Merge remote-tracking branch 'upstream/develop' into fix/patterns-init

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/errors.py

@@ -458,10 +458,10 @@ class Errors:
     # TODO: fix numbering after merging develop into master
     E900 = ("Patterns for component '{name}' not initialized. This can be fixed "
             "by calling 'add_patterns' or 'initialize'.")
-    E092 = ("The sentence-per-line IOB/IOB2 file is not formatted correctly. "
+    E902 = ("The sentence-per-line IOB/IOB2 file is not formatted correctly. "
             "Try checking whitespace and delimiters. See "
             "https://nightly.spacy.io/api/cli#convert")
-    E093 = ("The token-per-line NER file is not formatted correctly. Try checking "
+    E903 = ("The token-per-line NER file is not formatted correctly. Try checking "
             "whitespace and delimiters. See https://nightly.spacy.io/api/cli#convert")
     E904 = ("Cannot initialize StaticVectors layer: nO dimension unset. This "
             "dimension refers to the output width, after the linear projection "

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)
-            if not path.exists():
-                path.mkdir()
-            filepath = path / filename
-            with filepath.open("wb") as file_:
-                file_.write(self.to_bytes())
+        path = ensure_path(path)
+        if not path.exists():
+            path.mkdir()
+        filepath = path / filename
+        with filepath.open("wb") as file_:
+            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/tests/test_misc.py

@@ -7,6 +7,15 @@ from spacy import util
 from spacy import prefer_gpu, require_gpu
 from spacy.ml._precomputable_affine import PrecomputableAffine
 from spacy.ml._precomputable_affine import _backprop_precomputable_affine_padding
+from spacy.util import dot_to_object, SimpleFrozenList
+from thinc.api import Config, Optimizer, ConfigValidationError
+from spacy.training.batchers import minibatch_by_words
+from spacy.lang.en import English
+from spacy.lang.nl import Dutch
+from spacy.language import DEFAULT_CONFIG_PATH
+from spacy.schemas import ConfigSchemaTraining
+
+from .util import get_random_doc
 
 
 @pytest.fixture
@@ -157,3 +166,128 @@ def test_dot_to_dict(dot_notation, expected):
     result = util.dot_to_dict(dot_notation)
     assert result == expected
     assert util.dict_to_dot(result) == dot_notation
+
+
+@pytest.mark.parametrize(
+    "doc_sizes, expected_batches",
+    [
+        ([400, 400, 199], [3]),
+        ([400, 400, 199, 3], [4]),
+        ([400, 400, 199, 3, 200], [3, 2]),
+        ([400, 400, 199, 3, 1], [5]),
+        ([400, 400, 199, 3, 1, 1500], [5]),  # 1500 will be discarded
+        ([400, 400, 199, 3, 1, 200], [3, 3]),
+        ([400, 400, 199, 3, 1, 999], [3, 3]),
+        ([400, 400, 199, 3, 1, 999, 999], [3, 2, 1, 1]),
+        ([1, 2, 999], [3]),
+        ([1, 2, 999, 1], [4]),
+        ([1, 200, 999, 1], [2, 2]),
+        ([1, 999, 200, 1], [2, 2]),
+    ],
+)
+def test_util_minibatch(doc_sizes, expected_batches):
+    docs = [get_random_doc(doc_size) for doc_size in doc_sizes]
+    tol = 0.2
+    batch_size = 1000
+    batches = list(
+        minibatch_by_words(docs, size=batch_size, tolerance=tol, discard_oversize=True)
+    )
+    assert [len(batch) for batch in batches] == expected_batches
+
+    max_size = batch_size + batch_size * tol
+    for batch in batches:
+        assert sum([len(doc) for doc in batch]) < max_size
+
+
+@pytest.mark.parametrize(
+    "doc_sizes, expected_batches",
+    [
+        ([400, 4000, 199], [1, 2]),
+        ([400, 400, 199, 3000, 200], [1, 4]),
+        ([400, 400, 199, 3, 1, 1500], [1, 5]),
+        ([400, 400, 199, 3000, 2000, 200, 200], [1, 1, 3, 2]),
+        ([1, 2, 9999], [1, 2]),
+        ([2000, 1, 2000, 1, 1, 1, 2000], [1, 1, 1, 4]),
+    ],
+)
+def test_util_minibatch_oversize(doc_sizes, expected_batches):
+    """ Test that oversized documents are returned in their own batch"""
+    docs = [get_random_doc(doc_size) for doc_size in doc_sizes]
+    tol = 0.2
+    batch_size = 1000
+    batches = list(
+        minibatch_by_words(docs, size=batch_size, tolerance=tol, discard_oversize=False)
+    )
+    assert [len(batch) for batch in batches] == expected_batches
+
+
+def test_util_dot_section():
+    cfg_string = """
+    [nlp]
+    lang = "en"
+    pipeline = ["textcat"]
+
+    [components]
+
+    [components.textcat]
+    factory = "textcat"
+
+    [components.textcat.model]
+    @architectures = "spacy.TextCatBOW.v1"
+    exclusive_classes = true
+    ngram_size = 1
+    no_output_layer = false
+    """
+    nlp_config = Config().from_str(cfg_string)
+    en_nlp = util.load_model_from_config(nlp_config, auto_fill=True)
+    default_config = Config().from_disk(DEFAULT_CONFIG_PATH)
+    default_config["nlp"]["lang"] = "nl"
+    nl_nlp = util.load_model_from_config(default_config, auto_fill=True)
+    # Test that creation went OK
+    assert isinstance(en_nlp, English)
+    assert isinstance(nl_nlp, Dutch)
+    assert nl_nlp.pipe_names == []
+    assert en_nlp.pipe_names == ["textcat"]
+    # not exclusive_classes
+    assert en_nlp.get_pipe("textcat").model.attrs["multi_label"] is False
+    # Test that default values got overwritten
+    assert en_nlp.config["nlp"]["pipeline"] == ["textcat"]
+    assert nl_nlp.config["nlp"]["pipeline"] == []  # default value []
+    # Test proper functioning of 'dot_to_object'
+    with pytest.raises(KeyError):
+        dot_to_object(en_nlp.config, "nlp.pipeline.tagger")
+    with pytest.raises(KeyError):
+        dot_to_object(en_nlp.config, "nlp.unknownattribute")
+    T = util.registry.resolve(nl_nlp.config["training"], schema=ConfigSchemaTraining)
+    assert isinstance(dot_to_object({"training": T}, "training.optimizer"), Optimizer)
+
+
+def test_simple_frozen_list():
+    t = SimpleFrozenList(["foo", "bar"])
+    assert t == ["foo", "bar"]
+    assert t.index("bar") == 1  # okay method
+    with pytest.raises(NotImplementedError):
+        t.append("baz")
+    with pytest.raises(NotImplementedError):
+        t.sort()
+    with pytest.raises(NotImplementedError):
+        t.extend(["baz"])
+    with pytest.raises(NotImplementedError):
+        t.pop()
+    t = SimpleFrozenList(["foo", "bar"], error="Error!")
+    with pytest.raises(NotImplementedError):
+        t.append("baz")
+
+
+def test_resolve_dot_names():
+    config = {
+        "training": {"optimizer": {"@optimizers": "Adam.v1"}},
+        "foo": {"bar": "training.optimizer", "baz": "training.xyz"},
+    }
+    result = util.resolve_dot_names(config, ["training.optimizer"])
+    assert isinstance(result[0], Optimizer)
+    with pytest.raises(ConfigValidationError) as e:
+        util.resolve_dot_names(config, ["training.xyz", "training.optimizer"])
+    errors = e.value.errors
+    assert len(errors) == 1
+    assert errors[0]["loc"] == ["training", "xyz"]

spacy/tests/test_util.py

@@ -1,137 +0,0 @@
-import pytest
-
-from spacy import util
-from spacy.util import dot_to_object, SimpleFrozenList
-from thinc.api import Config, Optimizer, ConfigValidationError
-from spacy.training.batchers import minibatch_by_words
-from spacy.lang.en import English
-from spacy.lang.nl import Dutch
-from spacy.language import DEFAULT_CONFIG_PATH
-from spacy.schemas import ConfigSchemaTraining
-
-from .util import get_random_doc
-
-
-@pytest.mark.parametrize(
-    "doc_sizes, expected_batches",
-    [
-        ([400, 400, 199], [3]),
-        ([400, 400, 199, 3], [4]),
-        ([400, 400, 199, 3, 200], [3, 2]),
-        ([400, 400, 199, 3, 1], [5]),
-        ([400, 400, 199, 3, 1, 1500], [5]),  # 1500 will be discarded
-        ([400, 400, 199, 3, 1, 200], [3, 3]),
-        ([400, 400, 199, 3, 1, 999], [3, 3]),
-        ([400, 400, 199, 3, 1, 999, 999], [3, 2, 1, 1]),
-        ([1, 2, 999], [3]),
-        ([1, 2, 999, 1], [4]),
-        ([1, 200, 999, 1], [2, 2]),
-        ([1, 999, 200, 1], [2, 2]),
-    ],
-)
-def test_util_minibatch(doc_sizes, expected_batches):
-    docs = [get_random_doc(doc_size) for doc_size in doc_sizes]
-    tol = 0.2
-    batch_size = 1000
-    batches = list(
-        minibatch_by_words(docs, size=batch_size, tolerance=tol, discard_oversize=True)
-    )
-    assert [len(batch) for batch in batches] == expected_batches
-
-    max_size = batch_size + batch_size * tol
-    for batch in batches:
-        assert sum([len(doc) for doc in batch]) < max_size
-
-
-@pytest.mark.parametrize(
-    "doc_sizes, expected_batches",
-    [
-        ([400, 4000, 199], [1, 2]),
-        ([400, 400, 199, 3000, 200], [1, 4]),
-        ([400, 400, 199, 3, 1, 1500], [1, 5]),
-        ([400, 400, 199, 3000, 2000, 200, 200], [1, 1, 3, 2]),
-        ([1, 2, 9999], [1, 2]),
-        ([2000, 1, 2000, 1, 1, 1, 2000], [1, 1, 1, 4]),
-    ],
-)
-def test_util_minibatch_oversize(doc_sizes, expected_batches):
-    """ Test that oversized documents are returned in their own batch"""
-    docs = [get_random_doc(doc_size) for doc_size in doc_sizes]
-    tol = 0.2
-    batch_size = 1000
-    batches = list(
-        minibatch_by_words(docs, size=batch_size, tolerance=tol, discard_oversize=False)
-    )
-    assert [len(batch) for batch in batches] == expected_batches
-
-
-def test_util_dot_section():
-    cfg_string = """
-    [nlp]
-    lang = "en"
-    pipeline = ["textcat"]
-
-    [components]
-
-    [components.textcat]
-    factory = "textcat"
-
-    [components.textcat.model]
-    @architectures = "spacy.TextCatBOW.v1"
-    exclusive_classes = true
-    ngram_size = 1
-    no_output_layer = false
-    """
-    nlp_config = Config().from_str(cfg_string)
-    en_nlp = util.load_model_from_config(nlp_config, auto_fill=True)
-    default_config = Config().from_disk(DEFAULT_CONFIG_PATH)
-    default_config["nlp"]["lang"] = "nl"
-    nl_nlp = util.load_model_from_config(default_config, auto_fill=True)
-    # Test that creation went OK
-    assert isinstance(en_nlp, English)
-    assert isinstance(nl_nlp, Dutch)
-    assert nl_nlp.pipe_names == []
-    assert en_nlp.pipe_names == ["textcat"]
-    # not exclusive_classes
-    assert en_nlp.get_pipe("textcat").model.attrs["multi_label"] is False
-    # Test that default values got overwritten
-    assert en_nlp.config["nlp"]["pipeline"] == ["textcat"]
-    assert nl_nlp.config["nlp"]["pipeline"] == []  # default value []
-    # Test proper functioning of 'dot_to_object'
-    with pytest.raises(KeyError):
-        dot_to_object(en_nlp.config, "nlp.pipeline.tagger")
-    with pytest.raises(KeyError):
-        dot_to_object(en_nlp.config, "nlp.unknownattribute")
-    T = util.registry.resolve(nl_nlp.config["training"], schema=ConfigSchemaTraining)
-    assert isinstance(dot_to_object({"training": T}, "training.optimizer"), Optimizer)
-
-
-def test_simple_frozen_list():
-    t = SimpleFrozenList(["foo", "bar"])
-    assert t == ["foo", "bar"]
-    assert t.index("bar") == 1  # okay method
-    with pytest.raises(NotImplementedError):
-        t.append("baz")
-    with pytest.raises(NotImplementedError):
-        t.sort()
-    with pytest.raises(NotImplementedError):
-        t.extend(["baz"])
-    with pytest.raises(NotImplementedError):
-        t.pop()
-    t = SimpleFrozenList(["foo", "bar"], error="Error!")
-    with pytest.raises(NotImplementedError):
-        t.append("baz")
-
-
-def test_resolve_dot_names():
-    config = {
-        "training": {"optimizer": {"@optimizers": "Adam.v1"}},
-        "foo": {"bar": "training.optimizer", "baz": "training.xyz"},
-    }
-    result = util.resolve_dot_names(config, ["training.optimizer"])
-    assert isinstance(result[0], Optimizer)
-    with pytest.raises(ConfigValidationError) as e:
-        util.resolve_dot_names(config, ["training.xyz", "training.optimizer"])
-    errors = e.value.errors
-    assert len(errors) == 1
-    assert errors[0]["loc"] == ["training", "xyz"]

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
 
@@ -119,9 +119,8 @@ 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("words", [])
-    tags = token_dict.get("tags", [])
+    words = token_dict.get("ORTH", [])
+    tags = token_dict.get("TAG", [])
     # keep unmodified if words or tags are not defined
     if words and tags:
         if lower:
@@ -154,8 +153,8 @@ def make_orth_variants(
                             if words[word_idx] in pair:
                                 pair_idx = pair.index(words[word_idx])
                     words[word_idx] = punct_choices[punct_idx][pair_idx]
-        token_dict["words"] = words
-        token_dict["tags"] = tags
+        token_dict["ORTH"] = words
+        token_dict["TAG"] = tags
     # modify raw
     if raw is not None:
         variants = []

spacy/training/converters/conll_ner_to_docs.py

@@ -103,7 +103,7 @@ def conll_ner_to_docs(
             lines = [line.strip() for line in conll_sent.split("\n") if line.strip()]
             cols = list(zip(*[line.split() for line in lines]))
             if len(cols) < 2:
-                raise ValueError(Errors.E093)
+                raise ValueError(Errors.E903)
             length = len(cols[0])
             words.extend(cols[0])
             sent_starts.extend([True] + [False] * (length - 1))

spacy/training/converters/iob_to_docs.py

@@ -46,7 +46,7 @@ def read_iob(raw_sents, vocab, n_sents):
                 sent_words, sent_iob = zip(*sent_tokens)
                 sent_tags = ["-"] * len(sent_words)
             else:
-                raise ValueError(Errors.E092)
+                raise ValueError(Errors.E902)
             words.extend(sent_words)
             tags.extend(sent_tags)
             iob.extend(sent_iob)

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()):