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

examples/training/train_textcat.py

@@ -26,7 +26,7 @@ from spacy.pipeline import TextCategorizer
 @plac.annotations(
     model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
     output_dir=("Optional output directory", "option", "o", Path),
-    n_examples=("Number of texts to train from", "option", "N", int),
+    n_texts=("Number of texts to train from", "option", "t", int),
     n_iter=("Number of training iterations", "option", "n", int))
 def main(model=None, output_dir=None, n_iter=20, n_texts=2000):
     if model is not None:
@@ -39,20 +39,19 @@ def main(model=None, output_dir=None, n_iter=20, n_texts=2000):
     # add the text classifier to the pipeline if it doesn't exist
     # nlp.create_pipe works for built-ins that are registered with spaCy
     if 'textcat' not in nlp.pipe_names:
-        # textcat = nlp.create_pipe('textcat')
+        textcat = nlp.create_pipe('textcat')
-        textcat = TextCategorizer(nlp.vocab, labels=['POSITIVE'])
         nlp.add_pipe(textcat, last=True)
     # otherwise, get it, so we can add labels to it
     else:
         textcat = nlp.get_pipe('textcat')
 
     # add label to text classifier
-    # textcat.add_label('POSITIVE')
+    textcat.add_label('POSITIVE')
 
     # load the IMBD dataset
     print("Loading IMDB data...")
-    print("Using %d training examples" % n_texts)
     (train_texts, train_cats), (dev_texts, dev_cats) = load_data(limit=n_texts)
+    print("Using %d training examples" % n_texts)
     train_docs = [nlp.tokenizer(text) for text in train_texts]
     train_gold = [GoldParse(doc, cats=cats) for doc, cats in
                   zip(train_docs, train_cats)]

spacy/pipeline.pyx

@@ -441,11 +441,12 @@ class Tagger(Pipe):
     def add_label(self, label):
         if label in self.labels:
             return 0
-        smaller = self.model[-1]._layers[-1]
+        if self.model not in (True, False, None):
+            smaller = self.model._layers[-1]
             larger = Softmax(len(self.labels)+1, smaller.nI)
             copy_array(larger.W[:smaller.nO], smaller.W)
             copy_array(larger.b[:smaller.nO], smaller.b)
-        self.model[-1]._layers[-1] = larger
+            self.model._layers[-1] = larger
         self.labels.append(label)
         return 1
 
@@ -759,11 +760,12 @@ class TextCategorizer(Pipe):
     def add_label(self, label):
         if label in self.labels:
             return 0
-        smaller = self.model[-1]._layers[-1]
+        if self.model not in (None, True, False):
+            smaller = self.model._layers[-1]
             larger = Affine(len(self.labels)+1, smaller.nI)
             copy_array(larger.W[:smaller.nO], smaller.W)
             copy_array(larger.b[:smaller.nO], smaller.b)
-        self.model[-1]._layers[-1] = larger
+            self.model._layers[-1] = larger
         self.labels.append(label)
         return 1