Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Messily hook up vector in tokens

This commit is contained in:
Matthew Honnibal 2015-01-19 19:59:55 +11:00
parent 06e7456c65
commit b65b0c07bf
2 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/tokens.pxd
View File

@ -1,6 +1,6 @@
from libc.stdint cimport uint32_t from libc.stdint cimport uint32_t
from cython.view cimport array as cvarray from numpy cimport ndarray
from cymem.cymem cimport Pool from cymem.cymem cimport Pool
from thinc.typedefs cimport atom_t from thinc.typedefs cimport atom_t
@ -62,3 +62,5 @@ cdef class Token:
cdef readonly univ_tag_t pos cdef readonly univ_tag_t pos
cdef readonly attr_t tag cdef readonly attr_t tag
cdef readonly attr_t dep cdef readonly attr_t dep
cdef readonly ndarray vec

7
spacy/tokens.pyx
View File

@ -10,6 +10,9 @@ from .typedefs cimport LEMMA
from .typedefs cimport ID, SIC, NORM1, NORM2, SHAPE, PREFIX, SUFFIX, LENGTH, CLUSTER from .typedefs cimport ID, SIC, NORM1, NORM2, SHAPE, PREFIX, SUFFIX, LENGTH, CLUSTER
from .typedefs cimport POS, LEMMA from .typedefs cimport POS, LEMMA
cimport numpy
import numpy
cimport cython cimport cython
@ -201,6 +204,10 @@ cdef class Token:
self.tag = t.tag self.tag = t.tag
self.dep = t.dep self.dep = t.dep
self.vec = numpy.ndarray(shape=(300,), dtype=numpy.float32)
for i in range(300):
self.vec[i] = t.lex.vec[i]
def __unicode__(self): def __unicode__(self):
cdef const TokenC* t = &self._seq.data[self.i] cdef const TokenC* t = &self._seq.data[self.i]
cdef int end_idx = t.idx + t.lex.length cdef int end_idx = t.idx + t.lex.length