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

Merge pull request #7046 from adrianeboyd/bugfix/vocab-pickle-noun-chunks-6891

Browse Source 
Include noun chunks method when pickling Vocab
This commit is contained in:
Ines Montani 2021-02-13 11:43:03 +11:00 committed by GitHub
commit f4712a634e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 29 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
spacy/tests/test_pickles.py
View File

@ -1,7 +1,9 @@
import pytest
import numpy
import srsly
from spacy.lang.en import English
from spacy.strings import StringStore
from spacy.tokens import Doc
from spacy.vocab import Vocab
from spacy.attrs import NORM
@ -20,7 +22,10 @@ def test_pickle_string_store(text1, text2):
@pytest.mark.parametrize("text1,text2", [("dog", "cat")])
def test_pickle_vocab(text1, text2):
vocab = Vocab(lex_attr_getters={int(NORM): lambda string: string[:-1]})
vocab = Vocab(
lex_attr_getters={int(NORM): lambda string: string[:-1]},
get_noun_chunks=English.Defaults.syntax_iterators.get("noun_chunks"),
)
vocab.set_vector("dog", numpy.ones((5,), dtype="f"))
lex1 = vocab[text1]
lex2 = vocab[text2]
@ -34,4 +39,23 @@ def test_pickle_vocab(text1, text2):
assert unpickled[text2].norm == lex2.norm
assert unpickled[text1].norm != unpickled[text2].norm
assert unpickled.vectors is not None
assert unpickled.get_noun_chunks is not None
assert list(vocab["dog"].vector) == [1.0, 1.0, 1.0, 1.0, 1.0]
def test_pickle_doc(en_vocab):
words = ["a", "b", "c"]
deps = ["dep"] * len(words)
heads = [0] * len(words)
doc = Doc(
en_vocab,
words=words,
deps=deps,
heads=heads,
)
data = srsly.pickle_dumps(doc)
unpickled = srsly.pickle_loads(data)
assert [t.text for t in unpickled] == words
assert [t.dep_ for t in unpickled] == deps
assert [t.head.i for t in unpickled] == heads
assert list(doc.noun_chunks) == []

6
spacy/vocab.pyx
View File

@ -551,12 +551,13 @@ def pickle_vocab(vocab):
data_dir = vocab.data_dir
lex_attr_getters = srsly.pickle_dumps(vocab.lex_attr_getters)
lookups = vocab.lookups
get_noun_chunks = vocab.get_noun_chunks
return (unpickle_vocab,
(sstore, vectors, morph, data_dir, lex_attr_getters, lookups))
(sstore, vectors, morph, data_dir, lex_attr_getters, lookups, get_noun_chunks))
def unpickle_vocab(sstore, vectors, morphology, data_dir,
lex_attr_getters, lookups):
lex_attr_getters, lookups, get_noun_chunks):
cdef Vocab vocab = Vocab()
vocab.vectors = vectors
vocab.strings = sstore
@ -564,6 +565,7 @@ def unpickle_vocab(sstore, vectors, morphology, data_dir,
vocab.data_dir = data_dir
vocab.lex_attr_getters = srsly.pickle_loads(lex_attr_getters)
vocab.lookups = lookups
vocab.get_noun_chunks = get_noun_chunks
return vocab