diff --git a/.github/workflows/spacy_universe_alert.yml b/.github/workflows/spacy_universe_alert.yml index f507e0594..837aaeb33 100644 --- a/.github/workflows/spacy_universe_alert.yml +++ b/.github/workflows/spacy_universe_alert.yml @@ -19,6 +19,8 @@ jobs: - uses: actions/checkout@v3 - uses: actions/setup-python@v4 + with: + python-version: '3.10' - name: Install Bernadette app dependency and send an alert env: SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }} diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index df59697b1..e2c5e98fd 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -5,7 +5,7 @@ repos: - id: black language_version: python3.7 additional_dependencies: ['click==8.0.4'] -- repo: https://gitlab.com/pycqa/flake8 +- repo: https://github.com/pycqa/flake8 rev: 5.0.4 hooks: - id: flake8 diff --git a/azure-pipelines.yml b/azure-pipelines.yml index 3499042cb..9c3b92f06 100644 --- a/azure-pipelines.yml +++ b/azure-pipelines.yml @@ -87,13 +87,13 @@ jobs: # python.version: "3.10" Python311Linux: imageName: 'ubuntu-latest' - python.version: '3.11.0' + python.version: '3.11' Python311Windows: imageName: 'windows-latest' - python.version: '3.11.0' + python.version: '3.11' Python311Mac: imageName: 'macos-latest' - python.version: '3.11.0' + python.version: '3.11' maxParallel: 4 pool: vmImage: $(imageName) diff --git a/requirements.txt b/requirements.txt index 9d6bbb2c4..23bfa6f14 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,7 +9,7 @@ murmurhash>=0.28.0,<1.1.0 wasabi>=0.9.1,<1.1.0 srsly>=2.4.3,<3.0.0 catalogue>=2.0.6,<2.1.0 -typer>=0.3.0,<0.5.0 +typer>=0.3.0,<0.8.0 pathy>=0.3.5 # Third party dependencies numpy>=1.15.0 @@ -30,7 +30,7 @@ pytest-timeout>=1.3.0,<2.0.0 mock>=2.0.0,<3.0.0 flake8>=3.8.0,<6.0.0 hypothesis>=3.27.0,<7.0.0 -mypy>=0.980,<0.990; platform_machine != "aarch64" and python_version >= "3.7" +mypy>=0.990,<0.1000; platform_machine != "aarch64" and python_version >= "3.7" types-dataclasses>=0.1.3; python_version < "3.7" types-mock>=0.1.1 types-setuptools>=57.0.0 diff --git a/setup.cfg b/setup.cfg index c2653feba..82d4d2758 100644 --- a/setup.cfg +++ b/setup.cfg @@ -51,7 +51,7 @@ install_requires = srsly>=2.4.3,<3.0.0 catalogue>=2.0.6,<2.1.0 # Third-party dependencies - typer>=0.3.0,<0.5.0 + typer>=0.3.0,<0.8.0 pathy>=0.3.5 tqdm>=4.38.0,<5.0.0 numpy>=1.15.0 diff --git a/spacy/cli/project/assets.py b/spacy/cli/project/assets.py index 61438d1a8..8f35b2d23 100644 --- a/spacy/cli/project/assets.py +++ b/spacy/cli/project/assets.py @@ -189,7 +189,11 @@ def convert_asset_url(url: str) -> str: RETURNS (str): The converted URL. """ # If the asset URL is a regular GitHub URL it's likely a mistake - if re.match(r"(http(s?)):\/\/github.com", url) and "releases/download" not in url: + if ( + re.match(r"(http(s?)):\/\/github.com", url) + and "releases/download" not in url + and "/raw/" not in url + ): converted = url.replace("github.com", "raw.githubusercontent.com") converted = re.sub(r"/(tree|blob)/", "/", converted) msg.warn( diff --git a/spacy/cli/project/remote_storage.py b/spacy/cli/project/remote_storage.py index 336a4bcb3..12e252b3c 100644 --- a/spacy/cli/project/remote_storage.py +++ b/spacy/cli/project/remote_storage.py @@ -10,6 +10,7 @@ from .._util import get_hash, get_checksum, download_file, ensure_pathy from ...util import make_tempdir, get_minor_version, ENV_VARS, check_bool_env_var from ...git_info import GIT_VERSION from ... import about +from ...errors import Errors if TYPE_CHECKING: from pathy import Pathy # noqa: F401 @@ -84,7 +85,23 @@ class RemoteStorage: with tarfile.open(tar_loc, mode=mode_string) as tar_file: # This requires that the path is added correctly, relative # to root. This is how we set things up in push() - tar_file.extractall(self.root) + + # Disallow paths outside the current directory for the tar + # file (CVE-2007-4559, directory traversal vulnerability) + def is_within_directory(directory, target): + abs_directory = os.path.abspath(directory) + abs_target = os.path.abspath(target) + prefix = os.path.commonprefix([abs_directory, abs_target]) + return prefix == abs_directory + + def safe_extract(tar, path): + for member in tar.getmembers(): + member_path = os.path.join(path, member.name) + if not is_within_directory(path, member_path): + raise ValueError(Errors.E852) + tar.extractall(path) + + safe_extract(tar_file, self.root) return url def find( diff --git a/spacy/cli/project/run.py b/spacy/cli/project/run.py index ebab7471e..a109c4a5a 100644 --- a/spacy/cli/project/run.py +++ b/spacy/cli/project/run.py @@ -53,6 +53,7 @@ def project_run( force: bool = False, dry: bool = False, capture: bool = False, + skip_requirements_check: bool = False, ) -> None: """Run a named script defined in the project.yml. If the script is part of the default pipeline (defined in the "run" section), DVC is used to @@ -69,6 +70,7 @@ def project_run( sys.exit will be called with the return code. You should use capture=False when you want to turn over execution to the command, and capture=True when you want to run the command more like a function. + skip_requirements_check (bool): Whether to skip the requirements check. """ config = load_project_config(project_dir, overrides=overrides) commands = {cmd["name"]: cmd for cmd in config.get("commands", [])} @@ -76,9 +78,10 @@ def project_run( validate_subcommand(list(commands.keys()), list(workflows.keys()), subcommand) req_path = project_dir / "requirements.txt" - if config.get("check_requirements", True) and os.path.exists(req_path): - with req_path.open() as requirements_file: - _check_requirements([req.replace("\n", "") for req in requirements_file]) + if not skip_requirements_check: + if config.get("check_requirements", True) and os.path.exists(req_path): + with req_path.open() as requirements_file: + _check_requirements([req.strip() for req in requirements_file]) if subcommand in workflows: msg.info(f"Running workflow '{subcommand}'") @@ -90,6 +93,7 @@ def project_run( force=force, dry=dry, capture=capture, + skip_requirements_check=True, ) else: cmd = commands[subcommand] @@ -338,6 +342,12 @@ def _check_requirements(requirements: List[str]) -> Tuple[bool, bool]: failed_pkgs_msgs.append(dnf.report()) except pkg_resources.VersionConflict as vc: conflicting_pkgs_msgs.append(vc.report()) + except Exception: + msg.warn( + f"Unable to check requirement: {req} " + "Checks are currently limited to requirement specifiers " + "(PEP 508)" + ) if len(failed_pkgs_msgs) or len(conflicting_pkgs_msgs): msg.warn( diff --git a/spacy/cli/templates/quickstart_training_recommendations.yml b/spacy/cli/templates/quickstart_training_recommendations.yml index 27945e27a..4f214d22d 100644 --- a/spacy/cli/templates/quickstart_training_recommendations.yml +++ b/spacy/cli/templates/quickstart_training_recommendations.yml @@ -37,6 +37,15 @@ bn: accuracy: name: sagorsarker/bangla-bert-base size_factor: 3 +ca: + word_vectors: null + transformer: + efficiency: + name: projecte-aina/roberta-base-ca-v2 + size_factor: 3 + accuracy: + name: projecte-aina/roberta-base-ca-v2 + size_factor: 3 da: word_vectors: da_core_news_lg transformer: diff --git a/spacy/errors.py b/spacy/errors.py index 958859569..b2276642c 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -212,8 +212,8 @@ class Warnings(metaclass=ErrorsWithCodes): W121 = ("Attempting to trace non-existent method '{method}' in pipe '{pipe}'") W122 = ("Couldn't trace method '{method}' in pipe '{pipe}'. This can happen if the pipe class " "is a Cython extension type.") - W123 = ("Argument {arg} with value {arg_value} is used instead of {config_value} as specified in the config. Be " - "aware that this might affect other components in your pipeline.") + W123 = ("Argument `enable` with value {enable} does not contain all values specified in the config option " + "`enabled` ({enabled}). Be aware that this might affect other components in your pipeline.") class Errors(metaclass=ErrorsWithCodes): @@ -544,6 +544,10 @@ class Errors(metaclass=ErrorsWithCodes): "during training, make sure to include it in 'annotating components'") # New errors added in v3.x + E851 = ("The 'textcat' component labels should only have values of 0 or 1, " + "but found value of '{val}'.") + E852 = ("The tar file pulled from the remote attempted an unsafe path " + "traversal.") E853 = ("Unsupported component factory name '{name}'. The character '.' is " "not permitted in factory names.") E854 = ("Unable to set doc.ents. Check that the 'ents_filter' does not " diff --git a/spacy/lang/ru/tokenizer_exceptions.py b/spacy/lang/ru/tokenizer_exceptions.py index f3756e26c..e1889f785 100644 --- a/spacy/lang/ru/tokenizer_exceptions.py +++ b/spacy/lang/ru/tokenizer_exceptions.py @@ -61,6 +61,11 @@ for abbr in [ {ORTH: "2к23", NORM: "2023"}, {ORTH: "2к24", NORM: "2024"}, {ORTH: "2к25", NORM: "2025"}, + {ORTH: "2к26", NORM: "2026"}, + {ORTH: "2к27", NORM: "2027"}, + {ORTH: "2к28", NORM: "2028"}, + {ORTH: "2к29", NORM: "2029"}, + {ORTH: "2к30", NORM: "2030"}, ]: _exc[abbr[ORTH]] = [abbr] @@ -268,8 +273,8 @@ for abbr in [ {ORTH: "з-ка", NORM: "заимка"}, {ORTH: "п-к", NORM: "починок"}, {ORTH: "киш.", NORM: "кишлак"}, - {ORTH: "п. ст. ", NORM: "поселок станция"}, - {ORTH: "п. ж/д ст. ", NORM: "поселок при железнодорожной станции"}, + {ORTH: "п. ст.", NORM: "поселок станция"}, + {ORTH: "п. ж/д ст.", NORM: "поселок при железнодорожной станции"}, {ORTH: "ж/д бл-ст", NORM: "железнодорожный блокпост"}, {ORTH: "ж/д б-ка", NORM: "железнодорожная будка"}, {ORTH: "ж/д в-ка", NORM: "железнодорожная ветка"}, @@ -280,12 +285,12 @@ for abbr in [ {ORTH: "ж/д п.п.", NORM: "железнодорожный путевой пост"}, {ORTH: "ж/д о.п.", NORM: "железнодорожный остановочный пункт"}, {ORTH: "ж/д рзд.", NORM: "железнодорожный разъезд"}, - {ORTH: "ж/д ст. ", NORM: "железнодорожная станция"}, + {ORTH: "ж/д ст.", NORM: "железнодорожная станция"}, {ORTH: "м-ко", NORM: "местечко"}, {ORTH: "д.", NORM: "деревня"}, {ORTH: "с.", NORM: "село"}, {ORTH: "сл.", NORM: "слобода"}, - {ORTH: "ст. ", NORM: "станция"}, + {ORTH: "ст.", NORM: "станция"}, {ORTH: "ст-ца", NORM: "станица"}, {ORTH: "у.", NORM: "улус"}, {ORTH: "х.", NORM: "хутор"}, @@ -388,8 +393,9 @@ for abbr in [ {ORTH: "прим.", NORM: "примечание"}, {ORTH: "прим.ред.", NORM: "примечание редакции"}, {ORTH: "см. также", NORM: "смотри также"}, - {ORTH: "кв.м.", NORM: "квадрантный метр"}, - {ORTH: "м2", NORM: "квадрантный метр"}, + {ORTH: "см.", NORM: "смотри"}, + {ORTH: "кв.м.", NORM: "квадратный метр"}, + {ORTH: "м2", NORM: "квадратный метр"}, {ORTH: "б/у", NORM: "бывший в употреблении"}, {ORTH: "сокр.", NORM: "сокращение"}, {ORTH: "чел.", NORM: "человек"}, diff --git a/spacy/language.py b/spacy/language.py index d391f15ab..836f3abf9 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -706,13 +706,7 @@ class Language: # Check source type if not isinstance(source, Language): raise ValueError(Errors.E945.format(name=source_name, source=type(source))) - # Check vectors, with faster checks first - if ( - self.vocab.vectors.shape != source.vocab.vectors.shape - or self.vocab.vectors.key2row != source.vocab.vectors.key2row - or self.vocab.vectors.to_bytes(exclude=["strings"]) - != source.vocab.vectors.to_bytes(exclude=["strings"]) - ): + if self.vocab.vectors != source.vocab.vectors: warnings.warn(Warnings.W113.format(name=source_name)) if source_name not in source.component_names: raise KeyError( @@ -1879,31 +1873,22 @@ class Language: if isinstance(exclude, str): exclude = [exclude] - def fetch_pipes_status(value: Iterable[str], key: str) -> Iterable[str]: - """Fetch value for `enable` or `disable` w.r.t. the specified config and passed arguments passed to - .load(). If both arguments and config specified values for this field, the passed arguments take precedence - and a warning is printed. - value (Iterable[str]): Passed value for `enable` or `disable`. - key (str): Key for field in config (either "enabled" or "disabled"). - RETURN (Iterable[str]): - """ - # We assume that no argument was passed if the value is the specified default value. - if id(value) == id(_DEFAULT_EMPTY_PIPES): - return config["nlp"].get(key, []) - else: - if len(config["nlp"].get(key, [])): - warnings.warn( - Warnings.W123.format( - arg=key[:-1], - arg_value=value, - config_value=config["nlp"][key], - ) + # `enable` should not be merged with `enabled` (the opposite is true for `disable`/`disabled`). If the config + # specifies values for `enabled` not included in `enable`, emit warning. + if id(enable) != id(_DEFAULT_EMPTY_PIPES): + enabled = config["nlp"].get("enabled", []) + if len(enabled) and not set(enabled).issubset(enable): + warnings.warn( + Warnings.W123.format( + enable=enable, + enabled=enabled, ) - return value + ) + # Ensure sets of disabled/enabled pipe names are not contradictory. disabled_pipes = cls._resolve_component_status( - fetch_pipes_status(disable, "disabled"), - fetch_pipes_status(enable, "enabled"), + list({*disable, *config["nlp"].get("disabled", [])}), + enable, config["nlp"]["pipeline"], ) nlp._disabled = set(p for p in disabled_pipes if p not in exclude) @@ -2084,10 +2069,12 @@ class Language: if enable: if isinstance(enable, str): enable = [enable] - to_disable = [ - pipe_name for pipe_name in pipe_names if pipe_name not in enable - ] - if disable and disable != to_disable: + to_disable = { + *[pipe_name for pipe_name in pipe_names if pipe_name not in enable], + *disable, + } + # If any pipe to be enabled is in to_disable, the specification is inconsistent. + if len(set(enable) & to_disable): raise ValueError(Errors.E1042.format(enable=enable, disable=disable)) return tuple(to_disable) diff --git a/spacy/pipeline/textcat.py b/spacy/pipeline/textcat.py index 4023c4456..9490e3cb1 100644 --- a/spacy/pipeline/textcat.py +++ b/spacy/pipeline/textcat.py @@ -401,5 +401,9 @@ class TextCategorizer(TrainablePipe): def _validate_categories(self, examples: Iterable[Example]): """Check whether the provided examples all have single-label cats annotations.""" for ex in examples: - if list(ex.reference.cats.values()).count(1.0) > 1: + vals = list(ex.reference.cats.values()) + if vals.count(1.0) > 1: raise ValueError(Errors.E895.format(value=ex.reference.cats)) + for val in vals: + if not (val == 1.0 or val == 0.0): + raise ValueError(Errors.E851.format(val=val)) diff --git a/spacy/pipeline/textcat_multilabel.py b/spacy/pipeline/textcat_multilabel.py index eb83d9cb7..ef9bd6557 100644 --- a/spacy/pipeline/textcat_multilabel.py +++ b/spacy/pipeline/textcat_multilabel.py @@ -192,6 +192,8 @@ class MultiLabel_TextCategorizer(TextCategorizer): for label in labels: self.add_label(label) subbatch = list(islice(get_examples(), 10)) + self._validate_categories(subbatch) + doc_sample = [eg.reference for eg in subbatch] label_sample, _ = self._examples_to_truth(subbatch) self._require_labels() @@ -202,4 +204,8 @@ class MultiLabel_TextCategorizer(TextCategorizer): def _validate_categories(self, examples: Iterable[Example]): """This component allows any type of single- or multi-label annotations. This method overwrites the more strict one from 'textcat'.""" - pass + # check that annotation values are valid + for ex in examples: + for val in ex.reference.cats.values(): + if not (val == 1.0 or val == 0.0): + raise ValueError(Errors.E851.format(val=val)) diff --git a/spacy/tests/pipeline/test_pipe_methods.py b/spacy/tests/pipeline/test_pipe_methods.py index 14a7a36e5..4dd7bae16 100644 --- a/spacy/tests/pipeline/test_pipe_methods.py +++ b/spacy/tests/pipeline/test_pipe_methods.py @@ -615,20 +615,18 @@ def test_enable_disable_conflict_with_config(): with make_tempdir() as tmp_dir: nlp.to_disk(tmp_dir) - # Expected to fail, as config and arguments conflict. - with pytest.raises(ValueError): - spacy.load( - tmp_dir, enable=["tagger"], config={"nlp": {"disabled": ["senter"]}} - ) + # Expected to succeed, as config and arguments do not conflict. + assert spacy.load( + tmp_dir, enable=["tagger"], config={"nlp": {"disabled": ["senter"]}} + ).disabled == ["senter", "sentencizer"] # Expected to succeed without warning due to the lack of a conflicting config option. spacy.load(tmp_dir, enable=["tagger"]) - # Expected to succeed with a warning, as disable=[] should override the config setting. - with pytest.warns(UserWarning): + # Expected to fail due to conflict between enable and disabled. + with pytest.raises(ValueError): spacy.load( tmp_dir, - enable=["tagger"], - disable=[], - config={"nlp": {"disabled": ["senter"]}}, + enable=["senter"], + config={"nlp": {"disabled": ["senter", "tagger"]}}, ) diff --git a/spacy/tests/pipeline/test_textcat.py b/spacy/tests/pipeline/test_textcat.py index d359b77db..2eda9deaf 100644 --- a/spacy/tests/pipeline/test_textcat.py +++ b/spacy/tests/pipeline/test_textcat.py @@ -360,6 +360,30 @@ def test_label_types(name): nlp.initialize() +@pytest.mark.parametrize( + "name,get_examples", + [ + ("textcat", make_get_examples_single_label), + ("textcat_multilabel", make_get_examples_multi_label), + ], +) +def test_invalid_label_value(name, get_examples): + nlp = Language() + textcat = nlp.add_pipe(name) + example_getter = get_examples(nlp) + + def invalid_examples(): + # make one example with an invalid score + examples = example_getter() + ref = examples[0].reference + key = list(ref.cats.keys())[0] + ref.cats[key] = 2.0 + return examples + + with pytest.raises(ValueError): + nlp.initialize(get_examples=invalid_examples) + + @pytest.mark.parametrize("name", ["textcat", "textcat_multilabel"]) def test_no_label(name): nlp = Language() diff --git a/spacy/tests/serialize/test_serialize_pipeline.py b/spacy/tests/serialize/test_serialize_pipeline.py index b948bb76c..9fcf18e2d 100644 --- a/spacy/tests/serialize/test_serialize_pipeline.py +++ b/spacy/tests/serialize/test_serialize_pipeline.py @@ -404,11 +404,10 @@ def test_serialize_pipeline_disable_enable(): assert nlp3.component_names == ["ner", "tagger"] with make_tempdir() as d: nlp3.to_disk(d) - with pytest.warns(UserWarning): - nlp4 = spacy.load(d, disable=["ner"]) - assert nlp4.pipe_names == ["tagger"] + nlp4 = spacy.load(d, disable=["ner"]) + assert nlp4.pipe_names == [] assert nlp4.component_names == ["ner", "tagger"] - assert nlp4.disabled == ["ner"] + assert nlp4.disabled == ["ner", "tagger"] with make_tempdir() as d: nlp.to_disk(d) nlp5 = spacy.load(d, exclude=["tagger"]) diff --git a/spacy/tests/test_cli.py b/spacy/tests/test_cli.py index 838e00369..8225e14f1 100644 --- a/spacy/tests/test_cli.py +++ b/spacy/tests/test_cli.py @@ -1,5 +1,6 @@ import os import math +import pkg_resources from random import sample from typing import Counter @@ -25,6 +26,7 @@ from spacy.cli.download import get_compatibility, get_version from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config from spacy.cli.package import get_third_party_dependencies from spacy.cli.package import _is_permitted_package_name +from spacy.cli.project.run import _check_requirements from spacy.cli.validate import get_model_pkgs from spacy.lang.en import English from spacy.lang.nl import Dutch @@ -855,3 +857,42 @@ def test_span_length_freq_dist_output_must_be_correct(): span_freqs = _get_spans_length_freq_dist(sample_span_lengths, threshold) assert sum(span_freqs.values()) >= threshold assert list(span_freqs.keys()) == [3, 1, 4, 5, 2] + + +@pytest.mark.parametrize( + "reqs,output", + [ + [ + """ + spacy + + # comment + + thinc""", + (False, False), + ], + [ + """# comment + --some-flag + spacy""", + (False, False), + ], + [ + """# comment + --some-flag + spacy; python_version >= '3.6'""", + (False, False), + ], + [ + """# comment + spacyunknowndoesnotexist12345""", + (True, False), + ], + ], +) +def test_project_check_requirements(reqs, output): + # excessive guard against unlikely package name + try: + pkg_resources.require("spacyunknowndoesnotexist12345") + except pkg_resources.DistributionNotFound: + assert output == _check_requirements([req.strip() for req in reqs.split("\n")]) diff --git a/spacy/tests/vocab_vectors/test_vectors.py b/spacy/tests/vocab_vectors/test_vectors.py index dd2cfc596..70835816d 100644 --- a/spacy/tests/vocab_vectors/test_vectors.py +++ b/spacy/tests/vocab_vectors/test_vectors.py @@ -626,3 +626,23 @@ def test_floret_vectors(floret_vectors_vec_str, floret_vectors_hashvec_str): OPS.to_numpy(vocab_r[word].vector), decimal=6, ) + + +def test_equality(): + vectors1 = Vectors(shape=(10, 10)) + vectors2 = Vectors(shape=(10, 8)) + + assert vectors1 != vectors2 + + vectors2 = Vectors(shape=(10, 10)) + assert vectors1 == vectors2 + + vectors1.add("hello", row=2) + assert vectors1 != vectors2 + + vectors2.add("hello", row=2) + assert vectors1 == vectors2 + + vectors1.resize((5, 9)) + vectors2.resize((5, 9)) + assert vectors1 == vectors2 diff --git a/spacy/tests/vocab_vectors/test_vocab_api.py b/spacy/tests/vocab_vectors/test_vocab_api.py index 16cf80a08..b9c386eb8 100644 --- a/spacy/tests/vocab_vectors/test_vocab_api.py +++ b/spacy/tests/vocab_vectors/test_vocab_api.py @@ -1,8 +1,13 @@ +import os + import pytest from spacy.attrs import IS_ALPHA, LEMMA, ORTH +from spacy.lang.en import English from spacy.parts_of_speech import NOUN, VERB from spacy.vocab import Vocab +from ..util import make_tempdir + @pytest.mark.issue(1868) def test_issue1868(): @@ -59,3 +64,19 @@ def test_vocab_api_contains(en_vocab, text): def test_vocab_writing_system(en_vocab): assert en_vocab.writing_system["direction"] == "ltr" assert en_vocab.writing_system["has_case"] is True + + +def test_to_disk(): + nlp = English() + with make_tempdir() as d: + nlp.vocab.to_disk(d) + assert "vectors" in os.listdir(d) + assert "lookups.bin" in os.listdir(d) + + +def test_to_disk_exclude(): + nlp = English() + with make_tempdir() as d: + nlp.vocab.to_disk(d, exclude=("vectors", "lookups")) + assert "vectors" not in os.listdir(d) + assert "lookups.bin" not in os.listdir(d) diff --git a/spacy/tokens/span.pyi b/spacy/tokens/span.pyi index 617e3d19d..0a6f306a6 100644 --- a/spacy/tokens/span.pyi +++ b/spacy/tokens/span.pyi @@ -117,15 +117,13 @@ class Span: end_char: int label: int kb_id: int + id: int ent_id: int ent_id_: str @property - def id(self) -> int: ... - @property - def id_(self) -> str: ... - @property def orth_(self) -> str: ... @property def lemma_(self) -> str: ... label_: str kb_id_: str + id_: str diff --git a/spacy/vectors.pyx b/spacy/vectors.pyx index 8300220c1..be0f6db09 100644 --- a/spacy/vectors.pyx +++ b/spacy/vectors.pyx @@ -243,6 +243,15 @@ cdef class Vectors: else: return key in self.key2row + def __eq__(self, other): + # Check for equality, with faster checks first + return ( + self.shape == other.shape + and self.key2row == other.key2row + and self.to_bytes(exclude=["strings"]) + == other.to_bytes(exclude=["strings"]) + ) + def resize(self, shape, inplace=False): """Resize the underlying vectors array. If inplace=True, the memory is reallocated. This may cause other references to the data to become diff --git a/spacy/vocab.pyx b/spacy/vocab.pyx index 428cadd82..27f8e5f98 100644 --- a/spacy/vocab.pyx +++ b/spacy/vocab.pyx @@ -468,9 +468,9 @@ cdef class Vocab: setters = ["strings", "vectors"] if "strings" not in exclude: self.strings.to_disk(path / "strings.json") - if "vectors" not in "exclude": + if "vectors" not in exclude: self.vectors.to_disk(path, exclude=["strings"]) - if "lookups" not in "exclude": + if "lookups" not in exclude: self.lookups.to_disk(path) def from_disk(self, path, *, exclude=tuple()): diff --git a/website/README.md b/website/README.md index db050cf03..66bc20ad9 100644 --- a/website/README.md +++ b/website/README.md @@ -155,7 +155,7 @@ import Tag from 'components/tag' > ```jsx > method -> 2.1 +> 4 > tagger, parser > ``` @@ -170,7 +170,7 @@ installed. -method 2 tagger, +method 4 tagger, parser diff --git a/website/docs/api/cli.md b/website/docs/api/cli.md index fc2c46022..6e581b903 100644 --- a/website/docs/api/cli.md +++ b/website/docs/api/cli.md @@ -15,7 +15,6 @@ menu: - ['assemble', 'assemble'] - ['package', 'package'] - ['project', 'project'] - - ['ray', 'ray'] - ['huggingface-hub', 'huggingface-hub'] --- @@ -53,7 +52,7 @@ $ python -m spacy download [model] [--direct] [--sdist] [pip_args] | `--direct`, `-D` | Force direct download of exact package version. ~~bool (flag)~~ | | `--sdist`, `-S` 3 | Download the source package (`.tar.gz` archive) instead of the default pre-built binary wheel. ~~bool (flag)~~ | | `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| pip args 2.1 | Additional installation options to be passed to `pip install` when installing the pipeline package. For example, `--user` to install to the user home directory or `--no-deps` to not install package dependencies. ~~Any (option/flag)~~ | +| pip args | Additional installation options to be passed to `pip install` when installing the pipeline package. For example, `--user` to install to the user home directory or `--no-deps` to not install package dependencies. ~~Any (option/flag)~~ | | **CREATES** | The installed pipeline package in your `site-packages` directory. | ## info {#info tag="command"} @@ -77,15 +76,15 @@ $ python -m spacy info [--markdown] [--silent] [--exclude] $ python -m spacy info [model] [--markdown] [--silent] [--exclude] ``` -| Name | Description | -| ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------- | -| `model` | A trained pipeline, i.e. package name or path (optional). ~~Optional[str] \(option)~~ | -| `--markdown`, `-md` | Print information as Markdown. ~~bool (flag)~~ | -| `--silent`, `-s` 2.0.12 | Don't print anything, just return the values. ~~bool (flag)~~ | -| `--exclude`, `-e` | Comma-separated keys to exclude from the print-out. Defaults to `"labels"`. ~~Optional[str]~~ | -| `--url`, `-u` 3.5.0 | Print the URL to download the most recent compatible version of the pipeline. Requires a pipeline name. ~~bool (flag)~~ | -| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| **PRINTS** | Information about your spaCy installation. | +| Name | Description | +| -------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | +| `model` | A trained pipeline, i.e. package name or path (optional). ~~Optional[str] \(option)~~ | +| `--markdown`, `-md` | Print information as Markdown. ~~bool (flag)~~ | +| `--silent`, `-s` | Don't print anything, just return the values. ~~bool (flag)~~ | +| `--exclude`, `-e` | Comma-separated keys to exclude from the print-out. Defaults to `"labels"`. ~~Optional[str]~~ | +| `--url`, `-u` 3.5.0 | Print the URL to download the most recent compatible version of the pipeline. Requires a pipeline name. ~~bool (flag)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | +| **PRINTS** | Information about your spaCy installation. | ## validate {#validate new="2" tag="command"} @@ -260,22 +259,22 @@ chosen based on the file extension of the input file. $ python -m spacy convert [input_file] [output_dir] [--converter] [--file-type] [--n-sents] [--seg-sents] [--base] [--morphology] [--merge-subtokens] [--ner-map] [--lang] ``` -| Name | Description | -| ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------- | -| `input_path` | Input file or directory. ~~Path (positional)~~ | -| `output_dir` | Output directory for converted file. Defaults to `"-"`, meaning data will be written to `stdout`. ~~Optional[Path] \(option)~~ | -| `--converter`, `-c` 2 | Name of converter to use (see below). ~~str (option)~~ | -| `--file-type`, `-t` 2.1 | Type of file to create. Either `spacy` (default) for binary [`DocBin`](/api/docbin) data or `json` for v2.x JSON format. ~~str (option)~~ | -| `--n-sents`, `-n` | Number of sentences per document. Supported for: `conll`, `conllu`, `iob`, `ner` ~~int (option)~~ | -| `--seg-sents`, `-s` 2.2 | Segment sentences. Supported for: `conll`, `ner` ~~bool (flag)~~ | -| `--base`, `-b`, `--model` | Trained spaCy pipeline for sentence segmentation to use as base (for `--seg-sents`). ~~Optional[str](option)~~ | -| `--morphology`, `-m` | Enable appending morphology to tags. Supported for: `conllu` ~~bool (flag)~~ | -| `--merge-subtokens`, `-T` | Merge CoNLL-U subtokens ~~bool (flag)~~ | -| `--ner-map`, `-nm` | NER tag mapping (as JSON-encoded dict of entity types). Supported for: `conllu` ~~Optional[Path](option)~~ | -| `--lang`, `-l` 2.1 | Language code (if tokenizer required). ~~Optional[str] \(option)~~ | -| `--concatenate`, `-C` | Concatenate output to a single file ~~bool (flag)~~ | -| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| **CREATES** | Binary [`DocBin`](/api/docbin) training data that can be used with [`spacy train`](/api/cli#train). | +| Name | Description | +| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | +| `input_path` | Input file or directory. ~~Path (positional)~~ | +| `output_dir` | Output directory for converted file. Defaults to `"-"`, meaning data will be written to `stdout`. ~~Optional[Path] \(option)~~ | +| `--converter`, `-c` | Name of converter to use (see below). ~~str (option)~~ | +| `--file-type`, `-t` | Type of file to create. Either `spacy` (default) for binary [`DocBin`](/api/docbin) data or `json` for v2.x JSON format. ~~str (option)~~ | +| `--n-sents`, `-n` | Number of sentences per document. Supported for: `conll`, `conllu`, `iob`, `ner` ~~int (option)~~ | +| `--seg-sents`, `-s` | Segment sentences. Supported for: `conll`, `ner` ~~bool (flag)~~ | +| `--base`, `-b`, `--model` | Trained spaCy pipeline for sentence segmentation to use as base (for `--seg-sents`). ~~Optional[str](option)~~ | +| `--morphology`, `-m` | Enable appending morphology to tags. Supported for: `conllu` ~~bool (flag)~~ | +| `--merge-subtokens`, `-T` | Merge CoNLL-U subtokens ~~bool (flag)~~ | +| `--ner-map`, `-nm` | NER tag mapping (as JSON-encoded dict of entity types). Supported for: `conllu` ~~Optional[Path](option)~~ | +| `--lang`, `-l` | Language code (if tokenizer required). ~~Optional[str] \(option)~~ | +| `--concatenate`, `-C` | Concatenate output to a single file ~~bool (flag)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | +| **CREATES** | Binary [`DocBin`](/api/docbin) training data that can be used with [`spacy train`](/api/cli#train). | ### Converters {#converters} @@ -474,8 +473,7 @@ report span characteristics such as the average span length and the span (or span boundary) distinctiveness. The distinctiveness measure shows how different the tokens are with respect to the rest of the corpus using the KL-divergence of the token distributions. To learn more, you can check out Papay et al.'s work on -[*Dissecting Span Identification Tasks with Performance Prediction* (EMNLP -2020)](https://aclanthology.org/2020.emnlp-main.396/). +[*Dissecting Span Identification Tasks with Performance Prediction* (EMNLP 2020)](https://aclanthology.org/2020.emnlp-main.396/). @@ -1229,19 +1227,19 @@ $ python -m spacy package [input_dir] [output_dir] [--code] [--meta-path] [--cre > $ pip install dist/en_pipeline-0.0.0.tar.gz > ``` -| Name | Description | -| ------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `input_dir` | Path to directory containing pipeline data. ~~Path (positional)~~ | -| `output_dir` | Directory to create package folder in. ~~Path (positional)~~ | -| `--code`, `-c` 3 | Comma-separated paths to Python files to be included in the package and imported in its `__init__.py`. This allows including [registering functions](/usage/training#custom-functions) and [custom components](/usage/processing-pipelines#custom-components). ~~str (option)~~ | -| `--meta-path`, `-m` 2 | Path to [`meta.json`](/api/data-formats#meta) file (optional). ~~Optional[Path] \(option)~~ | -| `--create-meta`, `-C` 2 | Create a `meta.json` file on the command line, even if one already exists in the directory. If an existing file is found, its entries will be shown as the defaults in the command line prompt. ~~bool (flag)~~ | -| `--build`, `-b` 3 | Comma-separated artifact formats to build. Can be `sdist` (for a `.tar.gz` archive) and/or `wheel` (for a binary `.whl` file), or `none` if you want to run this step manually. The generated artifacts can be installed by `pip install`. Defaults to `sdist`. ~~str (option)~~ | -| `--name`, `-n` 3 | Package name to override in meta. ~~Optional[str] \(option)~~ | -| `--version`, `-v` 3 | Package version to override in meta. Useful when training new versions, as it doesn't require editing the meta template. ~~Optional[str] \(option)~~ | -| `--force`, `-f` | Force overwriting of existing folder in output directory. ~~bool (flag)~~ | -| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| **CREATES** | A Python package containing the spaCy pipeline. | +| Name | Description | +| -------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `input_dir` | Path to directory containing pipeline data. ~~Path (positional)~~ | +| `output_dir` | Directory to create package folder in. ~~Path (positional)~~ | +| `--code`, `-c` 3 | Comma-separated paths to Python files to be included in the package and imported in its `__init__.py`. This allows including [registering functions](/usage/training#custom-functions) and [custom components](/usage/processing-pipelines#custom-components). ~~str (option)~~ | +| `--meta-path`, `-m` | Path to [`meta.json`](/api/data-formats#meta) file (optional). ~~Optional[Path] \(option)~~ | +| `--create-meta`, `-C` | Create a `meta.json` file on the command line, even if one already exists in the directory. If an existing file is found, its entries will be shown as the defaults in the command line prompt. ~~bool (flag)~~ | +| `--build`, `-b` 3 | Comma-separated artifact formats to build. Can be `sdist` (for a `.tar.gz` archive) and/or `wheel` (for a binary `.whl` file), or `none` if you want to run this step manually. The generated artifacts can be installed by `pip install`. Defaults to `sdist`. ~~str (option)~~ | +| `--name`, `-n` 3 | Package name to override in meta. ~~Optional[str] \(option)~~ | +| `--version`, `-v` 3 | Package version to override in meta. Useful when training new versions, as it doesn't require editing the meta template. ~~Optional[str] \(option)~~ | +| `--force`, `-f` | Force overwriting of existing folder in output directory. ~~bool (flag)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | +| **CREATES** | A Python package containing the spaCy pipeline. | ## project {#project new="3"} @@ -1503,50 +1501,6 @@ $ python -m spacy project dvc [project_dir] [workflow] [--force] [--verbose] [-- | `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | | **CREATES** | A `dvc.yaml` file in the project directory, based on the steps defined in the given workflow. | -## ray {#ray new="3"} - -The `spacy ray` CLI includes commands for parallel and distributed computing via -[Ray](https://ray.io). - - - -To use this command, you need the -[`spacy-ray`](https://github.com/explosion/spacy-ray) package installed. -Installing the package will automatically add the `ray` command to the spaCy -CLI. - - - -### ray train {#ray-train tag="command"} - -Train a spaCy pipeline using [Ray](https://ray.io) for parallel training. The -command works just like [`spacy train`](/api/cli#train). For more details and -examples, see the usage guide on -[parallel training](/usage/training#parallel-training) and the spaCy project -[integration](/usage/projects#ray). - -```cli -$ python -m spacy ray train [config_path] [--code] [--output] [--n-workers] [--address] [--gpu-id] [--verbose] [overrides] -``` - -> #### Example -> -> ```cli -> $ python -m spacy ray train config.cfg --n-workers 2 -> ``` - -| Name | Description | -| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| `config_path` | Path to [training config](/api/data-formats#config) file containing all settings and hyperparameters. ~~Path (positional)~~ | -| `--code`, `-c` | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ | -| `--output`, `-o` | Directory or remote storage URL for saving trained pipeline. The directory will be created if it doesn't exist. ~~Optional[Path] \(option)~~ | -| `--n-workers`, `-n` | The number of workers. Defaults to `1`. ~~int (option)~~ | -| `--address`, `-a` | Optional address of the Ray cluster. If not set (default), Ray will run locally. ~~Optional[str] \(option)~~ | -| `--gpu-id`, `-g` | GPU ID or `-1` for CPU. Defaults to `-1`. ~~int (option)~~ | -| `--verbose`, `-V` | Display more information for debugging purposes. ~~bool (flag)~~ | -| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| overrides | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~ | - ## huggingface-hub {#huggingface-hub new="3.1"} The `spacy huggingface-cli` CLI includes commands for uploading your trained diff --git a/website/docs/api/doc.md b/website/docs/api/doc.md index f97ed4547..090489d83 100644 --- a/website/docs/api/doc.md +++ b/website/docs/api/doc.md @@ -209,15 +209,15 @@ alignment mode `"strict". > assert span.text == "New York" > ``` -| Name | Description | -| ------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `start` | The index of the first character of the span. ~~int~~ | -| `end` | The index of the last character after the span. ~~int~~ | -| `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ | -| `kb_id` 2.2 | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ | -| `vector` | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~ | -| `alignment_mode` | How character indices snap to token boundaries. Options: `"strict"` (no snapping), `"contract"` (span of all tokens completely within the character span), `"expand"` (span of all tokens at least partially covered by the character span). Defaults to `"strict"`. ~~str~~ | -| **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~ | +| Name | Description | +| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `start` | The index of the first character of the span. ~~int~~ | +| `end` | The index of the last character after the span. ~~int~~ | +| `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ | +| `kb_id` | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ | +| `vector` | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~ | +| `alignment_mode` | How character indices snap to token boundaries. Options: `"strict"` (no snapping), `"contract"` (span of all tokens completely within the character span), `"expand"` (span of all tokens at least partially covered by the character span). Defaults to `"strict"`. ~~str~~ | +| **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~ | ## Doc.set_ents {#set_ents tag="method" new="3"} @@ -751,22 +751,22 @@ The L2 norm of the document's vector representation. ## Attributes {#attributes} -| Name | Description | -| ------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------- | -| `text` | A string representation of the document text. ~~str~~ | -| `text_with_ws` | An alias of `Doc.text`, provided for duck-type compatibility with `Span` and `Token`. ~~str~~ | -| `mem` | The document's local memory heap, for all C data it owns. ~~cymem.Pool~~ | -| `vocab` | The store of lexical types. ~~Vocab~~ | -| `tensor` 2 | Container for dense vector representations. ~~numpy.ndarray~~ | -| `user_data` | A generic storage area, for user custom data. ~~Dict[str, Any]~~ | -| `lang` 2.1 | Language of the document's vocabulary. ~~int~~ | -| `lang_` 2.1 | Language of the document's vocabulary. ~~str~~ | -| `sentiment` | The document's positivity/negativity score, if available. ~~float~~ | -| `user_hooks` | A dictionary that allows customization of the `Doc`'s properties. ~~Dict[str, Callable]~~ | -| `user_token_hooks` | A dictionary that allows customization of properties of `Token` children. ~~Dict[str, Callable]~~ | -| `user_span_hooks` | A dictionary that allows customization of properties of `Span` children. ~~Dict[str, Callable]~~ | -| `has_unknown_spaces` | Whether the document was constructed without known spacing between tokens (typically when created from gold tokenization). ~~bool~~ | -| `_` | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~ | +| Name | Description | +| -------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | +| `text` | A string representation of the document text. ~~str~~ | +| `text_with_ws` | An alias of `Doc.text`, provided for duck-type compatibility with `Span` and `Token`. ~~str~~ | +| `mem` | The document's local memory heap, for all C data it owns. ~~cymem.Pool~~ | +| `vocab` | The store of lexical types. ~~Vocab~~ | +| `tensor` | Container for dense vector representations. ~~numpy.ndarray~~ | +| `user_data` | A generic storage area, for user custom data. ~~Dict[str, Any]~~ | +| `lang` | Language of the document's vocabulary. ~~int~~ | +| `lang_` | Language of the document's vocabulary. ~~str~~ | +| `sentiment` | The document's positivity/negativity score, if available. ~~float~~ | +| `user_hooks` | A dictionary that allows customization of the `Doc`'s properties. ~~Dict[str, Callable]~~ | +| `user_token_hooks` | A dictionary that allows customization of properties of `Token` children. ~~Dict[str, Callable]~~ | +| `user_span_hooks` | A dictionary that allows customization of properties of `Span` children. ~~Dict[str, Callable]~~ | +| `has_unknown_spaces` | Whether the document was constructed without known spacing between tokens (typically when created from gold tokenization). ~~bool~~ | +| `_` | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~ | ## Serialization fields {#serialization-fields} diff --git a/website/docs/api/language.md b/website/docs/api/language.md index 767a7450a..ad0ac2a46 100644 --- a/website/docs/api/language.md +++ b/website/docs/api/language.md @@ -63,18 +63,18 @@ spaCy loads a model under the hood based on its > nlp = Language.from_config(config) > ``` -| Name | Description | -| ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `config` | The loaded config. ~~Union[Dict[str, Any], Config]~~ | -| _keyword-only_ | | -| `vocab` | A `Vocab` object. If `True`, a vocab is created using the default language data settings. ~~Vocab~~ | -| `disable` | Name(s) of pipeline component(s) to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [`nlp.enable_pipe`](/api/language#enable_pipe). ~~Union[str, Iterable[str]]~~ | -| `enable` 3.4 | Name(s) of pipeline component(s) to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled, but can be enabled again using [`nlp.enable_pipe`](/api/language#enable_pipe). ~~Union[str, Iterable[str]]~~ | -| `exclude` | Name(s) of pipeline component(s) to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~Union[str, Iterable[str]]~~ | -| `meta` | [Meta data](/api/data-formats#meta) overrides. ~~Dict[str, Any]~~ | -| `auto_fill` | Whether to automatically fill in missing values in the config, based on defaults and function argument annotations. Defaults to `True`. ~~bool~~ | -| `validate` | Whether to validate the component config and arguments against the types expected by the factory. Defaults to `True`. ~~bool~~ | -| **RETURNS** | The initialized object. ~~Language~~ | +| Name | Description | +| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `config` | The loaded config. ~~Union[Dict[str, Any], Config]~~ | +| _keyword-only_ | | +| `vocab` | A `Vocab` object. If `True`, a vocab is created using the default language data settings. ~~Vocab~~ | +| `disable` | Name(s) of pipeline component(s) to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [nlp.enable_pipe](/api/language#enable_pipe). Is merged with the config entry `nlp.disabled`. ~~Union[str, Iterable[str]]~~ | +| `enable` 3.4 | Name(s) of pipeline component(s) to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled, but can be enabled again using [nlp.enable_pipe](/api/language#enable_pipe). ~~Union[str, Iterable[str]]~~ | +| `exclude` | Name(s) of pipeline component(s) to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~Union[str, Iterable[str]]~~ | +| `meta` | [Meta data](/api/data-formats#meta) overrides. ~~Dict[str, Any]~~ | +| `auto_fill` | Whether to automatically fill in missing values in the config, based on defaults and function argument annotations. Defaults to `True`. ~~bool~~ | +| `validate` | Whether to validate the component config and arguments against the types expected by the factory. Defaults to `True`. ~~bool~~ | +| **RETURNS** | The initialized object. ~~Language~~ | ## Language.component {#component tag="classmethod" new="3"} @@ -198,16 +198,16 @@ tokenization is skipped but the rest of the pipeline is run. > assert doc.has_annotation("DEP") > ``` -| Name | Description | -| ------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `texts` | A sequence of strings (or `Doc` objects). ~~Iterable[Union[str, Doc]]~~ | -| _keyword-only_ | | -| `as_tuples` | If set to `True`, inputs should be a sequence of `(text, context)` tuples. Output will then be a sequence of `(doc, context)` tuples. Defaults to `False`. ~~bool~~ | -| `batch_size` | The number of texts to buffer. ~~Optional[int]~~ | -| `disable` | Names of pipeline components to [disable](/usage/processing-pipelines#disabling). ~~List[str]~~ | -| `component_cfg` | Optional dictionary of keyword arguments for components, keyed by component names. Defaults to `None`. ~~Optional[Dict[str, Dict[str, Any]]]~~ | -| `n_process` 2.2.2 | Number of processors to use. Defaults to `1`. ~~int~~ | -| **YIELDS** | Documents in the order of the original text. ~~Doc~~ | +| Name | Description | +| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `texts` | A sequence of strings (or `Doc` objects). ~~Iterable[Union[str, Doc]]~~ | +| _keyword-only_ | | +| `as_tuples` | If set to `True`, inputs should be a sequence of `(text, context)` tuples. Output will then be a sequence of `(doc, context)` tuples. Defaults to `False`. ~~bool~~ | +| `batch_size` | The number of texts to buffer. ~~Optional[int]~~ | +| `disable` | Names of pipeline components to [disable](/usage/processing-pipelines#disabling). ~~List[str]~~ | +| `component_cfg` | Optional dictionary of keyword arguments for components, keyed by component names. Defaults to `None`. ~~Optional[Dict[str, Dict[str, Any]]]~~ | +| `n_process` | Number of processors to use. Defaults to `1`. ~~int~~ | +| **YIELDS** | Documents in the order of the original text. ~~Doc~~ | ## Language.set_error_handler {#set_error_handler tag="method" new="3"} @@ -1030,21 +1030,21 @@ details. ## Attributes {#attributes} -| Name | Description | -| --------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | -| `vocab` | A container for the lexical types. ~~Vocab~~ | -| `tokenizer` | The tokenizer. ~~Tokenizer~~ | -| `make_doc` | Callable that takes a string and returns a `Doc`. ~~Callable[[str], Doc]~~ | -| `pipeline` | List of `(name, component)` tuples describing the current processing pipeline, in order. ~~List[Tuple[str, Callable[[Doc], Doc]]]~~ | -| `pipe_names` 2 | List of pipeline component names, in order. ~~List[str]~~ | -| `pipe_labels` 2.2 | List of labels set by the pipeline components, if available, keyed by component name. ~~Dict[str, List[str]]~~ | -| `pipe_factories` 2.2 | Dictionary of pipeline component names, mapped to their factory names. ~~Dict[str, str]~~ | -| `factories` | All available factory functions, keyed by name. ~~Dict[str, Callable[[...], Callable[[Doc], Doc]]]~~ | -| `factory_names` 3 | List of all available factory names. ~~List[str]~~ | -| `components` 3 | List of all available `(name, component)` tuples, including components that are currently disabled. ~~List[Tuple[str, Callable[[Doc], Doc]]]~~ | -| `component_names` 3 | List of all available component names, including components that are currently disabled. ~~List[str]~~ | -| `disabled` 3 | Names of components that are currently disabled and don't run as part of the pipeline. ~~List[str]~~ | -| `path` 2 | Path to the pipeline data directory, if a pipeline is loaded from a path or package. Otherwise `None`. ~~Optional[Path]~~ | +| Name | Description | +| -------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | +| `vocab` | A container for the lexical types. ~~Vocab~~ | +| `tokenizer` | The tokenizer. ~~Tokenizer~~ | +| `make_doc` | Callable that takes a string and returns a `Doc`. ~~Callable[[str], Doc]~~ | +| `pipeline` | List of `(name, component)` tuples describing the current processing pipeline, in order. ~~List[Tuple[str, Callable[[Doc], Doc]]]~~ | +| `pipe_names` | List of pipeline component names, in order. ~~List[str]~~ | +| `pipe_labels` | List of labels set by the pipeline components, if available, keyed by component name. ~~Dict[str, List[str]]~~ | +| `pipe_factories` | Dictionary of pipeline component names, mapped to their factory names. ~~Dict[str, str]~~ | +| `factories` | All available factory functions, keyed by name. ~~Dict[str, Callable[[...], Callable[[Doc], Doc]]]~~ | +| `factory_names` 3 | List of all available factory names. ~~List[str]~~ | +| `components` 3 | List of all available `(name, component)` tuples, including components that are currently disabled. ~~List[Tuple[str, Callable[[Doc], Doc]]]~~ | +| `component_names` 3 | List of all available component names, including components that are currently disabled. ~~List[str]~~ | +| `disabled` 3 | Names of components that are currently disabled and don't run as part of the pipeline. ~~List[str]~~ | +| `path` | Path to the pipeline data directory, if a pipeline is loaded from a path or package. Otherwise `None`. ~~Optional[Path]~~ | ## Class attributes {#class-attributes} diff --git a/website/docs/api/lexeme.md b/website/docs/api/lexeme.md index c5d4b7544..eb76afa90 100644 --- a/website/docs/api/lexeme.md +++ b/website/docs/api/lexeme.md @@ -121,44 +121,44 @@ The L2 norm of the lexeme's vector representation. ## Attributes {#attributes} -| Name | Description | -| -------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `vocab` | The lexeme's vocabulary. ~~Vocab~~ | -| `text` | Verbatim text content. ~~str~~ | -| `orth` | ID of the verbatim text content. ~~int~~ | -| `orth_` | Verbatim text content (identical to `Lexeme.text`). Exists mostly for consistency with the other attributes. ~~str~~ | -| `rank` | Sequential ID of the lexeme's lexical type, used to index into tables, e.g. for word vectors. ~~int~~ | -| `flags` | Container of the lexeme's binary flags. ~~int~~ | -| `norm` | The lexeme's norm, i.e. a normalized form of the lexeme text. ~~int~~ | -| `norm_` | The lexeme's norm, i.e. a normalized form of the lexeme text. ~~str~~ | -| `lower` | Lowercase form of the word. ~~int~~ | -| `lower_` | Lowercase form of the word. ~~str~~ | -| `shape` | Transform of the word's string, to show orthographic features. Alphabetic characters are replaced by `x` or `X`, and numeric characters are replaced by `d`, and sequences of the same character are truncated after length 4. For example,`"Xxxx"`or`"dd"`. ~~int~~ | -| `shape_` | Transform of the word's string, to show orthographic features. Alphabetic characters are replaced by `x` or `X`, and numeric characters are replaced by `d`, and sequences of the same character are truncated after length 4. For example,`"Xxxx"`or`"dd"`. ~~str~~ | -| `prefix` | Length-N substring from the start of the word. Defaults to `N=1`. ~~int~~ | -| `prefix_` | Length-N substring from the start of the word. Defaults to `N=1`. ~~str~~ | -| `suffix` | Length-N substring from the end of the word. Defaults to `N=3`. ~~int~~ | -| `suffix_` | Length-N substring from the start of the word. Defaults to `N=3`. ~~str~~ | -| `is_alpha` | Does the lexeme consist of alphabetic characters? Equivalent to `lexeme.text.isalpha()`. ~~bool~~ | -| `is_ascii` | Does the lexeme consist of ASCII characters? Equivalent to `[any(ord(c) >= 128 for c in lexeme.text)]`. ~~bool~~ | -| `is_digit` | Does the lexeme consist of digits? Equivalent to `lexeme.text.isdigit()`. ~~bool~~ | -| `is_lower` | Is the lexeme in lowercase? Equivalent to `lexeme.text.islower()`. ~~bool~~ | -| `is_upper` | Is the lexeme in uppercase? Equivalent to `lexeme.text.isupper()`. ~~bool~~ | -| `is_title` | Is the lexeme in titlecase? Equivalent to `lexeme.text.istitle()`. ~~bool~~ | -| `is_punct` | Is the lexeme punctuation? ~~bool~~ | -| `is_left_punct` | Is the lexeme a left punctuation mark, e.g. `(`? ~~bool~~ | -| `is_right_punct` | Is the lexeme a right punctuation mark, e.g. `)`? ~~bool~~ | -| `is_space` | Does the lexeme consist of whitespace characters? Equivalent to `lexeme.text.isspace()`. ~~bool~~ | -| `is_bracket` | Is the lexeme a bracket? ~~bool~~ | -| `is_quote` | Is the lexeme a quotation mark? ~~bool~~ | -| `is_currency` 2.0.8 | Is the lexeme a currency symbol? ~~bool~~ | -| `like_url` | Does the lexeme resemble a URL? ~~bool~~ | -| `like_num` | Does the lexeme represent a number? e.g. "10.9", "10", "ten", etc. ~~bool~~ | -| `like_email` | Does the lexeme resemble an email address? ~~bool~~ | -| `is_oov` | Is the lexeme out-of-vocabulary (i.e. does it not have a word vector)? ~~bool~~ | -| `is_stop` | Is the lexeme part of a "stop list"? ~~bool~~ | -| `lang` | Language of the parent vocabulary. ~~int~~ | -| `lang_` | Language of the parent vocabulary. ~~str~~ | -| `prob` | Smoothed log probability estimate of the lexeme's word type (context-independent entry in the vocabulary). ~~float~~ | -| `cluster` | Brown cluster ID. ~~int~~ | -| `sentiment` | A scalar value indicating the positivity or negativity of the lexeme. ~~float~~ | +| Name | Description | +| ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `vocab` | The lexeme's vocabulary. ~~Vocab~~ | +| `text` | Verbatim text content. ~~str~~ | +| `orth` | ID of the verbatim text content. ~~int~~ | +| `orth_` | Verbatim text content (identical to `Lexeme.text`). Exists mostly for consistency with the other attributes. ~~str~~ | +| `rank` | Sequential ID of the lexeme's lexical type, used to index into tables, e.g. for word vectors. ~~int~~ | +| `flags` | Container of the lexeme's binary flags. ~~int~~ | +| `norm` | The lexeme's norm, i.e. a normalized form of the lexeme text. ~~int~~ | +| `norm_` | The lexeme's norm, i.e. a normalized form of the lexeme text. ~~str~~ | +| `lower` | Lowercase form of the word. ~~int~~ | +| `lower_` | Lowercase form of the word. ~~str~~ | +| `shape` | Transform of the word's string, to show orthographic features. Alphabetic characters are replaced by `x` or `X`, and numeric characters are replaced by `d`, and sequences of the same character are truncated after length 4. For example,`"Xxxx"`or`"dd"`. ~~int~~ | +| `shape_` | Transform of the word's string, to show orthographic features. Alphabetic characters are replaced by `x` or `X`, and numeric characters are replaced by `d`, and sequences of the same character are truncated after length 4. For example,`"Xxxx"`or`"dd"`. ~~str~~ | +| `prefix` | Length-N substring from the start of the word. Defaults to `N=1`. ~~int~~ | +| `prefix_` | Length-N substring from the start of the word. Defaults to `N=1`. ~~str~~ | +| `suffix` | Length-N substring from the end of the word. Defaults to `N=3`. ~~int~~ | +| `suffix_` | Length-N substring from the start of the word. Defaults to `N=3`. ~~str~~ | +| `is_alpha` | Does the lexeme consist of alphabetic characters? Equivalent to `lexeme.text.isalpha()`. ~~bool~~ | +| `is_ascii` | Does the lexeme consist of ASCII characters? Equivalent to `[any(ord(c) >= 128 for c in lexeme.text)]`. ~~bool~~ | +| `is_digit` | Does the lexeme consist of digits? Equivalent to `lexeme.text.isdigit()`. ~~bool~~ | +| `is_lower` | Is the lexeme in lowercase? Equivalent to `lexeme.text.islower()`. ~~bool~~ | +| `is_upper` | Is the lexeme in uppercase? Equivalent to `lexeme.text.isupper()`. ~~bool~~ | +| `is_title` | Is the lexeme in titlecase? Equivalent to `lexeme.text.istitle()`. ~~bool~~ | +| `is_punct` | Is the lexeme punctuation? ~~bool~~ | +| `is_left_punct` | Is the lexeme a left punctuation mark, e.g. `(`? ~~bool~~ | +| `is_right_punct` | Is the lexeme a right punctuation mark, e.g. `)`? ~~bool~~ | +| `is_space` | Does the lexeme consist of whitespace characters? Equivalent to `lexeme.text.isspace()`. ~~bool~~ | +| `is_bracket` | Is the lexeme a bracket? ~~bool~~ | +| `is_quote` | Is the lexeme a quotation mark? ~~bool~~ | +| `is_currency` | Is the lexeme a currency symbol? ~~bool~~ | +| `like_url` | Does the lexeme resemble a URL? ~~bool~~ | +| `like_num` | Does the lexeme represent a number? e.g. "10.9", "10", "ten", etc. ~~bool~~ | +| `like_email` | Does the lexeme resemble an email address? ~~bool~~ | +| `is_oov` | Is the lexeme out-of-vocabulary (i.e. does it not have a word vector)? ~~bool~~ | +| `is_stop` | Is the lexeme part of a "stop list"? ~~bool~~ | +| `lang` | Language of the parent vocabulary. ~~int~~ | +| `lang_` | Language of the parent vocabulary. ~~str~~ | +| `prob` | Smoothed log probability estimate of the lexeme's word type (context-independent entry in the vocabulary). ~~float~~ | +| `cluster` | Brown cluster ID. ~~int~~ | +| `sentiment` | A scalar value indicating the positivity or negativity of the lexeme. ~~float~~ | diff --git a/website/docs/api/matcher.md b/website/docs/api/matcher.md index 8cc446c6a..cd7bfa070 100644 --- a/website/docs/api/matcher.md +++ b/website/docs/api/matcher.md @@ -33,7 +33,7 @@ rule-based matching are: | Attribute | Description | | ---------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | | `ORTH` | The exact verbatim text of a token. ~~str~~ | -| `TEXT` 2.1 | The exact verbatim text of a token. ~~str~~ | +| `TEXT` | The exact verbatim text of a token. ~~str~~ | | `NORM` | The normalized form of the token text. ~~str~~ | | `LOWER` | The lowercase form of the token text. ~~str~~ | | `LENGTH` | The length of the token text. ~~int~~ | @@ -48,7 +48,7 @@ rule-based matching are: | `ENT_IOB` | The IOB part of the token's entity tag. ~~str~~ | | `ENT_ID` | The token's entity ID (`ent_id`). ~~str~~ | | `ENT_KB_ID` | The token's entity knowledge base ID (`ent_kb_id`). ~~str~~ | -| `_` 2.1 | Properties in [custom extension attributes](/usage/processing-pipelines#custom-components-attributes). ~~Dict[str, Any]~~ | +| `_` | Properties in [custom extension attributes](/usage/processing-pipelines#custom-components-attributes). ~~Dict[str, Any]~~ | | `OP` | Operator or quantifier to determine how often to match a token pattern. ~~str~~ | Operators and quantifiers define **how often** a token pattern should be @@ -64,7 +64,7 @@ matched: > ``` | OP | Description | -|---------|------------------------------------------------------------------------| +| ------- | ---------------------------------------------------------------------- | | `!` | Negate the pattern, by requiring it to match exactly 0 times. | | `?` | Make the pattern optional, by allowing it to match 0 or 1 times. | | `+` | Require the pattern to match 1 or more times. | @@ -109,10 +109,10 @@ string where an integer is expected) or unexpected property names. > matcher = Matcher(nlp.vocab) > ``` -| Name | Description | -| --------------------------------------- | ----------------------------------------------------------------------------------------------------- | -| `vocab` | The vocabulary object, which must be shared with the documents the matcher will operate on. ~~Vocab~~ | -| `validate` 2.1 | Validate all patterns added to this matcher. ~~bool~~ | +| Name | Description | +| ---------- | ----------------------------------------------------------------------------------------------------- | +| `vocab` | The vocabulary object, which must be shared with the documents the matcher will operate on. ~~Vocab~~ | +| `validate` | Validate all patterns added to this matcher. ~~bool~~ | ## Matcher.\_\_call\_\_ {#call tag="method"} diff --git a/website/docs/api/phrasematcher.md b/website/docs/api/phrasematcher.md index 2cef9ac2a..cd419ae5c 100644 --- a/website/docs/api/phrasematcher.md +++ b/website/docs/api/phrasematcher.md @@ -36,11 +36,11 @@ be shown. > matcher = PhraseMatcher(nlp.vocab) > ``` -| Name | Description | -| --------------------------------------- | ------------------------------------------------------------------------------------------------------ | -| `vocab` | The vocabulary object, which must be shared with the documents the matcher will operate on. ~~Vocab~~ | -| `attr` 2.1 | The token attribute to match on. Defaults to `ORTH`, i.e. the verbatim token text. ~~Union[int, str]~~ | -| `validate` 2.1 | Validate patterns added to the matcher. ~~bool~~ | +| Name | Description | +| ---------- | ------------------------------------------------------------------------------------------------------ | +| `vocab` | The vocabulary object, which must be shared with the documents the matcher will operate on. ~~Vocab~~ | +| `attr` | The token attribute to match on. Defaults to `ORTH`, i.e. the verbatim token text. ~~Union[int, str]~~ | +| `validate` | Validate patterns added to the matcher. ~~bool~~ | ## PhraseMatcher.\_\_call\_\_ {#call tag="method"} diff --git a/website/docs/api/span.md b/website/docs/api/span.md index 89f608994..69bbe8db1 100644 --- a/website/docs/api/span.md +++ b/website/docs/api/span.md @@ -186,14 +186,14 @@ the character indices don't map to a valid span. > assert span.text == "New York" > ``` -| Name | Description | -| ------------------------------------ | ----------------------------------------------------------------------------------------- | -| `start` | The index of the first character of the span. ~~int~~ | -| `end` | The index of the last character after the span. ~~int~~ | -| `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ | -| `kb_id` 2.2 | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ | -| `vector` | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~ | -| **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~ | +| Name | Description | +| ----------- | ----------------------------------------------------------------------------------------- | +| `start` | The index of the first character of the span. ~~int~~ | +| `end` | The index of the last character after the span. ~~int~~ | +| `label` | A label to attach to the span, e.g. for named entities. ~~Union[int, str]~~ | +| `kb_id` | An ID from a knowledge base to capture the meaning of a named entity. ~~Union[int, str]~~ | +| `vector` | A meaning representation of the span. ~~numpy.ndarray[ndim=1, dtype=float32]~~ | +| **RETURNS** | The newly constructed object or `None`. ~~Optional[Span]~~ | ## Span.similarity {#similarity tag="method" model="vectors"} @@ -544,26 +544,26 @@ overlaps with will be returned. ## Attributes {#attributes} -| Name | Description | -| --------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- | -| `doc` | The parent document. ~~Doc~~ | -| `tensor` 2.1.7 | The span's slice of the parent `Doc`'s tensor. ~~numpy.ndarray~~ | -| `start` | The token offset for the start of the span. ~~int~~ | -| `end` | The token offset for the end of the span. ~~int~~ | -| `start_char` | The character offset for the start of the span. ~~int~~ | -| `end_char` | The character offset for the end of the span. ~~int~~ | -| `text` | A string representation of the span text. ~~str~~ | -| `text_with_ws` | The text content of the span with a trailing whitespace character if the last token has one. ~~str~~ | -| `orth` | ID of the verbatim text content. ~~int~~ | -| `orth_` | Verbatim text content (identical to `Span.text`). Exists mostly for consistency with the other attributes. ~~str~~ | -| `label` | The hash value of the span's label. ~~int~~ | -| `label_` | The span's label. ~~str~~ | -| `lemma_` | The span's lemma. Equivalent to `"".join(token.text_with_ws for token in span)`. ~~str~~ | -| `kb_id` | The hash value of the knowledge base ID referred to by the span. ~~int~~ | -| `kb_id_` | The knowledge base ID referred to by the span. ~~str~~ | -| `ent_id` | The hash value of the named entity the root token is an instance of. ~~int~~ | -| `ent_id_` | The string ID of the named entity the root token is an instance of. ~~str~~ | -| `id` | The hash value of the span's ID. ~~int~~ | -| `id_` | The span's ID. ~~str~~ | -| `sentiment` | A scalar value indicating the positivity or negativity of the span. ~~float~~ | -| `_` | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~ | +| Name | Description | +| -------------- | ----------------------------------------------------------------------------------------------------------------------------- | +| `doc` | The parent document. ~~Doc~~ | +| `tensor` | The span's slice of the parent `Doc`'s tensor. ~~numpy.ndarray~~ | +| `start` | The token offset for the start of the span. ~~int~~ | +| `end` | The token offset for the end of the span. ~~int~~ | +| `start_char` | The character offset for the start of the span. ~~int~~ | +| `end_char` | The character offset for the end of the span. ~~int~~ | +| `text` | A string representation of the span text. ~~str~~ | +| `text_with_ws` | The text content of the span with a trailing whitespace character if the last token has one. ~~str~~ | +| `orth` | ID of the verbatim text content. ~~int~~ | +| `orth_` | Verbatim text content (identical to `Span.text`). Exists mostly for consistency with the other attributes. ~~str~~ | +| `label` | The hash value of the span's label. ~~int~~ | +| `label_` | The span's label. ~~str~~ | +| `lemma_` | The span's lemma. Equivalent to `"".join(token.text_with_ws for token in span)`. ~~str~~ | +| `kb_id` | The hash value of the knowledge base ID referred to by the span. ~~int~~ | +| `kb_id_` | The knowledge base ID referred to by the span. ~~str~~ | +| `ent_id` | The hash value of the named entity the root token is an instance of. ~~int~~ | +| `ent_id_` | The string ID of the named entity the root token is an instance of. ~~str~~ | +| `id` | The hash value of the span's ID. ~~int~~ | +| `id_` | The span's ID. ~~str~~ | +| `sentiment` | A scalar value indicating the positivity or negativity of the span. ~~float~~ | +| `_` | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~ | diff --git a/website/docs/api/token.md b/website/docs/api/token.md index d43cd3ff1..89bd77447 100644 --- a/website/docs/api/token.md +++ b/website/docs/api/token.md @@ -403,75 +403,75 @@ The L2 norm of the token's vector representation. ## Attributes {#attributes} -| Name | Description | -| -------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `doc` | The parent document. ~~Doc~~ | -| `lex` 3 | The underlying lexeme. ~~Lexeme~~ | -| `sent` 2.0.12 | The sentence span that this token is a part of. ~~Span~~ | -| `text` | Verbatim text content. ~~str~~ | -| `text_with_ws` | Text content, with trailing space character if present. ~~str~~ | -| `whitespace_` | Trailing space character if present. ~~str~~ | -| `orth` | ID of the verbatim text content. ~~int~~ | -| `orth_` | Verbatim text content (identical to `Token.text`). Exists mostly for consistency with the other attributes. ~~str~~ | -| `vocab` | The vocab object of the parent `Doc`. ~~vocab~~ | -| `tensor` 2.1.7 | The token's slice of the parent `Doc`'s tensor. ~~numpy.ndarray~~ | -| `head` | The syntactic parent, or "governor", of this token. ~~Token~~ | -| `left_edge` | The leftmost token of this token's syntactic descendants. ~~Token~~ | -| `right_edge` | The rightmost token of this token's syntactic descendants. ~~Token~~ | -| `i` | The index of the token within the parent document. ~~int~~ | -| `ent_type` | Named entity type. ~~int~~ | -| `ent_type_` | Named entity type. ~~str~~ | -| `ent_iob` | IOB code of named entity tag. `3` means the token begins an entity, `2` means it is outside an entity, `1` means it is inside an entity, and `0` means no entity tag is set. ~~int~~ | -| `ent_iob_` | IOB code of named entity tag. "B" means the token begins an entity, "I" means it is inside an entity, "O" means it is outside an entity, and "" means no entity tag is set. ~~str~~ | -| `ent_kb_id` 2.2 | Knowledge base ID that refers to the named entity this token is a part of, if any. ~~int~~ | -| `ent_kb_id_` 2.2 | Knowledge base ID that refers to the named entity this token is a part of, if any. ~~str~~ | -| `ent_id` | ID of the entity the token is an instance of, if any. Currently not used, but potentially for coreference resolution. ~~int~~ | -| `ent_id_` | ID of the entity the token is an instance of, if any. Currently not used, but potentially for coreference resolution. ~~str~~ | -| `lemma` | Base form of the token, with no inflectional suffixes. ~~int~~ | -| `lemma_` | Base form of the token, with no inflectional suffixes. ~~str~~ | -| `norm` | The token's norm, i.e. a normalized form of the token text. Can be set in the language's [tokenizer exceptions](/usage/linguistic-features#language-data). ~~int~~ | -| `norm_` | The token's norm, i.e. a normalized form of the token text. Can be set in the language's [tokenizer exceptions](/usage/linguistic-features#language-data). ~~str~~ | -| `lower` | Lowercase form of the token. ~~int~~ | -| `lower_` | Lowercase form of the token text. Equivalent to `Token.text.lower()`. ~~str~~ | -| `shape` | Transform of the token's string to show orthographic features. Alphabetic characters are replaced by `x` or `X`, and numeric characters are replaced by `d`, and sequences of the same character are truncated after length 4. For example,`"Xxxx"`or`"dd"`. ~~int~~ | -| `shape_` | Transform of the token's string to show orthographic features. Alphabetic characters are replaced by `x` or `X`, and numeric characters are replaced by `d`, and sequences of the same character are truncated after length 4. For example,`"Xxxx"`or`"dd"`. ~~str~~ | -| `prefix` | Hash value of a length-N substring from the start of the token. Defaults to `N=1`. ~~int~~ | -| `prefix_` | A length-N substring from the start of the token. Defaults to `N=1`. ~~str~~ | -| `suffix` | Hash value of a length-N substring from the end of the token. Defaults to `N=3`. ~~int~~ | -| `suffix_` | Length-N substring from the end of the token. Defaults to `N=3`. ~~str~~ | -| `is_alpha` | Does the token consist of alphabetic characters? Equivalent to `token.text.isalpha()`. ~~bool~~ | -| `is_ascii` | Does the token consist of ASCII characters? Equivalent to `all(ord(c) < 128 for c in token.text)`. ~~bool~~ | -| `is_digit` | Does the token consist of digits? Equivalent to `token.text.isdigit()`. ~~bool~~ | -| `is_lower` | Is the token in lowercase? Equivalent to `token.text.islower()`. ~~bool~~ | -| `is_upper` | Is the token in uppercase? Equivalent to `token.text.isupper()`. ~~bool~~ | -| `is_title` | Is the token in titlecase? Equivalent to `token.text.istitle()`. ~~bool~~ | -| `is_punct` | Is the token punctuation? ~~bool~~ | -| `is_left_punct` | Is the token a left punctuation mark, e.g. `"("` ? ~~bool~~ | -| `is_right_punct` | Is the token a right punctuation mark, e.g. `")"` ? ~~bool~~ | -| `is_sent_start` | Does the token start a sentence? ~~bool~~ or `None` if unknown. Defaults to `True` for the first token in the `Doc`. | -| `is_sent_end` | Does the token end a sentence? ~~bool~~ or `None` if unknown. | -| `is_space` | Does the token consist of whitespace characters? Equivalent to `token.text.isspace()`. ~~bool~~ | -| `is_bracket` | Is the token a bracket? ~~bool~~ | -| `is_quote` | Is the token a quotation mark? ~~bool~~ | -| `is_currency` 2.0.8 | Is the token a currency symbol? ~~bool~~ | -| `like_url` | Does the token resemble a URL? ~~bool~~ | -| `like_num` | Does the token represent a number? e.g. "10.9", "10", "ten", etc. ~~bool~~ | -| `like_email` | Does the token resemble an email address? ~~bool~~ | -| `is_oov` | Is the token out-of-vocabulary (i.e. does it not have a word vector)? ~~bool~~ | -| `is_stop` | Is the token part of a "stop list"? ~~bool~~ | -| `pos` | Coarse-grained part-of-speech from the [Universal POS tag set](https://universaldependencies.org/u/pos/). ~~int~~ | -| `pos_` | Coarse-grained part-of-speech from the [Universal POS tag set](https://universaldependencies.org/u/pos/). ~~str~~ | -| `tag` | Fine-grained part-of-speech. ~~int~~ | -| `tag_` | Fine-grained part-of-speech. ~~str~~ | -| `morph` 3 | Morphological analysis. ~~MorphAnalysis~~ | -| `dep` | Syntactic dependency relation. ~~int~~ | -| `dep_` | Syntactic dependency relation. ~~str~~ | -| `lang` | Language of the parent document's vocabulary. ~~int~~ | -| `lang_` | Language of the parent document's vocabulary. ~~str~~ | -| `prob` | Smoothed log probability estimate of token's word type (context-independent entry in the vocabulary). ~~float~~ | -| `idx` | The character offset of the token within the parent document. ~~int~~ | -| `sentiment` | A scalar value indicating the positivity or negativity of the token. ~~float~~ | -| `lex_id` | Sequential ID of the token's lexical type, used to index into tables, e.g. for word vectors. ~~int~~ | -| `rank` | Sequential ID of the token's lexical type, used to index into tables, e.g. for word vectors. ~~int~~ | -| `cluster` | Brown cluster ID. ~~int~~ | -| `_` | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~ | +| Name | Description | +| ---------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `doc` | The parent document. ~~Doc~~ | +| `lex` 3 | The underlying lexeme. ~~Lexeme~~ | +| `sent` | The sentence span that this token is a part of. ~~Span~~ | +| `text` | Verbatim text content. ~~str~~ | +| `text_with_ws` | Text content, with trailing space character if present. ~~str~~ | +| `whitespace_` | Trailing space character if present. ~~str~~ | +| `orth` | ID of the verbatim text content. ~~int~~ | +| `orth_` | Verbatim text content (identical to `Token.text`). Exists mostly for consistency with the other attributes. ~~str~~ | +| `vocab` | The vocab object of the parent `Doc`. ~~vocab~~ | +| `tensor` | The token's slice of the parent `Doc`'s tensor. ~~numpy.ndarray~~ | +| `head` | The syntactic parent, or "governor", of this token. ~~Token~~ | +| `left_edge` | The leftmost token of this token's syntactic descendants. ~~Token~~ | +| `right_edge` | The rightmost token of this token's syntactic descendants. ~~Token~~ | +| `i` | The index of the token within the parent document. ~~int~~ | +| `ent_type` | Named entity type. ~~int~~ | +| `ent_type_` | Named entity type. ~~str~~ | +| `ent_iob` | IOB code of named entity tag. `3` means the token begins an entity, `2` means it is outside an entity, `1` means it is inside an entity, and `0` means no entity tag is set. ~~int~~ | +| `ent_iob_` | IOB code of named entity tag. "B" means the token begins an entity, "I" means it is inside an entity, "O" means it is outside an entity, and "" means no entity tag is set. ~~str~~ | +| `ent_kb_id` | Knowledge base ID that refers to the named entity this token is a part of, if any. ~~int~~ | +| `ent_kb_id_` | Knowledge base ID that refers to the named entity this token is a part of, if any. ~~str~~ | +| `ent_id` | ID of the entity the token is an instance of, if any. Currently not used, but potentially for coreference resolution. ~~int~~ | +| `ent_id_` | ID of the entity the token is an instance of, if any. Currently not used, but potentially for coreference resolution. ~~str~~ | +| `lemma` | Base form of the token, with no inflectional suffixes. ~~int~~ | +| `lemma_` | Base form of the token, with no inflectional suffixes. ~~str~~ | +| `norm` | The token's norm, i.e. a normalized form of the token text. Can be set in the language's [tokenizer exceptions](/usage/linguistic-features#language-data). ~~int~~ | +| `norm_` | The token's norm, i.e. a normalized form of the token text. Can be set in the language's [tokenizer exceptions](/usage/linguistic-features#language-data). ~~str~~ | +| `lower` | Lowercase form of the token. ~~int~~ | +| `lower_` | Lowercase form of the token text. Equivalent to `Token.text.lower()`. ~~str~~ | +| `shape` | Transform of the token's string to show orthographic features. Alphabetic characters are replaced by `x` or `X`, and numeric characters are replaced by `d`, and sequences of the same character are truncated after length 4. For example,`"Xxxx"`or`"dd"`. ~~int~~ | +| `shape_` | Transform of the token's string to show orthographic features. Alphabetic characters are replaced by `x` or `X`, and numeric characters are replaced by `d`, and sequences of the same character are truncated after length 4. For example,`"Xxxx"`or`"dd"`. ~~str~~ | +| `prefix` | Hash value of a length-N substring from the start of the token. Defaults to `N=1`. ~~int~~ | +| `prefix_` | A length-N substring from the start of the token. Defaults to `N=1`. ~~str~~ | +| `suffix` | Hash value of a length-N substring from the end of the token. Defaults to `N=3`. ~~int~~ | +| `suffix_` | Length-N substring from the end of the token. Defaults to `N=3`. ~~str~~ | +| `is_alpha` | Does the token consist of alphabetic characters? Equivalent to `token.text.isalpha()`. ~~bool~~ | +| `is_ascii` | Does the token consist of ASCII characters? Equivalent to `all(ord(c) < 128 for c in token.text)`. ~~bool~~ | +| `is_digit` | Does the token consist of digits? Equivalent to `token.text.isdigit()`. ~~bool~~ | +| `is_lower` | Is the token in lowercase? Equivalent to `token.text.islower()`. ~~bool~~ | +| `is_upper` | Is the token in uppercase? Equivalent to `token.text.isupper()`. ~~bool~~ | +| `is_title` | Is the token in titlecase? Equivalent to `token.text.istitle()`. ~~bool~~ | +| `is_punct` | Is the token punctuation? ~~bool~~ | +| `is_left_punct` | Is the token a left punctuation mark, e.g. `"("` ? ~~bool~~ | +| `is_right_punct` | Is the token a right punctuation mark, e.g. `")"` ? ~~bool~~ | +| `is_sent_start` | Does the token start a sentence? ~~bool~~ or `None` if unknown. Defaults to `True` for the first token in the `Doc`. | +| `is_sent_end` | Does the token end a sentence? ~~bool~~ or `None` if unknown. | +| `is_space` | Does the token consist of whitespace characters? Equivalent to `token.text.isspace()`. ~~bool~~ | +| `is_bracket` | Is the token a bracket? ~~bool~~ | +| `is_quote` | Is the token a quotation mark? ~~bool~~ | +| `is_currency` | Is the token a currency symbol? ~~bool~~ | +| `like_url` | Does the token resemble a URL? ~~bool~~ | +| `like_num` | Does the token represent a number? e.g. "10.9", "10", "ten", etc. ~~bool~~ | +| `like_email` | Does the token resemble an email address? ~~bool~~ | +| `is_oov` | Is the token out-of-vocabulary (i.e. does it not have a word vector)? ~~bool~~ | +| `is_stop` | Is the token part of a "stop list"? ~~bool~~ | +| `pos` | Coarse-grained part-of-speech from the [Universal POS tag set](https://universaldependencies.org/u/pos/). ~~int~~ | +| `pos_` | Coarse-grained part-of-speech from the [Universal POS tag set](https://universaldependencies.org/u/pos/). ~~str~~ | +| `tag` | Fine-grained part-of-speech. ~~int~~ | +| `tag_` | Fine-grained part-of-speech. ~~str~~ | +| `morph` 3 | Morphological analysis. ~~MorphAnalysis~~ | +| `dep` | Syntactic dependency relation. ~~int~~ | +| `dep_` | Syntactic dependency relation. ~~str~~ | +| `lang` | Language of the parent document's vocabulary. ~~int~~ | +| `lang_` | Language of the parent document's vocabulary. ~~str~~ | +| `prob` | Smoothed log probability estimate of token's word type (context-independent entry in the vocabulary). ~~float~~ | +| `idx` | The character offset of the token within the parent document. ~~int~~ | +| `sentiment` | A scalar value indicating the positivity or negativity of the token. ~~float~~ | +| `lex_id` | Sequential ID of the token's lexical type, used to index into tables, e.g. for word vectors. ~~int~~ | +| `rank` | Sequential ID of the token's lexical type, used to index into tables, e.g. for word vectors. ~~int~~ | +| `cluster` | Brown cluster ID. ~~int~~ | +| `_` | User space for adding custom [attribute extensions](/usage/processing-pipelines#custom-components-attributes). ~~Underscore~~ | diff --git a/website/docs/api/top-level.md b/website/docs/api/top-level.md index bc53fc868..211affa4a 100644 --- a/website/docs/api/top-level.md +++ b/website/docs/api/top-level.md @@ -45,16 +45,16 @@ specified separately using the new `exclude` keyword argument. > nlp = spacy.load("en_core_web_sm", exclude=["parser", "tagger"]) > ``` -| Name | Description | -| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| `name` | Pipeline to load, i.e. package name or path. ~~Union[str, Path]~~ | -| _keyword-only_ | | -| `vocab` | Optional shared vocab to pass in on initialization. If `True` (default), a new `Vocab` object will be created. ~~Union[Vocab, bool]~~ | -| `disable` | Name(s) of pipeline component(s) to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [nlp.enable_pipe](/api/language#enable_pipe). ~~Union[str, Iterable[str]]~~ | -| `enable` 3.4 | Name(s) of pipeline component(s) to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled. ~~Union[str, Iterable[str]]~~ | -| `exclude` 3 | Name(s) of pipeline component(s) to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~Union[str, Iterable[str]]~~ | -| `config` 3 | Optional config overrides, either as nested dict or dict keyed by section value in dot notation, e.g. `"components.name.value"`. ~~Union[Dict[str, Any], Config]~~ | -| **RETURNS** | A `Language` object with the loaded pipeline. ~~Language~~ | +| Name | Description | +| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `name` | Pipeline to load, i.e. package name or path. ~~Union[str, Path]~~ | +| _keyword-only_ | | +| `vocab` | Optional shared vocab to pass in on initialization. If `True` (default), a new `Vocab` object will be created. ~~Union[Vocab, bool]~~ | +| `disable` | Name(s) of pipeline component(s) to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [nlp.enable_pipe](/api/language#enable_pipe). Is merged with the config entry `nlp.disabled`. ~~Union[str, Iterable[str]]~~ | +| `enable` 3.4 | Name(s) of pipeline component(s) to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled. ~~Union[str, Iterable[str]]~~ | +| `exclude` 3 | Name(s) of pipeline component(s) to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~Union[str, Iterable[str]]~~ | +| `config` 3 | Optional config overrides, either as nested dict or dict keyed by section value in dot notation, e.g. `"components.name.value"`. ~~Union[Dict[str, Any], Config]~~ | +| **RETURNS** | A `Language` object with the loaded pipeline. ~~Language~~ | Essentially, `spacy.load()` is a convenience wrapper that reads the pipeline's [`config.cfg`](/api/data-formats#config), uses the language and pipeline @@ -354,22 +354,22 @@ If a setting is not present in the options, the default value will be used. > displacy.serve(doc, style="dep", options=options) > ``` -| Name | Description | -| ------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------- | -| `fine_grained` | Use fine-grained part-of-speech tags (`Token.tag_`) instead of coarse-grained tags (`Token.pos_`). Defaults to `False`. ~~bool~~ | -| `add_lemma` 2.2.4 | Print the lemmas in a separate row below the token texts. Defaults to `False`. ~~bool~~ | -| `collapse_punct` | Attach punctuation to tokens. Can make the parse more readable, as it prevents long arcs to attach punctuation. Defaults to `True`. ~~bool~~ | -| `collapse_phrases` | Merge noun phrases into one token. Defaults to `False`. ~~bool~~ | -| `compact` | "Compact mode" with square arrows that takes up less space. Defaults to `False`. ~~bool~~ | -| `color` | Text color (HEX, RGB or color names). Defaults to `"#000000"`. ~~str~~ | -| `bg` | Background color (HEX, RGB or color names). Defaults to `"#ffffff"`. ~~str~~ | -| `font` | Font name or font family for all text. Defaults to `"Arial"`. ~~str~~ | -| `offset_x` | Spacing on left side of the SVG in px. Defaults to `50`. ~~int~~ | -| `arrow_stroke` | Width of arrow path in px. Defaults to `2`. ~~int~~ | -| `arrow_width` | Width of arrow head in px. Defaults to `10` in regular mode and `8` in compact mode. ~~int~~ | -| `arrow_spacing` | Spacing between arrows in px to avoid overlaps. Defaults to `20` in regular mode and `12` in compact mode. ~~int~~ | -| `word_spacing` | Vertical spacing between words and arcs in px. Defaults to `45`. ~~int~~ | -| `distance` | Distance between words in px. Defaults to `175` in regular mode and `150` in compact mode. ~~int~~ | +| Name | Description | +| ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------- | +| `fine_grained` | Use fine-grained part-of-speech tags (`Token.tag_`) instead of coarse-grained tags (`Token.pos_`). Defaults to `False`. ~~bool~~ | +| `add_lemma` | Print the lemmas in a separate row below the token texts. Defaults to `False`. ~~bool~~ | +| `collapse_punct` | Attach punctuation to tokens. Can make the parse more readable, as it prevents long arcs to attach punctuation. Defaults to `True`. ~~bool~~ | +| `collapse_phrases` | Merge noun phrases into one token. Defaults to `False`. ~~bool~~ | +| `compact` | "Compact mode" with square arrows that takes up less space. Defaults to `False`. ~~bool~~ | +| `color` | Text color (HEX, RGB or color names). Defaults to `"#000000"`. ~~str~~ | +| `bg` | Background color (HEX, RGB or color names). Defaults to `"#ffffff"`. ~~str~~ | +| `font` | Font name or font family for all text. Defaults to `"Arial"`. ~~str~~ | +| `offset_x` | Spacing on left side of the SVG in px. Defaults to `50`. ~~int~~ | +| `arrow_stroke` | Width of arrow path in px. Defaults to `2`. ~~int~~ | +| `arrow_width` | Width of arrow head in px. Defaults to `10` in regular mode and `8` in compact mode. ~~int~~ | +| `arrow_spacing` | Spacing between arrows in px to avoid overlaps. Defaults to `20` in regular mode and `12` in compact mode. ~~int~~ | +| `word_spacing` | Vertical spacing between words and arcs in px. Defaults to `45`. ~~int~~ | +| `distance` | Distance between words in px. Defaults to `175` in regular mode and `150` in compact mode. ~~int~~ | #### Named Entity Visualizer options {#displacy_options-ent} @@ -385,7 +385,7 @@ If a setting is not present in the options, the default value will be used. | ------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `ents` | Entity types to highlight or `None` for all types (default). ~~Optional[List[str]]~~ | | `colors` | Color overrides. Entity types should be mapped to color names or values. ~~Dict[str, str]~~ | -| `template` 2.2 | Optional template to overwrite the HTML used to render entity spans. Should be a format string and can use `{bg}`, `{text}` and `{label}`. See [`templates.py`](%%GITHUB_SPACY/spacy/displacy/templates.py) for examples. ~~Optional[str]~~ | +| `template` | Optional template to overwrite the HTML used to render entity spans. Should be a format string and can use `{bg}`, `{text}` and `{label}`. See [`templates.py`](%%GITHUB_SPACY/spacy/displacy/templates.py) for examples. ~~Optional[str]~~ | | `kb_url_template` 3.2.1 | Optional template to construct the KB url for the entity to link to. Expects a python f-string format with single field to fill in. ~~Optional[str]~~ | #### Span Visualizer options {#displacy_options-span} diff --git a/website/docs/api/vocab.md b/website/docs/api/vocab.md index 2e4a206ec..afbd1301d 100644 --- a/website/docs/api/vocab.md +++ b/website/docs/api/vocab.md @@ -21,15 +21,15 @@ Create the vocabulary. > vocab = Vocab(strings=["hello", "world"]) > ``` -| Name | Description | -| ------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `lex_attr_getters` | A dictionary mapping attribute IDs to functions to compute them. Defaults to `None`. ~~Optional[Dict[str, Callable[[str], Any]]]~~ | -| `strings` | A [`StringStore`](/api/stringstore) that maps strings to hash values, and vice versa, or a list of strings. ~~Union[List[str], StringStore]~~ | -| `lookups` | A [`Lookups`](/api/lookups) that stores the `lexeme_norm` and other large lookup tables. Defaults to `None`. ~~Optional[Lookups]~~ | -| `oov_prob` | The default OOV probability. Defaults to `-20.0`. ~~float~~ | -| `vectors_name` 2.2 | A name to identify the vectors table. ~~str~~ | -| `writing_system` | A dictionary describing the language's writing system. Typically provided by [`Language.Defaults`](/api/language#defaults). ~~Dict[str, Any]~~ | -| `get_noun_chunks` | A function that yields base noun phrases used for [`Doc.noun_chunks`](/api/doc#noun_chunks). ~~Optional[Callable[[Union[Doc, Span], Iterator[Tuple[int, int, int]]]]]~~ | +| Name | Description | +| ------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `lex_attr_getters` | A dictionary mapping attribute IDs to functions to compute them. Defaults to `None`. ~~Optional[Dict[str, Callable[[str], Any]]]~~ | +| `strings` | A [`StringStore`](/api/stringstore) that maps strings to hash values, and vice versa, or a list of strings. ~~Union[List[str], StringStore]~~ | +| `lookups` | A [`Lookups`](/api/lookups) that stores the `lexeme_norm` and other large lookup tables. Defaults to `None`. ~~Optional[Lookups]~~ | +| `oov_prob` | The default OOV probability. Defaults to `-20.0`. ~~float~~ | +| `vectors_name` | A name to identify the vectors table. ~~str~~ | +| `writing_system` | A dictionary describing the language's writing system. Typically provided by [`Language.Defaults`](/api/language#defaults). ~~Dict[str, Any]~~ | +| `get_noun_chunks` | A function that yields base noun phrases used for [`Doc.noun_chunks`](/api/doc#noun_chunks). ~~Optional[Callable[[Union[Doc, Span], Iterator[Tuple[int, int, int]]]]]~~ | ## Vocab.\_\_len\_\_ {#len tag="method"} @@ -311,10 +311,10 @@ Load state from a binary string. | Name | Description | | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `strings` | A table managing the string-to-int mapping. ~~StringStore~~ | -| `vectors` 2 | A table associating word IDs to word vectors. ~~Vectors~~ | +| `vectors` | A table associating word IDs to word vectors. ~~Vectors~~ | | `vectors_length` | Number of dimensions for each word vector. ~~int~~ | | `lookups` | The available lookup tables in this vocab. ~~Lookups~~ | -| `writing_system` 2.1 | A dict with information about the language's writing system. ~~Dict[str, Any]~~ | +| `writing_system` | A dict with information about the language's writing system. ~~Dict[str, Any]~~ | | `get_noun_chunks` 3.0 | A function that yields base noun phrases used for [`Doc.noun_chunks`](/ap/doc#noun_chunks). ~~Optional[Callable[[Union[Doc, Span], Iterator[Tuple[int, int, int]]]]]~~ | ## Serialization fields {#serialization-fields} diff --git a/website/docs/usage/index.md b/website/docs/usage/index.md index 1f4869606..dff5a16ba 100644 --- a/website/docs/usage/index.md +++ b/website/docs/usage/index.md @@ -75,7 +75,6 @@ spaCy's [`setup.cfg`](%%GITHUB_SPACY/setup.cfg) for details on what's included. | ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `lookups` | Install [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data) for data tables for lemmatization and lexeme normalization. The data is serialized with trained pipelines, so you only need this package if you want to train your own models. | | `transformers` | Install [`spacy-transformers`](https://github.com/explosion/spacy-transformers). The package will be installed automatically when you install a transformer-based pipeline. | -| `ray` | Install [`spacy-ray`](https://github.com/explosion/spacy-ray) to add CLI commands for [parallel training](/usage/training#parallel-training). | | `cuda`, ... | Install spaCy with GPU support provided by [CuPy](https://cupy.chainer.org) for your given CUDA version. See the GPU [installation instructions](#gpu) for details and options. | | `apple` | Install [`thinc-apple-ops`](https://github.com/explosion/thinc-apple-ops) to improve performance on an Apple M1. | | `ja`, `ko`, `th` | Install additional dependencies required for tokenization for the [languages](/usage/models#languages). | diff --git a/website/docs/usage/processing-pipelines.md b/website/docs/usage/processing-pipelines.md index bd28810ae..0b63cdcb8 100644 --- a/website/docs/usage/processing-pipelines.md +++ b/website/docs/usage/processing-pipelines.md @@ -363,7 +363,8 @@ nlp.enable_pipe("tagger") ``` In addition to `disable`, `spacy.load()` also accepts `enable`. If `enable` is -set, all components except for those in `enable` are disabled. +set, all components except for those in `enable` are disabled. If `enable` and +`disable` conflict (i.e. the same component is included in both), an error is raised. ```python # Load the complete pipeline, but disable all components except for tok2vec and tagger diff --git a/website/docs/usage/projects.md b/website/docs/usage/projects.md index 90b612358..34315e4e7 100644 --- a/website/docs/usage/projects.md +++ b/website/docs/usage/projects.md @@ -1014,54 +1014,6 @@ https://github.com/explosion/projects/blob/v3/integrations/fastapi/scripts/main. --- -### Ray {#ray} - -> #### Installation -> -> ```cli -> $ pip install -U %%SPACY_PKG_NAME[ray]%%SPACY_PKG_FLAGS -> # Check that the CLI is registered -> $ python -m spacy ray --help -> ``` - -[Ray](https://ray.io/) is a fast and simple framework for building and running -**distributed applications**. You can use Ray for parallel and distributed -training with spaCy via our lightweight -[`spacy-ray`](https://github.com/explosion/spacy-ray) extension package. If the -package is installed in the same environment as spaCy, it will automatically add -[`spacy ray`](/api/cli#ray) commands to your spaCy CLI. See the usage guide on -[parallel training](/usage/training#parallel-training) for more details on how -it works under the hood. - - - -Get started with parallel training using our project template. It trains a -simple model on a Universal Dependencies Treebank and lets you parallelize the -training with Ray. - - - -You can integrate [`spacy ray train`](/api/cli#ray-train) into your -`project.yml` just like the regular training command and pass it the config, and -optional output directory or remote storage URL and config overrides if needed. - - -```yaml -### project.yml -commands: - - name: "ray" - help: "Train a model via parallel training with Ray" - script: - - "python -m spacy ray train configs/config.cfg -o training/ --paths.train corpus/train.spacy --paths.dev corpus/dev.spacy" - deps: - - "corpus/train.spacy" - - "corpus/dev.spacy" - outputs: - - "training/model-best" -``` - ---- - ### Weights & Biases {#wandb} [Weights & Biases](https://www.wandb.com/) is a popular platform for experiment diff --git a/website/docs/usage/rule-based-matching.md b/website/docs/usage/rule-based-matching.md index 64bbf8e7b..ad8ea27f3 100644 --- a/website/docs/usage/rule-based-matching.md +++ b/website/docs/usage/rule-based-matching.md @@ -162,7 +162,7 @@ rule-based matching are: | Attribute | Description | | ---------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `ORTH` | The exact verbatim text of a token. ~~str~~ | -| `TEXT` 2.1 | The exact verbatim text of a token. ~~str~~ | +| `TEXT` | The exact verbatim text of a token. ~~str~~ | | `NORM` | The normalized form of the token text. ~~str~~ | | `LOWER` | The lowercase form of the token text. ~~str~~ | | `LENGTH` | The length of the token text. ~~int~~ | @@ -174,7 +174,7 @@ rule-based matching are: | `SPACY` | Token has a trailing space. ~~bool~~ | | `POS`, `TAG`, `MORPH`, `DEP`, `LEMMA`, `SHAPE` | The token's simple and extended part-of-speech tag, morphological analysis, dependency label, lemma, shape. Note that the values of these attributes are case-sensitive. For a list of available part-of-speech tags and dependency labels, see the [Annotation Specifications](/api/annotation). ~~str~~ | | `ENT_TYPE` | The token's entity label. ~~str~~ | -| `_` 2.1 | Properties in [custom extension attributes](/usage/processing-pipelines#custom-components-attributes). ~~Dict[str, Any]~~ | +| `_` | Properties in [custom extension attributes](/usage/processing-pipelines#custom-components-attributes). ~~Dict[str, Any]~~ | | `OP` | [Operator or quantifier](#quantifiers) to determine how often to match a token pattern. ~~str~~ | @@ -375,7 +375,7 @@ scoped quantifiers – instead, you can build those behaviors with `on_match` callbacks. | OP | Description | -|---------|------------------------------------------------------------------------| +| ------- | ---------------------------------------------------------------------- | | `!` | Negate the pattern, by requiring it to match exactly 0 times. | | `?` | Make the pattern optional, by allowing it to match 0 or 1 times. | | `+` | Require the pattern to match 1 or more times. | diff --git a/website/docs/usage/saving-loading.md b/website/docs/usage/saving-loading.md index 0fd713a49..29870a2e3 100644 --- a/website/docs/usage/saving-loading.md +++ b/website/docs/usage/saving-loading.md @@ -306,12 +306,12 @@ pipeline component factories, language classes and other settings. To make spaCy use your entry points, your package needs to expose them and it needs to be installed in the same environment – that's it. -| Entry point | Description | -| ------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| [`spacy_factories`](#entry-points-components) | Group of entry points for pipeline component factories, keyed by component name. Can be used to expose custom components defined by another package. | -| [`spacy_languages`](#entry-points-languages) | Group of entry points for custom [`Language` subclasses](/usage/linguistic-features#language-data), keyed by language shortcut. | -| `spacy_lookups` 2.2 | Group of entry points for custom [`Lookups`](/api/lookups), including lemmatizer data. Used by spaCy's [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data) package. | -| [`spacy_displacy_colors`](#entry-points-displacy) 2.2 | Group of entry points of custom label colors for the [displaCy visualizer](/usage/visualizers#ent). The key name doesn't matter, but it should point to a dict of labels and color values. Useful for custom models that predict different entity types. | +| Entry point | Description | +| ------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [`spacy_factories`](#entry-points-components) | Group of entry points for pipeline component factories, keyed by component name. Can be used to expose custom components defined by another package. | +| [`spacy_languages`](#entry-points-languages) | Group of entry points for custom [`Language` subclasses](/usage/linguistic-features#language-data), keyed by language shortcut. | +| `spacy_lookups` | Group of entry points for custom [`Lookups`](/api/lookups), including lemmatizer data. Used by spaCy's [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data) package. | +| [`spacy_displacy_colors`](#entry-points-displacy) | Group of entry points of custom label colors for the [displaCy visualizer](/usage/visualizers#ent). The key name doesn't matter, but it should point to a dict of labels and color values. Useful for custom models that predict different entity types. | ### Custom components via entry points {#entry-points-components} diff --git a/website/docs/usage/training.md b/website/docs/usage/training.md index 27a8bbca7..e40a395c4 100644 --- a/website/docs/usage/training.md +++ b/website/docs/usage/training.md @@ -1572,77 +1572,6 @@ token-based annotations like the dependency parse or entity labels, you'll need to take care to adjust the `Example` object so its annotations match and remain valid. -## Parallel & distributed training with Ray {#parallel-training} - -> #### Installation -> -> ```cli -> $ pip install -U %%SPACY_PKG_NAME[ray]%%SPACY_PKG_FLAGS -> # Check that the CLI is registered -> $ python -m spacy ray --help -> ``` - -[Ray](https://ray.io/) is a fast and simple framework for building and running -**distributed applications**. You can use Ray to train spaCy on one or more -remote machines, potentially speeding up your training process. Parallel -training won't always be faster though – it depends on your batch size, models, -and hardware. - - - -To use Ray with spaCy, you need the -[`spacy-ray`](https://github.com/explosion/spacy-ray) package installed. -Installing the package will automatically add the `ray` command to the spaCy -CLI. - - - -The [`spacy ray train`](/api/cli#ray-train) command follows the same API as -[`spacy train`](/api/cli#train), with a few extra options to configure the Ray -setup. You can optionally set the `--address` option to point to your Ray -cluster. If it's not set, Ray will run locally. - -```cli -python -m spacy ray train config.cfg --n-workers 2 -``` - - - -Get started with parallel training using our project template. It trains a -simple model on a Universal Dependencies Treebank and lets you parallelize the -training with Ray. - - - -### How parallel training works {#parallel-training-details} - -Each worker receives a shard of the **data** and builds a copy of the **model -and optimizer** from the [`config.cfg`](#config). It also has a communication -channel to **pass gradients and parameters** to the other workers. Additionally, -each worker is given ownership of a subset of the parameter arrays. Every -parameter array is owned by exactly one worker, and the workers are given a -mapping so they know which worker owns which parameter. - -![Illustration of setup](../images/spacy-ray.svg) - -As training proceeds, every worker will be computing gradients for **all** of -the model parameters. When they compute gradients for parameters they don't own, -they'll **send them to the worker** that does own that parameter, along with a -version identifier so that the owner can decide whether to discard the gradient. -Workers use the gradients they receive and the ones they compute locally to -update the parameters they own, and then broadcast the updated array and a new -version ID to the other workers. - -This training procedure is **asynchronous** and **non-blocking**. Workers always -push their gradient increments and parameter updates, they do not have to pull -them and block on the result, so the transfers can happen in the background, -overlapped with the actual training work. The workers also do not have to stop -and wait for each other ("synchronize") at the start of each batch. This is very -useful for spaCy, because spaCy is often trained on long documents, which means -**batches can vary in size** significantly. Uneven workloads make synchronous -gradient descent inefficient, because if one batch is slow, all of the other -workers are stuck waiting for it to complete before they can continue. - ## Internal training API {#api} diff --git a/website/docs/usage/v3.md b/website/docs/usage/v3.md index 971779ed3..64f93b7c0 100644 --- a/website/docs/usage/v3.md +++ b/website/docs/usage/v3.md @@ -15,18 +15,6 @@ menu: > To help you make the transition from v2.x to v3.0, we've uploaded the old > website to [**v2.spacy.io**](https://v2.spacy.io/docs). - - -Want to make the transition from spaCy v2 to spaCy v3 as smooth as possible for -you and your organization? We're now offering commercial **migration support** -for your spaCy pipelines! We've put a lot of work into making it easy to upgrade -your existing code and training workflows – but custom projects may always need -some custom work, especially when it comes to taking advantage of the new -capabilities. -[**Details & application →**](https://form.typeform.com/to/vMs2zSjM) - - -
diff --git a/website/meta/universe.json b/website/meta/universe.json index d7c99956b..57bf2d3e3 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -1,5 +1,31 @@ { "resources": [ + { + "id": "grecy", + "title": "greCy", + "slogan": "Ancient Greek pipelines for spaCy", + "description": "greCy offers state-of-the-art pipelines for ancient Greek NLP. The repository makes language models available in various sizes, some of them containing floret word vectors and a BERT transformer layer.", + "github": "jmyerston/greCy", + "code_example": [ + "import spacy", + "#After installing the grc_ud_proiel_trf wheel package from the greCy repository", + "", + "nlp = spacy.load('grc_ud_proiel_trf')", + "doc = nlp('δοκῶ μοι περὶ ὧν πυνθάνεσθε οὐκ ἀμελέτητος εἶναι.')", + "", + "for token in doc:", + " print(token.text, token.norm_, token.lemma_, token.pos_, token.tag_)" + ], + "code_language": "python", + "author": "Jacobo Myerston", + "author_links": { + "twitter": "@jcbmyrstn", + "github": "jmyerston", + "website": "https://huggingface.co/spaces/Jacobo/syntax" + }, + "category": ["pipeline", "research"], + "tags": ["ancient Greek"] + }, { "id": "spacy-cleaner", "title": "spacy-cleaner", @@ -435,37 +461,6 @@ }, "category": ["standalone"] }, - { - "id": "spikex", - "title": "SpikeX - SpaCy Pipes for Knowledge Extraction", - "slogan": "Use SpikeX to build knowledge extraction tools with almost-zero effort", - "description": "SpikeX is a collection of pipes ready to be plugged in a spaCy pipeline. It aims to help in building knowledge extraction tools with almost-zero effort.", - "github": "erre-quadro/spikex", - "pip": "spikex", - "code_example": [ - "from spacy import load as spacy_load", - "from spikex.wikigraph import load as wg_load", - "from spikex.pipes import WikiPageX", - "", - "# load a spacy model and get a doc", - "nlp = spacy_load('en_core_web_sm')", - "doc = nlp('An apple a day keeps the doctor away')", - "# load a WikiGraph", - "wg = wg_load('simplewiki_core')", - "# get a WikiPageX and extract all pages", - "wikipagex = WikiPageX(wg)", - "doc = wikipagex(doc)", - "# see all pages extracted from the doc", - "for span in doc._.wiki_spans:", - " print(span._.wiki_pages)" - ], - "category": ["pipeline", "standalone"], - "author": "Erre Quadro", - "author_links": { - "github": "erre-quadro", - "website": "https://www.errequadrosrl.com" - } - }, { "id": "spacy-dbpedia-spotlight", "title": "DBpedia Spotlight for SpaCy", @@ -531,17 +526,6 @@ "tags": ["sentiment", "textblob"], "spacy_version": 3 }, - { - "id": "spacy-ray", - "title": "spacy-ray", - "slogan": "Parallel and distributed training with spaCy and Ray", - "description": "[Ray](https://ray.io/) is a fast and simple framework for building and running **distributed applications**. This very lightweight extension package lets you use Ray for parallel and distributed training with spaCy. If `spacy-ray` is installed in the same environment as spaCy, it will automatically add `spacy ray` commands to your spaCy CLI.", - "github": "explosion/spacy-ray", - "pip": "spacy-ray", - "category": ["training"], - "author": "Explosion / Anyscale", - "thumb": "https://i.imgur.com/7so6ZpS.png" - }, { "id": "spacy-sentence-bert", "title": "spaCy - sentence-transformers",