Merge branch 'develop' into feature/lemmatizer

spacy/_ml.py

@@ -311,7 +311,7 @@ def link_vectors_to_models(vocab):
 
 def Tok2Vec(width, embed_size, **kwargs):
     pretrained_dims = kwargs.get('pretrained_dims', 0)
-    cnn_maxout_pieces = kwargs.get('cnn_maxout_pieces', 3)
+    cnn_maxout_pieces = kwargs.get('cnn_maxout_pieces', 2)
     cols = [ID, NORM, PREFIX, SUFFIX, SHAPE, ORTH]
     with Model.define_operators({'>>': chain, '|': concatenate, '**': clone, '+': add,
                                  '*': reapply}):

spacy/cli/train.py

@@ -68,6 +68,8 @@ def train(cmd, lang, output_dir, train_data, dev_data, n_iter=10, n_sents=0,
     if not isinstance(meta, dict):
         prints("Expected dict but got: {}".format(type(meta)),
                title="Not a valid meta.json format", exits=1)
+    meta.setdefault('lang', lang)
+    meta.setdefault('name', 'unnamed')
 
     pipeline = ['tagger', 'parser', 'ner']
     if no_tagger and 'tagger' in pipeline: pipeline.remove('tagger')
@@ -89,6 +91,8 @@ def train(cmd, lang, output_dir, train_data, dev_data, n_iter=10, n_sents=0,
 
     lang_class = util.get_lang_class(lang)
     nlp = lang_class()
+    meta['pipeline'] = pipeline
+    nlp.meta.update(meta)
     if vectors:
         util.load_model(vectors, vocab=nlp.vocab)
     for name in pipeline:

spacy/gold.pyx

@@ -213,7 +213,7 @@ class GoldCorpus(object):
         train_tuples = self.train_tuples
         if projectivize:
             train_tuples = nonproj.preprocess_training_data(
-                               self.train_tuples)
+                               self.train_tuples, label_freq_cutoff=100)
         random.shuffle(train_tuples)
         gold_docs = self.iter_gold_docs(nlp, train_tuples, gold_preproc,
                                         max_length=max_length,

spacy/syntax/nn_parser.pyx

@@ -239,13 +239,13 @@ cdef class Parser:
     """
     @classmethod
     def Model(cls, nr_class, **cfg):
-        depth = util.env_opt('parser_hidden_depth', cfg.get('hidden_depth', 0))
-        token_vector_width = util.env_opt('token_vector_width', cfg.get('token_vector_width', 128))
-        hidden_width = util.env_opt('hidden_width', cfg.get('hidden_width', 128))
-        parser_maxout_pieces = util.env_opt('parser_maxout_pieces', cfg.get('maxout_pieces', 3))
+        depth = util.env_opt('parser_hidden_depth', cfg.get('hidden_depth', 1))
+        token_vector_width = util.env_opt('token_vector_width', cfg.get('token_vector_width', 64))
+        hidden_width = util.env_opt('hidden_width', cfg.get('hidden_width', 64))
+        parser_maxout_pieces = util.env_opt('parser_maxout_pieces', cfg.get('maxout_pieces', 2))
         embed_size = util.env_opt('embed_size', cfg.get('embed_size', 7000))
-        hist_size = util.env_opt('history_feats', cfg.get('hist_size', 0))
-        hist_width = util.env_opt('history_width', cfg.get('hist_width', 0))
+        hist_size = util.env_opt('history_feats', cfg.get('hist_size', 4))
+        hist_width = util.env_opt('history_width', cfg.get('hist_width', 16))
         if hist_size >= 1 and depth == 0:
             raise ValueError("Inconsistent hyper-params: "
                 "history_feats >= 1 but parser_hidden_depth==0")
@@ -800,6 +800,15 @@ cdef class Parser:
         if self.model not in (True, False, None) and resized:
             # Weights are stored in (nr_out, nr_in) format, so we're basically
             # just adding rows here.
+            if self.model[-1].is_noop:
+                smaller = self.model[1]
+                dims = dict(self.model[1]._dims)
+                dims['nO'] = self.moves.n_moves
+                larger = self.model[1].__class__(**dims)
+                copy_array(larger.W[:, :smaller.nO], smaller.W)
+                copy_array(larger.b[:smaller.nO], smaller.b)
+                self.model = (self.model[0], larger, self.model[2])
+            else:
                 smaller = self.model[-1]._layers[-1]
                 larger = Affine(self.moves.n_moves, smaller.nI)
                 copy_array(larger.W[:smaller.nO], smaller.W)
@@ -809,7 +818,7 @@ cdef class Parser:
     def begin_training(self, gold_tuples, pipeline=None, **cfg):
         if 'model' in cfg:
             self.model = cfg['model']
-        gold_tuples = nonproj.preprocess_training_data(gold_tuples)
+        gold_tuples = nonproj.preprocess_training_data(gold_tuples, label_freq_cutoff=100)
         actions = self.moves.get_actions(gold_parses=gold_tuples)
         for action, labels in actions.items():
             for label in labels:

spacy/tests/parser/test_add_label.py

@@ -22,14 +22,14 @@ def vocab():
 @pytest.fixture
 def parser(vocab):
     parser = NeuralDependencyParser(vocab)
-    parser.cfg['token_vector_width'] = 4
-    parser.cfg['hidden_width'] = 6
+    parser.cfg['token_vector_width'] = 8
+    parser.cfg['hidden_width'] = 30
     parser.cfg['hist_size'] = 0
     parser.add_label('left')
     parser.begin_training([], **parser.cfg)
     sgd = Adam(NumpyOps(), 0.001)
 
-    for i in range(30):
+    for i in range(10):
         losses = {}
         doc = Doc(vocab, words=['a', 'b', 'c', 'd'])
         gold = GoldParse(doc, heads=[1, 1, 3, 3],
@@ -37,6 +37,8 @@ def parser(vocab):
         parser.update([doc], [gold], sgd=sgd, losses=losses)
     return parser
 
+def test_init_parser(parser):
+    pass
 
 def test_add_label(parser):
     doc = Doc(parser.vocab, words=['a', 'b', 'c', 'd'])

spacy/tests/parser/test_preset_sbd.py

@@ -64,7 +64,7 @@ def test_sents_1_3(parser):
     doc[1].sent_start = True
     doc[3].sent_start = True
     doc = parser(doc)
-    assert len(list(doc.sents)) == 4
+    assert len(list(doc.sents)) >= 3
     doc = Doc(parser.vocab, words=['a', 'b', 'c', 'd'])
     doc[1].sent_start = True
     doc[2].sent_start = False