spaCy/spacy/lang/en/__init__.py

82 lines
2.5 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
from __future__ import unicode_literals
2015-07-07 15:00:07 +03:00
2017-05-08 16:47:25 +03:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
2017-05-09 02:09:52 +03:00
from .lex_attrs import LEX_ATTRS
2017-05-08 16:47:25 +03:00
from .morph_rules import MORPH_RULES
from .syntax_iterators import SYNTAX_ITERATORS
2017-05-08 16:47:25 +03:00
2017-05-08 23:29:04 +03:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language
Reduce stored lexemes data, move feats to lookups (#5238) * 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>
2020-05-19 16:59:14 +03:00
from ...attrs import LANG
from ...util import update_exc
def _return_en(_):
return "en"
def en_is_base_form(univ_pos, morphology=None):
"""
Check whether we're dealing with an uninflected paradigm, so we can
avoid lemmatization entirely.
univ_pos (unicode / int): The token's universal part-of-speech tag.
morphology (dict): The token's morphological features following the
Universal Dependencies scheme.
"""
if morphology is None:
morphology = {}
if univ_pos == "noun" and morphology.get("Number") == "sing":
return True
elif univ_pos == "verb" and morphology.get("VerbForm") == "inf":
return True
# This maps 'VBP' to base form -- probably just need 'IS_BASE'
# morphology
elif univ_pos == "verb" and (
morphology.get("VerbForm") == "fin"
and morphology.get("Tense") == "pres"
and morphology.get("Number") is None
):
return True
elif univ_pos == "adj" and morphology.get("Degree") == "pos":
return True
elif morphology.get("VerbForm") == "inf":
return True
elif morphology.get("VerbForm") == "none":
return True
elif morphology.get("Degree") == "pos":
return True
else:
return False
class EnglishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = _return_en
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = TAG_MAP
stop_words = STOP_WORDS
morph_rules = MORPH_RULES
is_base_form = en_is_base_form
syntax_iterators = SYNTAX_ITERATORS
2019-09-11 15:00:36 +03:00
single_orth_variants = [
{"tags": ["NFP"], "variants": ["", "..."]},
{"tags": [":"], "variants": ["-", "", "", "--", "---", "——"]},
]
paired_orth_variants = [
{"tags": ["``", "''"], "variants": [("'", "'"), ("", "")]},
{"tags": ["``", "''"], "variants": [('"', '"'), ("", "")]},
]
2015-08-25 16:37:30 +03:00
class English(Language):
lang = "en"
Defaults = EnglishDefaults
__all__ = ["English"]