Tidy up references to n_threads and fix default

examples/deep_learning_keras.py

@@ -49,7 +49,7 @@ class SentimentAnalyser(object):
         y = self._model.predict(X)
         self.set_sentiment(doc, y)
 
-    def pipe(self, docs, batch_size=1000, n_threads=2):
+    def pipe(self, docs, batch_size=1000):
         for minibatch in cytoolz.partition_all(batch_size, docs):
             minibatch = list(minibatch)
             sentences = []
@@ -176,7 +176,7 @@ def evaluate(model_dir, texts, labels, max_length=100):
 
     correct = 0
     i = 0
-    for doc in nlp.pipe(texts, batch_size=1000, n_threads=4):
+    for doc in nlp.pipe(texts, batch_size=1000):
         correct += bool(doc.sentiment >= 0.5) == bool(labels[i])
         i += 1
     return float(correct) / i

spacy/language.py

@@ -644,7 +644,7 @@ class Language(object):
         self,
         texts,
         as_tuples=False,
-        n_threads=2,
+        n_threads=-1,
         batch_size=1000,
         disable=[],
         cleanup=False,
@@ -656,7 +656,6 @@ class Language(object):
         as_tuples (bool): If set to True, inputs should be a sequence of
             (text, context) tuples. Output will then be a sequence of
             (doc, context) tuples. Defaults to False.
-        n_threads (int): Currently inactive.
         batch_size (int): The number of texts to buffer.
         disable (list): Names of the pipeline components to disable.
         cleanup (bool): If True, unneeded strings are freed to control memory
@@ -673,7 +672,6 @@ class Language(object):
             contexts = (tc[1] for tc in text_context2)
             docs = self.pipe(
                 texts,
-                n_threads=n_threads,
                 batch_size=batch_size,
                 disable=disable,
                 component_cfg=component_cfg,
@@ -690,7 +688,6 @@ class Language(object):
             kwargs = component_cfg.get(name, {})
             # Allow component_cfg to overwrite the top-level kwargs.
             kwargs.setdefault("batch_size", batch_size)
-            kwargs.setdefault("n_threads", n_threads)
             if hasattr(proc, "pipe"):
                 docs = proc.pipe(docs, **kwargs)
             else:

spacy/matcher/matcher.pyx

@@ -153,13 +153,11 @@ cdef class Matcher:
             return default
         return (self._callbacks[key], self._patterns[key])
 
-    def pipe(self, docs, batch_size=1000, n_threads=2):
+    def pipe(self, docs, batch_size=1000, n_threads=-1):
         """Match a stream of documents, yielding them in turn.
 
         docs (iterable): A stream of documents.
         batch_size (int): Number of documents to accumulate into a working set.
-        n_threads (int): The number of threads with which to work on the buffer
-            in parallel, if the implementation supports multi-threading.
         YIELDS (Doc): Documents, in order.
         """
         for doc in docs:

spacy/matcher/phrasematcher.pyx

@@ -166,14 +166,12 @@ cdef class PhraseMatcher:
                 on_match(self, doc, i, matches)
         return matches
 
-    def pipe(self, stream, batch_size=1000, n_threads=1, return_matches=False,
+    def pipe(self, stream, batch_size=1000, n_threads=-1, return_matches=False,
              as_tuples=False):
         """Match a stream of documents, yielding them in turn.
 
         docs (iterable): A stream of documents.
         batch_size (int): Number of documents to accumulate into a working set.
-        n_threads (int): The number of threads with which to work on the buffer
-            in parallel, if the implementation supports multi-threading.
         return_matches (bool): Yield the match lists along with the docs, making
             results (doc, matches) tuples.
         as_tuples (bool): Interpret the input stream as (doc, context) tuples,

spacy/pipeline/pipes.pyx

@@ -257,7 +257,6 @@ class Tensorizer(Pipe):
 
         stream (iterator): A sequence of `Doc` objects to process.
         batch_size (int): Number of `Doc` objects to group.
-        n_threads (int): Number of threads.
         YIELDS (iterator): A sequence of `Doc` objects, in order of input.
         """
         for docs in util.minibatch(stream, size=batch_size):

spacy/syntax/nn_parser.pyx

@@ -205,13 +205,11 @@ cdef class Parser:
         self.set_annotations([doc], states, tensors=None)
         return doc
 
-    def pipe(self, docs, int batch_size=256, int n_threads=2, beam_width=None):
+    def pipe(self, docs, int batch_size=256, int n_threads=-1, beam_width=None):
         """Process a stream of documents.
 
         stream: The sequence of documents to process.
         batch_size (int): Number of documents to accumulate into a working set.
-        n_threads (int): The number of threads with which to work on the buffer
-            in parallel.
         YIELDS (Doc): Documents, in order.
         """
         if beam_width is None:

spacy/tokenizer.pyx

@@ -125,7 +125,7 @@ cdef class Tokenizer:
             doc.c[doc.length - 1].spacy = string[-1] == " " and not in_ws
         return doc
 
-    def pipe(self, texts, batch_size=1000, n_threads=2):
+    def pipe(self, texts, batch_size=1000, n_threads=-1):
         """Tokenize a stream of texts.
 
         texts: A sequence of unicode texts.