Merge branch 'develop' into feature/vectors

spacy/pipeline/entity_linker.py

@@ -387,7 +387,7 @@ class EntityLinker(Pipe):
         docs (Iterable[Doc]): The documents to modify.
         kb_ids (List[str]): The IDs to set, produced by EntityLinker.predict.
 
-        DOCS: https://spacy.io/api/entitylinker#predict
+        DOCS: https://spacy.io/api/entitylinker#set_annotations
         """
         count_ents = len([ent for doc in docs for ent in doc.ents])
         if count_ents != len(kb_ids):

spacy/pipeline/morphologizer.pyx

@@ -165,7 +165,7 @@ class Morphologizer(Tagger):
         docs (Iterable[Doc]): The documents to modify.
         batch_tag_ids: The IDs to set, produced by Morphologizer.predict.
 
-        DOCS: https://spacy.io/api/morphologizer#predict
+        DOCS: https://spacy.io/api/morphologizer#set_annotations
         """
         if isinstance(docs, Doc):
             docs = [docs]

spacy/pipeline/pipe.pyx

@@ -32,7 +32,9 @@ class Pipe:
         raise NotImplementedError
 
     def __call__(self, Doc doc):
-        """Add context-sensitive embeddings to the Doc.tensor attribute.
+        """Apply the pipe to one document. The document is modified in place,
+        and returned. This usually happens under the hood when the nlp object
+        is called on a text and all components are applied to the Doc.
 
         docs (Doc): The Doc to preocess.
         RETURNS (Doc): The processed Doc.
@@ -74,9 +76,9 @@ class Pipe:
         """Modify a batch of documents, using pre-computed scores.
 
         docs (Iterable[Doc]): The documents to modify.
-        tokvecses: The tensors to set, produced by Pipe.predict.
+        scores: The scores to assign.
 
-        DOCS: https://spacy.io/api/pipe#predict
+        DOCS: https://spacy.io/api/pipe#set_annotations
         """
         raise NotImplementedError
 

spacy/pipeline/senter.pyx

@@ -76,7 +76,7 @@ class SentenceRecognizer(Tagger):
         docs (Iterable[Doc]): The documents to modify.
         batch_tag_ids: The IDs to set, produced by SentenceRecognizer.predict.
 
-        DOCS: https://spacy.io/api/sentencerecognizer#predict
+        DOCS: https://spacy.io/api/sentencerecognizer#set_annotations
         """
         if isinstance(docs, Doc):
             docs = [docs]

spacy/pipeline/tagger.pyx

@@ -145,7 +145,7 @@ class Tagger(Pipe):
         docs (Iterable[Doc]): The documents to modify.
         batch_tag_ids: The IDs to set, produced by Tagger.predict.
 
-        DOCS: https://spacy.io/api/tagger#predict
+        DOCS: https://spacy.io/api/tagger#set_annotations
         """
         if isinstance(docs, Doc):
             docs = [docs]

spacy/pipeline/textcat.py

@@ -163,7 +163,7 @@ class TextCategorizer(Pipe):
         docs (Iterable[Doc]): The documents to modify.
         scores: The scores to set, produced by TextCategorizer.predict.
 
-        DOCS: https://spacy.io/api/textcategorizer#predict
+        DOCS: https://spacy.io/api/textcategorizer#set_annotations
         """
         for i, doc in enumerate(docs):
             for j, label in enumerate(self.labels):

spacy/pipeline/tok2vec.py

@@ -109,7 +109,7 @@ class Tok2Vec(Pipe):
         docs (Iterable[Doc]): The documents to modify.
         tokvecses: The tensors to set, produced by Tok2Vec.predict.
 
-        DOCS: https://spacy.io/api/tok2vec#predict
+        DOCS: https://spacy.io/api/tok2vec#set_annotations
         """
         for doc, tokvecs in zip(docs, tokvecses):
             assert tokvecs.shape[0] == len(doc)

spacy/tokens/_serialize.py

@@ -50,7 +50,7 @@ class DocBin:
         self,
         attrs: Iterable[str] = ALL_ATTRS,
         store_user_data: bool = False,
-        docs: Iterable[Doc]=[],
+        docs: Iterable[Doc] = tuple(),
     ) -> None:
         """Create a DocBin object to hold serialized annotations.