spaCy/spacy/tests/parser/test_ner.py

160 lines
4.5 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
from spacy.pipeline import EntityRecognizer
from spacy.vocab import Vocab
from spacy.syntax.ner import BiluoPushDown
from spacy.gold import GoldParse
from spacy.tokens import Doc
@pytest.fixture
def vocab():
return Vocab()
@pytest.fixture
def doc(vocab):
return Doc(vocab, words=["Casey", "went", "to", "New", "York", "."])
@pytest.fixture
def entity_annots(doc):
casey = doc[0:1]
ny = doc[3:5]
return [
(casey.start_char, casey.end_char, "PERSON"),
(ny.start_char, ny.end_char, "GPE"),
]
@pytest.fixture
def entity_types(entity_annots):
return sorted(set([label for (s, e, label) in entity_annots]))
@pytest.fixture
def tsys(vocab, entity_types):
actions = BiluoPushDown.get_actions(entity_types=entity_types)
return BiluoPushDown(vocab.strings, actions)
def test_get_oracle_moves(tsys, doc, entity_annots):
gold = GoldParse(doc, entities=entity_annots)
tsys.preprocess_gold(gold)
act_classes = tsys.get_oracle_sequence(doc, gold)
names = [tsys.get_class_name(act) for act in act_classes]
assert names == ["U-PERSON", "O", "O", "B-GPE", "L-GPE", "O"]
def test_get_oracle_moves_negative_entities(tsys, doc, entity_annots):
entity_annots = [(s, e, "!" + label) for s, e, label in entity_annots]
gold = GoldParse(doc, entities=entity_annots)
for i, tag in enumerate(gold.ner):
if tag == "L-!GPE":
gold.ner[i] = "-"
tsys.preprocess_gold(gold)
act_classes = tsys.get_oracle_sequence(doc, gold)
names = [tsys.get_class_name(act) for act in act_classes]
assert names
def test_get_oracle_moves_negative_entities2(tsys, vocab):
doc = Doc(vocab, words=["A", "B", "C", "D"])
gold = GoldParse(doc, entities=[])
gold.ner = ["B-!PERSON", "L-!PERSON", "B-!PERSON", "L-!PERSON"]
tsys.preprocess_gold(gold)
act_classes = tsys.get_oracle_sequence(doc, gold)
names = [tsys.get_class_name(act) for act in act_classes]
assert names
def test_get_oracle_moves_negative_O(tsys, vocab):
doc = Doc(vocab, words=["A", "B", "C", "D"])
gold = GoldParse(doc, entities=[])
gold.ner = ["O", "!O", "O", "!O"]
tsys.preprocess_gold(gold)
act_classes = tsys.get_oracle_sequence(doc, gold)
names = [tsys.get_class_name(act) for act in act_classes]
assert names
def test_doc_add_entities_set_ents_iob(en_vocab):
doc = Doc(en_vocab, words=["This", "is", "a", "lion"])
ner = EntityRecognizer(en_vocab)
ner.begin_training([])
ner(doc)
assert len(list(doc.ents)) == 0
assert [w.ent_iob_ for w in doc] == (["O"] * len(doc))
doc.ents = [(doc.vocab.strings["ANIMAL"], 3, 4)]
assert [w.ent_iob_ for w in doc] == ["", "", "", "B"]
doc.ents = [(doc.vocab.strings["WORD"], 0, 2)]
assert [w.ent_iob_ for w in doc] == ["B", "I", "", ""]
def test_oracle_moves_missing_B(en_vocab):
words = ["B", "52", "Bomber"]
biluo_tags = [None, None, "L-PRODUCT"]
doc = Doc(en_vocab, words=words)
gold = GoldParse(doc, words=words, entities=biluo_tags)
moves = BiluoPushDown(en_vocab.strings)
move_types = ("M", "B", "I", "L", "U", "O")
for tag in biluo_tags:
if tag is None:
continue
elif tag == "O":
moves.add_action(move_types.index("O"), "")
else:
action, label = tag.split("-")
moves.add_action(move_types.index("B"), label)
moves.add_action(move_types.index("I"), label)
moves.add_action(move_types.index("L"), label)
moves.add_action(move_types.index("U"), label)
moves.preprocess_gold(gold)
seq = moves.get_oracle_sequence(doc, gold)
print(seq)
def test_oracle_moves_whitespace(en_vocab):
words = [
"production",
"\n",
"of",
"Northrop",
"\n",
"Corp.",
"\n",
"'s",
"radar",
]
biluo_tags = [
"O",
"O",
"O",
"B-ORG",
None,
"I-ORG",
"L-ORG",
"O",
"O",
]
doc = Doc(en_vocab, words=words)
gold = GoldParse(doc, words=words, entities=biluo_tags)
moves = BiluoPushDown(en_vocab.strings)
move_types = ("M", "B", "I", "L", "U", "O")
for tag in biluo_tags:
if tag is None:
continue
elif tag == "O":
moves.add_action(move_types.index("O"), "")
else:
action, label = tag.split("-")
moves.add_action(move_types.index(action), label)
moves.preprocess_gold(gold)
seq = moves.get_oracle_sequence(doc, gold)