Fix augment

pyproject.toml

@@ -7,7 +7,7 @@ requires = [
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
     "thinc>=8.0.0a43,<8.0.0a50",
-    "blis>=0.4.0,<0.5.0",
+    "blis>=0.4.0,<0.8.0",
     "pytokenizations",
     "pathy"
 ]

requirements.txt

@@ -2,7 +2,7 @@
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
 thinc>=8.0.0a43,<8.0.0a50
-blis>=0.4.0,<0.5.0
+blis>=0.4.0,<0.8.0
 ml_datasets==0.2.0a0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.8.0,<1.1.0

setup.cfg

@@ -41,7 +41,7 @@ install_requires =
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
     thinc>=8.0.0a43,<8.0.0a50
-    blis>=0.4.0,<0.5.0
+    blis>=0.4.0,<0.8.0
     wasabi>=0.8.0,<1.1.0
     srsly>=2.3.0,<3.0.0
     catalogue>=2.0.1,<2.1.0

spacy/about.py

@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy-nightly"
-__version__ = "3.0.0a33"
+__version__ = "3.0.0a34"
 __release__ = True
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"

spacy/lookups.py

@@ -289,13 +289,12 @@ class Lookups:
 
         DOCS: https://nightly.spacy.io/api/lookups#to_disk
         """
-        if len(self._tables):
+        path = ensure_path(path)
-            path = ensure_path(path)
+        if not path.exists():
-            if not path.exists():
+            path.mkdir()
-                path.mkdir()
+        filepath = path / filename
-            filepath = path / filename
+        with filepath.open("wb") as file_:
-            with filepath.open("wb") as file_:
+            file_.write(self.to_bytes())
-                file_.write(self.to_bytes())
 
     def from_disk(
         self, path: Union[str, Path], filename: str = "lookups.bin", **kwargs

spacy/pipeline/morphologizer.pyx

@@ -210,7 +210,7 @@ class Morphologizer(Tagger):
 
         examples (Iterable[Examples]): The batch of examples.
         scores: Scores representing the model's predictions.
-        RETUTNRS (Tuple[float, float]): The loss and the gradient.
+        RETURNS (Tuple[float, float]): The loss and the gradient.
 
         DOCS: https://nightly.spacy.io/api/morphologizer#get_loss
         """

spacy/pipeline/pipe.pyx

@@ -162,7 +162,7 @@ cdef class Pipe:
 
         examples (Iterable[Examples]): The batch of examples.
         scores: Scores representing the model's predictions.
-        RETUTNRS (Tuple[float, float]): The loss and the gradient.
+        RETURNS (Tuple[float, float]): The loss and the gradient.
 
         DOCS: https://nightly.spacy.io/api/pipe#get_loss
         """

spacy/pipeline/senter.pyx

@@ -104,7 +104,7 @@ class SentenceRecognizer(Tagger):
 
         examples (Iterable[Examples]): The batch of examples.
         scores: Scores representing the model's predictions.
-        RETUTNRS (Tuple[float, float]): The loss and the gradient.
+        RETURNS (Tuple[float, float]): The loss and the gradient.
 
         DOCS: https://nightly.spacy.io/api/sentencerecognizer#get_loss
         """

spacy/pipeline/tagger.pyx

@@ -249,7 +249,7 @@ class Tagger(Pipe):
 
         examples (Iterable[Examples]): The batch of examples.
         scores: Scores representing the model's predictions.
-        RETUTNRS (Tuple[float, float]): The loss and the gradient.
+        RETURNS (Tuple[float, float]): The loss and the gradient.
 
         DOCS: https://nightly.spacy.io/api/tagger#get_loss
         """

spacy/pipeline/textcat.py

@@ -281,7 +281,7 @@ class TextCategorizer(Pipe):
 
         examples (Iterable[Examples]): The batch of examples.
         scores: Scores representing the model's predictions.
-        RETUTNRS (Tuple[float, float]): The loss and the gradient.
+        RETURNS (Tuple[float, float]): The loss and the gradient.
 
         DOCS: https://nightly.spacy.io/api/textcategorizer#get_loss
         """

spacy/training/augment.py

@@ -5,7 +5,7 @@ import copy
 from functools import partial
 from pydantic import BaseModel, StrictStr
 
-from ..util import registry, logger
+from ..util import registry
 from ..tokens import Doc
 from .example import Example
 
@@ -119,7 +119,6 @@ def make_orth_variants(
     orig_token_dict = copy.deepcopy(token_dict)
     ndsv = orth_variants.get("single", [])
     ndpv = orth_variants.get("paired", [])
-    logger.debug(f"Data augmentation: {len(ndsv)} single / {len(ndpv)} paired variants")
     words = token_dict.get("ORTH", [])
     tags = token_dict.get("TAG", [])
     # keep unmodified if words or tags are not defined
@@ -139,7 +138,7 @@ def make_orth_variants(
         punct_choices = [random.choice(x["variants"]) for x in ndpv]
         for word_idx in range(len(words)):
             for punct_idx in range(len(ndpv)):
-                if tags[word_idx] in ndpv[punct_idx]["TAG"] and words[
+                if tags[word_idx] in ndpv[punct_idx]["tags"] and words[
                     word_idx
                 ] in itertools.chain.from_iterable(ndpv[punct_idx]["variants"]):
                     # backup option: random left vs. right from pair

spacy/vocab.pyx

@@ -445,9 +445,9 @@ cdef class Vocab:
         setters = ["strings", "vectors"]
         if "strings" not in exclude:
             self.strings.to_disk(path / "strings.json")
-        if "vectors" not in "exclude" and self.vectors is not None:
+        if "vectors" not in "exclude":
             self.vectors.to_disk(path)
-        if "lookups" not in "exclude" and self.lookups is not None:
+        if "lookups" not in "exclude":
             self.lookups.to_disk(path)
 
     def from_disk(self, path, *, exclude=tuple()):