mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
a5cd203284
* Reduce stored lexemes data, move feats to lookups
* Move non-derivable lexemes features (`norm / cluster / prob`) to
`spacy-lookups-data` as lookups
* Get/set `norm` in both lookups and `LexemeC`, serialize in lookups
* Remove `cluster` and `prob` from `LexemesC`, get/set/serialize in
lookups only
* Remove serialization of lexemes data as `vocab/lexemes.bin`
* Remove `SerializedLexemeC`
* Remove `Lexeme.to_bytes/from_bytes`
* Modify normalization exception loading:
* Always create `Vocab.lookups` table `lexeme_norm` for
normalization exceptions
* Load base exceptions from `lang.norm_exceptions`, but load
language-specific exceptions from lookups
* Set `lex_attr_getter[NORM]` including new lookups table in
`BaseDefaults.create_vocab()` and when deserializing `Vocab`
* Remove all cached lexemes when deserializing vocab to override
existing normalizations with the new normalizations (as a replacement
for the previous step that replaced all lexemes data with the
deserialized data)
* Skip English normalization test
Skip English normalization test because the data is now in
`spacy-lookups-data`.
* Remove norm exceptions
Moved to spacy-lookups-data.
* Move norm exceptions test to spacy-lookups-data
* Load extra lookups from spacy-lookups-data lazily
Load extra lookups (currently for cluster and prob) lazily from the
entry point `lg_extra` as `Vocab.lookups_extra`.
* Skip creating lexeme cache on load
To improve model loading times, do not create the full lexeme cache when
loading. The lexemes will be created on demand when processing.
* Identify numeric values in Lexeme.set_attrs()
With the removal of a special case for `PROB`, also identify `float` to
avoid trying to convert it with the `StringStore`.
* Skip lexeme cache init in from_bytes
* Unskip and update lookups tests for python3.6+
* Update vocab pickle to include lookups_extra
* Update vocab serialization tests
Check strings rather than lexemes since lexemes aren't initialized
automatically, account for addition of "_SP".
* Re-skip lookups test because of python3.5
* Skip PROB/float values in Lexeme.set_attrs
* Convert is_oov from lexeme flag to lex in vectors
Instead of storing `is_oov` as a lexeme flag, `is_oov` reports whether
the lexeme has a vector.
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
50 lines
1.9 KiB
Python
50 lines
1.9 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.tokens import Doc
|
|
from spacy.language import Language
|
|
from spacy.lookups import Lookups
|
|
|
|
|
|
def test_lemmatizer_reflects_lookups_changes():
|
|
"""Test for an issue that'd cause lookups available in a model loaded from
|
|
disk to not be reflected in the lemmatizer."""
|
|
nlp = Language()
|
|
assert Doc(nlp.vocab, words=["foo"])[0].lemma_ == "foo"
|
|
table = nlp.vocab.lookups.add_table("lemma_lookup")
|
|
table["foo"] = "bar"
|
|
assert Doc(nlp.vocab, words=["foo"])[0].lemma_ == "bar"
|
|
table = nlp.vocab.lookups.get_table("lemma_lookup")
|
|
table["hello"] = "world"
|
|
# The update to the table should be reflected in the lemmatizer
|
|
assert Doc(nlp.vocab, words=["hello"])[0].lemma_ == "world"
|
|
new_nlp = Language()
|
|
table = new_nlp.vocab.lookups.add_table("lemma_lookup")
|
|
table["hello"] = "hi"
|
|
assert Doc(new_nlp.vocab, words=["hello"])[0].lemma_ == "hi"
|
|
nlp_bytes = nlp.to_bytes()
|
|
new_nlp.from_bytes(nlp_bytes)
|
|
# Make sure we have the previously saved lookup table
|
|
assert "lemma_lookup" in new_nlp.vocab.lookups
|
|
assert len(new_nlp.vocab.lookups.get_table("lemma_lookup")) == 2
|
|
assert new_nlp.vocab.lookups.get_table("lemma_lookup")["hello"] == "world"
|
|
assert Doc(new_nlp.vocab, words=["foo"])[0].lemma_ == "bar"
|
|
assert Doc(new_nlp.vocab, words=["hello"])[0].lemma_ == "world"
|
|
|
|
|
|
def test_tagger_warns_no_lemma_lookups():
|
|
nlp = Language()
|
|
nlp.vocab.lookups = Lookups()
|
|
assert not len(nlp.vocab.lookups)
|
|
tagger = nlp.create_pipe("tagger")
|
|
with pytest.warns(UserWarning):
|
|
tagger.begin_training()
|
|
nlp.add_pipe(tagger)
|
|
with pytest.warns(UserWarning):
|
|
nlp.begin_training()
|
|
nlp.vocab.lookups.add_table("lemma_lookup")
|
|
with pytest.warns(None) as record:
|
|
nlp.begin_training()
|
|
assert not record.list
|