Fix imports, types and default configs

spacy/ml/models/parser.py

@@ -5,6 +5,7 @@ from thinc.types import Floats2d
 from ...util import registry
 from .._precomputable_affine import PrecomputableAffine
 from ..tb_framework import TransitionModel
+from ...tokens import Doc
 
 
 @registry.architectures.register("spacy.TransitionBasedParser.v1")
@@ -35,7 +36,7 @@ def build_tb_parser_model(
         and applying the non-linearity.
     * upper (optional): A feed-forward network that predicts scores from the
         state representation. If not present, the output from the lower model is
-        ued as action scores directly.
+        used as action scores directly.
 
     tok2vec (Model[List[Doc], List[Floats2d]]):
         Subnetwork to map tokens into vector representations.

spacy/ml/models/simple_ner.py

@@ -10,7 +10,7 @@ from .._iob import IOB
 from ...util import registry
 
 
-@registry.architectures.register("spacy.BiluoTagger.v1")
+@registry.architectures.register("spacy.BILUOTagger.v1")
 def BiluoTagger(
     tok2vec: Model[List[Doc], List[Floats2d]]
 ) -> Model[List[Doc], List[Floats2d]]:
@@ -59,7 +59,7 @@ def IOBTagger(
     token and uses greedy decoding with transition-constraints to return a valid
     IOB tag sequence.
 
-    A IOB tag sequence encodes a sequence of non-overlapping labelled spans
+    An IOB tag sequence encodes a sequence of non-overlapping labelled spans
     into tags assigned to each token. The first token of a span is given the
     tag B-LABEL, and subsequent tokens are given the tag I-LABEL.
     All other tokens are assigned the tag O.

spacy/ml/models/tagger.py

@@ -3,7 +3,7 @@ from thinc.api import zero_init, with_array, Softmax, chain, Model
 from thinc.types import Floats2d
 
 from ...util import registry
-from ..tokens import Doc
+from ...tokens import Doc
 
 
 @registry.architectures.register("spacy.Tagger.v1")

spacy/ml/models/tok2vec.py

@@ -77,7 +77,7 @@ def build_Tok2Vec_model(
     """Construct a tok2vec model out of embedding and encoding subnetworks.
     See https://explosion.ai/blog/deep-learning-formula-nlp
 
-    embed (Model[List[Doc], List[Floats2d]]): Embed tokens into context-indepdent
+    embed (Model[List[Doc], List[Floats2d]]): Embed tokens into context-independent
         word vector representations.
     encode (Model[List[Floats2d], List[Floats2d]]): Encode context into the
         embeddings, using an architecture such as a CNN, BiLSTM or transformer.

spacy/pipeline/dep_parser.pyx

@@ -27,7 +27,6 @@ embed_size = 2000
 window_size = 1
 maxout_pieces = 3
 subword_features = true
-dropout = null
 """
 DEFAULT_PARSER_MODEL = Config().from_str(default_model_config)["model"]
 

spacy/pipeline/entity_linker.py

@@ -29,7 +29,6 @@ embed_size = 300
 window_size = 1
 maxout_pieces = 3
 subword_features = true
-dropout = null
 """
 DEFAULT_NEL_MODEL = Config().from_str(default_model_config)["model"]
 

spacy/pipeline/multitask.pyx

@@ -29,7 +29,6 @@ embed_size = 2000
 window_size = 1
 maxout_pieces = 2
 subword_features = true
-dropout = null
 """
 DEFAULT_MT_MODEL = Config().from_str(default_model_config)["model"]
 

spacy/pipeline/ner.pyx

@@ -25,7 +25,6 @@ embed_size = 2000
 window_size = 1
 maxout_pieces = 3
 subword_features = true
-dropout = null
 """
 DEFAULT_NER_MODEL = Config().from_str(default_model_config)["model"]
 

spacy/pipeline/senter.pyx

@@ -25,7 +25,6 @@ embed_size = 2000
 window_size = 1
 maxout_pieces = 2
 subword_features = true
-dropout = null
 """
 DEFAULT_SENTER_MODEL = Config().from_str(default_model_config)["model"]
 

spacy/pipeline/simple_ner.py

@@ -15,7 +15,7 @@ from .pipe import Pipe
 
 default_model_config = """
 [model]
-@architectures = "spacy.BiluoTagger.v1"
+@architectures = "spacy.BILUOTagger.v1"
 
 [model.tok2vec]
 @architectures = "spacy.HashEmbedCNN.v1"
@@ -26,7 +26,6 @@ embed_size = 7000
 window_size = 1
 maxout_pieces = 3
 subword_features = true
-dropout = null
 """
 DEFAULT_SIMPLE_NER_MODEL = Config().from_str(default_model_config)["model"]
 

spacy/pipeline/tagger.pyx

@@ -31,7 +31,6 @@ embed_size = 2000
 window_size = 1
 maxout_pieces = 3
 subword_features = true
-dropout = null
 """
 DEFAULT_TAGGER_MODEL = Config().from_str(default_model_config)["model"]
 

spacy/pipeline/textcat.py

@@ -48,7 +48,6 @@ embed_size = 2000
 window_size = 1
 maxout_pieces = 3
 subword_features = true
-dropout = null
 """
 
 

spacy/pipeline/tok2vec.py

@@ -20,7 +20,6 @@ embed_size = 2000
 window_size = 1
 maxout_pieces = 3
 subword_features = true
-dropout = null
 """
 DEFAULT_TOK2VEC_MODEL = Config().from_str(default_model_config)["model"]
 

spacy/tests/serialize/test_serialize_config.py

@@ -48,7 +48,6 @@ window_size = 1
 embed_size = 2000
 maxout_pieces = 3
 subword_features = true
-dropout = null
 
 [components.tagger]
 factory = "tagger"
@@ -78,7 +77,6 @@ embed_size = 5555
 window_size = 1
 maxout_pieces = 7
 subword_features = false
-dropout = null
 """