diff --git a/.github/azure-steps.yml b/.github/azure-steps.yml index cc0247b3a..e8bd0d212 100644 --- a/.github/azure-steps.yml +++ b/.github/azure-steps.yml @@ -1,9 +1,7 @@ parameters: python_version: '' - architecture: '' - prefix: '' - gpu: false - num_build_jobs: 1 + architecture: 'x64' + num_build_jobs: 2 steps: - task: UsePythonVersion@0 @@ -17,16 +15,16 @@ steps: displayName: 'Set variables' - script: | - ${{ parameters.prefix }} python -m pip install -U pip setuptools - ${{ parameters.prefix }} python -m pip install -U -r requirements.txt + python -m pip install -U build pip setuptools + python -m pip install -U -r requirements.txt displayName: "Install dependencies" - script: | - ${{ parameters.prefix }} python setup.py build_ext --inplace -j ${{ parameters.num_build_jobs }} - ${{ parameters.prefix }} python setup.py sdist --formats=gztar - displayName: "Compile and build sdist" + python -m build --sdist + displayName: "Build sdist" - - script: python -m mypy spacy + - script: | + python -m mypy spacy displayName: 'Run mypy' condition: ne(variables['python_version'], '3.6') @@ -35,35 +33,24 @@ steps: contents: "spacy" displayName: "Delete source directory" + - task: DeleteFiles@1 + inputs: + contents: "*.egg-info" + displayName: "Delete egg-info directory" + - script: | - ${{ parameters.prefix }} python -m pip freeze --exclude torch --exclude cupy-cuda110 > installed.txt - ${{ parameters.prefix }} python -m pip uninstall -y -r installed.txt + python -m pip freeze > installed.txt + python -m pip uninstall -y -r installed.txt displayName: "Uninstall all packages" - bash: | - ${{ parameters.prefix }} SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1) - ${{ parameters.prefix }} SPACY_NUM_BUILD_JOBS=2 python -m pip install dist/$SDIST + SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1) + SPACY_NUM_BUILD_JOBS=${{ parameters.num_build_jobs }} python -m pip install dist/$SDIST displayName: "Install from sdist" - script: | - ${{ parameters.prefix }} python -m pip install -U -r requirements.txt - displayName: "Install test requirements" - - - script: | - ${{ parameters.prefix }} python -m pip install -U cupy-cuda110 -f https://github.com/cupy/cupy/releases/v9.0.0 - ${{ parameters.prefix }} python -m pip install "torch==1.7.1+cu110" -f https://download.pytorch.org/whl/torch_stable.html - displayName: "Install GPU requirements" - condition: eq(${{ parameters.gpu }}, true) - - - script: | - ${{ parameters.prefix }} python -m pytest --pyargs spacy -W error - displayName: "Run CPU tests" - condition: eq(${{ parameters.gpu }}, false) - - - script: | - ${{ parameters.prefix }} python -m pytest --pyargs spacy -W error -p spacy.tests.enable_gpu - displayName: "Run GPU tests" - condition: eq(${{ parameters.gpu }}, true) + python -W error -c "import spacy" + displayName: "Test import" - script: | python -m spacy download ca_core_news_sm @@ -72,6 +59,11 @@ steps: displayName: 'Test download CLI' condition: eq(variables['python_version'], '3.8') + - script: | + python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')" + displayName: 'Test no warnings on load (#11713)' + condition: eq(variables['python_version'], '3.8') + - script: | python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json . displayName: 'Test convert CLI' @@ -106,13 +98,22 @@ steps: displayName: 'Test assemble CLI vectors warning' condition: eq(variables['python_version'], '3.8') + - script: | + python -m pip install -U -r requirements.txt + displayName: "Install test requirements" + + - script: | + python -m pytest --pyargs spacy -W error + displayName: "Run CPU tests" + + - script: | + python -m pip install --pre thinc-apple-ops + python -m pytest --pyargs spacy + displayName: "Run CPU tests with thinc-apple-ops" + condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.11')) + - script: | python .github/validate_universe_json.py website/meta/universe.json displayName: 'Test website/meta/universe.json' condition: eq(variables['python_version'], '3.8') - - script: | - ${{ parameters.prefix }} python -m pip install --pre thinc-apple-ops - ${{ parameters.prefix }} python -m pytest --pyargs spacy - displayName: "Run CPU tests with thinc-apple-ops" - condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.10')) diff --git a/.github/workflows/autoblack.yml b/.github/workflows/autoblack.yml index 3ad4cf408..70882c3cc 100644 --- a/.github/workflows/autoblack.yml +++ b/.github/workflows/autoblack.yml @@ -15,7 +15,7 @@ jobs: - uses: actions/checkout@v3 with: ref: ${{ github.head_ref }} - - uses: actions/setup-python@v3 + - uses: actions/setup-python@v4 - run: pip install black - name: Auto-format code if needed run: black spacy diff --git a/.github/workflows/explosionbot.yml b/.github/workflows/explosionbot.yml index d585ecd9c..6b472cd12 100644 --- a/.github/workflows/explosionbot.yml +++ b/.github/workflows/explosionbot.yml @@ -8,14 +8,14 @@ on: jobs: explosion-bot: - runs-on: ubuntu-18.04 + runs-on: ubuntu-latest steps: - name: Dump GitHub context env: GITHUB_CONTEXT: ${{ toJson(github) }} run: echo "$GITHUB_CONTEXT" - - uses: actions/checkout@v1 - - uses: actions/setup-python@v1 + - uses: actions/checkout@v3 + - uses: actions/setup-python@v4 - name: Install and run explosion-bot run: | pip install git+https://${{ secrets.EXPLOSIONBOT_TOKEN }}@github.com/explosion/explosion-bot diff --git a/.github/workflows/slowtests.yml b/.github/workflows/slowtests.yml index 38ceb18c6..f9fd3e817 100644 --- a/.github/workflows/slowtests.yml +++ b/.github/workflows/slowtests.yml @@ -14,7 +14,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Checkout - uses: actions/checkout@v1 + uses: actions/checkout@v3 with: ref: ${{ matrix.branch }} - name: Get commits from past 24 hours @@ -23,9 +23,9 @@ jobs: today=$(date '+%Y-%m-%d %H:%M:%S') yesterday=$(date -d "yesterday" '+%Y-%m-%d %H:%M:%S') if git log --after="$yesterday" --before="$today" | grep commit ; then - echo "::set-output name=run_tests::true" + echo run_tests=true >> $GITHUB_OUTPUT else - echo "::set-output name=run_tests::false" + echo run_tests=false >> $GITHUB_OUTPUT fi - name: Trigger buildkite build diff --git a/.github/workflows/spacy_universe_alert.yml b/.github/workflows/spacy_universe_alert.yml index cbbf14c6e..837aaeb33 100644 --- a/.github/workflows/spacy_universe_alert.yml +++ b/.github/workflows/spacy_universe_alert.yml @@ -17,8 +17,10 @@ jobs: run: | echo "$GITHUB_CONTEXT" - - uses: actions/checkout@v1 - - uses: actions/setup-python@v1 + - 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 eea07cb7a..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-rc.2' + python.version: '3.11' Python311Windows: imageName: 'windows-latest' - python.version: '3.11.0-rc.2' + python.version: '3.11' Python311Mac: imageName: 'macos-latest' - python.version: '3.11.0-rc.2' + python.version: '3.11' maxParallel: 4 pool: vmImage: $(imageName) @@ -101,20 +101,3 @@ jobs: - template: .github/azure-steps.yml parameters: python_version: '$(python.version)' - architecture: 'x64' - -# - job: "TestGPU" -# dependsOn: "Validate" -# strategy: -# matrix: -# Python38LinuxX64_GPU: -# python.version: '3.8' -# pool: -# name: "LinuxX64_GPU" -# steps: -# - template: .github/azure-steps.yml -# parameters: -# python_version: '$(python.version)' -# architecture: 'x64' -# gpu: true -# num_build_jobs: 24 diff --git a/requirements.txt b/requirements.txt index 9d6bbb2c4..dd2eff0c2 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,8 +9,9 @@ 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 +smart-open>=5.2.1,<7.0.0 # Third party dependencies numpy>=1.15.0 requests>=2.13.0,<3.0.0 @@ -30,7 +31,7 @@ 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..330dc8205 100644 --- a/setup.cfg +++ b/setup.cfg @@ -51,8 +51,9 @@ 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 + smart-open>=5.2.1,<7.0.0 tqdm>=4.38.0,<5.0.0 numpy>=1.15.0 requests>=2.13.0,<3.0.0 diff --git a/spacy/cli/__init__.py b/spacy/cli/__init__.py index ce76ef9a9..aab2c8d12 100644 --- a/spacy/cli/__init__.py +++ b/spacy/cli/__init__.py @@ -27,6 +27,7 @@ from .project.dvc import project_update_dvc # noqa: F401 from .project.push import project_push # noqa: F401 from .project.pull import project_pull # noqa: F401 from .project.document import project_document # noqa: F401 +from .find_threshold import find_threshold # noqa: F401 @app.command("link", no_args_is_help=True, deprecated=True, hidden=True) diff --git a/spacy/cli/_util.py b/spacy/cli/_util.py index 897964a88..872f69c88 100644 --- a/spacy/cli/_util.py +++ b/spacy/cli/_util.py @@ -358,7 +358,7 @@ def download_file(src: Union[str, "Pathy"], dest: Path, *, force: bool = False) if dest.exists() and not force: return None src = str(src) - with smart_open.open(src, mode="rb", ignore_ext=True) as input_file: + with smart_open.open(src, mode="rb", compression="disable") as input_file: with dest.open(mode="wb") as output_file: shutil.copyfileobj(input_file, output_file) diff --git a/spacy/cli/find_threshold.py b/spacy/cli/find_threshold.py new file mode 100644 index 000000000..efa664832 --- /dev/null +++ b/spacy/cli/find_threshold.py @@ -0,0 +1,233 @@ +import functools +import operator +from pathlib import Path +import logging +from typing import Optional, Tuple, Any, Dict, List + +import numpy +import wasabi.tables + +from ..pipeline import TextCategorizer, MultiLabel_TextCategorizer +from ..errors import Errors +from ..training import Corpus +from ._util import app, Arg, Opt, import_code, setup_gpu +from .. import util + +_DEFAULTS = { + "n_trials": 11, + "use_gpu": -1, + "gold_preproc": False, +} + + +@app.command( + "find-threshold", + context_settings={"allow_extra_args": False, "ignore_unknown_options": True}, +) +def find_threshold_cli( + # fmt: off + model: str = Arg(..., help="Model name or path"), + data_path: Path = Arg(..., help="Location of binary evaluation data in .spacy format", exists=True), + pipe_name: str = Arg(..., help="Name of pipe to examine thresholds for"), + threshold_key: str = Arg(..., help="Key of threshold attribute in component's configuration"), + scores_key: str = Arg(..., help="Metric to optimize"), + n_trials: int = Opt(_DEFAULTS["n_trials"], "--n_trials", "-n", help="Number of trials to determine optimal thresholds"), + code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"), + use_gpu: int = Opt(_DEFAULTS["use_gpu"], "--gpu-id", "-g", help="GPU ID or -1 for CPU"), + gold_preproc: bool = Opt(_DEFAULTS["gold_preproc"], "--gold-preproc", "-G", help="Use gold preprocessing"), + verbose: bool = Opt(False, "--silent", "-V", "-VV", help="Display more information for debugging purposes"), + # fmt: on +): + """ + Runs prediction trials for a trained model with varying tresholds to maximize + the specified metric. The search space for the threshold is traversed linearly + from 0 to 1 in `n_trials` steps. Results are displayed in a table on `stdout` + (the corresponding API call to `spacy.cli.find_threshold.find_threshold()` + returns all results). + + This is applicable only for components whose predictions are influenced by + thresholds - e.g. `textcat_multilabel` and `spancat`, but not `textcat`. Note + that the full path to the corresponding threshold attribute in the config has to + be provided. + + DOCS: https://spacy.io/api/cli#find-threshold + """ + + util.logger.setLevel(logging.DEBUG if verbose else logging.INFO) + import_code(code_path) + find_threshold( + model=model, + data_path=data_path, + pipe_name=pipe_name, + threshold_key=threshold_key, + scores_key=scores_key, + n_trials=n_trials, + use_gpu=use_gpu, + gold_preproc=gold_preproc, + silent=False, + ) + + +def find_threshold( + model: str, + data_path: Path, + pipe_name: str, + threshold_key: str, + scores_key: str, + *, + n_trials: int = _DEFAULTS["n_trials"], # type: ignore + use_gpu: int = _DEFAULTS["use_gpu"], # type: ignore + gold_preproc: bool = _DEFAULTS["gold_preproc"], # type: ignore + silent: bool = True, +) -> Tuple[float, float, Dict[float, float]]: + """ + Runs prediction trials for models with varying tresholds to maximize the specified metric. + model (Union[str, Path]): Pipeline to evaluate. Can be a package or a path to a data directory. + data_path (Path): Path to file with DocBin with docs to use for threshold search. + pipe_name (str): Name of pipe to examine thresholds for. + threshold_key (str): Key of threshold attribute in component's configuration. + scores_key (str): Name of score to metric to optimize. + n_trials (int): Number of trials to determine optimal thresholds. + use_gpu (int): GPU ID or -1 for CPU. + gold_preproc (bool): Whether to use gold preprocessing. Gold preprocessing helps the annotations align to the + tokenization, and may result in sequences of more consistent length. However, it may reduce runtime accuracy due + to train/test skew. + silent (bool): Whether to print non-error-related output to stdout. + RETURNS (Tuple[float, float, Dict[float, float]]): Best found threshold, the corresponding score, scores for all + evaluated thresholds. + """ + + setup_gpu(use_gpu, silent=silent) + data_path = util.ensure_path(data_path) + if not data_path.exists(): + wasabi.msg.fail("Evaluation data not found", data_path, exits=1) + nlp = util.load_model(model) + + if pipe_name not in nlp.component_names: + raise AttributeError( + Errors.E001.format(name=pipe_name, opts=nlp.component_names) + ) + pipe = nlp.get_pipe(pipe_name) + if not hasattr(pipe, "scorer"): + raise AttributeError(Errors.E1045) + + if type(pipe) == TextCategorizer: + wasabi.msg.warn( + "The `textcat` component doesn't use a threshold as it's not applicable to the concept of " + "exclusive classes. All thresholds will yield the same results." + ) + + if not silent: + wasabi.msg.info( + title=f"Optimizing for {scores_key} for component '{pipe_name}' with {n_trials} " + f"trials." + ) + + # Load evaluation corpus. + corpus = Corpus(data_path, gold_preproc=gold_preproc) + dev_dataset = list(corpus(nlp)) + config_keys = threshold_key.split(".") + + def set_nested_item( + config: Dict[str, Any], keys: List[str], value: float + ) -> Dict[str, Any]: + """Set item in nested dictionary. Adapted from https://stackoverflow.com/a/54138200. + config (Dict[str, Any]): Configuration dictionary. + keys (List[Any]): Path to value to set. + value (float): Value to set. + RETURNS (Dict[str, Any]): Updated dictionary. + """ + functools.reduce(operator.getitem, keys[:-1], config)[keys[-1]] = value + return config + + def filter_config( + config: Dict[str, Any], keys: List[str], full_key: str + ) -> Dict[str, Any]: + """Filters provided config dictionary so that only the specified keys path remains. + config (Dict[str, Any]): Configuration dictionary. + keys (List[Any]): Path to value to set. + full_key (str): Full user-specified key. + RETURNS (Dict[str, Any]): Filtered dictionary. + """ + if keys[0] not in config: + wasabi.msg.fail( + title=f"Failed to look up `{full_key}` in config: sub-key {[keys[0]]} not found.", + text=f"Make sure you specified {[keys[0]]} correctly. The following sub-keys are available instead: " + f"{list(config.keys())}", + exits=1, + ) + return { + keys[0]: filter_config(config[keys[0]], keys[1:], full_key) + if len(keys) > 1 + else config[keys[0]] + } + + # Evaluate with varying threshold values. + scores: Dict[float, float] = {} + config_keys_full = ["components", pipe_name, *config_keys] + table_col_widths = (10, 10) + thresholds = numpy.linspace(0, 1, n_trials) + print(wasabi.tables.row(["Threshold", f"{scores_key}"], widths=table_col_widths)) + for threshold in thresholds: + # Reload pipeline with overrides specifying the new threshold. + nlp = util.load_model( + model, + config=set_nested_item( + filter_config( + nlp.config, config_keys_full, ".".join(config_keys_full) + ).copy(), + config_keys_full, + threshold, + ), + ) + if hasattr(pipe, "cfg"): + setattr( + nlp.get_pipe(pipe_name), + "cfg", + set_nested_item(getattr(pipe, "cfg"), config_keys, threshold), + ) + + eval_scores = nlp.evaluate(dev_dataset) + if scores_key not in eval_scores: + wasabi.msg.fail( + title=f"Failed to look up score `{scores_key}` in evaluation results.", + text=f"Make sure you specified the correct value for `scores_key`. The following scores are " + f"available: {list(eval_scores.keys())}", + exits=1, + ) + scores[threshold] = eval_scores[scores_key] + + if not isinstance(scores[threshold], (float, int)): + wasabi.msg.fail( + f"Returned score for key '{scores_key}' is not numeric. Threshold optimization only works for numeric " + f"scores.", + exits=1, + ) + print( + wasabi.row( + [round(threshold, 3), round(scores[threshold], 3)], + widths=table_col_widths, + ) + ) + + best_threshold = max(scores.keys(), key=(lambda key: scores[key])) + + # If all scores are identical, emit warning. + if len(set(scores.values())) == 1: + wasabi.msg.warn( + title="All scores are identical. Verify that all settings are correct.", + text="" + if ( + not isinstance(pipe, MultiLabel_TextCategorizer) + or scores_key in ("cats_macro_f", "cats_micro_f") + ) + else "Use `cats_macro_f` or `cats_micro_f` when optimizing the threshold for `textcat_multilabel`.", + ) + + else: + if not silent: + print( + f"\nBest threshold: {round(best_threshold, ndigits=4)} with {scores_key} value of {scores[best_threshold]}." + ) + + return best_threshold, scores[best_threshold], scores 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/default_config.cfg b/spacy/default_config.cfg index 86a72926e..694fb732f 100644 --- a/spacy/default_config.cfg +++ b/spacy/default_config.cfg @@ -90,6 +90,8 @@ dev_corpus = "corpora.dev" train_corpus = "corpora.train" # Optional callback before nlp object is saved to disk after training before_to_disk = null +# Optional callback that is invoked at the start of each training step +before_update = null [training.logger] @loggers = "spacy.ConsoleLogger.v1" diff --git a/spacy/displacy/__init__.py b/spacy/displacy/__init__.py index 7bb300afa..bc32001d7 100644 --- a/spacy/displacy/__init__.py +++ b/spacy/displacy/__init__.py @@ -228,12 +228,13 @@ def parse_spans(doc: Doc, options: Dict[str, Any] = {}) -> Dict[str, Any]: "kb_id": span.kb_id_ if span.kb_id_ else "", "kb_url": kb_url_template.format(span.kb_id_) if kb_url_template else "#", } - for span in doc.spans[spans_key] + for span in doc.spans.get(spans_key, []) ] tokens = [token.text for token in doc] if not spans: - warnings.warn(Warnings.W117.format(spans_key=spans_key)) + keys = list(doc.spans.keys()) + warnings.warn(Warnings.W117.format(spans_key=spans_key, keys=keys)) title = doc.user_data.get("title", None) if hasattr(doc, "user_data") else None settings = get_doc_settings(doc) return { diff --git a/spacy/errors.py b/spacy/errors.py index e0628819d..e34614b0f 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -199,7 +199,7 @@ class Warnings(metaclass=ErrorsWithCodes): W117 = ("No spans to visualize found in Doc object with spans_key: '{spans_key}'. If this is " "surprising to you, make sure the Doc was processed using a model " "that supports span categorization, and check the `doc.spans[spans_key]` " - "property manually if necessary.") + "property manually if necessary.\n\nAvailable keys: {keys}") W118 = ("Term '{term}' not found in glossary. It may however be explained in documentation " "for the corpora used to train the language. Please check " "`nlp.meta[\"sources\"]` for any relevant links.") @@ -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 " @@ -952,6 +956,7 @@ class Errors(metaclass=ErrorsWithCodes): "sure it's overwritten on the subclass.") E1046 = ("{cls_name} is an abstract class and cannot be instantiated. If you are looking for spaCy's default " "knowledge base, use `InMemoryLookupKB`.") + E1047 = ("`find_threshold()` only supports components with a `scorer` attribute.") # Deprecated model shortcuts, only used in errors and warnings diff --git a/spacy/lang/ru/lemmatizer.py b/spacy/lang/ru/lemmatizer.py index c37a3a91a..f4a35de38 100644 --- a/spacy/lang/ru/lemmatizer.py +++ b/spacy/lang/ru/lemmatizer.py @@ -28,34 +28,39 @@ class RussianLemmatizer(Lemmatizer): from pymorphy2 import MorphAnalyzer except ImportError: raise ImportError( - "The Russian lemmatizer mode 'pymorphy2' requires the " - "pymorphy2 library. Install it with: pip install pymorphy2" + "The lemmatizer mode 'pymorphy2' requires the " + "pymorphy2 library and dictionaries. Install them with: " + "pip install pymorphy2" + "# for Ukrainian dictionaries:" + "pip install pymorphy2-dicts-uk" ) from None if getattr(self, "_morph", None) is None: - self._morph = MorphAnalyzer() - elif mode == "pymorphy3": + self._morph = MorphAnalyzer(lang="ru") + elif mode in {"pymorphy3", "pymorphy3_lookup"}: try: from pymorphy3 import MorphAnalyzer except ImportError: raise ImportError( - "The Russian lemmatizer mode 'pymorphy3' requires the " - "pymorphy3 library. Install it with: pip install pymorphy3" + "The lemmatizer mode 'pymorphy3' requires the " + "pymorphy3 library and dictionaries. Install them with: " + "pip install pymorphy3" + "# for Ukrainian dictionaries:" + "pip install pymorphy3-dicts-uk" ) from None if getattr(self, "_morph", None) is None: - self._morph = MorphAnalyzer() + self._morph = MorphAnalyzer(lang="ru") super().__init__( vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer ) - def pymorphy2_lemmatize(self, token: Token) -> List[str]: + def _pymorphy_lemmatize(self, token: Token) -> List[str]: string = token.text univ_pos = token.pos_ morphology = token.morph.to_dict() if univ_pos == "PUNCT": return [PUNCT_RULES.get(string, string)] if univ_pos not in ("ADJ", "DET", "NOUN", "NUM", "PRON", "PROPN", "VERB"): - # Skip unchangeable pos - return [string.lower()] + return self._pymorphy_lookup_lemmatize(token) analyses = self._morph.parse(string) filtered_analyses = [] for analysis in analyses: @@ -63,8 +68,10 @@ class RussianLemmatizer(Lemmatizer): # Skip suggested parse variant for unknown word for pymorphy continue analysis_pos, _ = oc2ud(str(analysis.tag)) - if analysis_pos == univ_pos or ( - analysis_pos in ("NOUN", "PROPN") and univ_pos in ("NOUN", "PROPN") + if ( + analysis_pos == univ_pos + or (analysis_pos in ("NOUN", "PROPN") and univ_pos in ("NOUN", "PROPN")) + or ((analysis_pos == "PRON") and (univ_pos == "DET")) ): filtered_analyses.append(analysis) if not len(filtered_analyses): @@ -107,15 +114,27 @@ class RussianLemmatizer(Lemmatizer): dict.fromkeys([analysis.normal_form for analysis in filtered_analyses]) ) - def pymorphy2_lookup_lemmatize(self, token: Token) -> List[str]: + def _pymorphy_lookup_lemmatize(self, token: Token) -> List[str]: string = token.text analyses = self._morph.parse(string) - if len(analyses) == 1: - return [analyses[0].normal_form] + # often multiple forms would derive from the same normal form + # thus check _unique_ normal forms + normal_forms = set([an.normal_form for an in analyses]) + if len(normal_forms) == 1: + return [next(iter(normal_forms))] return [string] + def pymorphy2_lemmatize(self, token: Token) -> List[str]: + return self._pymorphy_lemmatize(token) + + def pymorphy2_lookup_lemmatize(self, token: Token) -> List[str]: + return self._pymorphy_lookup_lemmatize(token) + def pymorphy3_lemmatize(self, token: Token) -> List[str]: - return self.pymorphy2_lemmatize(token) + return self._pymorphy_lemmatize(token) + + def pymorphy3_lookup_lemmatize(self, token: Token) -> List[str]: + return self._pymorphy_lookup_lemmatize(token) def oc2ud(oc_tag: str) -> Tuple[str, Dict[str, str]]: 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/lang/uk/lemmatizer.py b/spacy/lang/uk/lemmatizer.py index 8337e7328..37015cc2a 100644 --- a/spacy/lang/uk/lemmatizer.py +++ b/spacy/lang/uk/lemmatizer.py @@ -29,7 +29,7 @@ class UkrainianLemmatizer(RussianLemmatizer): ) from None if getattr(self, "_morph", None) is None: self._morph = MorphAnalyzer(lang="uk") - elif mode == "pymorphy3": + elif mode in {"pymorphy3", "pymorphy3_lookup"}: try: from pymorphy3 import MorphAnalyzer except ImportError: diff --git a/spacy/language.py b/spacy/language.py index d391f15ab..2789b6690 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( @@ -790,14 +784,6 @@ class Language: factory_name, source, name=name ) else: - if not self.has_factory(factory_name): - err = Errors.E002.format( - name=factory_name, - opts=", ".join(self.factory_names), - method="add_pipe", - lang=util.get_object_name(self), - lang_code=self.lang, - ) pipe_component = self.create_pipe( factory_name, name=name, @@ -1879,31 +1865,22 @@ 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 +2061,12 @@ 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/matcher/matcher.pyx b/spacy/matcher/matcher.pyx index 963c156d9..60a76280f 100644 --- a/spacy/matcher/matcher.pyx +++ b/spacy/matcher/matcher.pyx @@ -1,4 +1,4 @@ -# cython: infer_types=True, cython: profile=True +# cython: infer_types=True, profile=True from typing import List, Iterable from libcpp.vector cimport vector diff --git a/spacy/pipeline/spancat.py b/spacy/pipeline/spancat.py index 956bbb72c..0a84c72fd 100644 --- a/spacy/pipeline/spancat.py +++ b/spacy/pipeline/spancat.py @@ -1,7 +1,7 @@ -from typing import List, Dict, Callable, Tuple, Optional, Iterable, Any, cast +from typing import List, Dict, Callable, Tuple, Optional, Iterable, Any from thinc.api import Config, Model, get_current_ops, set_dropout_rate, Ops from thinc.api import Optimizer -from thinc.types import Ragged, Ints2d, Floats2d, Ints1d +from thinc.types import Ragged, Ints2d, Floats2d import numpy diff --git a/spacy/pipeline/textcat.py b/spacy/pipeline/textcat.py index 59549ad99..9490e3cb1 100644 --- a/spacy/pipeline/textcat.py +++ b/spacy/pipeline/textcat.py @@ -72,7 +72,7 @@ subword_features = true "textcat", assigns=["doc.cats"], default_config={ - "threshold": 0.5, + "threshold": 0.0, "model": DEFAULT_SINGLE_TEXTCAT_MODEL, "scorer": {"@scorers": "spacy.textcat_scorer.v1"}, }, @@ -144,7 +144,8 @@ class TextCategorizer(TrainablePipe): model (thinc.api.Model): The Thinc Model powering the pipeline component. name (str): The component instance name, used to add entries to the losses during training. - threshold (float): Cutoff to consider a prediction "positive". + threshold (float): Unused, not needed for single-label (exclusive + classes) classification. scorer (Optional[Callable]): The scoring method. Defaults to Scorer.score_cats for the attribute "cats". @@ -154,7 +155,11 @@ class TextCategorizer(TrainablePipe): self.model = model self.name = name self._rehearsal_model = None - cfg = {"labels": [], "threshold": threshold, "positive_label": None} + cfg: Dict[str, Any] = { + "labels": [], + "threshold": threshold, + "positive_label": None, + } self.cfg = dict(cfg) self.scorer = scorer @@ -396,5 +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/schemas.py b/spacy/schemas.py index 487dcbacb..1c5c6871e 100644 --- a/spacy/schemas.py +++ b/spacy/schemas.py @@ -335,6 +335,7 @@ class ConfigSchemaTraining(BaseModel): frozen_components: List[str] = Field(..., title="Pipeline components that shouldn't be updated during training") annotating_components: List[str] = Field(..., title="Pipeline components that should set annotations during training") before_to_disk: Optional[Callable[["Language"], "Language"]] = Field(..., title="Optional callback to modify nlp object after training, before it's saved to disk") + before_update: Optional[Callable[["Language", Dict[str, Any]], None]] = Field(..., title="Optional callback that is invoked at the start of each training step") # fmt: on class Config: diff --git a/spacy/scorer.py b/spacy/scorer.py index 8cd755ac4..16fc303a0 100644 --- a/spacy/scorer.py +++ b/spacy/scorer.py @@ -446,7 +446,7 @@ class Scorer: labels (Iterable[str]): The set of possible labels. Defaults to []. multi_label (bool): Whether the attribute allows multiple labels. Defaults to True. When set to False (exclusive labels), missing - gold labels are interpreted as 0.0. + gold labels are interpreted as 0.0 and the threshold is set to 0.0. positive_label (str): The positive label for a binary task with exclusive classes. Defaults to None. threshold (float): Cutoff to consider a prediction "positive". Defaults @@ -471,6 +471,8 @@ class Scorer: """ if threshold is None: threshold = 0.5 if multi_label else 0.0 + if not multi_label: + threshold = 0.0 f_per_type = {label: PRFScore() for label in labels} auc_per_type = {label: ROCAUCScore() for label in labels} labels = set(labels) @@ -505,20 +507,18 @@ class Scorer: # Get the highest-scoring for each. pred_label, pred_score = max(pred_cats.items(), key=lambda it: it[1]) gold_label, gold_score = max(gold_cats.items(), key=lambda it: it[1]) - if pred_label == gold_label and pred_score >= threshold: + if pred_label == gold_label: f_per_type[pred_label].tp += 1 else: f_per_type[gold_label].fn += 1 - if pred_score >= threshold: - f_per_type[pred_label].fp += 1 + f_per_type[pred_label].fp += 1 elif gold_cats: gold_label, gold_score = max(gold_cats, key=lambda it: it[1]) if gold_score > 0: f_per_type[gold_label].fn += 1 elif pred_cats: pred_label, pred_score = max(pred_cats.items(), key=lambda it: it[1]) - if pred_score >= threshold: - f_per_type[pred_label].fp += 1 + f_per_type[pred_label].fp += 1 micro_prf = PRFScore() for label_prf in f_per_type.values(): micro_prf.tp += label_prf.tp diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py index 0fc74243d..3a5c8e451 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -337,17 +337,17 @@ def ru_tokenizer(): return get_lang_class("ru")().tokenizer -@pytest.fixture +@pytest.fixture(scope="session") def ru_lemmatizer(): pytest.importorskip("pymorphy3") return get_lang_class("ru")().add_pipe("lemmatizer") -@pytest.fixture +@pytest.fixture(scope="session") def ru_lookup_lemmatizer(): - pytest.importorskip("pymorphy2") + pytest.importorskip("pymorphy3") return get_lang_class("ru")().add_pipe( - "lemmatizer", config={"mode": "pymorphy2_lookup"} + "lemmatizer", config={"mode": "pymorphy3_lookup"} ) @@ -423,19 +423,19 @@ def uk_tokenizer(): return get_lang_class("uk")().tokenizer -@pytest.fixture +@pytest.fixture(scope="session") def uk_lemmatizer(): pytest.importorskip("pymorphy3") pytest.importorskip("pymorphy3_dicts_uk") return get_lang_class("uk")().add_pipe("lemmatizer") -@pytest.fixture +@pytest.fixture(scope="session") def uk_lookup_lemmatizer(): - pytest.importorskip("pymorphy2") - pytest.importorskip("pymorphy2_dicts_uk") + pytest.importorskip("pymorphy3") + pytest.importorskip("pymorphy3_dicts_uk") return get_lang_class("uk")().add_pipe( - "lemmatizer", config={"mode": "pymorphy2_lookup"} + "lemmatizer", config={"mode": "pymorphy3_lookup"} ) diff --git a/spacy/tests/doc/test_json_doc_conversion.py b/spacy/tests/doc/test_json_doc_conversion.py index 19698cfb2..11a1817e6 100644 --- a/spacy/tests/doc/test_json_doc_conversion.py +++ b/spacy/tests/doc/test_json_doc_conversion.py @@ -370,3 +370,12 @@ def test_json_to_doc_validation_error(doc): doc_json.pop("tokens") with pytest.raises(ValueError): Doc(doc.vocab).from_json(doc_json, validate=True) + + +def test_to_json_underscore_doc_getters(doc): + def get_text_length(doc): + return len(doc.text) + + Doc.set_extension("text_length", getter=get_text_length) + doc_json = doc.to_json(underscore=["text_length"]) + assert doc_json["_"]["text_length"] == get_text_length(doc) diff --git a/spacy/tests/lang/ru/test_lemmatizer.py b/spacy/tests/lang/ru/test_lemmatizer.py index e82fd4f8c..9a5a9ad68 100644 --- a/spacy/tests/lang/ru/test_lemmatizer.py +++ b/spacy/tests/lang/ru/test_lemmatizer.py @@ -81,6 +81,7 @@ def test_ru_lemmatizer_punct(ru_lemmatizer): def test_ru_doc_lookup_lemmatization(ru_lookup_lemmatizer): + assert ru_lookup_lemmatizer.mode == "pymorphy3_lookup" words = ["мама", "мыла", "раму"] pos = ["NOUN", "VERB", "NOUN"] morphs = [ @@ -92,3 +93,17 @@ def test_ru_doc_lookup_lemmatization(ru_lookup_lemmatizer): doc = ru_lookup_lemmatizer(doc) lemmas = [token.lemma_ for token in doc] assert lemmas == ["мама", "мыла", "раму"] + + +@pytest.mark.parametrize( + "word,lemma", + ( + ("бременем", "бремя"), + ("будешь", "быть"), + ("какая-то", "какой-то"), + ), +) +def test_ru_lookup_lemmatizer(ru_lookup_lemmatizer, word, lemma): + assert ru_lookup_lemmatizer.mode == "pymorphy3_lookup" + doc = Doc(ru_lookup_lemmatizer.vocab, words=[word]) + assert ru_lookup_lemmatizer(doc)[0].lemma_ == lemma diff --git a/spacy/tests/lang/uk/test_lemmatizer.py b/spacy/tests/lang/uk/test_lemmatizer.py index 788744aa1..a65bb25e5 100644 --- a/spacy/tests/lang/uk/test_lemmatizer.py +++ b/spacy/tests/lang/uk/test_lemmatizer.py @@ -8,12 +8,20 @@ pytestmark = pytest.mark.filterwarnings("ignore::DeprecationWarning") def test_uk_lemmatizer(uk_lemmatizer): """Check that the default uk lemmatizer runs.""" doc = Doc(uk_lemmatizer.vocab, words=["a", "b", "c"]) + assert uk_lemmatizer.mode == "pymorphy3" uk_lemmatizer(doc) assert [token.lemma for token in doc] -def test_uk_lookup_lemmatizer(uk_lookup_lemmatizer): - """Check that the lookup uk lemmatizer runs.""" - doc = Doc(uk_lookup_lemmatizer.vocab, words=["a", "b", "c"]) - uk_lookup_lemmatizer(doc) - assert [token.lemma for token in doc] +@pytest.mark.parametrize( + "word,lemma", + ( + ("якийсь", "якийсь"), + ("розповідають", "розповідати"), + ("розповіси", "розповісти"), + ), +) +def test_uk_lookup_lemmatizer(uk_lookup_lemmatizer, word, lemma): + assert uk_lookup_lemmatizer.mode == "pymorphy3_lookup" + doc = Doc(uk_lookup_lemmatizer.vocab, words=[word]) + assert uk_lookup_lemmatizer(doc)[0].lemma_ == lemma 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 0bb036a33..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() @@ -823,10 +847,10 @@ def test_textcat_loss(multi_label: bool, expected_loss: float): assert loss == expected_loss -def test_textcat_threshold(): +def test_textcat_multilabel_threshold(): # Ensure the scorer can be called with a different threshold nlp = English() - nlp.add_pipe("textcat") + nlp.add_pipe("textcat_multilabel") train_examples = [] for text, annotations in TRAIN_DATA_SINGLE_LABEL: @@ -849,7 +873,7 @@ def test_textcat_threshold(): ) pos_f = scores["cats_score"] assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 1.0 - assert pos_f > macro_f + assert pos_f >= macro_f def test_textcat_multi_threshold(): 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..525c6d255 100644 --- a/spacy/tests/test_cli.py +++ b/spacy/tests/test_cli.py @@ -1,8 +1,10 @@ import os import math -from random import sample -from typing import Counter +from collections import Counter +from typing import Tuple, List, Dict, Any +import pkg_resources +import numpy import pytest import srsly from click import NoSuchOption @@ -15,6 +17,7 @@ from spacy.cli._util import is_subpath_of, load_project_config from spacy.cli._util import parse_config_overrides, string_to_list from spacy.cli._util import substitute_project_variables from spacy.cli._util import validate_project_commands +from spacy.cli._util import upload_file, download_file from spacy.cli.debug_data import _compile_gold, _get_labels_from_model from spacy.cli.debug_data import _get_labels_from_spancat from spacy.cli.debug_data import _get_distribution, _get_kl_divergence @@ -25,12 +28,14 @@ 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.cli.find_threshold import find_threshold from spacy.lang.en import English from spacy.lang.nl import Dutch from spacy.language import Language from spacy.schemas import ProjectConfigSchema, RecommendationSchema, validate -from spacy.tokens import Doc +from spacy.tokens import Doc, DocBin from spacy.tokens.span import Span from spacy.training import Example, docs_to_json, offsets_to_biluo_tags from spacy.training.converters import conll_ner_to_docs, conllu_to_docs @@ -855,3 +860,173 @@ 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] + + +def test_cli_find_threshold(capsys): + thresholds = numpy.linspace(0, 1, 10) + + def make_examples(nlp: Language) -> List[Example]: + docs: List[Example] = [] + + for t in [ + ( + "I am angry and confused in the Bank of America.", + { + "cats": {"ANGRY": 1.0, "CONFUSED": 1.0, "HAPPY": 0.0}, + "spans": {"sc": [(31, 46, "ORG")]}, + }, + ), + ( + "I am confused but happy in New York.", + { + "cats": {"ANGRY": 0.0, "CONFUSED": 1.0, "HAPPY": 1.0}, + "spans": {"sc": [(27, 35, "GPE")]}, + }, + ), + ]: + doc = nlp.make_doc(t[0]) + docs.append(Example.from_dict(doc, t[1])) + + return docs + + def init_nlp( + components: Tuple[Tuple[str, Dict[str, Any]], ...] = () + ) -> Tuple[Language, List[Example]]: + new_nlp = English() + new_nlp.add_pipe( # type: ignore + factory_name="textcat_multilabel", + name="tc_multi", + config={"threshold": 0.9}, + ) + + # Append additional components to pipeline. + for cfn, comp_config in components: + new_nlp.add_pipe(cfn, config=comp_config) + + new_examples = make_examples(new_nlp) + new_nlp.initialize(get_examples=lambda: new_examples) + for i in range(5): + new_nlp.update(new_examples) + + return new_nlp, new_examples + + with make_tempdir() as docs_dir: + # Check whether find_threshold() identifies lowest threshold above 0 as (first) ideal threshold, as this matches + # the current model behavior with the examples above. This can break once the model behavior changes and serves + # mostly as a smoke test. + nlp, examples = init_nlp() + DocBin(docs=[example.reference for example in examples]).to_disk( + docs_dir / "docs.spacy" + ) + with make_tempdir() as nlp_dir: + nlp.to_disk(nlp_dir) + res = find_threshold( + model=nlp_dir, + data_path=docs_dir / "docs.spacy", + pipe_name="tc_multi", + threshold_key="threshold", + scores_key="cats_macro_f", + silent=True, + ) + assert res[0] != thresholds[0] + assert thresholds[0] < res[0] < thresholds[9] + assert res[1] == 1.0 + assert res[2][1.0] == 0.0 + + # Test with spancat. + nlp, _ = init_nlp((("spancat", {}),)) + with make_tempdir() as nlp_dir: + nlp.to_disk(nlp_dir) + res = find_threshold( + model=nlp_dir, + data_path=docs_dir / "docs.spacy", + pipe_name="spancat", + threshold_key="threshold", + scores_key="spans_sc_f", + silent=True, + ) + assert res[0] != thresholds[0] + assert thresholds[0] < res[0] < thresholds[8] + assert res[1] >= 0.6 + assert res[2][1.0] == 0.0 + + # Having multiple textcat_multilabel components should work, since the name has to be specified. + nlp, _ = init_nlp((("textcat_multilabel", {}),)) + with make_tempdir() as nlp_dir: + nlp.to_disk(nlp_dir) + assert find_threshold( + model=nlp_dir, + data_path=docs_dir / "docs.spacy", + pipe_name="tc_multi", + threshold_key="threshold", + scores_key="cats_macro_f", + silent=True, + ) + + # Specifying the name of an non-existing pipe should fail. + nlp, _ = init_nlp() + with make_tempdir() as nlp_dir: + nlp.to_disk(nlp_dir) + with pytest.raises(AttributeError): + find_threshold( + model=nlp_dir, + data_path=docs_dir / "docs.spacy", + pipe_name="_", + threshold_key="threshold", + scores_key="cats_macro_f", + silent=True, + ) + + +@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")]) + + +def test_upload_download_local_file(): + with make_tempdir() as d1, make_tempdir() as d2: + filename = "f.txt" + content = "content" + local_file = d1 / filename + remote_file = d2 / filename + with local_file.open(mode="w") as file_: + file_.write(content) + upload_file(local_file, remote_file) + local_file.unlink() + download_file(remote_file, local_file) + with local_file.open(mode="r") as file_: + assert file_.read() == content diff --git a/spacy/tests/test_displacy.py b/spacy/tests/test_displacy.py index ccc145b44..f298b38e0 100644 --- a/spacy/tests/test_displacy.py +++ b/spacy/tests/test_displacy.py @@ -203,6 +203,16 @@ def test_displacy_parse_spans_different_spans_key(en_vocab): ] +def test_displacy_parse_empty_spans_key(en_vocab): + """Test that having an unset spans key doesn't raise an error""" + doc = Doc(en_vocab, words=["Welcome", "to", "the", "Bank", "of", "China"]) + doc.spans["custom"] = [Span(doc, 3, 6, "BANK")] + with pytest.warns(UserWarning, match="W117"): + spans = displacy.parse_spans(doc) + + assert isinstance(spans, dict) + + def test_displacy_parse_ents(en_vocab): """Test that named entities on a Doc are converted into displaCy's format.""" doc = Doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"]) diff --git a/spacy/tests/test_scorer.py b/spacy/tests/test_scorer.py index 6e15fa2de..b903f1669 100644 --- a/spacy/tests/test_scorer.py +++ b/spacy/tests/test_scorer.py @@ -474,3 +474,50 @@ def test_prf_score(): assert (a.precision, a.recall, a.fscore) == approx( (c.precision, c.recall, c.fscore) ) + + +def test_score_cats(en_tokenizer): + text = "some text" + gold_doc = en_tokenizer(text) + gold_doc.cats = {"POSITIVE": 1.0, "NEGATIVE": 0.0} + pred_doc = en_tokenizer(text) + pred_doc.cats = {"POSITIVE": 0.75, "NEGATIVE": 0.25} + example = Example(pred_doc, gold_doc) + # threshold is ignored for multi_label=False + scores1 = Scorer.score_cats( + [example], + "cats", + labels=list(gold_doc.cats.keys()), + multi_label=False, + positive_label="POSITIVE", + threshold=0.1, + ) + scores2 = Scorer.score_cats( + [example], + "cats", + labels=list(gold_doc.cats.keys()), + multi_label=False, + positive_label="POSITIVE", + threshold=0.9, + ) + assert scores1["cats_score"] == 1.0 + assert scores2["cats_score"] == 1.0 + assert scores1 == scores2 + # threshold is relevant for multi_label=True + scores = Scorer.score_cats( + [example], + "cats", + labels=list(gold_doc.cats.keys()), + multi_label=True, + threshold=0.9, + ) + assert scores["cats_macro_f"] == 0.0 + # threshold is relevant for multi_label=True + scores = Scorer.score_cats( + [example], + "cats", + labels=list(gold_doc.cats.keys()), + multi_label=True, + threshold=0.1, + ) + assert scores["cats_macro_f"] == 0.5 diff --git a/spacy/tests/training/test_training.py b/spacy/tests/training/test_training.py index 4384a796d..7933ea31f 100644 --- a/spacy/tests/training/test_training.py +++ b/spacy/tests/training/test_training.py @@ -2,6 +2,7 @@ import random import numpy import pytest +import spacy import srsly from spacy.lang.en import English from spacy.tokens import Doc, DocBin @@ -11,9 +12,10 @@ from spacy.training import offsets_to_biluo_tags from spacy.training.alignment_array import AlignmentArray from spacy.training.align import get_alignments from spacy.training.converters import json_to_docs +from spacy.training.loop import train_while_improving from spacy.util import get_words_and_spaces, load_model_from_path, minibatch from spacy.util import load_config_from_str -from thinc.api import compounding +from thinc.api import compounding, Adam from ..util import make_tempdir @@ -1112,3 +1114,39 @@ def test_retokenized_docs(doc): retokenizer.merge(doc1[0:2]) retokenizer.merge(doc1[5:7]) assert example.get_aligned("ORTH", as_string=True) == expected2 + + +def test_training_before_update(doc): + def before_update(nlp, args): + assert args["step"] == 0 + assert args["epoch"] == 1 + + # Raise an error here as the rest of the loop + # will not run to completion due to uninitialized + # models. + raise ValueError("ran_before_update") + + def generate_batch(): + yield 1, [Example(doc, doc)] + + nlp = spacy.blank("en") + nlp.add_pipe("tagger") + optimizer = Adam() + generator = train_while_improving( + nlp, + optimizer, + generate_batch(), + lambda: None, + dropout=0.1, + eval_frequency=100, + accumulate_gradient=10, + patience=10, + max_steps=100, + exclude=[], + annotating_components=[], + before_update=before_update, + ) + + with pytest.raises(ValueError, match="ran_before_update"): + for _ in generator: + pass 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/doc.pyx b/spacy/tokens/doc.pyx index 295f91c28..f2621292c 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -1668,6 +1668,20 @@ cdef class Doc: if underscore: user_keys = set() + # Handle doc attributes with .get to include values from getters + # and not only values stored in user_data, for backwards + # compatibility + for attr in underscore: + if self.has_extension(attr): + if "_" not in data: + data["_"] = {} + value = self._.get(attr) + if not srsly.is_json_serializable(value): + raise ValueError(Errors.E107.format(attr=attr, value=repr(value))) + data["_"][attr] = value + user_keys.add(attr) + # Token and span attributes only include values stored in user_data + # and not values generated by getters if self.user_data: for data_key, value in self.user_data.copy().items(): if type(data_key) == tuple and len(data_key) >= 4 and data_key[0] == "._.": @@ -1678,20 +1692,15 @@ cdef class Doc: user_keys.add(attr) if not srsly.is_json_serializable(value): raise ValueError(Errors.E107.format(attr=attr, value=repr(value))) - # Check if doc attribute - if start is None: - if "_" not in data: - data["_"] = {} - data["_"][attr] = value - # Check if token attribute - elif end is None: + # Token attribute + if start is not None and end is None: if "underscore_token" not in data: data["underscore_token"] = {} if attr not in data["underscore_token"]: data["underscore_token"][attr] = [] data["underscore_token"][attr].append({"start": start, "value": value}) - # Else span attribute - else: + # Span attribute + elif start is not None and end is not None: if "underscore_span" not in data: data["underscore_span"] = {} if attr not in data["underscore_span"]: 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/training/loop.py b/spacy/training/loop.py index 06372cbb0..885257772 100644 --- a/spacy/training/loop.py +++ b/spacy/training/loop.py @@ -59,6 +59,7 @@ def train( batcher = T["batcher"] train_logger = T["logger"] before_to_disk = create_before_to_disk_callback(T["before_to_disk"]) + before_update = T["before_update"] # Helper function to save checkpoints. This is a closure for convenience, # to avoid passing in all the args all the time. @@ -89,6 +90,7 @@ def train( eval_frequency=T["eval_frequency"], exclude=frozen_components, annotating_components=annotating_components, + before_update=before_update, ) clean_output_dir(output_path) stdout.write(msg.info(f"Pipeline: {nlp.pipe_names}") + "\n") @@ -150,6 +152,7 @@ def train_while_improving( max_steps: int, exclude: List[str], annotating_components: List[str], + before_update: Optional[Callable[["Language", Dict[str, Any]], None]], ): """Train until an evaluation stops improving. Works as a generator, with each iteration yielding a tuple `(batch, info, is_best_checkpoint)`, @@ -198,6 +201,9 @@ def train_while_improving( words_seen = 0 start_time = timer() for step, (epoch, batch) in enumerate(train_data): + if before_update: + before_update_args = {"step": step, "epoch": epoch} + before_update(nlp, before_update_args) dropout = next(dropouts) # type: ignore for subbatch in subdivide_batch(batch, accumulate_gradient): nlp.update( diff --git a/spacy/util.py b/spacy/util.py index 3034808ba..76a1e0bfa 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -443,9 +443,9 @@ def load_model_from_package( name: str, *, vocab: Union["Vocab", bool] = True, - disable: Union[str, Iterable[str]] = SimpleFrozenList(), - enable: Union[str, Iterable[str]] = SimpleFrozenList(), - exclude: Union[str, Iterable[str]] = SimpleFrozenList(), + disable: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES, + enable: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES, + exclude: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES, config: Union[Dict[str, Any], Config] = SimpleFrozenDict(), ) -> "Language": """Load a model from an installed package. @@ -619,9 +619,9 @@ def load_model_from_init_py( init_file: Union[Path, str], *, vocab: Union["Vocab", bool] = True, - disable: Union[str, Iterable[str]] = SimpleFrozenList(), - enable: Union[str, Iterable[str]] = SimpleFrozenList(), - exclude: Union[str, Iterable[str]] = SimpleFrozenList(), + disable: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES, + enable: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES, + exclude: Union[str, Iterable[str]] = _DEFAULT_EMPTY_PIPES, config: Union[Dict[str, Any], Config] = SimpleFrozenDict(), ) -> "Language": """Helper function to use in the `load()` method of a model package's 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..b42ba8a4f 100644 --- a/website/docs/api/cli.md +++ b/website/docs/api/cli.md @@ -12,10 +12,10 @@ menu: - ['train', 'train'] - ['pretrain', 'pretrain'] - ['evaluate', 'evaluate'] + - ['find-threshold', 'find-threshold'] - ['assemble', 'assemble'] - ['package', 'package'] - ['project', 'project'] - - ['ray', 'ray'] - ['huggingface-hub', 'huggingface-hub'] --- @@ -53,7 +53,7 @@ $ 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 +77,15 @@ $ 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 +260,22 @@ 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 +474,7 @@ 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/). @@ -1163,6 +1162,46 @@ $ python -m spacy evaluate [model] [data_path] [--output] [--code] [--gold-prepr | `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | | **CREATES** | Training results and optional metrics and visualizations. | +## find-threshold {#find-threshold new="3.5" tag="command"} + +Runs prediction trials for a trained model with varying tresholds to maximize +the specified metric. The search space for the threshold is traversed linearly +from 0 to 1 in `n_trials` steps. Results are displayed in a table on `stdout` +(the corresponding API call to `spacy.cli.find_threshold.find_threshold()` +returns all results). + +This is applicable only for components whose predictions are influenced by +thresholds - e.g. `textcat_multilabel` and `spancat`, but not `textcat`. Note +that the full path to the corresponding threshold attribute in the config has to +be provided. + +> #### Examples +> +> ```cli +> # For textcat_multilabel: +> $ python -m spacy find-threshold my_nlp data.spacy textcat_multilabel threshold cats_macro_f +> ``` +> +> ```cli +> # For spancat: +> $ python -m spacy find-threshold my_nlp data.spacy spancat threshold spans_sc_f +> ``` + + +| Name | Description | +| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `model` | Pipeline to evaluate. Can be a package or a path to a data directory. ~~str (positional)~~ | +| `data_path` | Path to file with DocBin with docs to use for threshold search. ~~Path (positional)~~ | +| `pipe_name` | Name of pipe to examine thresholds for. ~~str (positional)~~ | +| `threshold_key` | Key of threshold attribute in component's configuration. ~~str (positional)~~ | +| `scores_key` | Name of score to metric to optimize. ~~str (positional)~~ | +| `--n_trials`, `-n` | Number of trials to determine optimal thresholds. ~~int (option)~~ | +| `--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)~~ | +| `--gpu-id`, `-g` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~ | +| `--gold-preproc`, `-G` | Use gold preprocessing. ~~bool (flag)~~ | +| `--silent`, `-V`, `-VV` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | + ## assemble {#assemble tag="command"} Assemble a pipeline from a config file without additional training. Expects a @@ -1229,19 +1268,19 @@ $ 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 +1542,6 @@ $ 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/data-formats.md b/website/docs/api/data-formats.md index ce06c4ea8..768844cf3 100644 --- a/website/docs/api/data-formats.md +++ b/website/docs/api/data-formats.md @@ -186,6 +186,7 @@ process that are used when you run [`spacy train`](/api/cli#train). | `accumulate_gradient` | Whether to divide the batch up into substeps. Defaults to `1`. ~~int~~ | | `batcher` | Callable that takes an iterator of [`Doc`](/api/doc) objects and yields batches of `Doc`s. Defaults to [`batch_by_words`](/api/top-level#batch_by_words). ~~Callable[[Iterator[Doc], Iterator[List[Doc]]]]~~ | | `before_to_disk` | Optional callback to modify `nlp` object right before it is saved to disk during and after training. Can be used to remove or reset config values or disable components. Defaults to `null`. ~~Optional[Callable[[Language], Language]]~~ | +| `before_update` | Optional callback that is invoked at the start of each training step with the `nlp` object and a `Dict` containing the following entries: `step`, `epoch`. Can be used to make deferred changes to components. Defaults to `null`. ~~Optional[Callable[[Language, Dict[str, Any]], None]]~~ | | `dev_corpus` | Dot notation of the config location defining the dev corpus. Defaults to `corpora.dev`. ~~str~~ | | `dropout` | The dropout rate. Defaults to `0.1`. ~~float~~ | | `eval_frequency` | How often to evaluate during training (steps). Defaults to `200`. ~~int~~ | 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/scorer.md b/website/docs/api/scorer.md index ca3462aa9..9ef36e6fc 100644 --- a/website/docs/api/scorer.md +++ b/website/docs/api/scorer.md @@ -229,16 +229,17 @@ The reported `{attr}_score` depends on the classification properties: > print(scores["cats_macro_auc"]) > ``` -| Name | Description | -| ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | -| `examples` | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ | -| `attr` | The attribute to score. ~~str~~ | -| _keyword-only_ | | -| `getter` | Defaults to `getattr`. If provided, `getter(doc, attr)` should return the cats for an individual `Doc`. ~~Callable[[Doc, str], Dict[str, float]]~~ | -| labels | The set of possible labels. Defaults to `[]`. ~~Iterable[str]~~ | -| `multi_label` | Whether the attribute allows multiple labels. Defaults to `True`. ~~bool~~ | -| `positive_label` | The positive label for a binary task with exclusive classes. Defaults to `None`. ~~Optional[str]~~ | -| **RETURNS** | A dictionary containing the scores, with inapplicable scores as `None`. ~~Dict[str, Optional[float]]~~ | +| Name | Description | +| ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `examples` | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ | +| `attr` | The attribute to score. ~~str~~ | +| _keyword-only_ | | +| `getter` | Defaults to `getattr`. If provided, `getter(doc, attr)` should return the cats for an individual `Doc`. ~~Callable[[Doc, str], Dict[str, float]]~~ | +| labels | The set of possible labels. Defaults to `[]`. ~~Iterable[str]~~ | +| `multi_label` | Whether the attribute allows multiple labels. Defaults to `True`. When set to `False` (exclusive labels), missing gold labels are interpreted as `0.0` and the threshold is set to `0.0`. ~~bool~~ | +| `positive_label` | The positive label for a binary task with exclusive classes. Defaults to `None`. ~~Optional[str]~~ | +| `threshold` | Cutoff to consider a prediction "positive". Defaults to `0.5` for multi-label, and `0.0` (i.e. whatever's highest scoring) otherwise. ~~float~~ | +| **RETURNS** | A dictionary containing the scores, with inapplicable scores as `None`. ~~Dict[str, Optional[float]]~~ | ## Scorer.score_links {#score_links tag="staticmethod" new="3"} 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/textcategorizer.md b/website/docs/api/textcategorizer.md index 042b4ab76..f5f8706ec 100644 --- a/website/docs/api/textcategorizer.md +++ b/website/docs/api/textcategorizer.md @@ -63,7 +63,6 @@ architectures and their arguments and hyperparameters. > ```python > from spacy.pipeline.textcat import DEFAULT_SINGLE_TEXTCAT_MODEL > config = { -> "threshold": 0.5, > "model": DEFAULT_SINGLE_TEXTCAT_MODEL, > } > nlp.add_pipe("textcat", config=config) @@ -82,7 +81,7 @@ architectures and their arguments and hyperparameters. | Setting | Description | | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `threshold` | Cutoff to consider a prediction "positive", relevant when printing accuracy results. ~~float~~ | +| `threshold` | Cutoff to consider a prediction "positive", relevant for `textcat_multilabel` when calculating accuracy scores. ~~float~~ | | `model` | A model instance that predicts scores for each category. Defaults to [TextCatEnsemble](/api/architectures#TextCatEnsemble). ~~Model[List[Doc], List[Floats2d]]~~ | | `scorer` | The scoring method. Defaults to [`Scorer.score_cats`](/api/scorer#score_cats) for the attribute `"cats"`. ~~Optional[Callable]~~ | @@ -123,7 +122,7 @@ shortcut for this and instantiate the component using its string name and | `model` | The Thinc [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. ~~Model[List[Doc], List[Floats2d]]~~ | | `name` | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~ | | _keyword-only_ | | -| `threshold` | Cutoff to consider a prediction "positive", relevant when printing accuracy results. ~~float~~ | +| `threshold` | Cutoff to consider a prediction "positive", relevant for `textcat_multilabel` when calculating accuracy scores. ~~float~~ | | `scorer` | The scoring method. Defaults to [`Scorer.score_cats`](/api/scorer#score_cats) for the attribute `"cats"`. ~~Optional[Callable]~~ | ## TextCategorizer.\_\_call\_\_ {#call tag="method"} 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/vectors.md b/website/docs/api/vectors.md index 9636ea04c..d4702b592 100644 --- a/website/docs/api/vectors.md +++ b/website/docs/api/vectors.md @@ -50,7 +50,7 @@ modified later. | _keyword-only_ | | | `strings` | The string store. A new string store is created if one is not provided. Defaults to `None`. ~~Optional[StringStore]~~ | | `shape` | Size of the table as `(n_entries, n_columns)`, the number of entries and number of columns. Not required if you're initializing the object with `data` and `keys`. ~~Tuple[int, int]~~ | -| `data` | The vector data. ~~numpy.ndarray[ndim=1, dtype=float32]~~ | +| `data` | The vector data. ~~numpy.ndarray[ndim=2, dtype=float32]~~ | | `keys` | A sequence of keys aligned with the data. ~~Iterable[Union[str, int]]~~ | | `name` | A name to identify the vectors table. ~~str~~ | | `mode` 3.2 | Vectors mode: `"default"` or [`"floret"`](https://github.com/explosion/floret) (default: `"default"`). ~~str~~ | 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 f096890cb..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. | @@ -1792,7 +1792,7 @@ the entity `Span` – for example `._.orgs` or `._.prev_orgs` and > [`Doc.retokenize`](/api/doc#retokenize) context manager: > > ```python -> with doc.retokenize() as retokenize: +> with doc.retokenize() as retokenizer: > for ent in doc.ents: > retokenizer.merge(ent) > ``` 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/languages.json b/website/meta/languages.json index bd1535c90..15158df79 100644 --- a/website/meta/languages.json +++ b/website/meta/languages.json @@ -562,6 +562,7 @@ "url": "https://github.com/explosion/spacy-pkuseg" } ], + "example": "这是一个用于示例的句子。", "has_examples": true } ], diff --git a/website/meta/universe.json b/website/meta/universe.json index d7c99956b..97b53e9c5 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", @@ -2009,17 +1993,6 @@ }, "category": ["books"] }, - { - "type": "education", - "id": "learning-path-spacy", - "title": "Learning Path: Mastering spaCy for Natural Language Processing", - "slogan": "O'Reilly, 2017", - "description": "spaCy, a fast, user-friendly library for teaching computers to understand text, simplifies NLP techniques, such as speech tagging and syntactic dependencies, so you can easily extract information, attributes, and objects from massive amounts of text to then document, measure, and analyze. This Learning Path is a hands-on introduction to using spaCy to discover insights through natural language processing. While end-to-end natural language processing solutions can be complex, you’ll learn the linguistics, algorithms, and machine learning skills to get the job done.", - "url": "https://www.safaribooksonline.com/library/view/learning-path-mastering/9781491986653/", - "thumb": "https://i.imgur.com/9MIgMAc.jpg", - "author": "Aaron Kramer", - "category": ["courses"] - }, { "type": "education", "id": "introduction-into-spacy-3",