Merge branch 'develop' of https://github.com/explosion/spaCy into develop

spacy/syntax/nn_parser.pyx

@@ -837,6 +837,9 @@ cdef class Parser:
     def begin_training(self, get_gold_tuples, pipeline=None, sgd=None, **cfg):
         if 'model' in cfg:
             self.model = cfg['model']
+        if not hasattr(get_gold_tuples, '__call__'):
+            gold_tuples = get_gold_tuples
+            get_gold_tuples = lambda: gold_tuples
         cfg.setdefault('min_action_freq', 30)
         actions = self.moves.get_actions(gold_parses=get_gold_tuples(),
                                          min_freq=cfg.get('min_action_freq', 30))

spacy/tests/doc/test_token_api.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from ...attrs import IS_ALPHA, IS_DIGIT, IS_LOWER, IS_PUNCT, IS_TITLE, IS_STOP
+from ...symbols import NOUN, VERB
 from ..util import get_doc
 from ...vocab import Vocab
 from ...tokens import Doc
@@ -162,3 +163,10 @@ def test_is_sent_start(en_tokenizer):
     assert doc[5].is_sent_start is True
     doc.is_parsed = True
     assert len(list(doc.sents)) == 2
+
+def test_set_pos():
+    doc = Doc(Vocab(), words=['hello', 'world'])
+    doc[0].pos_ = 'NOUN'
+    assert doc[0].pos_ == 'NOUN'
+    doc[1].pos = VERB
+    assert doc[1].pos_ == 'VERB'

spacy/tokens/token.pyx

@@ -281,6 +281,8 @@ cdef class Token:
         """RETURNS (uint64): ID of coarse-grained part-of-speech tag."""
         def __get__(self):
             return self.c.pos
+        def __set__(self, pos):
+            self.c.pos = pos
 
     property tag:
         """RETURNS (uint64): ID of fine-grained part-of-speech tag."""
@@ -752,6 +754,8 @@ cdef class Token:
         """RETURNS (unicode): Coarse-grained part-of-speech tag."""
         def __get__(self):
             return parts_of_speech.NAMES[self.c.pos]
+        def __set__(self, pos_name):
+            self.c.pos = parts_of_speech.IDS[pos_name]
 
     property tag_:
         """RETURNS (unicode): Fine-grained part-of-speech tag."""