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

spacy/__main__.py

@@ -7,6 +7,7 @@ if __name__ == '__main__':
     import plac
     import sys
     from spacy.cli import download, link, info, package, train, convert, model
+    from spacy.cli import profile
     from spacy.util import prints
 
     commands = {
@@ -16,7 +17,8 @@ if __name__ == '__main__':
         'train': train,
         'convert': convert,
         'package': package,
-        'model': model
+        'model': model,
+        'profile': profile,
     }
     if len(sys.argv) == 1:
         prints(', '.join(commands), title="Available commands", exits=1)

spacy/_ml.py

@@ -218,7 +218,10 @@ def drop_layer(layer, factor=2.):
             return layer.begin_update(X, drop=drop)
         else:
             return X, lambda dX, sgd=None: dX
-    return wrap(drop_layer_fwd, layer)
+
+    model = wrap(drop_layer_fwd, layer)
+    model.predict = layer
+    return model
 
 
 def Tok2Vec(width, embed_size, preprocess=None):
@@ -382,10 +385,18 @@ def fine_tune(embedding, combine=None):
             sgd(model._mem.weights, model._mem.gradient, key=model.id)
             return [d_o * model.mix[0] for d_o in d_output]
         return output, fine_tune_bwd
+
+    def fine_tune_predict(docs_tokvecs):
+        docs, tokvecs = docs_tokvecs
+        vecs = embedding(docs)
+        return [model.mix[0]*tv+model.mix[1]*v
+                for tv, v in zip(tokvecs, vecs)]
+
     model = wrap(fine_tune_fwd, embedding)
     model.mix = model._mem.add((model.id, 'mix'), (2,))
     model.mix.fill(0.5)
     model.d_mix = model._mem.add_gradient((model.id, 'd_mix'), (model.id, 'mix'))
+    model.predict = fine_tune_predict
     return model
 
 

spacy/cli/__init__.py

@@ -2,6 +2,7 @@ from .download import download
 from .info import info
 from .link import link
 from .package import package
+from .profile import profile
 from .train import train
 from .convert import convert
 from .model import model

spacy/cli/profile.py

@@ -0,0 +1,45 @@
+# coding: utf8
+from __future__ import unicode_literals, division, print_function
+
+import plac
+from pathlib import Path
+import ujson
+import cProfile
+import pstats
+
+import spacy
+import sys
+import tqdm
+import cytoolz
+
+
+def read_inputs(loc):
+    if loc is None:
+        file_ = sys.stdin
+        file_ = (line.encode('utf8') for line in file_)
+    else:
+        file_ = Path(loc).open()
+    for line in file_:
+        data = ujson.loads(line)
+        text = data['text']
+        yield text
+
+
+@plac.annotations(
+    lang=("model/language", "positional", None, str),
+    inputs=("Location of input file", "positional", None, read_inputs)
+)
+def profile(cmd, lang, inputs=None):
+    """
+    Profile a spaCy pipeline, to find out which functions take the most time.
+    """
+    nlp = spacy.load(lang) 
+    texts = list(cytoolz.take(10000, inputs))
+    cProfile.runctx("parse_texts(nlp, texts)", globals(), locals(), "Profile.prof")
+    s = pstats.Stats("Profile.prof")
+    s.strip_dirs().sort_stats("time").print_stats()
+
+
+def parse_texts(nlp, texts):
+    for doc in nlp.pipe(tqdm.tqdm(texts), batch_size=128):
+        pass

spacy/tokens/doc.pyx

@@ -303,8 +303,14 @@ cdef class Doc:
                 return self.user_hooks['vector'](self)
             if self._vector is not None:
                 return self._vector
-            elif self.has_vector and len(self):
+            elif not len(self):
-                self._vector = sum(t.vector for t in self) / len(self)
+                self._vector = numpy.zeros((self.vocab.vectors_length,), dtype='f')
+                return self._vector
+            elif self.has_vector:
+                vector = numpy.zeros((self.vocab.vectors_length,), dtype='f')
+                for token in self.c[:self.length]:
+                    vector += self.vocab.get_vector(token.lex.orth)
+                self._vector = vector / len(self)
                 return self._vector
             elif self.tensor is not None:
                 self._vector = self.tensor.mean(axis=0)

spacy/vocab.pyx

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import bz2
 import ujson
 import re
+import numpy
 
 from libc.string cimport memset, memcpy
 from libc.stdint cimport int32_t
@@ -244,7 +245,7 @@ cdef class Vocab:
 
     @property
     def vectors_length(self):
-        return len(self.vectors)
+        return self.vectors.data.shape[1]
 
     def clear_vectors(self, new_dim=None):
         """Drop the current vector table. Because all vectors must be the same
@@ -268,7 +269,10 @@ cdef class Vocab:
         """
         if isinstance(orth, basestring_):
             orth = self.strings.add(orth)
-        return self.vectors[orth]
+        if orth in self.vectors.key2row:
+            return self.vectors[orth]
+        else:
+            return numpy.zeros((self.vectors_length,), dtype='f')
 
     def set_vector(self, orth, vector):
         """Set a vector for a word in the vocabulary.