explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Remove regularization cruft from _ml, move score from .pxd file to .pyx

Browse Source
This commit is contained in:
Matthew Honnibal 2015-05-31 18:48:05 +02:00
parent 08044ea70c
commit d82f9d958d
2 changed files with 7 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/_ml.pxd
View File

@ -18,18 +18,10 @@ cdef int arg_max(const weight_t* scores, const int n_classes) nogil
cdef class Model: cdef class Model:
cdef int n_classes cdef int n_classes
cdef int regularize(self, Feature* feats, int n, int a=*) except -1 cdef const weight_t* score(self, atom_t* context, bint regularize) except NULL
cdef int update(self, atom_t* context, class_t guess, class_t gold, int cost) except -1 cdef int update(self, atom_t* context, class_t guess, class_t gold, int cost) except -1
cdef object model_loc cdef object model_loc
cdef Extractor _extractor cdef Extractor _extractor
cdef LinearModel _model cdef LinearModel _model
cdef inline const weight_t* score(self, atom_t* context, bint regularize) except NULL:
cdef int n_feats
feats = self._extractor.get_feats(context, &n_feats)
if regularize:
self.regularize(feats, n_feats, 3)
return self._model.get_scores(feats, n_feats)

18
spacy/_ml.pyx
View File

@ -33,6 +33,11 @@ cdef class Model:
if self.model_loc and path.exists(self.model_loc): if self.model_loc and path.exists(self.model_loc):
self._model.load(self.model_loc, freq_thresh=0) self._model.load(self.model_loc, freq_thresh=0)
cdef const weight_t* score(self, atom_t* context, bint regularize) except NULL:
cdef int n_feats
feats = self._extractor.get_feats(context, &n_feats)
return self._model.get_scores(feats, n_feats)
cdef int update(self, atom_t* context, class_t guess, class_t gold, int cost) except -1: cdef int update(self, atom_t* context, class_t guess, class_t gold, int cost) except -1:
cdef int n_feats cdef int n_feats
if cost == 0: if cost == 0:
@ -44,19 +49,6 @@ cdef class Model:
count_feats(counts[guess], feats, n_feats, -cost) count_feats(counts[guess], feats, n_feats, -cost)
self._model.update(counts) self._model.update(counts)
@cython.cdivision
@cython.boundscheck(False)
cdef int regularize(self, Feature* feats, int n, int a=3) except -1:
pass
# Disable this for now, while we investigate effect.
# Use the Zipfian corruptions technique from here:
# http://www.aclweb.org/anthology/N13-1077
# This seems good for 0.1 - 0.3 % on OOD data.
#cdef int i
#cdef long[:] zipfs = numpy.random.zipf(a, n)
#for i in range(n):
# feats[i].value *= 1 / zipfs[i]
def end_training(self): def end_training(self):
self._model.end_training() self._model.end_training()
self._model.dump(self.model_loc, freq_thresh=0) self._model.dump(self.model_loc, freq_thresh=0)