP", "lemma": "Los Angeles", "ent_type": "GPE"},
)
retokenizer.merge(
doc[0:1],
attrs={"tag": "NNP", "lemma": "Los Angeles", "ent_type": "GPE"},
)
def test_doc_retokenize_span_np_merges(en_tokenizer):
text = "displaCy is a parse tool built with Javascript"
heads = [1, 1, 4, 4, 1, 4, 5, 6]
deps = ["dep"] * len(heads)
tokens = en_tokenizer(text)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
assert doc[4].head.i == 1
with doc.retokenize() as retokenizer:
attrs = {"tag": "NP", "lemma": "tool", "ent_type": "O"}
retokenizer.merge(doc[2:5], attrs=attrs)
assert doc[2].head.i == 1
text = "displaCy is a lightweight and modern dependency parse tree visualization tool built with CSS3 and JavaScript."
heads = [1, 1, 10, 7, 3, 3, 7, 10, 9, 10, 1, 10, 11, 12, 13, 13, 1]
deps = ["dep"] * len(heads)
tokens = en_tokenizer(text)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
with doc.retokenize() as retokenizer:
for ent in doc.ents:
attrs = {"tag": ent.label_, "lemma": ent.lemma_, "ent_type": ent.label_}
retokenizer.merge(ent, attrs=attrs)
text = "One test with entities like New York City so the ents list is not void"
heads = [1, 1, 1, 2, 3, 6, 7, 4, 12, 11, 11, 12, 1, 12, 12]
deps = ["dep"] * len(heads)
tokens = en_tokenizer(text)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
with doc.retokenize() as retokenizer:
for ent in doc.ents:
retokenizer.merge(ent)
def test_doc_retokenize_spans_entity_merge(en_tokenizer):
# fmt: off
text = "Stewart Lee is a stand up comedian who lives in England and loves Joe Pasquale.\n"
heads = [1, 2, 2, 4, 6, 4, 2, 8, 6, 8, 9, 8, 8, 14, 12, 2, 15]
deps = ["dep"] * len(heads)
tags = ["NNP", "NNP", "VBZ", "DT", "VB", "RP", "NN", "WP", "VBZ", "IN", "NNP", "CC", "VBZ", "NNP", "NNP", ".", "SP"]
ents = [("PERSON", 0, 2), ("GPE", 10, 11), ("PERSON", 13, 15)]
ents = ["O"] * len(heads)
ents[0] = "B-PERSON"
ents[1] = "I-PERSON"
ents[10] = "B-GPE"
ents[13] = "B-PERSON"
ents[14] = "I-PERSON"
# fmt: on
tokens = en_tokenizer(text)
doc = Doc(
tokens.vocab,
words=[t.text for t in tokens],
heads=heads,
deps=deps,
tags=tags,
ents=ents,
)
assert len(doc) == 17
with doc.retokenize() as retokenizer:
for ent in doc.ents:
ent_type = max(w.ent_type_ for w in ent)
attrs = {"lemma": ent.root.lemma_, "ent_type": ent_type}
retokenizer.merge(ent, attrs=attrs)
# check looping is ok
assert len(doc) == 15
def test_doc_retokenize_spans_entity_merge_iob(en_vocab):
# Test entity IOB stays consistent after merging
words = ["a", "b", "c", "d", "e"]
doc = Doc(Vocab(), words=words)
doc.ents = [
(doc.vocab.strings.add("ent-abc"), 0, 3),
(doc.vocab.strings.add("ent-d"), 3, 4),
]
assert doc[0].ent_iob_ == "B"
assert doc[1].ent_iob_ == "I"
assert doc[2].ent_iob_ == "I"
assert doc[3].ent_iob_ == "B"
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:2])
assert len(doc) == len(words) - 1
assert doc[0].ent_iob_ == "B"
assert doc[1].ent_iob_ == "I"
# Test that IOB stays consistent with provided IOB
words = ["a", "b", "c", "d", "e"]
doc = Doc(Vocab(), words=words)
with doc.retokenize() as retokenizer:
attrs = {"ent_type": "ent-abc", "ent_iob": 1}
retokenizer.merge(doc[0:3], attrs=attrs)
retokenizer.merge(doc[3:5], attrs=attrs)
assert doc[0].ent_iob_ == "B"
assert doc[1].ent_iob_ == "I"
# if no parse/heads, the first word in the span is the root and provides
# default values
words = ["a", "b", "c", "d", "e", "f", "g", "h", "i"]
doc = Doc(Vocab(), words=words)
doc.ents = [
(doc.vocab.strings.add("ent-de"), 3, 5),
(doc.vocab.strings.add("ent-fg"), 5, 7),
]
assert doc[3].ent_iob_ == "B"
assert doc[4].ent_iob_ == "I"
assert doc[5].ent_iob_ == "B"
assert doc[6].ent_iob_ == "I"
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[2:4])
retokenizer.merge(doc[4:6])
retokenizer.merge(doc[7:9])
assert len(doc) == 6
assert doc[3].ent_iob_ == "B"
assert doc[3].ent_type_ == "ent-de"
assert doc[4].ent_iob_ == "B"
assert doc[4].ent_type_ == "ent-fg"
# if there is a parse, span.root provides default values
words = ["a", "b", "c", "d", "e", "f", "g", "h", "i"]
heads = [0, 0, 3, 0, 0, 0, 5, 0, 0]
ents = ["O"] * len(words)
ents[3] = "B-ent-de"
ents[4] = "I-ent-de"
ents[5] = "B-ent-fg"
ents[6] = "I-ent-fg"
deps = ["dep"] * len(words)
en_vocab.strings.add("ent-de")
en_vocab.strings.add("ent-fg")
en_vocab.strings.add("dep")
doc = Doc(en_vocab, words=words, heads=heads, deps=deps, ents=ents)
assert doc[2:4].root == doc[3] # root of 'c d' is d
assert doc[4:6].root == doc[4] # root is 'e f' is e
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[2:4])
retokenizer.merge(doc[4:6])
retokenizer.merge(doc[7:9])
assert len(doc) == 6
assert doc[2].ent_iob_ == "B"
assert doc[2].ent_type_ == "ent-de"
assert doc[3].ent_iob_ == "I"
assert doc[3].ent_type_ == "ent-de"
assert doc[4].ent_iob_ == "B"
assert doc[4].ent_type_ == "ent-fg"
# check that B is preserved if span[start] is B
words = ["a", "b", "c", "d", "e", "f", "g", "h", "i"]
heads = [0, 0, 3, 4, 0, 0, 5, 0, 0]
ents = ["O"] * len(words)
ents[3] = "B-ent-de"
ents[4] = "I-ent-de"
ents[5] = "B-ent-de"
ents[6] = "I-ent-de"
deps = ["dep"] * len(words)
doc = Doc(en_vocab, words=words, heads=heads, deps=deps, ents=ents)
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[3:5])
retokenizer.merge(doc[5:7])
assert len(doc) == 7
assert doc[3].ent_iob_ == "B"
assert doc[3].ent_type_ == "ent-de"
assert doc[4].ent_iob_ == "B"
assert doc[4].ent_type_ == "ent-de"
def test_doc_retokenize_spans_sentence_update_after_merge(en_tokenizer):
# fmt: off
text = "Stewart Lee is a stand up comedian. He lives in England and loves Joe Pasquale."
heads = [1, 2, 2, 4, 2, 4, 4, 2, 9, 9, 9, 10, 9, 9, 15, 13, 9]
deps = ['compound', 'nsubj', 'ROOT', 'det', 'amod', 'prt', 'attr',
'punct', 'nsubj', 'ROOT', 'prep', 'pobj', 'cc', 'conj',
'compound', 'dobj', 'punct']
# fmt: on
tokens = en_tokenizer(text)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
sent1, sent2 = list(doc.sents)
init_len = len(sent1)
init_len2 = len(sent2)
with doc.retokenize() as retokenizer:
attrs = {"lemma": "none", "ent_type": "none"}
retokenizer.merge(doc[0:2], attrs=attrs)
retokenizer.merge(doc[-2:], attrs=attrs)
sent1, sent2 = list(doc.sents)
assert len(sent1) == init_len - 1
assert len(sent2) == init_len2 - 1
def test_doc_retokenize_spans_subtree_size_check(en_tokenizer):
# fmt: off
text = "Stewart Lee is a stand up comedian who lives in England and loves Joe Pasquale"
heads = [1, 2, 2, 4, 6, 4, 2, 8, 6, 8, 9, 8, 8, 14, 12]
deps = ["compound", "nsubj", "ROOT", "det", "amod", "prt", "attr",
"nsubj", "relcl", "prep", "pobj", "cc", "conj", "compound",
"dobj"]
# fmt: on
tokens = en_tokenizer(text)
doc = Doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
sent1 = list(doc.sents)[0]
init_len = len(list(sent1.root.subtree))
with doc.retokenize() as retokenizer:
attrs = {"lemma": "none", "ent_type": "none"}
retokenizer.merge(doc[0:2], attrs=attrs)
assert len(list(sent1.root.subtree)) == init_len - 1
def test_doc_retokenize_merge_extension_attrs(en_vocab):
Token.set_extension("a", default=False, force=True)
Token.set_extension("b", default="nothing", force=True)
doc = Doc(en_vocab, words=["hello", "world", "!"])
# Test regular merging
with doc.retokenize() as retokenizer:
attrs = {"lemma": "hello world", "_": {"a": True, "b": "1"}}
retokenizer.merge(doc[0:2], attrs=attrs)
assert doc[0].lemma_ == "hello world"
assert doc[0]._.a is True
assert doc[0]._.b == "1"
# Test bulk merging
doc = Doc(en_vocab, words=["hello", "world", "!", "!"])
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:2], attrs={"_": {"a": True, "b": "1"}})
retokenizer.merge(doc[2:4], attrs={"_": {"a": None, "b": "2"}})
assert doc[0]._.a is True
assert doc[0]._.b == "1"
assert doc[1]._.a is None
assert doc[1]._.b == "2"
@pytest.mark.parametrize("underscore_attrs", [{"a": "x"}, {"b": "x"}, {"c": "x"}, [1]])
def test_doc_retokenize_merge_extension_attrs_invalid(en_vocab, underscore_attrs):
Token.set_extension("a", getter=lambda x: x, force=True)
Token.set_extension("b", method=lambda x: x, force=True)
doc = Doc(en_vocab, words=["hello", "world", "!"])
attrs = {"_": underscore_attrs}
with pytest.raises(ValueError):
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:2], attrs=attrs)
def test_doc_retokenizer_merge_lex_attrs(en_vocab):
"""Test that retokenization also sets attributes on the lexeme if they're
lexical attributes. For example, if a user sets IS_STOP, it should mean that
"all tokens with that lexeme" are marked as a stop word, so the ambiguity
here is acceptable. Also see #2390.
"""
# Test regular merging
doc = Doc(en_vocab, words=["hello", "world", "!"])
assert not any(t.is_stop for t in doc)
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:2], attrs={"lemma": "hello world", "is_stop": True})
assert doc[0].lemma_ == "hello world"
assert doc[0].is_stop
# Test bulk merging
doc = Doc(en_vocab, words=["eins", "zwei", "!", "!"])
assert not any(t.like_num for t in doc)
assert not any(t.is_stop for t in doc)
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:2], attrs={"like_num": True})
retokenizer.merge(doc[2:4], attrs={"is_stop": True})
assert doc[0].like_num
assert doc[1].is_stop
assert not doc[0].is_stop
assert not doc[1].like_num
# Test that norm is only set on tokens
doc = Doc(en_vocab, words=["eins", "zwei", "!", "!"])
assert doc[0].norm_ == "eins"
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:1], attrs={"norm": "1"})
assert doc[0].norm_ == "1"
assert en_vocab["eins"].norm_ == "eins"
def test_retokenize_skip_duplicates(en_vocab):
"""Test that the retokenizer automatically skips duplicate spans instead
of complaining about overlaps. See #3687."""
doc = Doc(en_vocab, words=["hello", "world", "!"])
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[0:2])
retokenizer.merge(doc[0:2])
assert len(doc) == 2
assert doc[0].text == "hello world"
def test_retokenize_disallow_zero_length(en_vocab):
doc = Doc(en_vocab, words=["hello", "world", "!"])
with pytest.raises(ValueError):
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[1:1])
def test_doc_retokenize_merge_without_parse_keeps_sents(en_tokenizer):
text = "displaCy is a parse tool built with Javascript"
sent_starts = [1, 0, 0, 0, 1, 0, 0, 0]
tokens = en_tokenizer(text)
# merging within a sentence keeps all sentence boundaries
doc = Doc(tokens.vocab, words=[t.text for t in tokens], sent_starts=sent_starts)
assert len(list(doc.sents)) == 2
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[1:3])
assert len(list(doc.sents)) == 2
# merging over a sentence boundary unsets it by default
doc = Doc(tokens.vocab, words=[t.text for t in tokens], sent_starts=sent_starts)
assert len(list(doc.sents)) == 2
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[3:6])
assert doc[3].is_sent_start is None
# merging over a sentence boundary and setting sent_start
doc = Doc(tokens.vocab, words=[t.text for t in tokens], sent_starts=sent_starts)
assert len(list(doc.sents)) == 2
with doc.retokenize() as retokenizer:
retokenizer.merge(doc[3:6], attrs={"sent_start": True})
assert len(list(doc.sents)) == 2
Reference in New Issue View Git Blame Copy Permalink