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

Fix morphologizer class

This commit is contained in:
Matthew Honnibal 2018-09-25 10:58:13 +02:00
parent e6dde97295
commit c2357d3ba0
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/_morphologizer.pyx
View File

@ -12,7 +12,7 @@ from thinc.api import chain
from thinc.neural.util import to_categorical, copy_array from thinc.neural.util import to_categorical, copy_array
from . import util from . import util
from .pipe import Pipe from .pipe import Pipe
from ._ml import Tok2Vec, build_tagger_model from ._ml import Tok2Vec, build_morphologizer_model
from ._ml import link_vectors_to_models, zero_init, flatten from ._ml import link_vectors_to_models, zero_init, flatten
from ._ml import create_default_optimizer from ._ml import create_default_optimizer
from .errors import Errors, TempErrors from .errors import Errors, TempErrors
@ -20,6 +20,7 @@ from .compat import json_dumps, basestring_
from .tokens.doc cimport Doc from .tokens.doc cimport Doc
from .vocab cimport Vocab from .vocab cimport Vocab
from .morphology cimport Morphology from .morphology cimport Morphology
from .pipeline import Pipe
class Morphologizer(Pipe): class Morphologizer(Pipe):
@ -50,7 +51,7 @@ class Morphologizer(Pipe):
def __call__(self, doc): def __call__(self, doc):
features, tokvecs = self.predict([doc]) features, tokvecs = self.predict([doc])
self.set_annotations([doc], tags, tensors=tokvecs) self.set_annotations([doc], features, tensors=tokvecs)
return doc return doc
def pipe(self, stream, batch_size=128, n_threads=-1): def pipe(self, stream, batch_size=128, n_threads=-1):
@ -81,7 +82,7 @@ class Morphologizer(Pipe):
cdef Doc doc cdef Doc doc
cdef Vocab vocab = self.vocab cdef Vocab vocab = self.vocab
for i, doc in enumerate(docs): for i, doc in enumerate(docs):
doc_feat_ids = batch_feat_ids[i] doc_feat_ids = batch_feature_ids[i]
if hasattr(doc_feat_ids, 'get'): if hasattr(doc_feat_ids, 'get'):
doc_feat_ids = doc_feat_ids.get() doc_feat_ids = doc_feat_ids.get()
# Convert the neuron indices into feature IDs. # Convert the neuron indices into feature IDs.
@ -129,3 +130,9 @@ class Morphologizer(Pipe):
def use_params(self, params): def use_params(self, params):
with self.model.use_params(params): with self.model.use_params(params):
yield yield
def scores_to_guesses(scores, out_sizes):
raise NotImplementedError
def feature_to_column(feature):
raise NotImplementedError