Update test

examples/training/create_kb.py

@@ -30,7 +30,7 @@ ENTITIES = {"Q2146908": ("American golfer", 342), "Q7381115": ("publisher", 17)}
     model=("Model name, should have pretrained word embeddings", "positional", None, str),
     output_dir=("Optional output directory", "option", "o", Path),
 )
-def main(model=None, output_dir=None):
+def main(model, output_dir=None):
     """Load the model and create the KB with pre-defined entity encodings.
     If an output_dir is provided, the KB will be stored there in a file 'kb'.
     The updated vocab will also be written to a directory in the output_dir."""

spacy/gold/converters/json2docs.py

@@ -2,7 +2,7 @@ import tempfile
 import contextlib
 import shutil
 from pathlib import Path
-from ..gold_io import read_json_file
+from ..gold_io import json_to_annotations
 from ..example import annotations2doc
 from ..example import _fix_legacy_dict_data, _parse_example_dict_data
 from ...util import load_model
@@ -19,11 +19,7 @@ def make_tempdir():
 def json2docs(input_data, model=None, **kwargs):
     nlp = load_model(model) if model is not None else MultiLanguage()
     docs = []
-    with make_tempdir() as tmp_dir:
-        json_path = Path(tmp_dir) / "data.json"
-        with (json_path).open("w") as file_:
-            file_.write(input_data)
-        for json_annot in read_json_file(json_path):
+    for json_annot in json_to_annotations(input_data):
         example_dict = _fix_legacy_dict_data(json_annot)
         tok_dict, doc_dict = _parse_example_dict_data(example_dict)
         doc = annotations2doc(nlp.vocab, tok_dict, doc_dict)

spacy/gold/corpus.py

@@ -1,5 +1,3 @@
-import srsly
-from pathlib import Path
 import random
 from .. import util
 from .example import Example
@@ -7,21 +5,23 @@ from ..tokens import DocBin
 
 
 class Corpus:
-    """An annotated corpus, using the JSON file format. Manages
-    annotations for tagging, dependency parsing and NER.
+    """An annotated corpus, reading train and dev datasets from
+    the DocBin (.spacy) format.
 
     DOCS: https://spacy.io/api/goldcorpus
     """
 
     def __init__(self, train_loc, dev_loc, limit=0):
-        """Create a GoldCorpus.
+        """Create a Corpus.
 
         train (str / Path): File or directory of training data.
         dev (str / Path): File or directory of development data.
-        RETURNS (GoldCorpus): The newly created object.
+        limit (int): Max. number of examples returned
+        RETURNS (Corpus): The newly created object.
         """
         self.train_loc = train_loc
         self.dev_loc = dev_loc
+        self.limit = limit
 
     @staticmethod
     def walk_corpus(path):
@@ -43,12 +43,12 @@ class Corpus:
                 locs.append(path)
         return locs
 
-    def make_examples(self, nlp, reference_docs, **kwargs):
+    def make_examples(self, nlp, reference_docs):
         for reference in reference_docs:
             predicted = nlp.make_doc(reference.text)
             yield Example(predicted, reference)
 
-    def read_docbin(self, vocab, locs, limit=0):
+    def read_docbin(self, vocab, locs):
         """ Yield training examples as example dicts """
         i = 0
         for loc in locs:
@@ -57,6 +57,9 @@ class Corpus:
                 with loc.open("rb") as file_:
                     doc_bin = DocBin().from_bytes(file_.read())
                 yield from doc_bin.get_docs(vocab)
+                i += len(doc_bin)   # TODO: should we restrict to EXACTLY the limit ?
+                if i >= self.limit:
+                    break
 
     def count_train(self, nlp):
         """Returns count of words in train examples"""
@@ -64,20 +67,20 @@ class Corpus:
         i = 0
         for example in self.train_dataset(nlp):
             n += len(example.predicted)
-            if self.limit and i >= self.limit:
+            if i >= self.limit:
                 break
             i += 1
         return n
 
-    def train_dataset(self, nlp, shuffle=True, **kwargs):
+    def train_dataset(self, nlp, shuffle=True):
         ref_docs = self.read_docbin(nlp.vocab, self.walk_corpus(self.train_loc))
-        examples = self.make_examples(nlp, ref_docs, **kwargs)
+        examples = self.make_examples(nlp, ref_docs)
         if shuffle:
             examples = list(examples)
             random.shuffle(examples)
         yield from examples
 
-    def dev_dataset(self, nlp, **kwargs):
+    def dev_dataset(self, nlp):
         ref_docs = self.read_docbin(nlp.vocab, self.walk_corpus(self.dev_loc))
-        examples = self.make_examples(nlp, ref_docs, **kwargs)
+        examples = self.make_examples(nlp, ref_docs)
         yield from examples

spacy/gold/example.pyx

@@ -1,3 +1,5 @@
+import warnings
+
 import numpy
 
 from ..tokens import Token
@@ -8,7 +10,6 @@ from .iob_utils import biluo_to_iob, biluo_tags_from_offsets, biluo_tags_from_do
 from .iob_utils import spans_from_biluo_tags
 from .align import Alignment
 from ..errors import Errors, AlignmentError
-from ..structs cimport TokenC
 from ..syntax import nonproj
 
 
@@ -18,6 +19,7 @@ cpdef Doc annotations2doc(vocab, tok_annot, doc_annot):
     output = Doc(vocab, words=tok_annot["ORTH"], spaces=tok_annot["SPACY"])
     if array.size:
         output = output.from_array(attrs, array)
+    # TODO: links ?!
     output.cats.update(doc_annot.get("cats", {}))
     return output
 
@@ -262,15 +264,14 @@ def _annot2array(vocab, tok_annot, doc_annot):
     values = []
 
     for key, value in doc_annot.items():
-        if key == "entities":
         if value:
+            if key == "entities":
                 words = tok_annot["ORTH"]
                 spaces = tok_annot["SPACY"]
                 ent_iobs, ent_types = _parse_ner_tags(value, vocab, words, spaces)
                 tok_annot["ENT_IOB"] = ent_iobs
                 tok_annot["ENT_TYPE"] = ent_types
             elif key == "links":
-            if value:
                 entities = doc_annot.get("entities", {})
                 if value and not entities:
                     raise ValueError(Errors.E981)
@@ -356,6 +357,7 @@ def _fix_legacy_dict_data(example_dict):
     if "HEAD" in token_dict and "SENT_START" in token_dict:
         # If heads are set, we don't also redundantly specify SENT_START.
         token_dict.pop("SENT_START")
+        warnings.warn("Ignoring annotations for sentence starts, as dependency heads are set")
     return {
         "token_annotation": token_dict,
         "doc_annotation": doc_dict

spacy/gold/gold_io.pyx

@@ -2,7 +2,7 @@ import warnings
 import srsly
 from .. import util
 from ..errors import Warnings
-from ..tokens import Token, Doc
+from ..tokens import Doc
 from .iob_utils import biluo_tags_from_offsets
 
 

spacy/ml/models/multi_task.py

@@ -48,9 +48,7 @@ def build_masked_language_model(vocab, wrapped_model, mask_prob=0.15):
     def mlm_forward(model, docs, is_train):
         mask, docs = _apply_mask(docs, random_words, mask_prob=mask_prob)
         mask = model.ops.asarray(mask).reshape((mask.shape[0], 1))
-        output, backprop = model.get_ref("wrapped-model").begin_update(
-            docs
-        )  # drop=drop
+        output, backprop = model.get_ref("wrapped-model").begin_update(docs)
 
         def mlm_backward(d_output):
             d_output *= 1 - mask

spacy/ml/models/tok2vec.py

@@ -147,7 +147,7 @@ def hash_char_embed_bilstm_v1(
 
 @registry.architectures.register("spacy.LayerNormalizedMaxout.v1")
 def LayerNormalizedMaxout(width, maxout_pieces):
-    return Maxout(nO=width, nP=maxout_pieces, dropout=0.0, normalize=True,)
+    return Maxout(nO=width, nP=maxout_pieces, dropout=0.0, normalize=True)
 
 
 @registry.architectures.register("spacy.MultiHashEmbed.v1")

spacy/tests/parser/test_ner.py

@@ -7,10 +7,10 @@ from spacy.pipeline.defaults import default_ner
 from spacy.pipeline import EntityRecognizer, EntityRuler
 from spacy.vocab import Vocab
 from spacy.syntax.ner import BiluoPushDown
+from spacy.gold import Example
 from spacy.tokens import Doc
 
 from ..util import make_tempdir
-from ...gold import Example
 
 TRAIN_DATA = [
     ("Who is Shaka Khan?", {"entities": [(7, 17, "PERSON")]}),

spacy/tests/regression/test_issue4402.py

@@ -1,24 +1,31 @@
-import srsly
 from spacy.gold import Corpus
 from spacy.lang.en import English
 
 from ..util import make_tempdir
+from ...gold.converters import json2docs
+from ...tokens import DocBin
 
 
 def test_issue4402():
     nlp = English()
     with make_tempdir() as tmpdir:
-        json_path = tmpdir / "test4402.json"
-        srsly.write_json(json_path, json_data)
+        output_file = tmpdir / "test4402.spacy"
+        docs = json2docs(json_data)
+        data = DocBin(docs=docs, attrs =["ORTH", "SENT_START", "ENT_IOB", "ENT_TYPE"]).to_bytes()
+        with output_file.open("wb") as file_:
+            file_.write(data)
+        corpus = Corpus(train_loc=str(output_file), dev_loc=str(output_file))
 
-        corpus = Corpus(str(json_path), str(json_path))
+        train_data = list(corpus.train_dataset(nlp))
+        assert len(train_data) == 2
 
-        train_data = list(corpus.train_dataset(nlp, gold_preproc=True, max_length=0))
-        # assert that the data got split into 4 sentences
-        assert len(train_data) == 4
+        split_train_data = []
+        for eg in train_data:
+            split_train_data.extend(eg.split_sents())
+        assert len(split_train_data) == 4
 
 
-json_data = [
+json_data =\
     {
         "id": 0,
         "paragraphs": [
@@ -89,4 +96,3 @@ json_data = [
             },
         ],
     }
-]

spacy/tests/test_gold.py

@@ -5,7 +5,7 @@ from spacy.gold import Corpus, docs_to_json
 from spacy.gold.example import Example
 from spacy.lang.en import English
 from spacy.syntax.nonproj import is_nonproj_tree
-from spacy.tokens import Doc
+from spacy.tokens import Doc, DocBin
 from spacy.util import get_words_and_spaces, compounding, minibatch
 import pytest
 import srsly
@@ -349,9 +349,7 @@ def test_iob_to_biluo():
         iob_to_biluo(bad_iob)
 
 
-# This test is outdated as we use DocBin now. It should probably be removed?
-@pytest.mark.xfail(reason="Outdated")
-def test_roundtrip_docs_to_json(doc):
+def test_roundtrip_docs_to_docbin(doc):
     nlp = English()
     text = doc.text
     idx = [t.idx for t in doc]
@@ -364,14 +362,18 @@ def test_roundtrip_docs_to_json(doc):
     cats = doc.cats
     ents = [(e.start_char, e.end_char, e.label_) for e in doc.ents]
 
-    # roundtrip to JSON
+    # roundtrip to DocBin
     with make_tempdir() as tmpdir:
         json_file = tmpdir / "roundtrip.json"
         srsly.write_json(json_file, [docs_to_json(doc)])
         goldcorpus = Corpus(str(json_file), str(json_file))
-
+        output_file = tmpdir / "roundtrip.spacy"
+        data = DocBin(docs=[doc]).to_bytes()
+        with output_file.open("wb") as file_:
+            file_.write(data)
+        goldcorpus = Corpus(train_loc=str(output_file), dev_loc=str(output_file))
         reloaded_example = next(goldcorpus.dev_dataset(nlp=nlp))
-        assert len(doc) == goldcorpus.count_train()
+        assert len(doc) == goldcorpus.count_train(nlp)
     assert text == reloaded_example.reference.text
     assert idx == [t.idx for t in reloaded_example.reference]
     assert tags == [t.tag_ for t in reloaded_example.reference]
@@ -425,14 +427,14 @@ def test_ignore_misaligned(doc):
 
 # We probably want the orth variant logic back, but this test won't be quite
 # right -- we need to go from DocBin.
-@pytest.mark.xfail(reason="Outdated")
 def test_make_orth_variants(doc):
     nlp = English()
     with make_tempdir() as tmpdir:
-        json_file = tmpdir / "test.json"
-        # write to JSON train dicts
-        srsly.write_json(json_file, [docs_to_json(doc)])
-        goldcorpus = Corpus(str(json_file), str(json_file))
+        output_file = tmpdir / "roundtrip.spacy"
+        data = DocBin(docs=[doc]).to_bytes()
+        with output_file.open("wb") as file_:
+            file_.write(data)
+        goldcorpus = Corpus(train_loc=str(output_file), dev_loc=str(output_file))
 
         # due to randomness, test only that this runs with no errors for now
         train_example = next(goldcorpus.train_dataset(nlp))