Python Doc.set_extension方法代码示例

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
    def __init__(self, nlp, label='GPE'):
        """Initialise the pipeline component. The shared nlp instance is used
        to initialise the matcher with the shared vocab, get the label ID and
        generate Doc objects as phrase match patterns.
        """
        # Make request once on initialisation and store the data
        r = requests.get('https://restcountries.eu/rest/v2/all')
        r.raise_for_status()  # make sure requests raises an error if it fails
        countries = r.json()

        # Convert API response to dict keyed by country name for easy lookup
        # This could also be extended using the alternative and foreign language
        # names provided by the API
        self.countries = {c['name']: c for c in countries}
        self.label = nlp.vocab.strings[label]  # get entity label ID

        # Set up the PhraseMatcher with Doc patterns for each country name
        patterns = [nlp(c) for c in self.countries.keys()]
        self.matcher = PhraseMatcher(nlp.vocab)
        self.matcher.add('COUNTRIES', None, *patterns)

        # Register attribute on the Token. We'll be overwriting this based on
        # the matches, so we're only setting a default value, not a getter.
        # If no default value is set, it defaults to None.
        Token.set_extension('is_country', default=False)
        Token.set_extension('country_capital')
        Token.set_extension('country_latlng')
        Token.set_extension('country_flag')

        # Register attributes on Doc and Span via a getter that checks if one of
        # the contained tokens is set to is_country == True.
        Doc.set_extension('has_country', getter=self.has_country)
        Span.set_extension('has_country', getter=self.has_country)

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def test_doc_to_json_underscore(doc):
    Doc.set_extension("json_test1", default=False)
    Doc.set_extension("json_test2", default=False)
    doc._.json_test1 = "hello world"
    doc._.json_test2 = [1, 2, 3]
    json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
    assert "_" in json_doc
    assert json_doc["_"]["json_test1"] == "hello world"
    assert json_doc["_"]["json_test2"] == [1, 2, 3]

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def test_underscore_dir(en_vocab):
    """Test that dir() correctly returns extension attributes. This enables
    things like tab-completion for the attributes in doc._."""
    Doc.set_extension("test_dir", default=None)
    doc = Doc(en_vocab, words=["hello", "world"])
    assert "_" in dir(doc)
    assert "test_dir" in dir(doc._)
    assert "test_dir" not in dir(doc[0]._)
    assert "test_dir" not in dir(doc[0:2]._)

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def test_underscore_docstring(en_vocab):
    """Test that docstrings are available for extension methods, even though
    they're partials."""

    def test_method(doc, arg1=1, arg2=2):
        """I am a docstring"""
        return (arg1, arg2)

    Doc.set_extension("test_docstrings", method=test_method)
    doc = Doc(en_vocab, words=["hello", "world"])
    assert test_method.__doc__ == "I am a docstring"
    assert doc._.test_docstrings.__doc__.rsplit(". ")[-1] == "I am a docstring"

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def test_underscore_mutable_defaults_list(en_vocab):
    """Test that mutable default arguments are handled correctly (see #2581)."""
    Doc.set_extension("mutable", default=[])
    doc1 = Doc(en_vocab, words=["one"])
    doc2 = Doc(en_vocab, words=["two"])
    doc1._.mutable.append("foo")
    assert len(doc1._.mutable) == 1
    assert doc1._.mutable[0] == "foo"
    assert len(doc2._.mutable) == 0
    doc1._.mutable = ["bar", "baz"]
    doc1._.mutable.append("foo")
    assert len(doc1._.mutable) == 3
    assert len(doc2._.mutable) == 0

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def main(output_dir=None):
    nlp = English()  # start off with blank English class

    Doc.set_extension('overlap', method=overlap_tokens)
    doc1 = nlp(u"Peach emoji is where it has always been.")
    doc2 = nlp(u"Peach is the superior emoji.")
    print("Text 1:", doc1.text)
    print("Text 2:", doc2.text)
    print("Overlapping tokens:", doc1._.overlap(doc2))

    Doc.set_extension('to_html', method=to_html)
    doc = nlp(u"This is a sentence about Apple.")
    # add entity manually for demo purposes, to make it work without a model
    doc.ents = [Span(doc, 5, 6, label=nlp.vocab.strings['ORG'])]
    print("Text:", doc.text)
    doc._.to_html(output=output_dir, style='ent')

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
    def __init__(self, nlp, companies=tuple(), label='ORG'):
        """Initialise the pipeline component. The shared nlp instance is used
        to initialise the matcher with the shared vocab, get the label ID and
        generate Doc objects as phrase match patterns.
        """
        self.label = nlp.vocab.strings[label]  # get entity label ID

        # Set up the PhraseMatcher – it can now take Doc objects as patterns,
        # so even if the list of companies is long, it's very efficient
        patterns = [nlp(org) for org in companies]
        self.matcher = PhraseMatcher(nlp.vocab)
        self.matcher.add('TECH_ORGS', None, *patterns)

        # Register attribute on the Token. We'll be overwriting this based on
        # the matches, so we're only setting a default value, not a getter.
        Token.set_extension('is_tech_org', default=False)

        # Register attributes on Doc and Span via a getter that checks if one of
        # the contained tokens is set to is_tech_org == True.
        Doc.set_extension('has_tech_org', getter=self.has_tech_org)
        Span.set_extension('has_tech_org', getter=self.has_tech_org)

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def doc_w_attrs(en_tokenizer):
    Doc.set_extension("_test_attr", default=False)
    Doc.set_extension("_test_prop", getter=lambda doc: len(doc.text))
    Doc.set_extension(
        "_test_method", method=lambda doc, arg: "{}{}".format(len(doc.text), arg)
    )
    doc = en_tokenizer("This is a test.")
    doc._._test_attr = "test"
    return doc

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def test_doc_to_json_underscore_error_serialize(doc):
    """Test that Doc.to_json() raises an error if a custom attribute value
    isn't JSON-serializable."""
    Doc.set_extension("json_test4", method=lambda doc: doc.text)
    with pytest.raises(ValueError):
        doc.to_json(underscore=["json_test4"])

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def test_underscore_raises_for_invalid(invalid_kwargs):
    invalid_kwargs["force"] = True
    with pytest.raises(ValueError):
        Doc.set_extension("test", **invalid_kwargs)

# 需要导入模块: from spacy.tokens import Doc [as 别名]
# 或者: from spacy.tokens.Doc import set_extension [as 别名]
def test_underscore_accepts_valid(valid_kwargs):
    valid_kwargs["force"] = True
    Doc.set_extension("test", **valid_kwargs)