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

README.rst

@@ -229,7 +229,7 @@ Compile from source
 The other way to install spaCy is to clone its
 `GitHub repository <https://github.com/explosion/spaCy>`_ and build it from
 source. That is the common way if you want to make changes to the code base.
-You'll need to make sure that you have a development enviroment consisting of a
+You'll need to make sure that you have a development environment consisting of a
 Python distribution including header files, a compiler,
 `pip <https://pip.pypa.io/en/latest/installing/>`__, `virtualenv <https://virtualenv.pypa.io/>`_
 and `git <https://git-scm.com>`_ installed. The compiler part is the trickiest.

spacy/__main__.py

@@ -3,15 +3,21 @@ from __future__ import print_function
 # NB! This breaks in plac on Python 2!!
 #from __future__ import unicode_literals
 
-
 if __name__ == '__main__':
     import plac
     import sys
-    from spacy.cli import download, link, info, package, train, convert
+    from spacy.cli import download, link, info, package, train, convert, model
     from spacy.util import prints
 
-    commands = {'download': download, 'link': link, 'info': info, 'train': train,
-                'convert': convert, 'package': package}
+    commands = {
+        'download': download,
+        'link': link,
+        'info': info,
+        'train': train,
+        'convert': convert,
+        'package': package,
+        'model': model
+    }
     if len(sys.argv) == 1:
         prints(', '.join(commands), title="Available commands", exits=1)
     command = sys.argv.pop(1)
@@ -19,5 +25,7 @@ if __name__ == '__main__':
     if command in commands:
         plac.call(commands[command])
     else:
-        prints("Available: %s" % ', '.join(commands),
-               title="Unknown command: %s" % command, exits=1)
+        prints(
+            "Available: %s" % ', '.join(commands),
+            title="Unknown command: %s" % command,
+            exits=1)

spacy/cli/__init__.py

@@ -4,3 +4,4 @@ from .link import link
 from .package import package
 from .train import train
 from .convert import convert
+from .model import model

spacy/cli/model.py

@@ -0,0 +1,119 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import gzip
+import math
+from ast import literal_eval
+from pathlib import Path
+from preshed.counter import PreshCounter
+
+import spacy
+from ..compat import fix_text
+from .. import util
+
+
+def model(cmd, lang, model_dir, freqs_data, clusters_data, vectors_data):
+    model_path = Path(model_dir)
+    freqs_path = Path(freqs_data)
+    clusters_path = Path(clusters_data) if clusters_data else None
+    vectors_path = Path(vectors_data) if vectors_data else None
+
+    check_dirs(freqs_path, clusters_path, vectors_path)
+    # vocab = util.get_lang_class(lang).Defaults.create_vocab()
+    nlp = spacy.blank(lang)
+    vocab = nlp.vocab
+    probs, oov_prob = read_probs(freqs_path)
+    clusters = read_clusters(clusters_path) if clusters_path else {}
+    populate_vocab(vocab, clusters, probs, oov_prob)
+    create_model(model_path, nlp)
+
+
+def create_model(model_path, model):
+    if not model_path.exists():
+        model_path.mkdir()
+    model.to_disk(model_path.as_posix())
+
+
+def read_probs(freqs_path, max_length=100, min_doc_freq=5, min_freq=200):
+    counts = PreshCounter()
+    total = 0
+    freqs_file = check_unzip(freqs_path)
+    for i, line in enumerate(freqs_file):
+        freq, doc_freq, key = line.rstrip().split('\t', 2)
+        freq = int(freq)
+        counts.inc(i + 1, freq)
+        total += freq
+    counts.smooth()
+    log_total = math.log(total)
+    freqs_file = check_unzip(freqs_path)
+    probs = {}
+    for line in freqs_file:
+        freq, doc_freq, key = line.rstrip().split('\t', 2)
+        doc_freq = int(doc_freq)
+        freq = int(freq)
+        if doc_freq >= min_doc_freq and freq >= min_freq and len(
+                key) < max_length:
+            word = literal_eval(key)
+            smooth_count = counts.smoother(int(freq))
+            probs[word] = math.log(smooth_count) - log_total
+    oov_prob = math.log(counts.smoother(0)) - log_total
+    return probs, oov_prob
+
+
+def read_clusters(clusters_path):
+    clusters = {}
+    with clusters_path.open() as f:
+        for line in f:
+            try:
+                cluster, word, freq = line.split()
+                word = fix_text(word)
+            except ValueError:
+                continue
+            # If the clusterer has only seen the word a few times, its
+            # cluster is unreliable.
+            if int(freq) >= 3:
+                clusters[word] = cluster
+            else:
+                clusters[word] = '0'
+    # Expand clusters with re-casing
+    for word, cluster in list(clusters.items()):
+        if word.lower() not in clusters:
+            clusters[word.lower()] = cluster
+        if word.title() not in clusters:
+            clusters[word.title()] = cluster
+        if word.upper() not in clusters:
+            clusters[word.upper()] = cluster
+    return clusters
+
+
+def populate_vocab(vocab, clusters, probs, oov_prob):
+    for word, prob in reversed(
+            sorted(list(probs.items()), key=lambda item: item[1])):
+        lexeme = vocab[word]
+        lexeme.prob = prob
+        lexeme.is_oov = False
+        # Decode as a little-endian string, so that we can do & 15 to get
+        # the first 4 bits. See _parse_features.pyx
+        if word in clusters:
+            lexeme.cluster = int(clusters[word][::-1], 2)
+        else:
+            lexeme.cluster = 0
+
+
+def check_unzip(file_path):
+    file_path_str = file_path.as_posix()
+    if file_path_str.endswith('gz'):
+        return gzip.open(file_path_str)
+    else:
+        return file_path.open()
+
+
+def check_dirs(freqs_data, clusters_data, vectors_data):
+    if not freqs_data.is_file():
+        util.sys_exit(freqs_data.as_posix(), title="No frequencies file found")
+    if clusters_data and not clusters_data.is_file():
+        util.sys_exit(
+            clusters_data.as_posix(), title="No Brown clusters file found")
+    if vectors_data and not vectors_data.is_file():
+        util.sys_exit(
+            vectors_data.as_posix(), title="No word vectors file found")

spacy/gold.pyx

@@ -406,11 +406,11 @@ cdef class GoldParse:
         if tags is None:
             tags = [None for _ in doc]
         if heads is None:
-            heads = [token.i for token in doc]
+            heads = [None for token in doc]
         if deps is None:
             deps = [None for _ in doc]
         if entities is None:
-            entities = ['-' for _ in doc]
+            entities = [None for _ in doc]
         elif len(entities) == 0:
             entities = ['O' for _ in doc]
         elif not isinstance(entities[0], basestring):

spacy/language.py

@@ -200,6 +200,7 @@ class Language(object):
             else:
                 flat_list.append(pipe)
         self.pipeline = flat_list
+        self._optimizer = None
 
     @property
     def meta(self):
@@ -278,7 +279,7 @@ class Language(object):
         return self.tokenizer(text)
 
     def update(self, docs, golds, drop=0., sgd=None, losses=None,
-            update_tensors=False):
+            update_shared=False):
         """Update the models in the pipeline.
 
         docs (iterable): A batch of `Doc` objects.
@@ -298,6 +299,10 @@ class Language(object):
                 "Got: %d, %d" % (len(docs), len(golds)))
         if len(docs) == 0:
             return
+        if sgd is None:
+            if self._optimizer is None:
+                self._optimizer = Adam(Model.ops, 0.001)
+            sgd = self._optimizer
         tok2vec = self.pipeline[0]
         feats = tok2vec.doc2feats(docs)
         grads = {}
@@ -312,12 +317,13 @@ class Language(object):
                 continue
             d_tokvecses = proc.update((docs, tokvecses), golds,
                                       drop=drop, sgd=get_grads, losses=losses)
-            if update_tensors and d_tokvecses is not None:
+            if update_shared and d_tokvecses is not None:
                 for i, d_tv in enumerate(d_tokvecses):
                     all_d_tokvecses[i] += d_tv
-        bp_tokvecses(all_d_tokvecses, sgd=sgd)
-        for key, (W, dW) in grads.items():
-            sgd(W, dW, key=key)
+        if update_shared and bp_tokvecses is not None:
+            bp_tokvecses(all_d_tokvecses, sgd=sgd)
+            for key, (W, dW) in grads.items():
+                sgd(W, dW, key=key)
         # Clear the tensor variable, to free GPU memory.
         # If we don't do this, the memory leak gets pretty
         # bad, because we may be holding part of a batch.
@@ -378,11 +384,11 @@ class Language(object):
         eps = util.env_opt('optimizer_eps', 1e-08)
         L2 = util.env_opt('L2_penalty', 1e-6)
         max_grad_norm = util.env_opt('grad_norm_clip', 1.)
-        optimizer = Adam(Model.ops, learn_rate, L2=L2, beta1=beta1,
-                         beta2=beta2, eps=eps)
-        optimizer.max_grad_norm = max_grad_norm
-        optimizer.device = device
-        return optimizer
+        self._optimizer = Adam(Model.ops, learn_rate, L2=L2, beta1=beta1,
+                              beta2=beta2, eps=eps)
+        self._optimizer.max_grad_norm = max_grad_norm
+        self._optimizer.device = device
+        return self._optimizer
 
     def evaluate(self, docs_golds):
         scorer = Scorer()

spacy/pipeline.pyx

@@ -294,6 +294,8 @@ class NeuralTagger(BaseThincComponent):
         doc.is_tagged = True
 
     def update(self, docs_tokvecs, golds, drop=0., sgd=None, losses=None):
+        if losses is not None and self.name not in losses:
+            losses[self.name] = 0.
         docs, tokvecs = docs_tokvecs
 
         if self.model.nI is None:
@@ -302,6 +304,8 @@ class NeuralTagger(BaseThincComponent):
         loss, d_tag_scores = self.get_loss(docs, golds, tag_scores)
 
         d_tokvecs = bp_tag_scores(d_tag_scores, sgd=sgd)
+        if losses is not None:
+            losses[self.name] += loss
         return d_tokvecs
 
     def get_loss(self, docs, golds, scores):

spacy/syntax/ner.pyx

@@ -113,7 +113,7 @@ cdef class BiluoPushDown(TransitionSystem):
 
     def has_gold(self, GoldParse gold, start=0, end=None):
         end = end or len(gold.ner)
-        if all([tag == '-' for tag in gold.ner[start:end]]):
+        if all([tag in ('-', None) for tag in gold.ner[start:end]]):
             return False
         else:
             return True

spacy/syntax/nn_parser.pyx

@@ -483,6 +483,9 @@ cdef class Parser:
         return beams
 
     def update(self, docs_tokvecs, golds, drop=0., sgd=None, losses=None):
+        docs_tokvecs, golds = self._filter_unlabelled(docs_tokvecs, golds)
+        if not golds:
+            return None
         if self.cfg.get('beam_width', 1) >= 2 and numpy.random.random() >= 0.5:
             return self.update_beam(docs_tokvecs, golds,
                     self.cfg['beam_width'], self.cfg['beam_density'],
@@ -555,6 +558,9 @@ cdef class Parser:
 
     def update_beam(self, docs_tokvecs, golds, width=None, density=None,
             drop=0., sgd=None, losses=None):
+        docs_tokvecs, golds = self._filter_unlabelled(docs_tokvecs, golds)
+        if not golds:
+            return None
         if width is None:
             width = self.cfg.get('beam_width', 2)
         if density is None:
@@ -605,6 +611,15 @@ cdef class Parser:
             bp_my_tokvecs(d_tokvecs, sgd=sgd)
         return d_tokvecs
 
+    def _filter_unlabelled(self, docs_tokvecs, golds):
+        '''Remove inputs that have no relevant labels before update'''
+        has_golds = [self.moves.has_gold(gold) for gold in golds]
+        docs, tokvecs = docs_tokvecs
+        docs = [docs[i] for i, has_gold in enumerate(has_golds) if has_gold]
+        tokvecs = [tokvecs[i] for i, has_gold in enumerate(has_golds) if has_gold]
+        golds = [golds[i] for i, has_gold in enumerate(has_golds) if has_gold]
+        return (docs, tokvecs), golds
+
     def _init_gold_batch(self, whole_docs, whole_golds):
         """Make a square batch, of length equal to the shortest doc. A long
         doc will get multiple states. Let's say we have a doc of length 2*N,

website/docs/api/span.jade

@@ -205,7 +205,7 @@ p Retokenize the document, such that the span is merged into a single token.
 
 p
     |  The token within the span that's highest in the parse tree. If there's a
-    |  tie, the earlist is prefered.
+    |  tie, the earliest is preferred.
 
 +aside-code("Example").
     doc = nlp(u'I like New York in Autumn.')

website/docs/usage/customizing-tokenizer.jade

@@ -39,7 +39,7 @@ p
 +h(2, "special-cases") Adding special case tokenization rules
 
 p
-    |  Most domains have at least some idiosyncracies that require custom
+    |  Most domains have at least some idiosyncrasies that require custom
     |  tokenization rules. This could be very certain expressions, or
     |  abbreviations only used in this specific field.
 

website/docs/usage/index.jade

@@ -109,7 +109,7 @@ p
     |  The other way to install spaCy is to clone its
     |  #[+a(gh("spaCy")) GitHub repository] and build it from source. That is
     |  the common way if you want to make changes to the code base. You'll need to
-    |  make sure that you have a development enviroment consisting of a Python
+    |  make sure that you have a development environment consisting of a Python
     |  distribution including header files, a compiler,
     |  #[+a("https://pip.pypa.io/en/latest/installing/") pip],
     |  #[+a("https://virtualenv.pypa.io/") virtualenv] and

website/docs/usage/pos-tagging.jade

@@ -40,7 +40,7 @@ p
         +cell #[code VerbForm=Fin], #[code Mood=Ind], #[code Tense=Pres]
 
     +row
-        +cell I read the paper yesteday
+        +cell I read the paper yesterday
         +cell read
         +cell read
         +cell verb

website/docs/usage/production-use.jade

@@ -94,7 +94,7 @@ p
     |  is mostly intended as a convenient, interactive wrapper. It performs
     |  compatibility checks and prints detailed error messages and warnings.
     |  However, if you're downloading models as part of an automated build
-    |  process, this only adds an unecessary layer of complexity. If you know
+    |  process, this only adds an unnecessary layer of complexity. If you know
     |  which models your application needs, you should be specifying them directly.
 
 p