explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-27 02:16:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add symbols to the vocab before reading the strings, so that they line up correctly

Browse Source
This commit is contained in:
Matthew Honnibal 2015-10-10 17:58:29 +11:00
parent 74c0853471
commit a29c8ee23d
1 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
spacy/vocab.pyx
View File

@ -19,6 +19,9 @@ from .typedefs cimport attr_t
from .cfile cimport CFile from .cfile cimport CFile
from .lemmatizer import Lemmatizer from .lemmatizer import Lemmatizer
from . import attrs
from . import parts_of_speech
from cymem.cymem cimport Address from cymem.cymem cimport Address
from . import util from . import util
from .serialize.packer cimport Packer from .serialize.packer cimport Packer
@ -72,15 +75,15 @@ cdef class Vocab:
# is the frequency rank of the word, plus a certain offset. The structural # is the frequency rank of the word, plus a certain offset. The structural
# strings are loaded first, because the vocab is open-class, and these # strings are loaded first, because the vocab is open-class, and these
# symbols are closed class. # symbols are closed class.
#for attr_name in sorted(ATTR_NAMES.keys()): for name in attrs.NAMES:
# _ = self.strings[attr_name] _ = self.strings[name]
#for univ_pos_name in sorted(UNIV_POS_NAMES.keys()): for name in parts_of_speech.NAMES:
# _ = self.strings[pos_name] _ = self.strings[name]
#for morph_name in sorted(UNIV_MORPH_NAMES.keys()): #for morph_name in UNIV_MORPH_NAMES:
# _ = self.strings[morph_name] # _ = self.strings[morph_name]
#for entity_type_name in sorted(ENTITY_TYPES.keys()): #for entity_type_name in entity_types.NAMES:
# _ = self.strings[entity_type_name] # _ = self.strings[entity_type_name]
#for tag_name in sorted(TAG_MAP.keys()): #for tag_name in sorted(tag_map.keys()):
# _ = self.strings[tag_name] # _ = self.strings[tag_name]
self.get_lex_attr = get_lex_attr self.get_lex_attr = get_lex_attr
self.morphology = Morphology(self.strings, tag_map, lemmatizer) self.morphology = Morphology(self.strings, tag_map, lemmatizer)