mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-03 09:27:56 +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>
68 lines
2.3 KiB
Python
68 lines
2.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import numpy
|
|
from spacy.attrs import IS_ALPHA, IS_DIGIT
|
|
from spacy.util import OOV_RANK
|
|
|
|
|
|
@pytest.mark.parametrize("text1,prob1,text2,prob2", [("NOUN", -1, "opera", -2)])
|
|
def test_vocab_lexeme_lt(en_vocab, text1, text2, prob1, prob2):
|
|
"""More frequent is l.t. less frequent"""
|
|
lex1 = en_vocab[text1]
|
|
lex1.prob = prob1
|
|
lex2 = en_vocab[text2]
|
|
lex2.prob = prob2
|
|
|
|
assert lex1 < lex2
|
|
assert lex2 > lex1
|
|
|
|
|
|
@pytest.mark.parametrize("text1,text2", [("phantom", "opera")])
|
|
def test_vocab_lexeme_hash(en_vocab, text1, text2):
|
|
"""Test that lexemes are hashable."""
|
|
lex1 = en_vocab[text1]
|
|
lex2 = en_vocab[text2]
|
|
lexes = {lex1: lex1, lex2: lex2}
|
|
assert lexes[lex1].orth_ == text1
|
|
assert lexes[lex2].orth_ == text2
|
|
|
|
|
|
def test_vocab_lexeme_is_alpha(en_vocab):
|
|
assert en_vocab["the"].flags & (1 << IS_ALPHA)
|
|
assert not en_vocab["1999"].flags & (1 << IS_ALPHA)
|
|
assert not en_vocab["hello1"].flags & (1 << IS_ALPHA)
|
|
|
|
|
|
def test_vocab_lexeme_is_digit(en_vocab):
|
|
assert not en_vocab["the"].flags & (1 << IS_DIGIT)
|
|
assert en_vocab["1999"].flags & (1 << IS_DIGIT)
|
|
assert not en_vocab["hello1"].flags & (1 << IS_DIGIT)
|
|
|
|
|
|
def test_vocab_lexeme_add_flag_auto_id(en_vocab):
|
|
is_len4 = en_vocab.add_flag(lambda string: len(string) == 4)
|
|
assert en_vocab["1999"].check_flag(is_len4) is True
|
|
assert en_vocab["1999"].check_flag(IS_DIGIT) is True
|
|
assert en_vocab["199"].check_flag(is_len4) is False
|
|
assert en_vocab["199"].check_flag(IS_DIGIT) is True
|
|
assert en_vocab["the"].check_flag(is_len4) is False
|
|
assert en_vocab["dogs"].check_flag(is_len4) is True
|
|
|
|
|
|
def test_vocab_lexeme_add_flag_provided_id(en_vocab):
|
|
is_len4 = en_vocab.add_flag(lambda string: len(string) == 4, flag_id=IS_DIGIT)
|
|
assert en_vocab["1999"].check_flag(is_len4) is True
|
|
assert en_vocab["199"].check_flag(is_len4) is False
|
|
assert en_vocab["199"].check_flag(IS_DIGIT) is False
|
|
assert en_vocab["the"].check_flag(is_len4) is False
|
|
assert en_vocab["dogs"].check_flag(is_len4) is True
|
|
|
|
|
|
def test_vocab_lexeme_oov_rank(en_vocab):
|
|
"""Test that default rank is OOV_RANK."""
|
|
lex = en_vocab["word"]
|
|
assert OOV_RANK == numpy.iinfo(numpy.uint64).max
|
|
assert lex.rank == OOV_RANK
|