Merge pull request #570 from kendricktan/master

Fixed training examples

examples/training/train_ner.py

@@ -6,6 +6,7 @@ import random
 import spacy
 from spacy.pipeline import EntityRecognizer
 from spacy.gold import GoldParse
+from spacy.tagger import Tagger
 
 
 def train_ner(nlp, train_data, entity_types):
@@ -29,6 +30,15 @@ def main(model_dir=None):
 
     nlp = spacy.load('en', parser=False, entity=False, add_vectors=False)
 
+    # v1.1.2 onwards
+    if nlp.tagger is None:
+        print('---- WARNING ----')
+        print('Data directory not found')
+        print('please run: `python -m spacy.en.download –force all` for better performance')
+        print('Using feature templates for tagging')
+        print('-----------------')
+        nlp.tagger = Tagger(nlp.vocab, features=Tagger.feature_templates)
+
     train_data = [
         (
             'Who is Shaka Khan?',

examples/training/train_tagger.py

@@ -10,8 +10,9 @@ from pathlib import Path
 from spacy.vocab import Vocab
 from spacy.tagger import Tagger
 from spacy.tokens import Doc
-import random
+from spacy.gold import GoldParse
 
+import random
 
 # You need to define a mapping from your data's part-of-speech tag names to the
 # Universal Part-of-Speech tag set, as spaCy includes an enum of these tags.
@@ -23,7 +24,7 @@ TAG_MAP = {
     'N': {"pos": "NOUN"},
     'V': {"pos": "VERB"},
     'J': {"pos": "ADJ"}
-    }
+}
 
 # Usually you'll read this in, of course. Data formats vary.
 # Ensure your strings are unicode.
@@ -38,6 +39,7 @@ DATA = [
     )
 ]
 
+
 def ensure_dir(path):
     if not path.exists():
         path.mkdir()
@@ -54,13 +56,14 @@ def main(output_dir=None):
     # The default_templates argument is where features are specified. See
     # spacy/tagger.pyx for the defaults.
     tagger = Tagger(vocab)
-    for i in range(5):
+    for i in range(25):
         for words, tags in DATA:
             doc = Doc(vocab, words=words)
-            tagger.update(doc, tags)
+            gold = GoldParse(doc, tags=tags)
+            tagger.update(doc, gold)
         random.shuffle(DATA)
     tagger.model.end_training()
-    doc = Doc(vocab, orths_and_spaces=zip(["I", "like", "blue", "eggs"], [True]*4))
+    doc = Doc(vocab, orths_and_spaces=zip(["I", "like", "blue", "eggs"], [True] * 4))
     tagger(doc)
     for word in doc:
         print(word.text, word.tag_, word.pos_)