mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +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>
140 lines
5.2 KiB
Python
140 lines
5.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import pickle
|
|
from spacy.vocab import Vocab
|
|
from spacy.strings import StringStore
|
|
|
|
from ..util import make_tempdir
|
|
|
|
|
|
test_strings = [([], []), (["rats", "are", "cute"], ["i", "like", "rats"])]
|
|
test_strings_attrs = [(["rats", "are", "cute"], "Hello")]
|
|
|
|
|
|
@pytest.mark.xfail
|
|
@pytest.mark.parametrize("text", ["rat"])
|
|
def test_serialize_vocab(en_vocab, text):
|
|
text_hash = en_vocab.strings.add(text)
|
|
vocab_bytes = en_vocab.to_bytes(exclude=["lookups"])
|
|
new_vocab = Vocab().from_bytes(vocab_bytes)
|
|
assert new_vocab.strings[text_hash] == text
|
|
assert new_vocab.to_bytes(exclude=["lookups"]) == vocab_bytes
|
|
|
|
|
|
@pytest.mark.parametrize("strings1,strings2", test_strings)
|
|
def test_serialize_vocab_roundtrip_bytes(strings1, strings2):
|
|
vocab1 = Vocab(strings=strings1)
|
|
vocab2 = Vocab(strings=strings2)
|
|
vocab1_b = vocab1.to_bytes()
|
|
vocab2_b = vocab2.to_bytes()
|
|
if strings1 == strings2:
|
|
assert vocab1_b == vocab2_b
|
|
else:
|
|
assert vocab1_b != vocab2_b
|
|
vocab1 = vocab1.from_bytes(vocab1_b)
|
|
assert vocab1.to_bytes() == vocab1_b
|
|
new_vocab1 = Vocab().from_bytes(vocab1_b)
|
|
assert new_vocab1.to_bytes() == vocab1_b
|
|
assert len(new_vocab1.strings) == len(strings1) + 1 # adds _SP
|
|
assert sorted([s for s in new_vocab1.strings]) == sorted(strings1 + ["_SP"])
|
|
|
|
|
|
@pytest.mark.parametrize("strings1,strings2", test_strings)
|
|
def test_serialize_vocab_roundtrip_disk(strings1, strings2):
|
|
vocab1 = Vocab(strings=strings1)
|
|
vocab2 = Vocab(strings=strings2)
|
|
with make_tempdir() as d:
|
|
file_path1 = d / "vocab1"
|
|
file_path2 = d / "vocab2"
|
|
vocab1.to_disk(file_path1)
|
|
vocab2.to_disk(file_path2)
|
|
vocab1_d = Vocab().from_disk(file_path1)
|
|
vocab2_d = Vocab().from_disk(file_path2)
|
|
# check strings rather than lexemes, which are only reloaded on demand
|
|
assert strings1 == [s for s in vocab1_d.strings if s != "_SP"]
|
|
assert strings2 == [s for s in vocab2_d.strings if s != "_SP"]
|
|
if strings1 == strings2:
|
|
assert [s for s in vocab1_d.strings if s != "_SP"] == [s for s in vocab2_d.strings if s != "_SP"]
|
|
else:
|
|
assert [s for s in vocab1_d.strings if s != "_SP"] != [s for s in vocab2_d.strings if s != "_SP"]
|
|
|
|
|
|
@pytest.mark.parametrize("strings,lex_attr", test_strings_attrs)
|
|
def test_serialize_vocab_lex_attrs_bytes(strings, lex_attr):
|
|
vocab1 = Vocab(strings=strings)
|
|
vocab2 = Vocab()
|
|
vocab1[strings[0]].norm_ = lex_attr
|
|
assert vocab1[strings[0]].norm_ == lex_attr
|
|
assert vocab2[strings[0]].norm_ != lex_attr
|
|
vocab2 = vocab2.from_bytes(vocab1.to_bytes())
|
|
assert vocab2[strings[0]].norm_ == lex_attr
|
|
|
|
|
|
@pytest.mark.parametrize("strings,lex_attr", test_strings_attrs)
|
|
def test_deserialize_vocab_seen_entries(strings, lex_attr):
|
|
# Reported in #2153
|
|
vocab = Vocab(strings=strings)
|
|
length = len(vocab)
|
|
vocab.from_bytes(vocab.to_bytes())
|
|
assert len(vocab.strings) == len(strings) + 1 # adds _SP
|
|
|
|
|
|
@pytest.mark.parametrize("strings,lex_attr", test_strings_attrs)
|
|
def test_serialize_vocab_lex_attrs_disk(strings, lex_attr):
|
|
vocab1 = Vocab(strings=strings)
|
|
vocab2 = Vocab()
|
|
vocab1[strings[0]].norm_ = lex_attr
|
|
assert vocab1[strings[0]].norm_ == lex_attr
|
|
assert vocab2[strings[0]].norm_ != lex_attr
|
|
with make_tempdir() as d:
|
|
file_path = d / "vocab"
|
|
vocab1.to_disk(file_path)
|
|
vocab2 = vocab2.from_disk(file_path)
|
|
assert vocab2[strings[0]].norm_ == lex_attr
|
|
|
|
|
|
@pytest.mark.parametrize("strings1,strings2", test_strings)
|
|
def test_serialize_stringstore_roundtrip_bytes(strings1, strings2):
|
|
sstore1 = StringStore(strings=strings1)
|
|
sstore2 = StringStore(strings=strings2)
|
|
sstore1_b = sstore1.to_bytes()
|
|
sstore2_b = sstore2.to_bytes()
|
|
if strings1 == strings2:
|
|
assert sstore1_b == sstore2_b
|
|
else:
|
|
assert sstore1_b != sstore2_b
|
|
sstore1 = sstore1.from_bytes(sstore1_b)
|
|
assert sstore1.to_bytes() == sstore1_b
|
|
new_sstore1 = StringStore().from_bytes(sstore1_b)
|
|
assert new_sstore1.to_bytes() == sstore1_b
|
|
assert list(new_sstore1) == strings1
|
|
|
|
|
|
@pytest.mark.parametrize("strings1,strings2", test_strings)
|
|
def test_serialize_stringstore_roundtrip_disk(strings1, strings2):
|
|
sstore1 = StringStore(strings=strings1)
|
|
sstore2 = StringStore(strings=strings2)
|
|
with make_tempdir() as d:
|
|
file_path1 = d / "strings1"
|
|
file_path2 = d / "strings2"
|
|
sstore1.to_disk(file_path1)
|
|
sstore2.to_disk(file_path2)
|
|
sstore1_d = StringStore().from_disk(file_path1)
|
|
sstore2_d = StringStore().from_disk(file_path2)
|
|
assert list(sstore1_d) == list(sstore1)
|
|
assert list(sstore2_d) == list(sstore2)
|
|
if strings1 == strings2:
|
|
assert list(sstore1_d) == list(sstore2_d)
|
|
else:
|
|
assert list(sstore1_d) != list(sstore2_d)
|
|
|
|
@pytest.mark.parametrize("strings,lex_attr", test_strings_attrs)
|
|
def test_pickle_vocab(strings, lex_attr):
|
|
vocab = Vocab(strings=strings)
|
|
vocab[strings[0]].norm_ = lex_attr
|
|
vocab_pickled = pickle.dumps(vocab)
|
|
vocab_unpickled = pickle.loads(vocab_pickled)
|
|
assert vocab.to_bytes() == vocab_unpickled.to_bytes()
|