diff --git a/.github/ISSUE_TEMPLATE/01_bugs.md b/.github/ISSUE_TEMPLATE/01_bugs.md index 255a5241e..f0d0ba912 100644 --- a/.github/ISSUE_TEMPLATE/01_bugs.md +++ b/.github/ISSUE_TEMPLATE/01_bugs.md @@ -10,7 +10,7 @@ about: Use this template if you came across a bug or unexpected behaviour differ ## Your Environment - + * Operating System: * Python Version Used: * spaCy Version Used: diff --git a/.github/azure-steps.yml b/.github/azure-steps.yml index c7722391f..e8bd0d212 100644 --- a/.github/azure-steps.yml +++ b/.github/azure-steps.yml @@ -1,68 +1,56 @@ parameters: python_version: '' - architecture: '' - prefix: '' - gpu: false - num_build_jobs: 1 + architecture: 'x64' + num_build_jobs: 2 steps: - task: UsePythonVersion@0 inputs: versionSpec: ${{ parameters.python_version }} architecture: ${{ parameters.architecture }} + allowUnstable: true - bash: | echo "##vso[task.setvariable variable=python_version]${{ parameters.python_version }}" 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'], '3.10') + condition: ne(variables['python_version'], '3.6') - task: DeleteFiles@1 inputs: 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 @@ -71,6 +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' @@ -105,13 +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 8d0282650..70882c3cc 100644 --- a/.github/workflows/autoblack.yml +++ b/.github/workflows/autoblack.yml @@ -12,10 +12,10 @@ jobs: if: github.repository_owner == 'explosion' runs-on: ubuntu-latest steps: - - uses: actions/checkout@v2 + - uses: actions/checkout@v3 with: ref: ${{ github.head_ref }} - - uses: actions/setup-python@v2 + - uses: actions/setup-python@v4 - run: pip install black - name: Auto-format code if needed run: black spacy @@ -23,10 +23,11 @@ jobs: # code and makes GitHub think the action failed - name: Check for modified files id: git-check - run: echo ::set-output name=modified::$(if git diff-index --quiet HEAD --; then echo "false"; else echo "true"; fi) + run: echo modified=$(if git diff-index --quiet HEAD --; then echo "false"; else echo "true"; fi) >> $GITHUB_OUTPUT + - name: Create Pull Request if: steps.git-check.outputs.modified == 'true' - uses: peter-evans/create-pull-request@v3 + uses: peter-evans/create-pull-request@v4 with: title: Auto-format code with black labels: meta 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 b959262e3..df59697b1 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -6,7 +6,7 @@ repos: language_version: python3.7 additional_dependencies: ['click==8.0.4'] - repo: https://gitlab.com/pycqa/flake8 - rev: 3.9.2 + rev: 5.0.4 hooks: - id: flake8 args: diff --git a/README.md b/README.md index d9ef83e01..abfc3da67 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ be used in real products. spaCy comes with [pretrained pipelines](https://spacy.io/models) and -currently supports tokenization and training for **60+ languages**. It features +currently supports tokenization and training for **70+ languages**. It features state-of-the-art speed and **neural network models** for tagging, parsing, **named entity recognition**, **text classification** and more, multi-task learning with pretrained **transformers** like BERT, as well as a @@ -16,7 +16,7 @@ production-ready [**training system**](https://spacy.io/usage/training) and easy model packaging, deployment and workflow management. spaCy is commercial open-source software, released under the MIT license. -💫 **Version 3.4.0 out now!** +💫 **Version 3.4 out now!** [Check out the release notes here.](https://github.com/explosion/spaCy/releases) [![Azure Pipelines](https://img.shields.io/azure-devops/build/explosion-ai/public/8/master.svg?logo=azure-pipelines&style=flat-square&label=build)](https://dev.azure.com/explosion-ai/public/_build?definitionId=8) @@ -79,7 +79,7 @@ more people can benefit from it. ## Features -- Support for **60+ languages** +- Support for **70+ languages** - **Trained pipelines** for different languages and tasks - Multi-task learning with pretrained **transformers** like BERT - Support for pretrained **word vectors** and embeddings diff --git a/azure-pipelines.yml b/azure-pipelines.yml index f475b7fdd..9c3b92f06 100644 --- a/azure-pipelines.yml +++ b/azure-pipelines.yml @@ -31,7 +31,7 @@ jobs: inputs: versionSpec: "3.7" - script: | - pip install flake8==3.9.2 + pip install flake8==5.0.4 python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics displayName: "flake8" @@ -76,15 +76,24 @@ jobs: # Python39Mac: # imageName: "macos-latest" # python.version: "3.9" - Python310Linux: - imageName: "ubuntu-latest" - python.version: "3.10" + # Python310Linux: + # imageName: "ubuntu-latest" + # python.version: "3.10" Python310Windows: imageName: "windows-latest" python.version: "3.10" - Python310Mac: - imageName: "macos-latest" - python.version: "3.10" + # Python310Mac: + # imageName: "macos-latest" + # python.version: "3.10" + Python311Linux: + imageName: 'ubuntu-latest' + python.version: '3.11' + Python311Windows: + imageName: 'windows-latest' + python.version: '3.11' + Python311Mac: + imageName: 'macos-latest' + python.version: '3.11' maxParallel: 4 pool: vmImage: $(imageName) @@ -92,20 +101,3 @@ jobs: - template: .github/azure-steps.yml parameters: python_version: '$(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 3e8501b2f..d91a3b3d4 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,13 +9,13 @@ murmurhash>=0.28.0,<1.1.0 wasabi>=0.9.1,<1.1.0 srsly>=2.4.3,<3.0.0 catalogue>=2.0.6,<2.1.0 -typer>=0.3.0,<0.5.0 +typer>=0.3.0,<0.8.0 pathy>=0.3.5 # Third party dependencies numpy>=1.15.0 requests>=2.13.0,<3.0.0 tqdm>=4.38.0,<5.0.0 -pydantic>=1.7.4,!=1.8,!=1.8.1,<1.10.0 +pydantic>=1.7.4,!=1.8,!=1.8.1,<1.11.0 jinja2 langcodes>=3.2.0,<4.0.0 # Official Python utilities @@ -28,11 +28,12 @@ cython>=0.25,<3.0 pytest>=5.2.0,!=7.1.0 pytest-timeout>=1.3.0,<2.0.0 mock>=2.0.0,<3.0.0 -flake8>=3.8.0,<3.10.0 +flake8>=3.8.0,<6.0.0 hypothesis>=3.27.0,<7.0.0 -mypy>=0.910,<0.970; platform_machine!='aarch64' +mypy>=0.980,<0.990; 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 types-requests types-setuptools>=57.0.0 black>=22.0,<23.0 diff --git a/setup.cfg b/setup.cfg index 2dc5e7042..82d4d2758 100644 --- a/setup.cfg +++ b/setup.cfg @@ -51,12 +51,12 @@ install_requires = srsly>=2.4.3,<3.0.0 catalogue>=2.0.6,<2.1.0 # Third-party dependencies - typer>=0.3.0,<0.5.0 + typer>=0.3.0,<0.8.0 pathy>=0.3.5 tqdm>=4.38.0,<5.0.0 numpy>=1.15.0 requests>=2.13.0,<3.0.0 - pydantic>=1.7.4,!=1.8,!=1.8.1,<1.10.0 + pydantic>=1.7.4,!=1.8,!=1.8.1,<1.11.0 jinja2 # Official Python utilities setuptools diff --git a/setup.py b/setup.py index c4138aa93..243554c7a 100755 --- a/setup.py +++ b/setup.py @@ -30,7 +30,9 @@ MOD_NAMES = [ "spacy.lexeme", "spacy.vocab", "spacy.attrs", - "spacy.kb", + "spacy.kb.candidate", + "spacy.kb.kb", + "spacy.kb.kb_in_memory", "spacy.ml.parser_model", "spacy.morphology", "spacy.pipeline.dep_parser", diff --git a/spacy/__init__.py b/spacy/__init__.py index d60f46b96..c3568bc5c 100644 --- a/spacy/__init__.py +++ b/spacy/__init__.py @@ -31,9 +31,9 @@ def load( name: Union[str, Path], *, vocab: Union[Vocab, bool] = True, - disable: Union[str, Iterable[str]] = util.SimpleFrozenList(), - enable: Union[str, Iterable[str]] = util.SimpleFrozenList(), - exclude: Union[str, Iterable[str]] = util.SimpleFrozenList(), + disable: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES, + enable: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES, + exclude: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES, config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(), ) -> Language: """Load a spaCy model from an installed package or a local path. diff --git a/spacy/about.py b/spacy/about.py index 843c15aba..ce86e6294 100644 --- a/spacy/about.py +++ b/spacy/about.py @@ -1,6 +1,6 @@ # fmt: off __title__ = "spacy" -__version__ = "3.4.1" +__version__ = "3.4.2" __download_url__ = "https://github.com/explosion/spacy-models/releases/download" __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json" __projects__ = "https://github.com/explosion/projects" diff --git a/spacy/cli/_util.py b/spacy/cli/_util.py index ae43b991b..897964a88 100644 --- a/spacy/cli/_util.py +++ b/spacy/cli/_util.py @@ -573,3 +573,12 @@ def setup_gpu(use_gpu: int, silent=None) -> None: local_msg.info("Using CPU") if gpu_is_available(): local_msg.info("To switch to GPU 0, use the option: --gpu-id 0") + + +def _format_number(number: Union[int, float], ndigits: int = 2) -> str: + """Formats a number (float or int) rounding to `ndigits`, without truncating trailing 0s, + as happens with `round(number, ndigits)`""" + if isinstance(number, float): + return f"{number:.{ndigits}f}" + else: + return str(number) diff --git a/spacy/cli/debug_data.py b/spacy/cli/debug_data.py index bd05471b1..963d5b926 100644 --- a/spacy/cli/debug_data.py +++ b/spacy/cli/debug_data.py @@ -9,7 +9,7 @@ import typer import math from ._util import app, Arg, Opt, show_validation_error, parse_config_overrides -from ._util import import_code, debug_cli +from ._util import import_code, debug_cli, _format_number from ..training import Example, remove_bilu_prefix from ..training.initialize import get_sourced_components from ..schemas import ConfigSchemaTraining @@ -989,7 +989,8 @@ def _get_kl_divergence(p: Counter, q: Counter) -> float: def _format_span_row(span_data: List[Dict], labels: List[str]) -> List[Any]: """Compile into one list for easier reporting""" d = { - label: [label] + list(round(d[label], 2) for d in span_data) for label in labels + label: [label] + list(_format_number(d[label]) for d in span_data) + for label in labels } return list(d.values()) @@ -1004,6 +1005,10 @@ def _get_span_characteristics( label: _gmean(l) for label, l in compiled_gold["spans_length"][spans_key].items() } + spans_per_type = { + label: len(spans) + for label, spans in compiled_gold["spans_per_type"][spans_key].items() + } min_lengths = [min(l) for l in compiled_gold["spans_length"][spans_key].values()] max_lengths = [max(l) for l in compiled_gold["spans_length"][spans_key].values()] @@ -1031,6 +1036,7 @@ def _get_span_characteristics( return { "sd": span_distinctiveness, "bd": sb_distinctiveness, + "spans_per_type": spans_per_type, "lengths": span_length, "min_length": min(min_lengths), "max_length": max(max_lengths), @@ -1045,12 +1051,15 @@ def _get_span_characteristics( def _print_span_characteristics(span_characteristics: Dict[str, Any]): """Print all span characteristics into a table""" - headers = ("Span Type", "Length", "SD", "BD") + headers = ("Span Type", "Length", "SD", "BD", "N") + # Wasabi has this at 30 by default, but we might have some long labels + max_col = max(30, max(len(label) for label in span_characteristics["labels"])) # Prepare table data with all span characteristics table_data = [ span_characteristics["lengths"], span_characteristics["sd"], span_characteristics["bd"], + span_characteristics["spans_per_type"], ] table = _format_span_row( span_data=table_data, labels=span_characteristics["labels"] @@ -1061,8 +1070,18 @@ def _print_span_characteristics(span_characteristics: Dict[str, Any]): span_characteristics["avg_sd"], span_characteristics["avg_bd"], ] - footer = ["Wgt. Average"] + [str(round(f, 2)) for f in footer_data] - msg.table(table, footer=footer, header=headers, divider=True) + + footer = ( + ["Wgt. Average"] + ["{:.2f}".format(round(f, 2)) for f in footer_data] + ["-"] + ) + msg.table( + table, + footer=footer, + header=headers, + divider=True, + aligns=["l"] + ["r"] * (len(footer_data) + 1), + max_col=max_col, + ) def _get_spans_length_freq_dist( diff --git a/spacy/cli/package.py b/spacy/cli/package.py index b8c8397b6..324c5d1bb 100644 --- a/spacy/cli/package.py +++ b/spacy/cli/package.py @@ -299,8 +299,8 @@ def get_meta( } nlp = util.load_model_from_path(Path(model_path)) meta.update(nlp.meta) - meta.update(existing_meta) meta["spacy_version"] = util.get_minor_version_range(about.__version__) + meta.update(existing_meta) meta["vectors"] = { "width": nlp.vocab.vectors_length, "vectors": len(nlp.vocab.vectors), diff --git a/spacy/cli/project/dvc.py b/spacy/cli/project/dvc.py index 83dc5efbf..a15353855 100644 --- a/spacy/cli/project/dvc.py +++ b/spacy/cli/project/dvc.py @@ -25,6 +25,7 @@ def project_update_dvc_cli( project_dir: Path = Arg(Path.cwd(), help="Location of project directory. Defaults to current working directory.", exists=True, file_okay=False), workflow: Optional[str] = Arg(None, help=f"Name of workflow defined in {PROJECT_FILE}. Defaults to first workflow if not set."), verbose: bool = Opt(False, "--verbose", "-V", help="Print more info"), + quiet: bool = Opt(False, "--quiet", "-q", help="Print less info"), force: bool = Opt(False, "--force", "-F", help="Force update DVC config"), # fmt: on ): @@ -36,7 +37,7 @@ def project_update_dvc_cli( DOCS: https://spacy.io/api/cli#project-dvc """ - project_update_dvc(project_dir, workflow, verbose=verbose, force=force) + project_update_dvc(project_dir, workflow, verbose=verbose, quiet=quiet, force=force) def project_update_dvc( @@ -44,6 +45,7 @@ def project_update_dvc( workflow: Optional[str] = None, *, verbose: bool = False, + quiet: bool = False, force: bool = False, ) -> None: """Update the auto-generated Data Version Control (DVC) config file. A DVC @@ -54,11 +56,12 @@ def project_update_dvc( workflow (Optional[str]): Optional name of workflow defined in project.yml. If not set, the first workflow will be used. verbose (bool): Print more info. + quiet (bool): Print less info. force (bool): Force update DVC config. """ config = load_project_config(project_dir) updated = update_dvc_config( - project_dir, config, workflow, verbose=verbose, force=force + project_dir, config, workflow, verbose=verbose, quiet=quiet, force=force ) help_msg = "To execute the workflow with DVC, run: dvc repro" if updated: @@ -72,7 +75,7 @@ def update_dvc_config( config: Dict[str, Any], workflow: Optional[str] = None, verbose: bool = False, - silent: bool = False, + quiet: bool = False, force: bool = False, ) -> bool: """Re-run the DVC commands in dry mode and update dvc.yaml file in the @@ -83,7 +86,7 @@ def update_dvc_config( path (Path): The path to the project directory. config (Dict[str, Any]): The loaded project.yml. verbose (bool): Whether to print additional info (via DVC). - silent (bool): Don't output anything (via DVC). + quiet (bool): Don't output anything (via DVC). force (bool): Force update, even if hashes match. RETURNS (bool): Whether the DVC config file was updated. """ @@ -105,6 +108,14 @@ def update_dvc_config( dvc_config_path.unlink() dvc_commands = [] config_commands = {cmd["name"]: cmd for cmd in config.get("commands", [])} + + # some flags that apply to every command + flags = [] + if verbose: + flags.append("--verbose") + if quiet: + flags.append("--quiet") + for name in workflows[workflow]: command = config_commands[name] deps = command.get("deps", []) @@ -118,14 +129,26 @@ def update_dvc_config( deps_cmd = [c for cl in [["-d", p] for p in deps] for c in cl] outputs_cmd = [c for cl in [["-o", p] for p in outputs] for c in cl] outputs_nc_cmd = [c for cl in [["-O", p] for p in outputs_no_cache] for c in cl] - dvc_cmd = ["run", "-n", name, "-w", str(path), "--no-exec"] + + dvc_cmd = ["run", *flags, "-n", name, "-w", str(path), "--no-exec"] if command.get("no_skip"): dvc_cmd.append("--always-changed") full_cmd = [*dvc_cmd, *deps_cmd, *outputs_cmd, *outputs_nc_cmd, *project_cmd] dvc_commands.append(join_command(full_cmd)) + + if not dvc_commands: + # If we don't check for this, then there will be an error when reading the + # config, since DVC wouldn't create it. + msg.fail( + "No usable commands for DVC found. This can happen if none of your " + "commands have dependencies or outputs.", + exits=1, + ) + with working_dir(path): - dvc_flags = {"--verbose": verbose, "--quiet": silent} - run_dvc_commands(dvc_commands, flags=dvc_flags) + for c in dvc_commands: + dvc_command = "dvc " + c + run_command(dvc_command) with dvc_config_path.open("r+", encoding="utf8") as f: content = f.read() f.seek(0, 0) @@ -133,26 +156,6 @@ def update_dvc_config( return True -def run_dvc_commands( - commands: Iterable[str] = SimpleFrozenList(), flags: Dict[str, bool] = {} -) -> None: - """Run a sequence of DVC commands in a subprocess, in order. - - commands (List[str]): The string commands without the leading "dvc". - flags (Dict[str, bool]): Conditional flags to be added to command. Makes it - easier to pass flags like --quiet that depend on a variable or - command-line setting while avoiding lots of nested conditionals. - """ - for c in commands: - command = split_command(c) - dvc_command = ["dvc", *command] - # Add the flags if they are set to True - for flag, is_active in flags.items(): - if is_active: - dvc_command.append(flag) - run_command(dvc_command) - - def check_workflows(workflows: List[str], workflow: Optional[str] = None) -> None: """Validate workflows provided in project.yml and check that a given workflow can be used to generate a DVC config. 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 d42d95465..a109c4a5a 100644 --- a/spacy/cli/project/run.py +++ b/spacy/cli/project/run.py @@ -1,5 +1,8 @@ -from typing import Optional, List, Dict, Sequence, Any, Iterable +from typing import Optional, List, Dict, Sequence, Any, Iterable, Tuple +import os.path from pathlib import Path + +import pkg_resources from wasabi import msg from wasabi.util import locale_escape import sys @@ -50,6 +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 @@ -66,11 +70,19 @@ 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", [])} workflows = config.get("workflows", {}) validate_subcommand(list(commands.keys()), list(workflows.keys()), subcommand) + + req_path = project_dir / "requirements.txt" + 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}'") for cmd in workflows[subcommand]: @@ -81,6 +93,7 @@ def project_run( force=force, dry=dry, capture=capture, + skip_requirements_check=True, ) else: cmd = commands[subcommand] @@ -310,3 +323,38 @@ def get_fileinfo(project_dir: Path, paths: List[str]) -> List[Dict[str, Optional md5 = get_checksum(file_path) if file_path.exists() else None data.append({"path": path, "md5": md5}) return data + + +def _check_requirements(requirements: List[str]) -> Tuple[bool, bool]: + """Checks whether requirements are installed and free of version conflicts. + requirements (List[str]): List of requirements. + RETURNS (Tuple[bool, bool]): Whether (1) any packages couldn't be imported, (2) any packages with version conflicts + exist. + """ + + failed_pkgs_msgs: List[str] = [] + conflicting_pkgs_msgs: List[str] = [] + + for req in requirements: + try: + pkg_resources.require(req) + except pkg_resources.DistributionNotFound as dnf: + 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( + title="Missing requirements or requirement conflicts detected. Make sure your Python environment is set up " + "correctly and you installed all requirements specified in your project's requirements.txt: " + ) + for pgk_msg in failed_pkgs_msgs + conflicting_pkgs_msgs: + msg.text(pgk_msg) + + return len(failed_pkgs_msgs) > 0, len(conflicting_pkgs_msgs) > 0 diff --git a/spacy/errors.py b/spacy/errors.py index f55b378e9..278e5496a 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -212,6 +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 `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): @@ -538,8 +540,12 @@ class Errors(metaclass=ErrorsWithCodes): E199 = ("Unable to merge 0-length span at `doc[{start}:{end}]`.") E200 = ("Can't set {attr} from Span.") E202 = ("Unsupported {name} mode '{mode}'. Supported modes: {modes}.") + E203 = ("If the {name} embedding layer is not updated " + "during training, make sure to include it in 'annotating components'") # New errors added in v3.x + 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 " @@ -709,9 +715,9 @@ class Errors(metaclass=ErrorsWithCodes): "`nlp.enable_pipe` instead.") E927 = ("Can't write to frozen list. Maybe you're trying to modify a computed " "property or default function argument?") - E928 = ("A KnowledgeBase can only be serialized to/from from a directory, " + E928 = ("An InMemoryLookupKB can only be serialized to/from from a directory, " "but the provided argument {loc} points to a file.") - E929 = ("Couldn't read KnowledgeBase from {loc}. The path does not seem to exist.") + E929 = ("Couldn't read InMemoryLookupKB from {loc}. The path does not seem to exist.") E930 = ("Received invalid get_examples callback in `{method}`. " "Expected function that returns an iterable of Example objects but " "got: {obj}") @@ -937,10 +943,17 @@ class Errors(metaclass=ErrorsWithCodes): E1040 = ("Doc.from_json requires all tokens to have the same attributes. " "Some tokens do not contain annotation for: {partial_attrs}") E1041 = ("Expected a string, Doc, or bytes as input, but got: {type}") - E1042 = ("Function was called with `{arg1}`={arg1_values} and " - "`{arg2}`={arg2_values} but these arguments are conflicting.") + E1042 = ("`enable={enable}` and `disable={disable}` are inconsistent with each other.\nIf you only passed " + "one of `enable` or `disable`, the other argument is specified in your pipeline's configuration.\nIn that " + "case pass an empty list for the previously not specified argument to avoid this error.") E1043 = ("Expected None or a value in range [{range_start}, {range_end}] for entity linker threshold, but got " "{value}.") + E1044 = ("Expected `candidates_batch_size` to be >= 1, but got: {value}") + E1045 = ("Encountered {parent} subclass without `{parent}.{method}` " + "method in '{name}'. If you want to use this method, make " + "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`.") # Deprecated model shortcuts, only used in errors and warnings diff --git a/spacy/kb/__init__.py b/spacy/kb/__init__.py new file mode 100644 index 000000000..1d70a9b34 --- /dev/null +++ b/spacy/kb/__init__.py @@ -0,0 +1,3 @@ +from .kb import KnowledgeBase +from .kb_in_memory import InMemoryLookupKB +from .candidate import Candidate, get_candidates, get_candidates_batch diff --git a/spacy/kb/candidate.pxd b/spacy/kb/candidate.pxd new file mode 100644 index 000000000..942ce9dd0 --- /dev/null +++ b/spacy/kb/candidate.pxd @@ -0,0 +1,12 @@ +from .kb cimport KnowledgeBase +from libcpp.vector cimport vector +from ..typedefs cimport hash_t + +# Object used by the Entity Linker that summarizes one entity-alias candidate combination. +cdef class Candidate: + cdef readonly KnowledgeBase kb + cdef hash_t entity_hash + cdef float entity_freq + cdef vector[float] entity_vector + cdef hash_t alias_hash + cdef float prior_prob diff --git a/spacy/kb/candidate.pyx b/spacy/kb/candidate.pyx new file mode 100644 index 000000000..c89efeb03 --- /dev/null +++ b/spacy/kb/candidate.pyx @@ -0,0 +1,74 @@ +# cython: infer_types=True, profile=True + +from typing import Iterable +from .kb cimport KnowledgeBase +from ..tokens import Span + +cdef class Candidate: + """A `Candidate` object refers to a textual mention (`alias`) that may or may not be resolved + to a specific `entity` from a Knowledge Base. This will be used as input for the entity linking + algorithm which will disambiguate the various candidates to the correct one. + Each candidate (alias, entity) pair is assigned a certain prior probability. + + DOCS: https://spacy.io/api/kb/#candidate-init + """ + + def __init__(self, KnowledgeBase kb, entity_hash, entity_freq, entity_vector, alias_hash, prior_prob): + self.kb = kb + self.entity_hash = entity_hash + self.entity_freq = entity_freq + self.entity_vector = entity_vector + self.alias_hash = alias_hash + self.prior_prob = prior_prob + + @property + def entity(self) -> int: + """RETURNS (uint64): hash of the entity's KB ID/name""" + return self.entity_hash + + @property + def entity_(self) -> str: + """RETURNS (str): ID/name of this entity in the KB""" + return self.kb.vocab.strings[self.entity_hash] + + @property + def alias(self) -> int: + """RETURNS (uint64): hash of the alias""" + return self.alias_hash + + @property + def alias_(self) -> str: + """RETURNS (str): ID of the original alias""" + return self.kb.vocab.strings[self.alias_hash] + + @property + def entity_freq(self) -> float: + return self.entity_freq + + @property + def entity_vector(self) -> Iterable[float]: + return self.entity_vector + + @property + def prior_prob(self) -> float: + return self.prior_prob + + +def get_candidates(kb: KnowledgeBase, mention: Span) -> Iterable[Candidate]: + """ + Return candidate entities for a given mention and fetching appropriate entries from the index. + kb (KnowledgeBase): Knowledge base to query. + mention (Span): Entity mention for which to identify candidates. + RETURNS (Iterable[Candidate]): Identified candidates. + """ + return kb.get_candidates(mention) + + +def get_candidates_batch(kb: KnowledgeBase, mentions: Iterable[Span]) -> Iterable[Iterable[Candidate]]: + """ + Return candidate entities for the given mentions and fetching appropriate entries from the index. + kb (KnowledgeBase): Knowledge base to query. + mention (Iterable[Span]): Entity mentions for which to identify candidates. + RETURNS (Iterable[Iterable[Candidate]]): Identified candidates. + """ + return kb.get_candidates_batch(mentions) diff --git a/spacy/kb/kb.pxd b/spacy/kb/kb.pxd new file mode 100644 index 000000000..1adeef8ae --- /dev/null +++ b/spacy/kb/kb.pxd @@ -0,0 +1,10 @@ +"""Knowledge-base for entity or concept linking.""" + +from cymem.cymem cimport Pool +from libc.stdint cimport int64_t +from ..vocab cimport Vocab + +cdef class KnowledgeBase: + cdef Pool mem + cdef readonly Vocab vocab + cdef readonly int64_t entity_vector_length diff --git a/spacy/kb/kb.pyx b/spacy/kb/kb.pyx new file mode 100644 index 000000000..ce4bc0138 --- /dev/null +++ b/spacy/kb/kb.pyx @@ -0,0 +1,108 @@ +# cython: infer_types=True, profile=True + +from pathlib import Path +from typing import Iterable, Tuple, Union +from cymem.cymem cimport Pool + +from .candidate import Candidate +from ..tokens import Span +from ..util import SimpleFrozenList +from ..errors import Errors + + +cdef class KnowledgeBase: + """A `KnowledgeBase` instance stores unique identifiers for entities and their textual aliases, + to support entity linking of named entities to real-world concepts. + This is an abstract class and requires its operations to be implemented. + + DOCS: https://spacy.io/api/kb + """ + + def __init__(self, vocab: Vocab, entity_vector_length: int): + """Create a KnowledgeBase.""" + # Make sure abstract KB is not instantiated. + if self.__class__ == KnowledgeBase: + raise TypeError( + Errors.E1046.format(cls_name=self.__class__.__name__) + ) + + self.vocab = vocab + self.entity_vector_length = entity_vector_length + self.mem = Pool() + + def get_candidates_batch(self, mentions: Iterable[Span]) -> Iterable[Iterable[Candidate]]: + """ + Return candidate entities for specified texts. Each candidate defines the entity, the original alias, + and the prior probability of that alias resolving to that entity. + If no candidate is found for a given text, an empty list is returned. + mentions (Iterable[Span]): Mentions for which to get candidates. + RETURNS (Iterable[Iterable[Candidate]]): Identified candidates. + """ + return [self.get_candidates(span) for span in mentions] + + def get_candidates(self, mention: Span) -> Iterable[Candidate]: + """ + Return candidate entities for specified text. Each candidate defines the entity, the original alias, + and the prior probability of that alias resolving to that entity. + If the no candidate is found for a given text, an empty list is returned. + mention (Span): Mention for which to get candidates. + RETURNS (Iterable[Candidate]): Identified candidates. + """ + raise NotImplementedError( + Errors.E1045.format(parent="KnowledgeBase", method="get_candidates", name=self.__name__) + ) + + def get_vectors(self, entities: Iterable[str]) -> Iterable[Iterable[float]]: + """ + Return vectors for entities. + entity (str): Entity name/ID. + RETURNS (Iterable[Iterable[float]]): Vectors for specified entities. + """ + return [self.get_vector(entity) for entity in entities] + + def get_vector(self, str entity) -> Iterable[float]: + """ + Return vector for entity. + entity (str): Entity name/ID. + RETURNS (Iterable[float]): Vector for specified entity. + """ + raise NotImplementedError( + Errors.E1045.format(parent="KnowledgeBase", method="get_vector", name=self.__name__) + ) + + def to_bytes(self, **kwargs) -> bytes: + """Serialize the current state to a binary string. + RETURNS (bytes): Current state as binary string. + """ + raise NotImplementedError( + Errors.E1045.format(parent="KnowledgeBase", method="to_bytes", name=self.__name__) + ) + + def from_bytes(self, bytes_data: bytes, *, exclude: Tuple[str] = tuple()): + """Load state from a binary string. + bytes_data (bytes): KB state. + exclude (Tuple[str]): Properties to exclude when restoring KB. + """ + raise NotImplementedError( + Errors.E1045.format(parent="KnowledgeBase", method="from_bytes", name=self.__name__) + ) + + def to_disk(self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()) -> None: + """ + Write KnowledgeBase content to disk. + path (Union[str, Path]): Target file path. + exclude (Iterable[str]): List of components to exclude. + """ + raise NotImplementedError( + Errors.E1045.format(parent="KnowledgeBase", method="to_disk", name=self.__name__) + ) + + def from_disk(self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()) -> None: + """ + Load KnowledgeBase content from disk. + path (Union[str, Path]): Target file path. + exclude (Iterable[str]): List of components to exclude. + """ + raise NotImplementedError( + Errors.E1045.format(parent="KnowledgeBase", method="from_disk", name=self.__name__) + ) diff --git a/spacy/kb.pxd b/spacy/kb/kb_in_memory.pxd similarity index 92% rename from spacy/kb.pxd rename to spacy/kb/kb_in_memory.pxd index a823dbe1e..825a6bde9 100644 --- a/spacy/kb.pxd +++ b/spacy/kb/kb_in_memory.pxd @@ -1,14 +1,12 @@ """Knowledge-base for entity or concept linking.""" -from cymem.cymem cimport Pool from preshed.maps cimport PreshMap from libcpp.vector cimport vector from libc.stdint cimport int32_t, int64_t from libc.stdio cimport FILE -from .vocab cimport Vocab -from .typedefs cimport hash_t -from .structs cimport KBEntryC, AliasC - +from ..typedefs cimport hash_t +from ..structs cimport KBEntryC, AliasC +from .kb cimport KnowledgeBase ctypedef vector[KBEntryC] entry_vec ctypedef vector[AliasC] alias_vec @@ -16,21 +14,7 @@ ctypedef vector[float] float_vec ctypedef vector[float_vec] float_matrix -# Object used by the Entity Linker that summarizes one entity-alias candidate combination. -cdef class Candidate: - cdef readonly KnowledgeBase kb - cdef hash_t entity_hash - cdef float entity_freq - cdef vector[float] entity_vector - cdef hash_t alias_hash - cdef float prior_prob - - -cdef class KnowledgeBase: - cdef Pool mem - cdef readonly Vocab vocab - cdef int64_t entity_vector_length - +cdef class InMemoryLookupKB(KnowledgeBase): # This maps 64bit keys (hash of unique entity string) # to 64bit values (position of the _KBEntryC struct in the _entries vector). # The PreshMap is pretty space efficient, as it uses open addressing. So diff --git a/spacy/kb.pyx b/spacy/kb/kb_in_memory.pyx similarity index 90% rename from spacy/kb.pyx rename to spacy/kb/kb_in_memory.pyx index ae1983a8d..485e52c2f 100644 --- a/spacy/kb.pyx +++ b/spacy/kb/kb_in_memory.pyx @@ -1,8 +1,7 @@ # cython: infer_types=True, profile=True -from typing import Iterator, Iterable, Callable, Dict, Any +from typing import Iterable, Callable, Dict, Any, Union import srsly -from cymem.cymem cimport Pool from preshed.maps cimport PreshMap from cpython.exc cimport PyErr_SetFromErrno from libc.stdio cimport fopen, fclose, fread, fwrite, feof, fseek @@ -12,85 +11,28 @@ from libcpp.vector cimport vector from pathlib import Path import warnings -from .typedefs cimport hash_t -from .errors import Errors, Warnings -from . import util -from .util import SimpleFrozenList, ensure_path - -cdef class Candidate: - """A `Candidate` object refers to a textual mention (`alias`) that may or may not be resolved - to a specific `entity` from a Knowledge Base. This will be used as input for the entity linking - algorithm which will disambiguate the various candidates to the correct one. - Each candidate (alias, entity) pair is assigned to a certain prior probability. - - DOCS: https://spacy.io/api/kb/#candidate_init - """ - - def __init__(self, KnowledgeBase kb, entity_hash, entity_freq, entity_vector, alias_hash, prior_prob): - self.kb = kb - self.entity_hash = entity_hash - self.entity_freq = entity_freq - self.entity_vector = entity_vector - self.alias_hash = alias_hash - self.prior_prob = prior_prob - - @property - def entity(self): - """RETURNS (uint64): hash of the entity's KB ID/name""" - return self.entity_hash - - @property - def entity_(self): - """RETURNS (str): ID/name of this entity in the KB""" - return self.kb.vocab.strings[self.entity_hash] - - @property - def alias(self): - """RETURNS (uint64): hash of the alias""" - return self.alias_hash - - @property - def alias_(self): - """RETURNS (str): ID of the original alias""" - return self.kb.vocab.strings[self.alias_hash] - - @property - def entity_freq(self): - return self.entity_freq - - @property - def entity_vector(self): - return self.entity_vector - - @property - def prior_prob(self): - return self.prior_prob +from ..tokens import Span +from ..typedefs cimport hash_t +from ..errors import Errors, Warnings +from .. import util +from ..util import SimpleFrozenList, ensure_path +from ..vocab cimport Vocab +from .kb cimport KnowledgeBase +from .candidate import Candidate as Candidate -def get_candidates(KnowledgeBase kb, span) -> Iterator[Candidate]: - """ - Return candidate entities for a given span by using the text of the span as the alias - and fetching appropriate entries from the index. - This particular function is optimized to work with the built-in KB functionality, - but any other custom candidate generation method can be used in combination with the KB as well. - """ - return kb.get_alias_candidates(span.text) - - -cdef class KnowledgeBase: - """A `KnowledgeBase` instance stores unique identifiers for entities and their textual aliases, +cdef class InMemoryLookupKB(KnowledgeBase): + """An `InMemoryLookupKB` instance stores unique identifiers for entities and their textual aliases, to support entity linking of named entities to real-world concepts. - DOCS: https://spacy.io/api/kb + DOCS: https://spacy.io/api/kb_in_memory """ def __init__(self, Vocab vocab, entity_vector_length): - """Create a KnowledgeBase.""" - self.mem = Pool() - self.entity_vector_length = entity_vector_length + """Create an InMemoryLookupKB.""" + super().__init__(vocab, entity_vector_length) self._entry_index = PreshMap() self._alias_index = PreshMap() - self.vocab = vocab self._create_empty_vectors(dummy_hash=self.vocab.strings[""]) def _initialize_entities(self, int64_t nr_entities): @@ -104,11 +46,6 @@ cdef class KnowledgeBase: self._alias_index = PreshMap(nr_aliases + 1) self._aliases_table = alias_vec(nr_aliases + 1) - @property - def entity_vector_length(self): - """RETURNS (uint64): length of the entity vectors""" - return self.entity_vector_length - def __len__(self): return self.get_size_entities() @@ -286,7 +223,10 @@ cdef class KnowledgeBase: alias_entry.probs = probs self._aliases_table[alias_index] = alias_entry - def get_alias_candidates(self, str alias) -> Iterator[Candidate]: + def get_candidates(self, mention: Span) -> Iterable[Candidate]: + return self.get_alias_candidates(mention.text) # type: ignore + + def get_alias_candidates(self, str alias) -> Iterable[Candidate]: """ Return candidate entities for an alias. Each candidate defines the entity, the original alias, and the prior probability of that alias resolving to that entity. diff --git a/spacy/lang/ca/lemmatizer.py b/spacy/lang/ca/lemmatizer.py index 2fd012912..0f15e6e65 100644 --- a/spacy/lang/ca/lemmatizer.py +++ b/spacy/lang/ca/lemmatizer.py @@ -72,10 +72,10 @@ class CatalanLemmatizer(Lemmatizer): oov_forms.append(form) if not forms: forms.extend(oov_forms) - if not forms and string in lookup_table.keys(): - forms.append(self.lookup_lemmatize(token)[0]) + + # use lookups, and fall back to the token itself if not forms: - forms.append(string) + forms.append(lookup_table.get(string, [string])[0]) forms = list(dict.fromkeys(forms)) self.cache[cache_key] = forms return forms diff --git a/spacy/lang/char_classes.py b/spacy/lang/char_classes.py index 1d204c46c..37c58c85f 100644 --- a/spacy/lang/char_classes.py +++ b/spacy/lang/char_classes.py @@ -280,7 +280,7 @@ _currency = ( _punct = ( r"… …… , : ; \! \? ¿ ؟ ¡ \( \) \[ \] \{ \} < > _ # \* & 。 ？ ！ ， 、 ； ： ～ · । ، ۔ ؛ ٪" ) -_quotes = r'\' " ” “ ` ‘ ´ ’ ‚ , „ » « 「 」 『 』 （ ） 〔 〕 【 】 《 》 〈 〉' +_quotes = r'\' " ” “ ` ‘ ´ ’ ‚ , „ » « 「 」 『 』 （ ） 〔 〕 【 】 《 》 〈 〉 〈 〉 ⟦ ⟧' _hyphens = "- – — -- --- —— ~" # Various symbols like dingbats, but also emoji diff --git a/spacy/lang/fr/lemmatizer.py b/spacy/lang/fr/lemmatizer.py index c6422cf96..a7cbe0bcf 100644 --- a/spacy/lang/fr/lemmatizer.py +++ b/spacy/lang/fr/lemmatizer.py @@ -53,11 +53,16 @@ class FrenchLemmatizer(Lemmatizer): rules = rules_table.get(univ_pos, []) string = string.lower() forms = [] + # first try lookup in table based on upos if string in index: forms.append(string) self.cache[cache_key] = forms return forms + + # then add anything in the exceptions table forms.extend(exceptions.get(string, [])) + + # if nothing found yet, use the rules oov_forms = [] if not forms: for old, new in rules: @@ -69,12 +74,14 @@ class FrenchLemmatizer(Lemmatizer): forms.append(form) else: oov_forms.append(form) + + # if still nothing, add the oov forms from rules if not forms: forms.extend(oov_forms) - if not forms and string in lookup_table.keys(): - forms.append(self.lookup_lemmatize(token)[0]) + + # use lookups, which fall back to the token itself if not forms: - forms.append(string) + forms.append(lookup_table.get(string, [string])[0]) forms = list(dict.fromkeys(forms)) self.cache[cache_key] = forms return forms diff --git a/spacy/lang/grc/__init__.py b/spacy/lang/grc/__init__.py index e83f0c5a5..019b3802e 100644 --- a/spacy/lang/grc/__init__.py +++ b/spacy/lang/grc/__init__.py @@ -1,11 +1,15 @@ from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .stop_words import STOP_WORDS from .lex_attrs import LEX_ATTRS +from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES from ...language import Language, BaseDefaults class AncientGreekDefaults(BaseDefaults): tokenizer_exceptions = TOKENIZER_EXCEPTIONS + prefixes = TOKENIZER_PREFIXES + suffixes = TOKENIZER_SUFFIXES + infixes = TOKENIZER_INFIXES lex_attr_getters = LEX_ATTRS stop_words = STOP_WORDS diff --git a/spacy/lang/grc/punctuation.py b/spacy/lang/grc/punctuation.py new file mode 100644 index 000000000..8f3589e9a --- /dev/null +++ b/spacy/lang/grc/punctuation.py @@ -0,0 +1,46 @@ +from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY +from ..char_classes import LIST_ICONS, ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS +from ..char_classes import CONCAT_QUOTES + +_prefixes = ( + [ + "†", + "⸏", + ] + + LIST_PUNCT + + LIST_ELLIPSES + + LIST_QUOTES + + LIST_CURRENCY + + LIST_ICONS +) + +_suffixes = ( + LIST_PUNCT + + LIST_ELLIPSES + + LIST_QUOTES + + LIST_ICONS + + [ + "†", + "⸎", + r"(?<=[\u1F00-\u1FFF\u0370-\u03FF])[\-\.⸏]", + ] +) + +_infixes = ( + LIST_ELLIPSES + + LIST_ICONS + + [ + r"(?<=[0-9])[+\-\*^](?=[0-9-])", + r"(?<=[{al}{q}])\.(?=[{au}{q}])".format( + al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES + ), + r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA), + r"(?<=[{a}0-9])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS), + r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA), + r"(?<=[\u1F00-\u1FFF\u0370-\u03FF])—", + ] +) + +TOKENIZER_PREFIXES = _prefixes +TOKENIZER_SUFFIXES = _suffixes +TOKENIZER_INFIXES = _infixes diff --git a/spacy/lang/ru/__init__.py b/spacy/lang/ru/__init__.py index c118c26ff..7d17628c4 100644 --- a/spacy/lang/ru/__init__.py +++ b/spacy/lang/ru/__init__.py @@ -28,7 +28,7 @@ class Russian(Language): assigns=["token.lemma"], default_config={ "model": None, - "mode": "pymorphy2", + "mode": "pymorphy3", "overwrite": False, "scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"}, }, diff --git a/spacy/lang/ru/lemmatizer.py b/spacy/lang/ru/lemmatizer.py index 85180b1e4..c37a3a91a 100644 --- a/spacy/lang/ru/lemmatizer.py +++ b/spacy/lang/ru/lemmatizer.py @@ -19,11 +19,11 @@ class RussianLemmatizer(Lemmatizer): model: Optional[Model], name: str = "lemmatizer", *, - mode: str = "pymorphy2", + mode: str = "pymorphy3", overwrite: bool = False, scorer: Optional[Callable] = lemmatizer_score, ) -> None: - if mode == "pymorphy2": + if mode in {"pymorphy2", "pymorphy2_lookup"}: try: from pymorphy2 import MorphAnalyzer except ImportError: @@ -33,6 +33,16 @@ class RussianLemmatizer(Lemmatizer): ) from None if getattr(self, "_morph", None) is None: self._morph = MorphAnalyzer() + elif mode == "pymorphy3": + try: + from pymorphy3 import MorphAnalyzer + except ImportError: + raise ImportError( + "The Russian lemmatizer mode 'pymorphy3' requires the " + "pymorphy3 library. Install it with: pip install pymorphy3" + ) from None + if getattr(self, "_morph", None) is None: + self._morph = MorphAnalyzer() super().__init__( vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer ) @@ -104,6 +114,9 @@ class RussianLemmatizer(Lemmatizer): return [analyses[0].normal_form] return [string] + def pymorphy3_lemmatize(self, token: Token) -> List[str]: + return self.pymorphy2_lemmatize(token) + def oc2ud(oc_tag: str) -> Tuple[str, Dict[str, str]]: gram_map = { diff --git a/spacy/lang/sl/__init__.py b/spacy/lang/sl/__init__.py index 9ddd676bf..0070e9fa1 100644 --- a/spacy/lang/sl/__init__.py +++ b/spacy/lang/sl/__init__.py @@ -1,9 +1,17 @@ +from .lex_attrs import LEX_ATTRS +from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES from .stop_words import STOP_WORDS +from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from ...language import Language, BaseDefaults class SlovenianDefaults(BaseDefaults): stop_words = STOP_WORDS + tokenizer_exceptions = TOKENIZER_EXCEPTIONS + prefixes = TOKENIZER_PREFIXES + infixes = TOKENIZER_INFIXES + suffixes = TOKENIZER_SUFFIXES + lex_attr_getters = LEX_ATTRS class Slovenian(Language): diff --git a/spacy/lang/sl/lex_attrs.py b/spacy/lang/sl/lex_attrs.py new file mode 100644 index 000000000..958152e37 --- /dev/null +++ b/spacy/lang/sl/lex_attrs.py @@ -0,0 +1,145 @@ +from ...attrs import LIKE_NUM +from ...attrs import IS_CURRENCY +import unicodedata + + +_num_words = set( + """ + nula ničla nič ena dva tri štiri pet šest sedem osem + devet deset enajst dvanajst trinajst štirinajst petnajst + šestnajst sedemnajst osemnajst devetnajst dvajset trideset štirideset + petdeset šestdest sedemdeset osemdeset devedeset sto tisoč + milijon bilijon trilijon kvadrilijon nešteto + + en eden enega enemu ennem enim enih enima enimi ene eni eno + dveh dvema dvem dvoje trije treh trem tremi troje štirje štirih štirim štirimi + petih petim petimi šestih šestim šestimi sedmih sedmim sedmimi osmih osmim osmimi + devetih devetim devetimi desetih desetim desetimi enajstih enajstim enajstimi + dvanajstih dvanajstim dvanajstimi trinajstih trinajstim trinajstimi + šestnajstih šestnajstim šestnajstimi petnajstih petnajstim petnajstimi + sedemnajstih sedemnajstim sedemnajstimi osemnajstih osemnajstim osemnajstimi + devetnajstih devetnajstim devetnajstimi dvajsetih dvajsetim dvajsetimi + """.split() +) + +_ordinal_words = set( + """ + prvi drugi tretji četrti peti šesti sedmi osmi + deveti deseti enajsti dvanajsti trinajsti štirinajsti + petnajsti šestnajsti sedemnajsti osemnajsti devetnajsti + dvajseti trideseti štirideseti petdeseti šestdeseti sedemdeseti + osemdeseti devetdeseti stoti tisoči milijonti bilijonti + trilijonti kvadrilijonti nešteti + + prva druga tretja četrta peta šesta sedma osma + deveta deseta enajsta dvanajsta trinajsta štirnajsta + petnajsta šestnajsta sedemnajsta osemnajsta devetnajsta + dvajseta trideseta štirideseta petdeseta šestdeseta sedemdeseta + osemdeseta devetdeseta stota tisoča milijonta bilijonta + trilijonta kvadrilijonta nešteta + + prvo drugo tretje četrto peto šestro sedmo osmo + deveto deseto enajsto dvanajsto trinajsto štirnajsto + petnajsto šestnajsto sedemnajsto osemnajsto devetnajsto + dvajseto trideseto štirideseto petdeseto šestdeseto sedemdeseto + osemdeseto devetdeseto stoto tisočo milijonto bilijonto + trilijonto kvadrilijonto nešteto + + prvega drugega tretjega četrtega petega šestega sedmega osmega + devega desetega enajstega dvanajstega trinajstega štirnajstega + petnajstega šestnajstega sedemnajstega osemnajstega devetnajstega + dvajsetega tridesetega štiridesetega petdesetega šestdesetega sedemdesetega + osemdesetega devetdesetega stotega tisočega milijontega bilijontega + trilijontega kvadrilijontega neštetega + + prvemu drugemu tretjemu četrtemu petemu šestemu sedmemu osmemu devetemu desetemu + enajstemu dvanajstemu trinajstemu štirnajstemu petnajstemu šestnajstemu sedemnajstemu + osemnajstemu devetnajstemu dvajsetemu tridesetemu štiridesetemu petdesetemu šestdesetemu + sedemdesetemu osemdesetemu devetdesetemu stotemu tisočemu milijontemu bilijontemu + trilijontemu kvadrilijontemu neštetemu + + prvem drugem tretjem četrtem petem šestem sedmem osmem devetem desetem + enajstem dvanajstem trinajstem štirnajstem petnajstem šestnajstem sedemnajstem + osemnajstem devetnajstem dvajsetem tridesetem štiridesetem petdesetem šestdesetem + sedemdesetem osemdesetem devetdesetem stotem tisočem milijontem bilijontem + trilijontem kvadrilijontem neštetem + + prvim drugim tretjim četrtim petim šestim sedtim osmim devetim desetim + enajstim dvanajstim trinajstim štirnajstim petnajstim šestnajstim sedemnajstim + osemnajstim devetnajstim dvajsetim tridesetim štiridesetim petdesetim šestdesetim + sedemdesetim osemdesetim devetdesetim stotim tisočim milijontim bilijontim + trilijontim kvadrilijontim neštetim + + prvih drugih tretjih četrthih petih šestih sedmih osmih deveth desetih + enajstih dvanajstih trinajstih štirnajstih petnajstih šestnajstih sedemnajstih + osemnajstih devetnajstih dvajsetih tridesetih štiridesetih petdesetih šestdesetih + sedemdesetih osemdesetih devetdesetih stotih tisočih milijontih bilijontih + trilijontih kvadrilijontih nešteth + + prvima drugima tretjima četrtima petima šestima sedmima osmima devetima desetima + enajstima dvanajstima trinajstima štirnajstima petnajstima šestnajstima sedemnajstima + osemnajstima devetnajstima dvajsetima tridesetima štiridesetima petdesetima šestdesetima + sedemdesetima osemdesetima devetdesetima stotima tisočima milijontima bilijontima + trilijontima kvadrilijontima neštetima + + prve druge četrte pete šeste sedme osme devete desete + enajste dvanajste trinajste štirnajste petnajste šestnajste sedemnajste + osemnajste devetnajste dvajsete tridesete štiridesete petdesete šestdesete + sedemdesete osemdesete devetdesete stote tisoče milijonte bilijonte + trilijonte kvadrilijonte neštete + + prvimi drugimi tretjimi četrtimi petimi šestimi sedtimi osmimi devetimi desetimi + enajstimi dvanajstimi trinajstimi štirnajstimi petnajstimi šestnajstimi sedemnajstimi + osemnajstimi devetnajstimi dvajsetimi tridesetimi štiridesetimi petdesetimi šestdesetimi + sedemdesetimi osemdesetimi devetdesetimi stotimi tisočimi milijontimi bilijontimi + trilijontimi kvadrilijontimi neštetimi + """.split() +) + +_currency_words = set( + """ + evro evra evru evrom evrov evroma evrih evrom evre evri evr eur + cent centa centu cenom centov centoma centih centom cente centi + dolar dolarja dolarji dolarju dolarjem dolarjev dolarjema dolarjih dolarje usd + tolar tolarja tolarji tolarju tolarjem tolarjev tolarjema tolarjih tolarje tol + dinar dinarja dinarji dinarju dinarjem dinarjev dinarjema dinarjih dinarje din + funt funta funti funtu funtom funtov funtoma funtih funte gpb + forint forinta forinti forintu forintom forintov forintoma forintih forinte + zlot zlota zloti zlotu zlotom zlotov zlotoma zlotih zlote + rupij rupija rupiji rupiju rupijem rupijev rupijema rupijih rupije + jen jena jeni jenu jenom jenov jenoma jenih jene + kuna kuni kune kuno kun kunama kunah kunam kunami + marka marki marke markama markah markami + """.split() +) + + +def like_num(text): + if text.startswith(("+", "-", "±", "~")): + text = text[1:] + text = text.replace(",", "").replace(".", "") + if text.isdigit(): + return True + if text.count("/") == 1: + num, denom = text.split("/") + if num.isdigit() and denom.isdigit(): + return True + text_lower = text.lower() + if text_lower in _num_words: + return True + if text_lower in _ordinal_words: + return True + return False + + +def is_currency(text): + text_lower = text.lower() + if text in _currency_words: + return True + for char in text: + if unicodedata.category(char) != "Sc": + return False + return True + + +LEX_ATTRS = {LIKE_NUM: like_num, IS_CURRENCY: is_currency} diff --git a/spacy/lang/sl/punctuation.py b/spacy/lang/sl/punctuation.py new file mode 100644 index 000000000..b6ca1830e --- /dev/null +++ b/spacy/lang/sl/punctuation.py @@ -0,0 +1,84 @@ +from ..char_classes import ( + LIST_ELLIPSES, + LIST_ICONS, + HYPHENS, + LIST_PUNCT, + LIST_QUOTES, + CURRENCY, + UNITS, + PUNCT, + LIST_CURRENCY, + CONCAT_QUOTES, +) +from ..char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA +from ..char_classes import merge_chars +from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES + + +INCLUDE_SPECIAL = ["\\+", "\\/", "\\•", "\\¯", "\\=", "\\×"] + HYPHENS.split("|") + +_prefixes = INCLUDE_SPECIAL + BASE_TOKENIZER_PREFIXES + +_suffixes = ( + INCLUDE_SPECIAL + + LIST_PUNCT + + LIST_ELLIPSES + + LIST_QUOTES + + LIST_ICONS + + [ + r"(?<=°[FfCcKk])\.", + r"(?<=[0-9])(?:{c})".format(c=CURRENCY), + r"(?<=[0-9])(?:{u})".format(u=UNITS), + r"(?<=[{al}{e}{p}(?:{q})])\.".format( + al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT + ), + r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER), + # split initials like J.K. Rowling + r"(?<=[A-Z]\.)(?:[A-Z].)", + ] +) + +# a list of all suffixes following a hyphen that are shouldn't split (eg. BTC-jev) +# source: Obeliks tokenizer - https://github.com/clarinsi/obeliks/blob/master/obeliks/res/TokRulesPart1.txt +CONCAT_QUOTES = CONCAT_QUOTES.replace("'", "") +HYPHENS_PERMITTED = ( + "((a)|(evemu)|(evskega)|(i)|(jevega)|(jevska)|(jevskimi)|(jinemu)|(oma)|(ovim)|" + "(ovski)|(e)|(evi)|(evskem)|(ih)|(jevem)|(jevske)|(jevsko)|(jini)|(ov)|(ovima)|" + "(ovskih)|(em)|(evih)|(evskemu)|(ja)|(jevemu)|(jevskega)|(ji)|(jinih)|(ova)|" + "(ovimi)|(ovskim)|(ema)|(evim)|(evski)|(je)|(jevi)|(jevskem)|(jih)|(jinim)|" + "(ove)|(ovo)|(ovskima)|(ev)|(evima)|(evskih)|(jem)|(jevih)|(jevskemu)|(jin)|" + "(jinima)|(ovega)|(ovska)|(ovskimi)|(eva)|(evimi)|(evskim)|(jema)|(jevim)|" + "(jevski)|(jina)|(jinimi)|(ovem)|(ovske)|(ovsko)|(eve)|(evo)|(evskima)|(jev)|" + "(jevima)|(jevskih)|(jine)|(jino)|(ovemu)|(ovskega)|(u)|(evega)|(evska)|" + "(evskimi)|(jeva)|(jevimi)|(jevskim)|(jinega)|(ju)|(ovi)|(ovskem)|(evem)|" + "(evske)|(evsko)|(jeve)|(jevo)|(jevskima)|(jinem)|(om)|(ovih)|(ovskemu)|" + "(ovec)|(ovca)|(ovcu)|(ovcem)|(ovcev)|(ovcema)|(ovcih)|(ovci)|(ovce)|(ovcimi)|" + "(evec)|(evca)|(evcu)|(evcem)|(evcev)|(evcema)|(evcih)|(evci)|(evce)|(evcimi)|" + "(jevec)|(jevca)|(jevcu)|(jevcem)|(jevcev)|(jevcema)|(jevcih)|(jevci)|(jevce)|" + "(jevcimi)|(ovka)|(ovke)|(ovki)|(ovko)|(ovk)|(ovkama)|(ovkah)|(ovkam)|(ovkami)|" + "(evka)|(evke)|(evki)|(evko)|(evk)|(evkama)|(evkah)|(evkam)|(evkami)|(jevka)|" + "(jevke)|(jevki)|(jevko)|(jevk)|(jevkama)|(jevkah)|(jevkam)|(jevkami)|(timi)|" + "(im)|(ima)|(a)|(imi)|(e)|(o)|(ega)|(ti)|(em)|(tih)|(emu)|(tim)|(i)|(tima)|" + "(ih)|(ta)|(te)|(to)|(tega)|(tem)|(temu))" +) + +_infixes = ( + LIST_ELLIPSES + + LIST_ICONS + + [ + r"(?<=[0-9])[+\-\*^](?=[0-9-])", + r"(?<=[{al}{q}])\.(?=[{au}{q}])".format( + al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES + ), + r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA), + r"(?<=[{a}0-9])(?:{h})(?!{hp}$)(?=[{a}])".format( + a=ALPHA, h=HYPHENS, hp=HYPHENS_PERMITTED + ), + r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA), + ] +) + + +TOKENIZER_PREFIXES = _prefixes +TOKENIZER_SUFFIXES = _suffixes +TOKENIZER_INFIXES = _infixes diff --git a/spacy/lang/sl/stop_words.py b/spacy/lang/sl/stop_words.py index c9004ed5d..8491efcb5 100644 --- a/spacy/lang/sl/stop_words.py +++ b/spacy/lang/sl/stop_words.py @@ -1,326 +1,84 @@ # Source: https://github.com/stopwords-iso/stopwords-sl -# Removed various words that are not normally considered stop words, such as months. STOP_WORDS = set( """ -a -ali -b -bi -bil -bila -bile -bili -bilo -biti -blizu -bo -bodo -bolj -bom -bomo -boste -bova -boš -brez -c -cel -cela -celi -celo -d -da -daleč -dan -danes -do -dober -dobra -dobri -dobro -dokler -dol -dovolj -e -eden -en -ena -ene -eni -enkrat -eno -etc. +a ali + +b bi bil bila bile bili bilo biti blizu bo bodo bojo bolj bom bomo +boste bova boš brez + +c cel cela celi celo + +č če često četrta četrtek četrti četrto čez čigav + +d da daleč dan danes datum deset deseta deseti deseto devet +deveta deveti deveto do dober dobra dobri dobro dokler dol dolg +dolga dolgi dovolj drug druga drugi drugo dva dve + +e eden en ena ene eni enkrat eno etc. + f -g -g. -ga -ga. -gor -gospa -gospod -h -halo -i -idr. -ii -iii -in -iv -ix -iz -j -jaz -je -ji -jih -jim -jo -k -kadarkoli -kaj -kajti -kako -kakor -kamor -kamorkoli -kar -karkoli -katerikoli -kdaj -kdo -kdorkoli -ker -ki -kje -kjer -kjerkoli -ko -koderkoli -koga -komu -kot -l -le -lep -lepa -lepe -lepi -lepo -m -manj -me -med -medtem -mene -mi -midva -midve -mnogo -moj -moja -moje -mora -morajo -moram -moramo -morate -moraš -morem -mu -n -na -nad -naj -najina -najino -najmanj -naju -največ -nam -nas -nato -nazaj -naš -naša -naše -ne -nedavno -nek -neka -nekaj -nekatere -nekateri -nekatero -nekdo -neke -nekega -neki -nekje -neko -nekoga -nekoč -ni -nikamor -nikdar -nikjer -nikoli -nič -nje -njega -njegov -njegova -njegovo -njej -njemu -njen -njena -njeno -nji -njih -njihov -njihova -njihovo -njiju -njim -njo -njun -njuna -njuno -no -nocoj -npr. -o -ob -oba -obe -oboje -od -okoli -on -onadva -one -oni -onidve -oz. -p -pa -po -pod -pogosto -poleg -ponavadi -ponovno -potem -povsod -prbl. -precej -pred -prej -preko -pri -pribl. -približno -proti -r -redko -res -s -saj -sam -sama -same -sami -samo -se -sebe -sebi -sedaj -sem -seveda -si -sicer -skoraj -skozi -smo -so -spet -sta -ste -sva -t -ta -tak -taka -take -taki -tako -takoj -tam -te -tebe -tebi -tega -ti -tista -tiste -tisti -tisto -tj. -tja -to -toda -tu -tudi -tukaj -tvoj -tvoja -tvoje + +g g. ga ga. gor gospa gospod + +h halo + +i idr. ii iii in iv ix iz + +j jaz je ji jih jim jo jutri + +k kadarkoli kaj kajti kako kakor kamor kamorkoli kar karkoli +katerikoli kdaj kdo kdorkoli ker ki kje kjer kjerkoli +ko koder koderkoli koga komu kot kratek kratka kratke kratki + +l lahka lahke lahki lahko le lep lepa lepe lepi lepo leto + +m majhen majhna majhni malce malo manj me med medtem mene +mesec mi midva midve mnogo moj moja moje mora morajo moram +moramo morate moraš morem mu + +n na nad naj najina najino najmanj naju največ nam narobe +nas nato nazaj naš naša naše ne nedavno nedelja nek neka +nekaj nekatere nekateri nekatero nekdo neke nekega neki +nekje neko nekoga nekoč ni nikamor nikdar nikjer nikoli +nič nje njega njegov njegova njegovo njej njemu njen +njena njeno nji njih njihov njihova njihovo njiju njim +njo njun njuna njuno no nocoj npr. + +o ob oba obe oboje od odprt odprta odprti okoli on +onadva one oni onidve osem osma osmi osmo oz. + +p pa pet peta petek peti peto po pod pogosto poleg poln +polna polni polno ponavadi ponedeljek ponovno potem +povsod pozdravljen pozdravljeni prav prava prave pravi +pravo prazen prazna prazno prbl. precej pred prej preko +pri pribl. približno primer pripravljen pripravljena +pripravljeni proti prva prvi prvo + +r ravno redko res reč + +s saj sam sama same sami samo se sebe sebi sedaj sedem +sedma sedmi sedmo sem seveda si sicer skoraj skozi slab sm +so sobota spet sreda srednja srednji sta ste stran stvar sva + +š šest šesta šesti šesto štiri + +t ta tak taka take taki tako takoj tam te tebe tebi tega +težak težka težki težko ti tista tiste tisti tisto tj. +tja to toda torek tretja tretje tretji tri tu tudi tukaj +tvoj tvoja tvoje + u -v -vaju -vam -vas -vaš -vaša -vaše -ve -vedno -vendar -ves -več -vi -vidva -vii -viii -vsa -vsaj -vsak -vsaka -vsakdo -vsake -vsaki -vsakomur -vse -vsega -vsi -vso -včasih -x -z -za -zadaj -zadnji -zakaj -zdaj -zelo -zunaj -č -če -često -čez -čigav -š -ž -že + +v vaju vam vas vaš vaša vaše ve vedno velik velika veliki +veliko vendar ves več vi vidva vii viii visok visoka visoke +visoki vsa vsaj vsak vsaka vsakdo vsake vsaki vsakomur vse +vsega vsi vso včasih včeraj + +x + +z za zadaj zadnji zakaj zaprta zaprti zaprto zdaj zelo zunaj + +ž že """.split() ) diff --git a/spacy/lang/sl/tokenizer_exceptions.py b/spacy/lang/sl/tokenizer_exceptions.py new file mode 100644 index 000000000..3d4109228 --- /dev/null +++ b/spacy/lang/sl/tokenizer_exceptions.py @@ -0,0 +1,272 @@ +from typing import Dict, List +from ..tokenizer_exceptions import BASE_EXCEPTIONS +from ...symbols import ORTH, NORM +from ...util import update_exc + +_exc: Dict[str, List[Dict]] = {} + +_other_exc = { + "t.i.": [{ORTH: "t.", NORM: "tako"}, {ORTH: "i.", NORM: "imenovano"}], + "t.j.": [{ORTH: "t.", NORM: "to"}, {ORTH: "j.", NORM: "je"}], + "T.j.": [{ORTH: "T.", NORM: "to"}, {ORTH: "j.", NORM: "je"}], + "d.o.o.": [ + {ORTH: "d.", NORM: "družba"}, + {ORTH: "o.", NORM: "omejeno"}, + {ORTH: "o.", NORM: "odgovornostjo"}, + ], + "D.O.O.": [ + {ORTH: "D.", NORM: "družba"}, + {ORTH: "O.", NORM: "omejeno"}, + {ORTH: "O.", NORM: "odgovornostjo"}, + ], + "d.n.o.": [ + {ORTH: "d.", NORM: "družba"}, + {ORTH: "n.", NORM: "neomejeno"}, + {ORTH: "o.", NORM: "odgovornostjo"}, + ], + "D.N.O.": [ + {ORTH: "D.", NORM: "družba"}, + {ORTH: "N.", NORM: "neomejeno"}, + {ORTH: "O.", NORM: "odgovornostjo"}, + ], + "d.d.": [{ORTH: "d.", NORM: "delniška"}, {ORTH: "d.", NORM: "družba"}], + "D.D.": [{ORTH: "D.", NORM: "delniška"}, {ORTH: "D.", NORM: "družba"}], + "s.p.": [{ORTH: "s.", NORM: "samostojni"}, {ORTH: "p.", NORM: "podjetnik"}], + "S.P.": [{ORTH: "S.", NORM: "samostojni"}, {ORTH: "P.", NORM: "podjetnik"}], + "l.r.": [{ORTH: "l.", NORM: "lastno"}, {ORTH: "r.", NORM: "ročno"}], + "le-te": [{ORTH: "le"}, {ORTH: "-"}, {ORTH: "te"}], + "Le-te": [{ORTH: "Le"}, {ORTH: "-"}, {ORTH: "te"}], + "le-ti": [{ORTH: "le"}, {ORTH: "-"}, {ORTH: "ti"}], + "Le-ti": [{ORTH: "Le"}, {ORTH: "-"}, {ORTH: "ti"}], + "le-to": [{ORTH: "le"}, {ORTH: "-"}, {ORTH: "to"}], + "Le-to": [{ORTH: "Le"}, {ORTH: "-"}, {ORTH: "to"}], + "le-ta": [{ORTH: "le"}, {ORTH: "-"}, {ORTH: "ta"}], + "Le-ta": [{ORTH: "Le"}, {ORTH: "-"}, {ORTH: "ta"}], + "le-tega": [{ORTH: "le"}, {ORTH: "-"}, {ORTH: "tega"}], + "Le-tega": [{ORTH: "Le"}, {ORTH: "-"}, {ORTH: "tega"}], +} + +_exc.update(_other_exc) + + +for exc_data in [ + {ORTH: "adm.", NORM: "administracija"}, + {ORTH: "aer.", NORM: "aeronavtika"}, + {ORTH: "agr.", NORM: "agronomija"}, + {ORTH: "amer.", NORM: "ameriško"}, + {ORTH: "anat.", NORM: "anatomija"}, + {ORTH: "angl.", NORM: "angleški"}, + {ORTH: "ant.", NORM: "antonim"}, + {ORTH: "antr.", NORM: "antropologija"}, + {ORTH: "apr.", NORM: "april"}, + {ORTH: "arab.", NORM: "arabsko"}, + {ORTH: "arheol.", NORM: "arheologija"}, + {ORTH: "arhit.", NORM: "arhitektura"}, + {ORTH: "avg.", NORM: "avgust"}, + {ORTH: "avstr.", NORM: "avstrijsko"}, + {ORTH: "avt.", NORM: "avtomobilizem"}, + {ORTH: "bibl.", NORM: "biblijsko"}, + {ORTH: "biokem.", NORM: "biokemija"}, + {ORTH: "biol.", NORM: "biologija"}, + {ORTH: "bolg.", NORM: "bolgarski"}, + {ORTH: "bot.", NORM: "botanika"}, + {ORTH: "cit.", NORM: "citat"}, + {ORTH: "daj.", NORM: "dajalnik"}, + {ORTH: "del.", NORM: "deležnik"}, + {ORTH: "ed.", NORM: "ednina"}, + {ORTH: "etn.", NORM: "etnografija"}, + {ORTH: "farm.", NORM: "farmacija"}, + {ORTH: "filat.", NORM: "filatelija"}, + {ORTH: "filoz.", NORM: "filozofija"}, + {ORTH: "fin.", NORM: "finančništvo"}, + {ORTH: "fiz.", NORM: "fizika"}, + {ORTH: "fot.", NORM: "fotografija"}, + {ORTH: "fr.", NORM: "francoski"}, + {ORTH: "friz.", NORM: "frizerstvo"}, + {ORTH: "gastr.", NORM: "gastronomija"}, + {ORTH: "geogr.", NORM: "geografija"}, + {ORTH: "geol.", NORM: "geologija"}, + {ORTH: "geom.", NORM: "geometrija"}, + {ORTH: "germ.", NORM: "germanski"}, + {ORTH: "gl.", NORM: "glej"}, + {ORTH: "glag.", NORM: "glagolski"}, + {ORTH: "glasb.", NORM: "glasba"}, + {ORTH: "gled.", NORM: "gledališče"}, + {ORTH: "gost.", NORM: "gostinstvo"}, + {ORTH: "gozd.", NORM: "gozdarstvo"}, + {ORTH: "gr.", NORM: "grški"}, + {ORTH: "grad.", NORM: "gradbeništvo"}, + {ORTH: "hebr.", NORM: "hebrejsko"}, + {ORTH: "hrv.", NORM: "hrvaško"}, + {ORTH: "ide.", NORM: "indoevropsko"}, + {ORTH: "igr.", NORM: "igre"}, + {ORTH: "im.", NORM: "imenovalnik"}, + {ORTH: "iron.", NORM: "ironično"}, + {ORTH: "it.", NORM: "italijanski"}, + {ORTH: "itd.", NORM: "in tako dalje"}, + {ORTH: "itn.", NORM: "in tako naprej"}, + {ORTH: "ipd.", NORM: "in podobno"}, + {ORTH: "jap.", NORM: "japonsko"}, + {ORTH: "jul.", NORM: "julij"}, + {ORTH: "jun.", NORM: "junij"}, + {ORTH: "kit.", NORM: "kitajsko"}, + {ORTH: "knj.", NORM: "knjižno"}, + {ORTH: "knjiž.", NORM: "knjižno"}, + {ORTH: "kor.", NORM: "koreografija"}, + {ORTH: "lat.", NORM: "latinski"}, + {ORTH: "les.", NORM: "lesna stroka"}, + {ORTH: "lingv.", NORM: "lingvistika"}, + {ORTH: "lit.", NORM: "literarni"}, + {ORTH: "ljubk.", NORM: "ljubkovalno"}, + {ORTH: "lov.", NORM: "lovstvo"}, + {ORTH: "m.", NORM: "moški"}, + {ORTH: "mak.", NORM: "makedonski"}, + {ORTH: "mar.", NORM: "marec"}, + {ORTH: "mat.", NORM: "matematika"}, + {ORTH: "med.", NORM: "medicina"}, + {ORTH: "meh.", NORM: "mehiško"}, + {ORTH: "mest.", NORM: "mestnik"}, + {ORTH: "mdr.", NORM: "med drugim"}, + {ORTH: "min.", NORM: "mineralogija"}, + {ORTH: "mitol.", NORM: "mitologija"}, + {ORTH: "mn.", NORM: "množina"}, + {ORTH: "mont.", NORM: "montanistika"}, + {ORTH: "muz.", NORM: "muzikologija"}, + {ORTH: "nam.", NORM: "namenilnik"}, + {ORTH: "nar.", NORM: "narečno"}, + {ORTH: "nav.", NORM: "navadno"}, + {ORTH: "nedol.", NORM: "nedoločnik"}, + {ORTH: "nedov.", NORM: "nedovršni"}, + {ORTH: "neprav.", NORM: "nepravilno"}, + {ORTH: "nepreh.", NORM: "neprehodno"}, + {ORTH: "neskl.", NORM: "nesklonljiv(o)"}, + {ORTH: "nestrok.", NORM: "nestrokovno"}, + {ORTH: "num.", NORM: "numizmatika"}, + {ORTH: "npr.", NORM: "na primer"}, + {ORTH: "obrt.", NORM: "obrtništvo"}, + {ORTH: "okt.", NORM: "oktober"}, + {ORTH: "or.", NORM: "orodnik"}, + {ORTH: "os.", NORM: "oseba"}, + {ORTH: "otr.", NORM: "otroško"}, + {ORTH: "oz.", NORM: "oziroma"}, + {ORTH: "pal.", NORM: "paleontologija"}, + {ORTH: "papir.", NORM: "papirništvo"}, + {ORTH: "ped.", NORM: "pedagogika"}, + {ORTH: "pisar.", NORM: "pisarniško"}, + {ORTH: "pog.", NORM: "pogovorno"}, + {ORTH: "polit.", NORM: "politika"}, + {ORTH: "polj.", NORM: "poljsko"}, + {ORTH: "poljud.", NORM: "poljudno"}, + {ORTH: "preg.", NORM: "pregovor"}, + {ORTH: "preh.", NORM: "prehodno"}, + {ORTH: "pren.", NORM: "preneseno"}, + {ORTH: "prid.", NORM: "pridevnik"}, + {ORTH: "prim.", NORM: "primerjaj"}, + {ORTH: "prisl.", NORM: "prislov"}, + {ORTH: "psih.", NORM: "psihologija"}, + {ORTH: "psiht.", NORM: "psihiatrija"}, + {ORTH: "rad.", NORM: "radiotehnika"}, + {ORTH: "rač.", NORM: "računalništvo"}, + {ORTH: "rib.", NORM: "ribištvo"}, + {ORTH: "rod.", NORM: "rodilnik"}, + {ORTH: "rus.", NORM: "rusko"}, + {ORTH: "s.", NORM: "srednji"}, + {ORTH: "sam.", NORM: "samostalniški"}, + {ORTH: "sed.", NORM: "sedanjik"}, + {ORTH: "sep.", NORM: "september"}, + {ORTH: "slabš.", NORM: "slabšalno"}, + {ORTH: "slovan.", NORM: "slovansko"}, + {ORTH: "slovaš.", NORM: "slovaško"}, + {ORTH: "srb.", NORM: "srbsko"}, + {ORTH: "star.", NORM: "starinsko"}, + {ORTH: "stil.", NORM: "stilno"}, + {ORTH: "sv.", NORM: "svet(i)"}, + {ORTH: "teh.", NORM: "tehnika"}, + {ORTH: "tisk.", NORM: "tiskarstvo"}, + {ORTH: "tj.", NORM: "to je"}, + {ORTH: "tož.", NORM: "tožilnik"}, + {ORTH: "trg.", NORM: "trgovina"}, + {ORTH: "ukr.", NORM: "ukrajinski"}, + {ORTH: "um.", NORM: "umetnost"}, + {ORTH: "vel.", NORM: "velelnik"}, + {ORTH: "vet.", NORM: "veterina"}, + {ORTH: "vez.", NORM: "veznik"}, + {ORTH: "vn.", NORM: "visokonemško"}, + {ORTH: "voj.", NORM: "vojska"}, + {ORTH: "vrtn.", NORM: "vrtnarstvo"}, + {ORTH: "vulg.", NORM: "vulgarno"}, + {ORTH: "vznes.", NORM: "vzneseno"}, + {ORTH: "zal.", NORM: "založništvo"}, + {ORTH: "zastar.", NORM: "zastarelo"}, + {ORTH: "zgod.", NORM: "zgodovina"}, + {ORTH: "zool.", NORM: "zoologija"}, + {ORTH: "čeb.", NORM: "čebelarstvo"}, + {ORTH: "češ.", NORM: "češki"}, + {ORTH: "člov.", NORM: "človeškost"}, + {ORTH: "šah.", NORM: "šahovski"}, + {ORTH: "šalj.", NORM: "šaljivo"}, + {ORTH: "šp.", NORM: "španski"}, + {ORTH: "špan.", NORM: "špansko"}, + {ORTH: "šport.", NORM: "športni"}, + {ORTH: "štev.", NORM: "števnik"}, + {ORTH: "šved.", NORM: "švedsko"}, + {ORTH: "švic.", NORM: "švicarsko"}, + {ORTH: "ž.", NORM: "ženski"}, + {ORTH: "žarg.", NORM: "žargonsko"}, + {ORTH: "žel.", NORM: "železnica"}, + {ORTH: "živ.", NORM: "živost"}, +]: + _exc[exc_data[ORTH]] = [exc_data] + + +abbrv = """ +Co. Ch. DIPL. DR. Dr. Ev. Inc. Jr. Kr. Mag. M. MR. Mr. Mt. Murr. Npr. OZ. +Opr. Osn. Prim. Roj. ST. Sim. Sp. Sred. St. Sv. Škofl. Tel. UR. Zb. +a. aa. ab. abc. abit. abl. abs. abt. acc. accel. add. adj. adv. aet. afr. akad. al. alban. all. alleg. +alp. alt. alter. alžir. am. an. andr. ang. anh. anon. ans. antrop. apoc. app. approx. apt. ar. arc. arch. +arh. arr. as. asist. assist. assoc. asst. astr. attn. aug. avstral. az. b. bab. bal. bbl. bd. belg. bioinf. +biomed. bk. bl. bn. borg. bp. br. braz. brit. bros. broš. bt. bu. c. ca. cal. can. cand. cantab. cap. capt. +cat. cath. cc. cca. cd. cdr. cdre. cent. cerkv. cert. cf. cfr. ch. chap. chem. chr. chs. cic. circ. civ. cl. +cm. cmd. cnr. co. cod. col. coll. colo. com. comp. con. conc. cond. conn. cons. cont. coop. corr. cost. cp. +cpl. cr. crd. cres. cresc. ct. cu. d. dan. dat. davč. ddr. dec. ded. def. dem. dent. dept. dia. dip. dipl. +dir. disp. diss. div. do. doc. dok. dol. doo. dop. dott. dr. dram. druž. družb. drž. dt. duh. dur. dvr. dwt. e. +ea. ecc. eccl. eccles. econ. edn. egipt. egr. ekon. eksp. el. em. enc. eng. eo. ep. err. esp. esq. est. +et. etc. etnogr. etnol. ev. evfem. evr. ex. exc. excl. exp. expl. ext. exx. f. fa. facs. fak. faks. fas. +fasc. fco. fcp. feb. febr. fec. fed. fem. ff. fff. fid. fig. fil. film. fiziol. fiziot. flam. fm. fo. fol. folk. +frag. fran. franc. fsc. g. ga. gal. gdč. ge. gen. geod. geog. geotehnol. gg. gimn. glas. glav. gnr. go. gor. +gosp. gp. graf. gram. gren. grš. gs. h. hab. hf. hist. ho. hort. i. ia. ib. ibid. id. idr. idridr. ill. imen. +imp. impf. impr. in. inc. incl. ind. indus. inf. inform. ing. init. ins. int. inv. inšp. inštr. inž. is. islam. +ist. ital. iur. iz. izbr. izd. izg. izgr. izr. izv. j. jak. jam. jan. jav. je. jez. jr. jsl. jud. jug. +jugoslovan. jur. juž. jv. jz. k. kal. kan. kand. kat. kdo. kem. kip. kmet. kol. kom. komp. konf. kont. kost. kov. +kp. kpfw. kr. kraj. krat. kub. kult. kv. kval. l. la. lab. lb. ld. let. lib. lik. litt. lj. ljud. ll. loc. log. +loč. lt. ma. madž. mag. manag. manjš. masc. mass. mater. max. maxmax. mb. md. mech. medic. medij. medn. +mehč. mem. menedž. mes. mess. metal. meteor. meteorol. mex. mi. mikr. mil. minn. mio. misc. miss. mit. mk. +mkt. ml. mlad. mlle. mlr. mm. mme. množ. mo. moj. moš. možn. mr. mrd. mrs. ms. msc. msgr. mt. murr. mus. mut. +n. na. nad. nadalj. nadom. nagl. nakl. namer. nan. naniz. nasl. nat. navt. nač. ned. nem. nik. nizoz. nm. nn. +no. nom. norv. notr. nov. novogr. ns. o. ob. obd. obj. oblač. obl. oblik. obr. obraz. obs. obst. obt. obč. oc. +oct. od. odd. odg. odn. odst. odv. oec. off. ok. okla. okr. ont. oo. op. opis. opp. opr. orch. ord. ore. oreg. +org. orient. orig. ork. ort. oseb. osn. ot. ozir. ošk. p. pag. par. para. parc. parl. part. past. pat. pdk. +pen. perf. pert. perz. pesn. pet. pev. pf. pfc. ph. pharm. phil. pis. pl. po. pod. podr. podaljš. pogl. pogoj. pojm. +pok. pokr. pol. poljed. poljub. polu. pom. pomen. pon. ponov. pop. por. port. pos. posl. posn. pov. pp. ppl. pr. +praet. prav. pravopis. pravosl. preb. pred. predl. predm. predp. preds. pref. pregib. prel. prem. premen. prep. +pres. pret. prev. pribl. prih. pril. primerj. primor. prip. pripor. prir. prist. priv. proc. prof. prog. proiz. +prom. pron. prop. prot. protest. prov. ps. pss. pt. publ. pz. q. qld. qu. quad. que. r. racc. rastl. razgl. +razl. razv. rd. red. ref. reg. rel. relig. rep. repr. rer. resp. rest. ret. rev. revol. rež. rim. rist. rkp. rm. +roj. rom. romun. rp. rr. rt. rud. ruš. ry. sal. samogl. san. sc. scen. sci. scr. sdv. seg. sek. sen. sept. ser. +sev. sg. sgt. sh. sig. sigg. sign. sim. sin. sing. sinh. skand. skl. sklad. sklanj. sklep. skr. sl. slik. slov. +slovak. slovn. sn. so. sob. soc. sociol. sod. sopomen. sopr. sor. sov. sovj. sp. spec. spl. spr. spreg. sq. sr. +sre. sred. sredoz. srh. ss. ssp. st. sta. stan. stanstar. stcsl. ste. stim. stol. stom. str. stroj. strok. stsl. +stud. sup. supl. suppl. svet. sz. t. tab. tech. ted. tehn. tehnol. tek. teks. tekst. tel. temp. ten. teol. ter. +term. test. th. theol. tim. tip. tisočl. tit. tl. tol. tolmač. tom. tor. tov. tr. trad. traj. trans. tren. +trib. tril. trop. trp. trž. ts. tt. tu. tur. turiz. tvor. tvorb. tč. u. ul. umet. un. univ. up. upr. ur. urad. +us. ust. utr. v. va. val. var. varn. ven. ver. verb. vest. vezal. vic. vis. viv. viz. viš. vod. vok. vol. vpr. +vrst. vrstil. vs. vv. vzd. vzg. vzh. vzor. w. wed. wg. wk. x. y. z. zah. zaim. zak. zap. zasl. zavar. zač. zb. +združ. zg. zn. znan. znanstv. zoot. zun. zv. zvd. á. é. ć. č. čas. čet. čl. člen. čustv. đ. ľ. ł. ş. ŠT. š. šir. +škofl. škot. šol. št. števil. štud. ů. ű. žen. žival. +""".split() + +for orth in abbrv: + _exc[orth] = [{ORTH: orth}] + + +TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc) diff --git a/spacy/lang/uk/__init__.py b/spacy/lang/uk/__init__.py index 737243b66..bfea9ff69 100644 --- a/spacy/lang/uk/__init__.py +++ b/spacy/lang/uk/__init__.py @@ -29,7 +29,7 @@ class Ukrainian(Language): assigns=["token.lemma"], default_config={ "model": None, - "mode": "pymorphy2", + "mode": "pymorphy3", "overwrite": False, "scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"}, }, diff --git a/spacy/lang/uk/lemmatizer.py b/spacy/lang/uk/lemmatizer.py index a8bc56057..8337e7328 100644 --- a/spacy/lang/uk/lemmatizer.py +++ b/spacy/lang/uk/lemmatizer.py @@ -14,11 +14,11 @@ class UkrainianLemmatizer(RussianLemmatizer): model: Optional[Model], name: str = "lemmatizer", *, - mode: str = "pymorphy2", + mode: str = "pymorphy3", overwrite: bool = False, scorer: Optional[Callable] = lemmatizer_score, ) -> None: - if mode == "pymorphy2": + if mode in {"pymorphy2", "pymorphy2_lookup"}: try: from pymorphy2 import MorphAnalyzer except ImportError: @@ -29,6 +29,17 @@ class UkrainianLemmatizer(RussianLemmatizer): ) from None if getattr(self, "_morph", None) is None: self._morph = MorphAnalyzer(lang="uk") + elif mode == "pymorphy3": + try: + from pymorphy3 import MorphAnalyzer + except ImportError: + raise ImportError( + "The Ukrainian lemmatizer mode 'pymorphy3' requires the " + "pymorphy3 library and dictionaries. Install them with: " + "pip install pymorphy3 pymorphy3-dicts-uk" + ) from None + if getattr(self, "_morph", None) is None: + self._morph = MorphAnalyzer(lang="uk") super().__init__( vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer ) diff --git a/spacy/language.py b/spacy/language.py index 34a06e576..967af1e62 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -1,4 +1,4 @@ -from typing import Iterator, Optional, Any, Dict, Callable, Iterable, Collection +from typing import Iterator, Optional, Any, Dict, Callable, Iterable from typing import Union, Tuple, List, Set, Pattern, Sequence from typing import NoReturn, TYPE_CHECKING, TypeVar, cast, overload @@ -10,6 +10,7 @@ from contextlib import contextmanager from copy import deepcopy from pathlib import Path import warnings + from thinc.api import get_current_ops, Config, CupyOps, Optimizer import srsly import multiprocessing as mp @@ -24,7 +25,7 @@ from .pipe_analysis import validate_attrs, analyze_pipes, print_pipe_analysis from .training import Example, validate_examples from .training.initialize import init_vocab, init_tok2vec from .scorer import Scorer -from .util import registry, SimpleFrozenList, _pipe, raise_error +from .util import registry, SimpleFrozenList, _pipe, raise_error, _DEFAULT_EMPTY_PIPES from .util import SimpleFrozenDict, combine_score_weights, CONFIG_SECTION_ORDER from .util import warn_if_jupyter_cupy from .lang.tokenizer_exceptions import URL_MATCH, BASE_EXCEPTIONS @@ -1698,9 +1699,9 @@ class Language: config: Union[Dict[str, Any], Config] = {}, *, 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, meta: Dict[str, Any] = SimpleFrozenDict(), auto_fill: bool = True, validate: bool = True, @@ -1727,12 +1728,6 @@ class Language: DOCS: https://spacy.io/api/language#from_config """ - if isinstance(disable, str): - disable = [disable] - if isinstance(enable, str): - enable = [enable] - if isinstance(exclude, str): - exclude = [exclude] if auto_fill: config = Config( cls.default_config, section_order=CONFIG_SECTION_ORDER @@ -1877,9 +1872,29 @@ class Language: nlp.vocab.from_bytes(vocab_b) # Resolve disabled/enabled settings. + if isinstance(disable, str): + disable = [disable] + if isinstance(enable, str): + enable = [enable] + if isinstance(exclude, str): + exclude = [exclude] + + # `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, + ) + ) + + # Ensure sets of disabled/enabled pipe names are not contradictory. disabled_pipes = cls._resolve_component_status( - [*config["nlp"]["disabled"], *disable], - [*config["nlp"].get("enabled", []), *enable], + list({*disable, *config["nlp"].get("disabled", [])}), + enable, config["nlp"]["pipeline"], ) nlp._disabled = set(p for p in disabled_pipes if p not in exclude) @@ -2060,18 +2075,13 @@ 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: - raise ValueError( - Errors.E1042.format( - arg1="enable", - arg2="disable", - arg1_values=enable, - arg2_values=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/ml/models/entity_linker.py b/spacy/ml/models/entity_linker.py index d847342a3..299b6bb52 100644 --- a/spacy/ml/models/entity_linker.py +++ b/spacy/ml/models/entity_linker.py @@ -1,11 +1,12 @@ from pathlib import Path from typing import Optional, Callable, Iterable, List, Tuple from thinc.types import Floats2d -from thinc.api import chain, clone, list2ragged, reduce_mean, residual -from thinc.api import Model, Maxout, Linear, noop, tuplify, Ragged +from thinc.api import chain, list2ragged, reduce_mean, residual +from thinc.api import Model, Maxout, Linear, tuplify, Ragged from ...util import registry -from ...kb import KnowledgeBase, Candidate, get_candidates +from ...kb import KnowledgeBase, InMemoryLookupKB +from ...kb import Candidate, get_candidates, get_candidates_batch from ...vocab import Vocab from ...tokens import Span, Doc from ..extract_spans import extract_spans @@ -70,17 +71,18 @@ def span_maker_forward(model, docs: List[Doc], is_train) -> Tuple[Ragged, Callab cands.append((start_token, end_token)) candidates.append(ops.asarray2i(cands)) - candlens = ops.asarray1i([len(cands) for cands in candidates]) - candidates = ops.xp.concatenate(candidates) - outputs = Ragged(candidates, candlens) + lengths = model.ops.asarray1i([len(cands) for cands in candidates]) + out = Ragged(model.ops.flatten(candidates), lengths) # because this is just rearranging docs, the backprop does nothing - return outputs, lambda x: [] + return out, lambda x: [] @registry.misc("spacy.KBFromFile.v1") -def load_kb(kb_path: Path) -> Callable[[Vocab], KnowledgeBase]: - def kb_from_file(vocab): - kb = KnowledgeBase(vocab, entity_vector_length=1) +def load_kb( + kb_path: Path, +) -> Callable[[Vocab], KnowledgeBase]: + def kb_from_file(vocab: Vocab): + kb = InMemoryLookupKB(vocab, entity_vector_length=1) kb.from_disk(kb_path) return kb @@ -88,9 +90,11 @@ def load_kb(kb_path: Path) -> Callable[[Vocab], KnowledgeBase]: @registry.misc("spacy.EmptyKB.v1") -def empty_kb(entity_vector_length: int) -> Callable[[Vocab], KnowledgeBase]: - def empty_kb_factory(vocab): - return KnowledgeBase(vocab=vocab, entity_vector_length=entity_vector_length) +def empty_kb( + entity_vector_length: int, +) -> Callable[[Vocab], KnowledgeBase]: + def empty_kb_factory(vocab: Vocab): + return InMemoryLookupKB(vocab=vocab, entity_vector_length=entity_vector_length) return empty_kb_factory @@ -98,3 +102,10 @@ def empty_kb(entity_vector_length: int) -> Callable[[Vocab], KnowledgeBase]: @registry.misc("spacy.CandidateGenerator.v1") def create_candidates() -> Callable[[KnowledgeBase, Span], Iterable[Candidate]]: return get_candidates + + +@registry.misc("spacy.CandidateBatchGenerator.v1") +def create_candidates_batch() -> Callable[ + [KnowledgeBase, Iterable[Span]], Iterable[Iterable[Candidate]] +]: + return get_candidates_batch diff --git a/spacy/pipeline/edit_tree_lemmatizer.py b/spacy/pipeline/edit_tree_lemmatizer.py index b7d615f6d..12f9b73a3 100644 --- a/spacy/pipeline/edit_tree_lemmatizer.py +++ b/spacy/pipeline/edit_tree_lemmatizer.py @@ -1,7 +1,6 @@ from typing import cast, Any, Callable, Dict, Iterable, List, Optional -from typing import Sequence, Tuple, Union +from typing import Tuple from collections import Counter -from copy import deepcopy from itertools import islice import numpy as np @@ -149,9 +148,7 @@ class EditTreeLemmatizer(TrainablePipe): if not any(len(doc) for doc in docs): # Handle cases where there are no tokens in any docs. n_labels = len(self.cfg["labels"]) - guesses: List[Ints2d] = [ - self.model.ops.alloc((0, n_labels), dtype="i") for doc in docs - ] + guesses: List[Ints2d] = [self.model.ops.alloc2i(0, n_labels) for _ in docs] assert len(guesses) == n_docs return guesses scores = self.model.predict(docs) diff --git a/spacy/pipeline/entity_linker.py b/spacy/pipeline/entity_linker.py index 73a90b268..62845287b 100644 --- a/spacy/pipeline/entity_linker.py +++ b/spacy/pipeline/entity_linker.py @@ -53,9 +53,11 @@ DEFAULT_NEL_MODEL = Config().from_str(default_model_config)["model"] "incl_context": True, "entity_vector_length": 64, "get_candidates": {"@misc": "spacy.CandidateGenerator.v1"}, + "get_candidates_batch": {"@misc": "spacy.CandidateBatchGenerator.v1"}, "overwrite": True, "scorer": {"@scorers": "spacy.entity_linker_scorer.v1"}, "use_gold_ents": True, + "candidates_batch_size": 1, "threshold": None, }, default_score_weights={ @@ -75,9 +77,13 @@ def make_entity_linker( incl_context: bool, entity_vector_length: int, get_candidates: Callable[[KnowledgeBase, Span], Iterable[Candidate]], + get_candidates_batch: Callable[ + [KnowledgeBase, Iterable[Span]], Iterable[Iterable[Candidate]] + ], overwrite: bool, scorer: Optional[Callable], use_gold_ents: bool, + candidates_batch_size: int, threshold: Optional[float] = None, ): """Construct an EntityLinker component. @@ -90,17 +96,21 @@ def make_entity_linker( incl_prior (bool): Whether or not to include prior probabilities from the KB in the model. incl_context (bool): Whether or not to include the local context in the model. entity_vector_length (int): Size of encoding vectors in the KB. - get_candidates (Callable[[KnowledgeBase, "Span"], Iterable[Candidate]]): Function that + get_candidates (Callable[[KnowledgeBase, Span], Iterable[Candidate]]): Function that produces a list of candidates, given a certain knowledge base and a textual mention. + get_candidates_batch ( + Callable[[KnowledgeBase, Iterable[Span]], Iterable[Iterable[Candidate]]], Iterable[Candidate]] + ): Function that produces a list of candidates, given a certain knowledge base and several textual mentions. scorer (Optional[Callable]): The scoring method. use_gold_ents (bool): Whether to copy entities from gold docs or not. If false, another component must provide entity annotations. + candidates_batch_size (int): Size of batches for entity candidate generation. threshold (Optional[float]): Confidence threshold for entity predictions. If confidence is below the threshold, prediction is discarded. If None, predictions are not filtered by any threshold. """ if not model.attrs.get("include_span_maker", False): - # The only difference in arguments here is that use_gold_ents is not available + # The only difference in arguments here is that use_gold_ents and threshold aren't available. return EntityLinker_v1( nlp.vocab, model, @@ -124,9 +134,11 @@ def make_entity_linker( incl_context=incl_context, entity_vector_length=entity_vector_length, get_candidates=get_candidates, + get_candidates_batch=get_candidates_batch, overwrite=overwrite, scorer=scorer, use_gold_ents=use_gold_ents, + candidates_batch_size=candidates_batch_size, threshold=threshold, ) @@ -160,9 +172,13 @@ class EntityLinker(TrainablePipe): incl_context: bool, entity_vector_length: int, get_candidates: Callable[[KnowledgeBase, Span], Iterable[Candidate]], + get_candidates_batch: Callable[ + [KnowledgeBase, Iterable[Span]], Iterable[Iterable[Candidate]] + ], overwrite: bool = BACKWARD_OVERWRITE, scorer: Optional[Callable] = entity_linker_score, use_gold_ents: bool, + candidates_batch_size: int, threshold: Optional[float] = None, ) -> None: """Initialize an entity linker. @@ -178,10 +194,14 @@ class EntityLinker(TrainablePipe): entity_vector_length (int): Size of encoding vectors in the KB. get_candidates (Callable[[KnowledgeBase, Span], Iterable[Candidate]]): Function that produces a list of candidates, given a certain knowledge base and a textual mention. - scorer (Optional[Callable]): The scoring method. Defaults to - Scorer.score_links. + get_candidates_batch ( + Callable[[KnowledgeBase, Iterable[Span]], Iterable[Iterable[Candidate]]], + Iterable[Candidate]] + ): Function that produces a list of candidates, given a certain knowledge base and several textual mentions. + scorer (Optional[Callable]): The scoring method. Defaults to Scorer.score_links. use_gold_ents (bool): Whether to copy entities from gold docs or not. If false, another component must provide entity annotations. + candidates_batch_size (int): Size of batches for entity candidate generation. threshold (Optional[float]): Confidence threshold for entity predictions. If confidence is below the threshold, prediction is discarded. If None, predictions are not filtered by any threshold. DOCS: https://spacy.io/api/entitylinker#init @@ -204,22 +224,27 @@ class EntityLinker(TrainablePipe): self.incl_prior = incl_prior self.incl_context = incl_context self.get_candidates = get_candidates + self.get_candidates_batch = get_candidates_batch self.cfg: Dict[str, Any] = {"overwrite": overwrite} self.distance = CosineDistance(normalize=False) # how many neighbour sentences to take into account - # create an empty KB by default. If you want to load a predefined one, specify it in 'initialize'. + # create an empty KB by default self.kb = empty_kb(entity_vector_length)(self.vocab) self.scorer = scorer self.use_gold_ents = use_gold_ents + self.candidates_batch_size = candidates_batch_size self.threshold = threshold + if candidates_batch_size < 1: + raise ValueError(Errors.E1044) + def set_kb(self, kb_loader: Callable[[Vocab], KnowledgeBase]): """Define the KB of this pipe by providing a function that will create it using this object's vocab.""" if not callable(kb_loader): raise ValueError(Errors.E885.format(arg_type=type(kb_loader))) - self.kb = kb_loader(self.vocab) + self.kb = kb_loader(self.vocab) # type: ignore def validate_kb(self) -> None: # Raise an error if the knowledge base is not initialized. @@ -241,8 +266,8 @@ class EntityLinker(TrainablePipe): get_examples (Callable[[], Iterable[Example]]): Function that returns a representative sample of gold-standard Example objects. nlp (Language): The current nlp object the component is part of. - kb_loader (Callable[[Vocab], KnowledgeBase]): A function that creates a KnowledgeBase from a Vocab instance. - Note that providing this argument, will overwrite all data accumulated in the current KB. + kb_loader (Callable[[Vocab], KnowledgeBase]): A function that creates a KnowledgeBase from a Vocab + instance. Note that providing this argument will overwrite all data accumulated in the current KB. Use this only when loading a KB as-such from file. DOCS: https://spacy.io/api/entitylinker#initialize @@ -419,66 +444,93 @@ class EntityLinker(TrainablePipe): if len(doc) == 0: continue sentences = [s for s in doc.sents] - # Looping through each entity (TODO: rewrite) - for ent in doc.ents: - sent_index = sentences.index(ent.sent) - assert sent_index >= 0 - if self.incl_context: - # get n_neighbour sentences, clipped to the length of the document - start_sentence = max(0, sent_index - self.n_sents) - end_sentence = min(len(sentences) - 1, sent_index + self.n_sents) - start_token = sentences[start_sentence].start - end_token = sentences[end_sentence].end - sent_doc = doc[start_token:end_token].as_doc() - # currently, the context is the same for each entity in a sentence (should be refined) - sentence_encoding = self.model.predict([sent_doc])[0] - sentence_encoding_t = sentence_encoding.T - sentence_norm = xp.linalg.norm(sentence_encoding_t) - entity_count += 1 - if ent.label_ in self.labels_discard: - # ignoring this entity - setting to NIL - final_kb_ids.append(self.NIL) - else: - candidates = list(self.get_candidates(self.kb, ent)) - if not candidates: - # no prediction possible for this entity - setting to NIL - final_kb_ids.append(self.NIL) - elif len(candidates) == 1 and self.threshold is None: - # shortcut for efficiency reasons: take the 1 candidate - final_kb_ids.append(candidates[0].entity_) - else: - random.shuffle(candidates) - # set all prior probabilities to 0 if incl_prior=False - prior_probs = xp.asarray([c.prior_prob for c in candidates]) - if not self.incl_prior: - prior_probs = xp.asarray([0.0 for _ in candidates]) - scores = prior_probs - # add in similarity from the context - if self.incl_context: - entity_encodings = xp.asarray( - [c.entity_vector for c in candidates] - ) - entity_norm = xp.linalg.norm(entity_encodings, axis=1) - if len(entity_encodings) != len(prior_probs): - raise RuntimeError( - Errors.E147.format( - method="predict", - msg="vectors not of equal length", - ) - ) - # cosine similarity - sims = xp.dot(entity_encodings, sentence_encoding_t) / ( - sentence_norm * entity_norm - ) - if sims.shape != prior_probs.shape: - raise ValueError(Errors.E161) - scores = prior_probs + sims - (prior_probs * sims) - final_kb_ids.append( - candidates[scores.argmax().item()].entity_ - if self.threshold is None or scores.max() >= self.threshold - else EntityLinker.NIL + # Loop over entities in batches. + for ent_idx in range(0, len(doc.ents), self.candidates_batch_size): + ent_batch = doc.ents[ent_idx : ent_idx + self.candidates_batch_size] + + # Look up candidate entities. + valid_ent_idx = [ + idx + for idx in range(len(ent_batch)) + if ent_batch[idx].label_ not in self.labels_discard + ] + + batch_candidates = list( + self.get_candidates_batch( + self.kb, [ent_batch[idx] for idx in valid_ent_idx] + ) + if self.candidates_batch_size > 1 + else [ + self.get_candidates(self.kb, ent_batch[idx]) + for idx in valid_ent_idx + ] + ) + + # Looping through each entity in batch (TODO: rewrite) + for j, ent in enumerate(ent_batch): + sent_index = sentences.index(ent.sent) + assert sent_index >= 0 + + if self.incl_context: + # get n_neighbour sentences, clipped to the length of the document + start_sentence = max(0, sent_index - self.n_sents) + end_sentence = min( + len(sentences) - 1, sent_index + self.n_sents ) + start_token = sentences[start_sentence].start + end_token = sentences[end_sentence].end + sent_doc = doc[start_token:end_token].as_doc() + # currently, the context is the same for each entity in a sentence (should be refined) + sentence_encoding = self.model.predict([sent_doc])[0] + sentence_encoding_t = sentence_encoding.T + sentence_norm = xp.linalg.norm(sentence_encoding_t) + entity_count += 1 + if ent.label_ in self.labels_discard: + # ignoring this entity - setting to NIL + final_kb_ids.append(self.NIL) + else: + candidates = list(batch_candidates[j]) + if not candidates: + # no prediction possible for this entity - setting to NIL + final_kb_ids.append(self.NIL) + elif len(candidates) == 1 and self.threshold is None: + # shortcut for efficiency reasons: take the 1 candidate + final_kb_ids.append(candidates[0].entity_) + else: + random.shuffle(candidates) + # set all prior probabilities to 0 if incl_prior=False + prior_probs = xp.asarray([c.prior_prob for c in candidates]) + if not self.incl_prior: + prior_probs = xp.asarray([0.0 for _ in candidates]) + scores = prior_probs + # add in similarity from the context + if self.incl_context: + entity_encodings = xp.asarray( + [c.entity_vector for c in candidates] + ) + entity_norm = xp.linalg.norm(entity_encodings, axis=1) + if len(entity_encodings) != len(prior_probs): + raise RuntimeError( + Errors.E147.format( + method="predict", + msg="vectors not of equal length", + ) + ) + # cosine similarity + sims = xp.dot(entity_encodings, sentence_encoding_t) / ( + sentence_norm * entity_norm + ) + if sims.shape != prior_probs.shape: + raise ValueError(Errors.E161) + scores = prior_probs + sims - (prior_probs * sims) + final_kb_ids.append( + candidates[scores.argmax().item()].entity_ + if self.threshold is None + or scores.max() >= self.threshold + else EntityLinker.NIL + ) + if not (len(final_kb_ids) == entity_count): err = Errors.E147.format( method="predict", msg="result variables not of equal length" diff --git a/spacy/pipeline/entityruler.py b/spacy/pipeline/entityruler.py index 3cb1ca676..8154a077d 100644 --- a/spacy/pipeline/entityruler.py +++ b/spacy/pipeline/entityruler.py @@ -1,6 +1,5 @@ -import warnings from typing import Optional, Union, List, Dict, Tuple, Iterable, Any, Callable, Sequence -from typing import cast +import warnings from collections import defaultdict from pathlib import Path import srsly @@ -317,7 +316,7 @@ class EntityRuler(Pipe): phrase_pattern["id"] = ent_id phrase_patterns.append(phrase_pattern) for entry in token_patterns + phrase_patterns: # type: ignore[operator] - label = entry["label"] + label = entry["label"] # type: ignore if "id" in entry: ent_label = label label = self._create_label(label, entry["id"]) diff --git a/spacy/pipeline/legacy/entity_linker.py b/spacy/pipeline/legacy/entity_linker.py index 2f8a1f8ea..c14dfa1db 100644 --- a/spacy/pipeline/legacy/entity_linker.py +++ b/spacy/pipeline/legacy/entity_linker.py @@ -68,8 +68,7 @@ class EntityLinker_v1(TrainablePipe): entity_vector_length (int): Size of encoding vectors in the KB. get_candidates (Callable[[KnowledgeBase, Span], Iterable[Candidate]]): Function that produces a list of candidates, given a certain knowledge base and a textual mention. - scorer (Optional[Callable]): The scoring method. Defaults to - Scorer.score_links. + scorer (Optional[Callable]): The scoring method. Defaults to Scorer.score_links. DOCS: https://spacy.io/api/entitylinker#init """ self.vocab = vocab @@ -115,7 +114,7 @@ class EntityLinker_v1(TrainablePipe): get_examples (Callable[[], Iterable[Example]]): Function that returns a representative sample of gold-standard Example objects. nlp (Language): The current nlp object the component is part of. - kb_loader (Callable[[Vocab], KnowledgeBase]): A function that creates a KnowledgeBase from a Vocab instance. + kb_loader (Callable[[Vocab], KnowledgeBase]): A function that creates an InMemoryLookupKB from a Vocab instance. Note that providing this argument, will overwrite all data accumulated in the current KB. Use this only when loading a KB as-such from file. diff --git a/spacy/pipeline/spancat.py b/spacy/pipeline/spancat.py index 1b7a9eecb..956bbb72c 100644 --- a/spacy/pipeline/spancat.py +++ b/spacy/pipeline/spancat.py @@ -26,17 +26,17 @@ scorer = {"@layers": "spacy.LinearLogistic.v1"} hidden_size = 128 [model.tok2vec] -@architectures = "spacy.Tok2Vec.v1" +@architectures = "spacy.Tok2Vec.v2" [model.tok2vec.embed] -@architectures = "spacy.MultiHashEmbed.v1" +@architectures = "spacy.MultiHashEmbed.v2" width = 96 rows = [5000, 2000, 1000, 1000] attrs = ["ORTH", "PREFIX", "SUFFIX", "SHAPE"] include_static_vectors = false [model.tok2vec.encode] -@architectures = "spacy.MaxoutWindowEncoder.v1" +@architectures = "spacy.MaxoutWindowEncoder.v2" width = ${model.tok2vec.embed.width} window_size = 1 maxout_pieces = 3 @@ -133,6 +133,9 @@ def make_spancat( spans_key (str): Key of the doc.spans dict to save the spans under. During initialization and training, the component will look for spans on the reference document under the same key. + scorer (Optional[Callable]): The scoring method. Defaults to + Scorer.score_spans for the Doc.spans[spans_key] with overlapping + spans allowed. threshold (float): Minimum probability to consider a prediction positive. Spans with a positive prediction will be saved on the Doc. Defaults to 0.5. diff --git a/spacy/pipeline/textcat.py b/spacy/pipeline/textcat.py index c45f819fc..4023c4456 100644 --- a/spacy/pipeline/textcat.py +++ b/spacy/pipeline/textcat.py @@ -24,8 +24,8 @@ single_label_default_config = """ [model.tok2vec.embed] @architectures = "spacy.MultiHashEmbed.v2" width = 64 -rows = [2000, 2000, 1000, 1000, 1000, 1000] -attrs = ["ORTH", "LOWER", "PREFIX", "SUFFIX", "SHAPE", "ID"] +rows = [2000, 2000, 500, 1000, 500] +attrs = ["NORM", "LOWER", "PREFIX", "SUFFIX", "SHAPE"] include_static_vectors = false [model.tok2vec.encode] @@ -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 diff --git a/spacy/pipeline/textcat_multilabel.py b/spacy/pipeline/textcat_multilabel.py index e33a885f8..eb83d9cb7 100644 --- a/spacy/pipeline/textcat_multilabel.py +++ b/spacy/pipeline/textcat_multilabel.py @@ -19,17 +19,17 @@ multi_label_default_config = """ @architectures = "spacy.TextCatEnsemble.v2" [model.tok2vec] -@architectures = "spacy.Tok2Vec.v1" +@architectures = "spacy.Tok2Vec.v2" [model.tok2vec.embed] @architectures = "spacy.MultiHashEmbed.v2" width = 64 -rows = [2000, 2000, 1000, 1000, 1000, 1000] -attrs = ["ORTH", "LOWER", "PREFIX", "SUFFIX", "SHAPE", "ID"] +rows = [2000, 2000, 500, 1000, 500] +attrs = ["NORM", "LOWER", "PREFIX", "SUFFIX", "SHAPE"] include_static_vectors = false [model.tok2vec.encode] -@architectures = "spacy.MaxoutWindowEncoder.v1" +@architectures = "spacy.MaxoutWindowEncoder.v2" width = ${model.tok2vec.embed.width} window_size = 1 maxout_pieces = 3 @@ -96,8 +96,8 @@ def make_multilabel_textcat( model: Model[List[Doc], List[Floats2d]], threshold: float, scorer: Optional[Callable], -) -> "TextCategorizer": - """Create a TextCategorizer component. The text categorizer predicts categories +) -> "MultiLabel_TextCategorizer": + """Create a MultiLabel_TextCategorizer component. The text categorizer predicts categories over a whole document. It can learn one or more labels, and the labels are considered to be non-mutually exclusive, which means that there can be zero or more labels per doc). @@ -105,6 +105,7 @@ def make_multilabel_textcat( model (Model[List[Doc], List[Floats2d]]): A model instance that predicts scores for each category. threshold (float): Cutoff to consider a prediction "positive". + scorer (Optional[Callable]): The scoring method. """ return MultiLabel_TextCategorizer( nlp.vocab, model, name, threshold=threshold, scorer=scorer @@ -147,6 +148,7 @@ class MultiLabel_TextCategorizer(TextCategorizer): name (str): The component instance name, used to add entries to the losses during training. threshold (float): Cutoff to consider a prediction "positive". + scorer (Optional[Callable]): The scoring method. DOCS: https://spacy.io/api/textcategorizer#init """ diff --git a/spacy/pipeline/tok2vec.py b/spacy/pipeline/tok2vec.py index 2e3dde3cb..c742aaeaa 100644 --- a/spacy/pipeline/tok2vec.py +++ b/spacy/pipeline/tok2vec.py @@ -123,9 +123,6 @@ class Tok2Vec(TrainablePipe): width = self.model.get_dim("nO") return [self.model.ops.alloc((0, width)) for doc in docs] tokvecs = self.model.predict(docs) - batch_id = Tok2VecListener.get_batch_id(docs) - for listener in self.listeners: - listener.receive(batch_id, tokvecs, _empty_backprop) return tokvecs def set_annotations(self, docs: Sequence[Doc], tokvecses) -> None: @@ -286,8 +283,19 @@ class Tok2VecListener(Model): def forward(model: Tok2VecListener, inputs, is_train: bool): """Supply the outputs from the upstream Tok2Vec component.""" if is_train: - model.verify_inputs(inputs) - return model._outputs, model._backprop + # This might occur during training when the tok2vec layer is frozen / hasn't been updated. + # In that case, it should be set to "annotating" so we can retrieve the embeddings from the doc. + if model._batch_id is None: + outputs = [] + for doc in inputs: + if doc.tensor.size == 0: + raise ValueError(Errors.E203.format(name="tok2vec")) + else: + outputs.append(doc.tensor) + return outputs, _empty_backprop + else: + model.verify_inputs(inputs) + return model._outputs, model._backprop else: # This is pretty grim, but it's hard to do better :(. # It's hard to avoid relying on the doc.tensor attribute, because the @@ -306,7 +314,7 @@ def forward(model: Tok2VecListener, inputs, is_train: bool): outputs.append(model.ops.alloc2f(len(doc), width)) else: outputs.append(doc.tensor) - return outputs, lambda dX: [] + return outputs, _empty_backprop def _empty_backprop(dX): # for pickling diff --git a/spacy/schemas.py b/spacy/schemas.py index 048082134..c824d76b9 100644 --- a/spacy/schemas.py +++ b/spacy/schemas.py @@ -181,12 +181,12 @@ class TokenPatternNumber(BaseModel): IS_SUBSET: Optional[List[StrictInt]] = Field(None, alias="is_subset") IS_SUPERSET: Optional[List[StrictInt]] = Field(None, alias="is_superset") INTERSECTS: Optional[List[StrictInt]] = Field(None, alias="intersects") - EQ: Union[StrictInt, StrictFloat] = Field(None, alias="==") - NEQ: Union[StrictInt, StrictFloat] = Field(None, alias="!=") - GEQ: Union[StrictInt, StrictFloat] = Field(None, alias=">=") - LEQ: Union[StrictInt, StrictFloat] = Field(None, alias="<=") - GT: Union[StrictInt, StrictFloat] = Field(None, alias=">") - LT: Union[StrictInt, StrictFloat] = Field(None, alias="<") + EQ: Optional[Union[StrictInt, StrictFloat]] = Field(None, alias="==") + NEQ: Optional[Union[StrictInt, StrictFloat]] = Field(None, alias="!=") + GEQ: Optional[Union[StrictInt, StrictFloat]] = Field(None, alias=">=") + LEQ: Optional[Union[StrictInt, StrictFloat]] = Field(None, alias="<=") + GT: Optional[Union[StrictInt, StrictFloat]] = Field(None, alias=">") + LT: Optional[Union[StrictInt, StrictFloat]] = Field(None, alias="<") class Config: extra = "forbid" @@ -430,7 +430,7 @@ class ProjectConfigAssetURL(BaseModel): # fmt: off dest: StrictStr = Field(..., title="Destination of downloaded asset") url: Optional[StrictStr] = Field(None, title="URL of asset") - checksum: str = Field(None, title="MD5 hash of file", regex=r"([a-fA-F\d]{32})") + checksum: Optional[str] = Field(None, title="MD5 hash of file", regex=r"([a-fA-F\d]{32})") description: StrictStr = Field("", title="Description of asset") # fmt: on @@ -438,7 +438,7 @@ class ProjectConfigAssetURL(BaseModel): class ProjectConfigAssetGit(BaseModel): # fmt: off git: ProjectConfigAssetGitItem = Field(..., title="Git repo information") - checksum: str = Field(None, title="MD5 hash of file", regex=r"([a-fA-F\d]{32})") + checksum: Optional[str] = Field(None, title="MD5 hash of file", regex=r"([a-fA-F\d]{32})") description: Optional[StrictStr] = Field(None, title="Description of asset") # fmt: on @@ -508,9 +508,9 @@ class DocJSONSchema(BaseModel): None, title="Indices of sentences' start and end indices" ) text: StrictStr = Field(..., title="Document text") - spans: Dict[StrictStr, List[Dict[StrictStr, Union[StrictStr, StrictInt]]]] = Field( - None, title="Span information - end/start indices, label, KB ID" - ) + spans: Optional[ + Dict[StrictStr, List[Dict[StrictStr, Union[StrictStr, StrictInt]]]] + ] = Field(None, title="Span information - end/start indices, label, KB ID") tokens: List[Dict[StrictStr, Union[StrictStr, StrictInt]]] = Field( ..., title="Token information - ID, start, annotations" ) @@ -519,9 +519,9 @@ class DocJSONSchema(BaseModel): title="Any custom data stored in the document's _ attribute", alias="_", ) - underscore_token: Optional[Dict[StrictStr, Dict[StrictStr, Any]]] = Field( + underscore_token: Optional[Dict[StrictStr, List[Dict[StrictStr, Any]]]] = Field( None, title="Any custom data stored in the token's _ attribute" ) - underscore_span: Optional[Dict[StrictStr, Dict[StrictStr, Any]]] = Field( + underscore_span: Optional[Dict[StrictStr, List[Dict[StrictStr, Any]]]] = Field( None, title="Any custom data stored in the span's _ attribute" ) 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 742bfcc6a..0fc74243d 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -333,16 +333,24 @@ def ro_tokenizer(): @pytest.fixture(scope="session") def ru_tokenizer(): - pytest.importorskip("pymorphy2") + pytest.importorskip("pymorphy3") return get_lang_class("ru")().tokenizer @pytest.fixture def ru_lemmatizer(): - pytest.importorskip("pymorphy2") + pytest.importorskip("pymorphy3") return get_lang_class("ru")().add_pipe("lemmatizer") +@pytest.fixture +def ru_lookup_lemmatizer(): + pytest.importorskip("pymorphy2") + return get_lang_class("ru")().add_pipe( + "lemmatizer", config={"mode": "pymorphy2_lookup"} + ) + + @pytest.fixture(scope="session") def sa_tokenizer(): return get_lang_class("sa")().tokenizer @@ -411,15 +419,24 @@ def ky_tokenizer(): @pytest.fixture(scope="session") def uk_tokenizer(): - pytest.importorskip("pymorphy2") + pytest.importorskip("pymorphy3") return get_lang_class("uk")().tokenizer @pytest.fixture def uk_lemmatizer(): + pytest.importorskip("pymorphy3") + pytest.importorskip("pymorphy3_dicts_uk") + return get_lang_class("uk")().add_pipe("lemmatizer") + + +@pytest.fixture +def uk_lookup_lemmatizer(): pytest.importorskip("pymorphy2") pytest.importorskip("pymorphy2_dicts_uk") - return get_lang_class("uk")().add_pipe("lemmatizer") + return get_lang_class("uk")().add_pipe( + "lemmatizer", config={"mode": "pymorphy2_lookup"} + ) @pytest.fixture(scope="session") diff --git a/spacy/tests/doc/test_doc_api.py b/spacy/tests/doc/test_doc_api.py index a64ab2ba8..38003dea9 100644 --- a/spacy/tests/doc/test_doc_api.py +++ b/spacy/tests/doc/test_doc_api.py @@ -82,6 +82,21 @@ def test_issue2396(en_vocab): assert (span.get_lca_matrix() == matrix).all() +@pytest.mark.issue(11499) +def test_init_args_unmodified(en_vocab): + words = ["A", "sentence"] + ents = ["B-TYPE1", ""] + sent_starts = [True, False] + Doc( + vocab=en_vocab, + words=words, + ents=ents, + sent_starts=sent_starts, + ) + assert ents == ["B-TYPE1", ""] + assert sent_starts == [True, False] + + @pytest.mark.parametrize("text", ["-0.23", "+123,456", "±1"]) @pytest.mark.parametrize("lang_cls", [English, MultiLanguage]) @pytest.mark.issue(2782) diff --git a/spacy/tests/doc/test_json_doc_conversion.py b/spacy/tests/doc/test_json_doc_conversion.py index 0d7c061c9..11a1817e6 100644 --- a/spacy/tests/doc/test_json_doc_conversion.py +++ b/spacy/tests/doc/test_json_doc_conversion.py @@ -128,7 +128,9 @@ def test_doc_to_json_with_token_span_attributes(doc): doc._.json_test1 = "hello world" doc._.json_test2 = [1, 2, 3] doc[0:1]._.span_test = "span_attribute" + doc[0:2]._.span_test = "span_attribute_2" doc[0]._.token_test = 117 + doc[1]._.token_test = 118 doc.spans["span_group"] = [doc[0:1]] json_doc = doc.to_json( underscore=["json_test1", "json_test2", "token_test", "span_test"] @@ -139,8 +141,10 @@ def test_doc_to_json_with_token_span_attributes(doc): assert json_doc["_"]["json_test2"] == [1, 2, 3] assert "underscore_token" in json_doc assert "underscore_span" in json_doc - assert json_doc["underscore_token"]["token_test"]["value"] == 117 - assert json_doc["underscore_span"]["span_test"]["value"] == "span_attribute" + assert json_doc["underscore_token"]["token_test"][0]["value"] == 117 + assert json_doc["underscore_token"]["token_test"][1]["value"] == 118 + assert json_doc["underscore_span"]["span_test"][0]["value"] == "span_attribute" + assert json_doc["underscore_span"]["span_test"][1]["value"] == "span_attribute_2" assert len(schemas.validate(schemas.DocJSONSchema, json_doc)) == 0 assert srsly.json_loads(srsly.json_dumps(json_doc)) == json_doc @@ -161,8 +165,8 @@ def test_doc_to_json_with_custom_user_data(doc): assert json_doc["_"]["json_test"] == "hello world" assert "underscore_token" in json_doc assert "underscore_span" in json_doc - assert json_doc["underscore_token"]["token_test"]["value"] == 117 - assert json_doc["underscore_span"]["span_test"]["value"] == "span_attribute" + assert json_doc["underscore_token"]["token_test"][0]["value"] == 117 + assert json_doc["underscore_span"]["span_test"][0]["value"] == "span_attribute" assert len(schemas.validate(schemas.DocJSONSchema, json_doc)) == 0 assert srsly.json_loads(srsly.json_dumps(json_doc)) == json_doc @@ -181,8 +185,8 @@ def test_doc_to_json_with_token_span_same_identifier(doc): assert json_doc["_"]["my_ext"] == "hello world" assert "underscore_token" in json_doc assert "underscore_span" in json_doc - assert json_doc["underscore_token"]["my_ext"]["value"] == 117 - assert json_doc["underscore_span"]["my_ext"]["value"] == "span_attribute" + assert json_doc["underscore_token"]["my_ext"][0]["value"] == 117 + assert json_doc["underscore_span"]["my_ext"][0]["value"] == "span_attribute" assert len(schemas.validate(schemas.DocJSONSchema, json_doc)) == 0 assert srsly.json_loads(srsly.json_dumps(json_doc)) == json_doc @@ -195,10 +199,9 @@ def test_doc_to_json_with_token_attributes_missing(doc): doc[0]._.token_test = 117 json_doc = doc.to_json(underscore=["span_test"]) - assert "underscore_token" in json_doc assert "underscore_span" in json_doc - assert json_doc["underscore_span"]["span_test"]["value"] == "span_attribute" - assert "token_test" not in json_doc["underscore_token"] + assert json_doc["underscore_span"]["span_test"][0]["value"] == "span_attribute" + assert "underscore_token" not in json_doc assert len(schemas.validate(schemas.DocJSONSchema, json_doc)) == 0 @@ -283,7 +286,9 @@ def test_json_to_doc_with_token_span_attributes(doc): doc._.json_test1 = "hello world" doc._.json_test2 = [1, 2, 3] doc[0:1]._.span_test = "span_attribute" + doc[0:2]._.span_test = "span_attribute_2" doc[0]._.token_test = 117 + doc[1]._.token_test = 118 json_doc = doc.to_json( underscore=["json_test1", "json_test2", "token_test", "span_test"] @@ -295,7 +300,9 @@ def test_json_to_doc_with_token_span_attributes(doc): assert new_doc._.json_test1 == "hello world" assert new_doc._.json_test2 == [1, 2, 3] assert new_doc[0]._.token_test == 117 + assert new_doc[1]._.token_test == 118 assert new_doc[0:1]._.span_test == "span_attribute" + assert new_doc[0:2]._.span_test == "span_attribute_2" assert new_doc.user_data == doc.user_data assert new_doc.to_bytes(exclude=["user_data"]) == doc.to_bytes( exclude=["user_data"] @@ -363,3 +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/grc/test_tokenizer.py b/spacy/tests/lang/grc/test_tokenizer.py new file mode 100644 index 000000000..3df5b546b --- /dev/null +++ b/spacy/tests/lang/grc/test_tokenizer.py @@ -0,0 +1,18 @@ +import pytest + + +# fmt: off +GRC_TOKEN_EXCEPTION_TESTS = [ + ("τὸ 〈τῆς〉 φιλοσοφίας ἔργον ἔνιοί φασιν ἀπὸ ⟦βαρβάρων⟧ ἄρξαι.", ["τὸ", "〈", "τῆς", "〉", "φιλοσοφίας", "ἔργον", "ἔνιοί", "φασιν", "ἀπὸ", "⟦", "βαρβάρων", "⟧", "ἄρξαι", "."]), + ("τὴν δὲ τῶν Αἰγυπτίων φιλοσοφίαν εἶναι τοιαύτην περί τε †θεῶν† καὶ ὑπὲρ δικαιοσύνης.", ["τὴν", "δὲ", "τῶν", "Αἰγυπτίων", "φιλοσοφίαν", "εἶναι", "τοιαύτην", "περί", "τε", "†", "θεῶν", "†", "καὶ", "ὑπὲρ", "δικαιοσύνης", "."]), + ("⸏πόσις δ' Ἐρεχθεύς ἐστί μοι σεσωσμένος⸏", ["⸏", "πόσις", "δ'", "Ἐρεχθεύς", "ἐστί", "μοι", "σεσωσμένος", "⸏"]), + ("⸏ὔπνον ἴδωμεν⸎", ["⸏", "ὔπνον", "ἴδωμεν", "⸎"]), +] +# fmt: on + + +@pytest.mark.parametrize("text,expected_tokens", GRC_TOKEN_EXCEPTION_TESTS) +def test_grc_tokenizer(grc_tokenizer, text, expected_tokens): + tokens = grc_tokenizer(text) + token_list = [token.text for token in tokens if not token.is_space] + assert expected_tokens == token_list diff --git a/spacy/tests/lang/ru/test_lemmatizer.py b/spacy/tests/lang/ru/test_lemmatizer.py index 9ca7f441b..e82fd4f8c 100644 --- a/spacy/tests/lang/ru/test_lemmatizer.py +++ b/spacy/tests/lang/ru/test_lemmatizer.py @@ -78,3 +78,17 @@ def test_ru_lemmatizer_punct(ru_lemmatizer): assert ru_lemmatizer.pymorphy2_lemmatize(doc[0]) == ['"'] doc = Doc(ru_lemmatizer.vocab, words=["»"], pos=["PUNCT"]) assert ru_lemmatizer.pymorphy2_lemmatize(doc[0]) == ['"'] + + +def test_ru_doc_lookup_lemmatization(ru_lookup_lemmatizer): + words = ["мама", "мыла", "раму"] + pos = ["NOUN", "VERB", "NOUN"] + morphs = [ + "Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing", + "Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act", + "Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing", + ] + doc = Doc(ru_lookup_lemmatizer.vocab, words=words, pos=pos, morphs=morphs) + doc = ru_lookup_lemmatizer(doc) + lemmas = [token.lemma_ for token in doc] + assert lemmas == ["мама", "мыла", "раму"] diff --git a/spacy/tests/lang/sl/test_text.py b/spacy/tests/lang/sl/test_text.py index ddc5b6b5d..a2a932077 100644 --- a/spacy/tests/lang/sl/test_text.py +++ b/spacy/tests/lang/sl/test_text.py @@ -20,7 +20,6 @@ od katerih so te svoboščine odvisne, assert len(tokens) == 116 -@pytest.mark.xfail def test_ordinal_number(sl_tokenizer): text = "10. decembra 1948" tokens = sl_tokenizer(text) diff --git a/spacy/tests/lang/uk/test_lemmatizer.py b/spacy/tests/lang/uk/test_lemmatizer.py index 57dd4198a..788744aa1 100644 --- a/spacy/tests/lang/uk/test_lemmatizer.py +++ b/spacy/tests/lang/uk/test_lemmatizer.py @@ -9,3 +9,11 @@ def test_uk_lemmatizer(uk_lemmatizer): """Check that the default uk lemmatizer runs.""" doc = Doc(uk_lemmatizer.vocab, words=["a", "b", "c"]) 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] diff --git a/spacy/tests/pipeline/test_entity_linker.py b/spacy/tests/pipeline/test_entity_linker.py index 82bc976bb..99f164f15 100644 --- a/spacy/tests/pipeline/test_entity_linker.py +++ b/spacy/tests/pipeline/test_entity_linker.py @@ -6,9 +6,10 @@ from numpy.testing import assert_equal from spacy import registry, util from spacy.attrs import ENT_KB_ID from spacy.compat import pickle -from spacy.kb import Candidate, KnowledgeBase, get_candidates +from spacy.kb import Candidate, InMemoryLookupKB, get_candidates, KnowledgeBase from spacy.lang.en import English from spacy.ml import load_kb +from spacy.ml.models.entity_linker import build_span_maker from spacy.pipeline import EntityLinker from spacy.pipeline.legacy import EntityLinker_v1 from spacy.pipeline.tok2vec import DEFAULT_TOK2VEC_MODEL @@ -34,7 +35,7 @@ def assert_almost_equal(a, b): def test_issue4674(): """Test that setting entities with overlapping identifiers does not mess up IO""" nlp = English() - kb = KnowledgeBase(nlp.vocab, entity_vector_length=3) + kb = InMemoryLookupKB(nlp.vocab, entity_vector_length=3) vector1 = [0.9, 1.1, 1.01] vector2 = [1.8, 2.25, 2.01] with pytest.warns(UserWarning): @@ -51,7 +52,7 @@ def test_issue4674(): dir_path.mkdir() file_path = dir_path / "kb" kb.to_disk(str(file_path)) - kb2 = KnowledgeBase(nlp.vocab, entity_vector_length=3) + kb2 = InMemoryLookupKB(nlp.vocab, entity_vector_length=3) kb2.from_disk(str(file_path)) assert kb2.get_size_entities() == 1 @@ -59,9 +60,9 @@ def test_issue4674(): @pytest.mark.issue(6730) def test_issue6730(en_vocab): """Ensure that the KB does not accept empty strings, but otherwise IO works fine.""" - from spacy.kb import KnowledgeBase + from spacy.kb.kb_in_memory import InMemoryLookupKB - kb = KnowledgeBase(en_vocab, entity_vector_length=3) + kb = InMemoryLookupKB(en_vocab, entity_vector_length=3) kb.add_entity(entity="1", freq=148, entity_vector=[1, 2, 3]) with pytest.raises(ValueError): @@ -127,7 +128,7 @@ def test_issue7065_b(): def create_kb(vocab): # create artificial KB - mykb = KnowledgeBase(vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(vocab, entity_vector_length=vector_length) mykb.add_entity(entity="Q270853", freq=12, entity_vector=[9, 1, -7]) mykb.add_alias( alias="No. 8", @@ -190,7 +191,7 @@ def test_no_entities(): def create_kb(vocab): # create artificial KB - mykb = KnowledgeBase(vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(vocab, entity_vector_length=vector_length) mykb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) mykb.add_alias("Russ Cochran", ["Q2146908"], [0.9]) return mykb @@ -231,7 +232,7 @@ def test_partial_links(): def create_kb(vocab): # create artificial KB - mykb = KnowledgeBase(vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(vocab, entity_vector_length=vector_length) mykb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) mykb.add_alias("Russ Cochran", ["Q2146908"], [0.9]) return mykb @@ -263,7 +264,7 @@ def test_partial_links(): def test_kb_valid_entities(nlp): """Test the valid construction of a KB with 3 entities and two aliases""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=3) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=3) # adding entities mykb.add_entity(entity="Q1", freq=19, entity_vector=[8, 4, 3]) @@ -292,7 +293,7 @@ def test_kb_valid_entities(nlp): def test_kb_invalid_entities(nlp): """Test the invalid construction of a KB with an alias linked to a non-existing entity""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) # adding entities mykb.add_entity(entity="Q1", freq=19, entity_vector=[1]) @@ -308,7 +309,7 @@ def test_kb_invalid_entities(nlp): def test_kb_invalid_probabilities(nlp): """Test the invalid construction of a KB with wrong prior probabilities""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) # adding entities mykb.add_entity(entity="Q1", freq=19, entity_vector=[1]) @@ -322,7 +323,7 @@ def test_kb_invalid_probabilities(nlp): def test_kb_invalid_combination(nlp): """Test the invalid construction of a KB with non-matching entity and probability lists""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) # adding entities mykb.add_entity(entity="Q1", freq=19, entity_vector=[1]) @@ -338,7 +339,7 @@ def test_kb_invalid_combination(nlp): def test_kb_invalid_entity_vector(nlp): """Test the invalid construction of a KB with non-matching entity vector lengths""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=3) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=3) # adding entities mykb.add_entity(entity="Q1", freq=19, entity_vector=[1, 2, 3]) @@ -376,7 +377,7 @@ def test_kb_initialize_empty(nlp): def test_kb_serialize(nlp): """Test serialization of the KB""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) with make_tempdir() as d: # normal read-write behaviour mykb.to_disk(d / "kb") @@ -393,12 +394,12 @@ def test_kb_serialize(nlp): @pytest.mark.issue(9137) def test_kb_serialize_2(nlp): v = [5, 6, 7, 8] - kb1 = KnowledgeBase(vocab=nlp.vocab, entity_vector_length=4) + kb1 = InMemoryLookupKB(vocab=nlp.vocab, entity_vector_length=4) kb1.set_entities(["E1"], [1], [v]) assert kb1.get_vector("E1") == v with make_tempdir() as d: kb1.to_disk(d / "kb") - kb2 = KnowledgeBase(vocab=nlp.vocab, entity_vector_length=4) + kb2 = InMemoryLookupKB(vocab=nlp.vocab, entity_vector_length=4) kb2.from_disk(d / "kb") assert kb2.get_vector("E1") == v @@ -408,7 +409,7 @@ def test_kb_set_entities(nlp): v = [5, 6, 7, 8] v1 = [1, 1, 1, 0] v2 = [2, 2, 2, 3] - kb1 = KnowledgeBase(vocab=nlp.vocab, entity_vector_length=4) + kb1 = InMemoryLookupKB(vocab=nlp.vocab, entity_vector_length=4) kb1.set_entities(["E0"], [1], [v]) assert kb1.get_entity_strings() == ["E0"] kb1.set_entities(["E1", "E2"], [1, 9], [v1, v2]) @@ -417,7 +418,7 @@ def test_kb_set_entities(nlp): assert kb1.get_vector("E2") == v2 with make_tempdir() as d: kb1.to_disk(d / "kb") - kb2 = KnowledgeBase(vocab=nlp.vocab, entity_vector_length=4) + kb2 = InMemoryLookupKB(vocab=nlp.vocab, entity_vector_length=4) kb2.from_disk(d / "kb") assert set(kb2.get_entity_strings()) == {"E1", "E2"} assert kb2.get_vector("E1") == v1 @@ -428,7 +429,7 @@ def test_kb_serialize_vocab(nlp): """Test serialization of the KB and custom strings""" entity = "MyFunnyID" assert entity not in nlp.vocab.strings - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) assert not mykb.contains_entity(entity) mykb.add_entity(entity, freq=342, entity_vector=[3]) assert mykb.contains_entity(entity) @@ -436,14 +437,14 @@ def test_kb_serialize_vocab(nlp): with make_tempdir() as d: # normal read-write behaviour mykb.to_disk(d / "kb") - mykb_new = KnowledgeBase(Vocab(), entity_vector_length=1) + mykb_new = InMemoryLookupKB(Vocab(), entity_vector_length=1) mykb_new.from_disk(d / "kb") assert entity in mykb_new.vocab.strings def test_candidate_generation(nlp): """Test correct candidate generation""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) doc = nlp("douglas adam Adam shrubbery") douglas_ent = doc[0:1] @@ -481,7 +482,7 @@ def test_el_pipe_configuration(nlp): ruler.add_patterns([pattern]) def create_kb(vocab): - kb = KnowledgeBase(vocab, entity_vector_length=1) + kb = InMemoryLookupKB(vocab, entity_vector_length=1) kb.add_entity(entity="Q2", freq=12, entity_vector=[2]) kb.add_entity(entity="Q3", freq=5, entity_vector=[3]) kb.add_alias(alias="douglas", entities=["Q2", "Q3"], probabilities=[0.8, 0.1]) @@ -500,10 +501,21 @@ def test_el_pipe_configuration(nlp): def get_lowercased_candidates(kb, span): return kb.get_alias_candidates(span.text.lower()) + def get_lowercased_candidates_batch(kb, spans): + return [get_lowercased_candidates(kb, span) for span in spans] + @registry.misc("spacy.LowercaseCandidateGenerator.v1") - def create_candidates() -> Callable[[KnowledgeBase, "Span"], Iterable[Candidate]]: + def create_candidates() -> Callable[ + [InMemoryLookupKB, "Span"], Iterable[Candidate] + ]: return get_lowercased_candidates + @registry.misc("spacy.LowercaseCandidateBatchGenerator.v1") + def create_candidates_batch() -> Callable[ + [InMemoryLookupKB, Iterable["Span"]], Iterable[Iterable[Candidate]] + ]: + return get_lowercased_candidates_batch + # replace the pipe with a new one with with a different candidate generator entity_linker = nlp.replace_pipe( "entity_linker", @@ -511,6 +523,9 @@ def test_el_pipe_configuration(nlp): config={ "incl_context": False, "get_candidates": {"@misc": "spacy.LowercaseCandidateGenerator.v1"}, + "get_candidates_batch": { + "@misc": "spacy.LowercaseCandidateBatchGenerator.v1" + }, }, ) entity_linker.set_kb(create_kb) @@ -532,7 +547,7 @@ def test_nel_nsents(nlp): def test_vocab_serialization(nlp): """Test that string information is retained across storage""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) # adding entities mykb.add_entity(entity="Q1", freq=27, entity_vector=[1]) @@ -552,7 +567,7 @@ def test_vocab_serialization(nlp): with make_tempdir() as d: mykb.to_disk(d / "kb") - kb_new_vocab = KnowledgeBase(Vocab(), entity_vector_length=1) + kb_new_vocab = InMemoryLookupKB(Vocab(), entity_vector_length=1) kb_new_vocab.from_disk(d / "kb") candidates = kb_new_vocab.get_alias_candidates("adam") @@ -568,7 +583,7 @@ def test_vocab_serialization(nlp): def test_append_alias(nlp): """Test that we can append additional alias-entity pairs""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) # adding entities mykb.add_entity(entity="Q1", freq=27, entity_vector=[1]) @@ -599,7 +614,7 @@ def test_append_alias(nlp): @pytest.mark.filterwarnings("ignore:\\[W036") def test_append_invalid_alias(nlp): """Test that append an alias will throw an error if prior probs are exceeding 1""" - mykb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) # adding entities mykb.add_entity(entity="Q1", freq=27, entity_vector=[1]) @@ -621,7 +636,7 @@ def test_preserving_links_asdoc(nlp): vector_length = 1 def create_kb(vocab): - mykb = KnowledgeBase(vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(vocab, entity_vector_length=vector_length) # adding entities mykb.add_entity(entity="Q1", freq=19, entity_vector=[1]) mykb.add_entity(entity="Q2", freq=8, entity_vector=[1]) @@ -701,7 +716,11 @@ TRAIN_DATA = [ ("Russ Cochran was a member of University of Kentucky's golf team.", {"links": {(0, 12): {"Q7381115": 0.0, "Q2146908": 1.0}}, "entities": [(0, 12, "PERSON"), (43, 51, "LOC")], - "sent_starts": [1, -1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]}) + "sent_starts": [1, -1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]}), + # having a blank instance shouldn't break things + ("The weather is nice today.", + {"links": {}, "entities": [], + "sent_starts": [1, -1, 0, 0, 0, 0]}) ] GOLD_entities = ["Q2146908", "Q7381115", "Q7381115", "Q2146908"] # fmt: on @@ -723,7 +742,7 @@ def test_overfitting_IO(): # create artificial KB - assign same prior weight to the two russ cochran's # Q2146908 (Russ Cochran): American golfer # Q7381115 (Russ Cochran): publisher - mykb = KnowledgeBase(vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(vocab, entity_vector_length=vector_length) mykb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) mykb.add_entity(entity="Q7381115", freq=12, entity_vector=[9, 1, -7]) mykb.add_alias( @@ -805,7 +824,7 @@ def test_kb_serialization(): kb_dir = tmp_dir / "kb" nlp1 = English() assert "Q2146908" not in nlp1.vocab.strings - mykb = KnowledgeBase(nlp1.vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(nlp1.vocab, entity_vector_length=vector_length) mykb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) mykb.add_alias(alias="Russ Cochran", entities=["Q2146908"], probabilities=[0.8]) assert "Q2146908" in nlp1.vocab.strings @@ -828,7 +847,7 @@ def test_kb_serialization(): def test_kb_pickle(): # Test that the KB can be pickled nlp = English() - kb_1 = KnowledgeBase(nlp.vocab, entity_vector_length=3) + kb_1 = InMemoryLookupKB(nlp.vocab, entity_vector_length=3) kb_1.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) assert not kb_1.contains_alias("Russ Cochran") kb_1.add_alias(alias="Russ Cochran", entities=["Q2146908"], probabilities=[0.8]) @@ -842,7 +861,7 @@ def test_kb_pickle(): def test_nel_pickle(): # Test that a pipeline with an EL component can be pickled def create_kb(vocab): - kb = KnowledgeBase(vocab, entity_vector_length=3) + kb = InMemoryLookupKB(vocab, entity_vector_length=3) kb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) kb.add_alias(alias="Russ Cochran", entities=["Q2146908"], probabilities=[0.8]) return kb @@ -864,7 +883,7 @@ def test_nel_pickle(): def test_kb_to_bytes(): # Test that the KB's to_bytes method works correctly nlp = English() - kb_1 = KnowledgeBase(nlp.vocab, entity_vector_length=3) + kb_1 = InMemoryLookupKB(nlp.vocab, entity_vector_length=3) kb_1.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) kb_1.add_entity(entity="Q66", freq=9, entity_vector=[1, 2, 3]) kb_1.add_alias(alias="Russ Cochran", entities=["Q2146908"], probabilities=[0.8]) @@ -874,7 +893,7 @@ def test_kb_to_bytes(): ) assert kb_1.contains_alias("Russ Cochran") kb_bytes = kb_1.to_bytes() - kb_2 = KnowledgeBase(nlp.vocab, entity_vector_length=3) + kb_2 = InMemoryLookupKB(nlp.vocab, entity_vector_length=3) assert not kb_2.contains_alias("Russ Cochran") kb_2 = kb_2.from_bytes(kb_bytes) # check that both KBs are exactly the same @@ -897,7 +916,7 @@ def test_kb_to_bytes(): def test_nel_to_bytes(): # Test that a pipeline with an EL component can be converted to bytes def create_kb(vocab): - kb = KnowledgeBase(vocab, entity_vector_length=3) + kb = InMemoryLookupKB(vocab, entity_vector_length=3) kb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) kb.add_alias(alias="Russ Cochran", entities=["Q2146908"], probabilities=[0.8]) return kb @@ -987,7 +1006,7 @@ def test_legacy_architectures(name, config): train_examples.append(Example.from_dict(doc, annotation)) def create_kb(vocab): - mykb = KnowledgeBase(vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(vocab, entity_vector_length=vector_length) mykb.add_entity(entity="Q2146908", freq=12, entity_vector=[6, -4, 3]) mykb.add_entity(entity="Q7381115", freq=12, entity_vector=[9, 1, -7]) mykb.add_alias( @@ -1054,7 +1073,7 @@ def test_no_gold_ents(patterns): def create_kb(vocab): # create artificial KB - mykb = KnowledgeBase(vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(vocab, entity_vector_length=vector_length) mykb.add_entity(entity="Q613241", freq=12, entity_vector=[6, -4, 3]) mykb.add_alias("Kirby", ["Q613241"], [0.9]) # Placeholder @@ -1104,7 +1123,7 @@ def test_tokenization_mismatch(): def create_kb(vocab): # create placeholder KB - mykb = KnowledgeBase(vocab, entity_vector_length=vector_length) + mykb = InMemoryLookupKB(vocab, entity_vector_length=vector_length) mykb.add_entity(entity="Q613241", freq=12, entity_vector=[6, -4, 3]) mykb.add_alias("Kirby", ["Q613241"], [0.9]) return mykb @@ -1121,6 +1140,12 @@ def test_tokenization_mismatch(): nlp.evaluate(train_examples) +def test_abstract_kb_instantiation(): + """Test whether instantiation of abstract KB base class fails.""" + with pytest.raises(TypeError): + KnowledgeBase(None, 3) + + # fmt: off @pytest.mark.parametrize( "meet_threshold,config", @@ -1151,7 +1176,7 @@ def test_threshold(meet_threshold: bool, config: Dict[str, Any]): def create_kb(vocab): # create artificial KB - mykb = KnowledgeBase(vocab, entity_vector_length=3) + mykb = InMemoryLookupKB(vocab, entity_vector_length=3) mykb.add_entity(entity=entity_id, freq=12, entity_vector=[6, -4, 3]) mykb.add_alias( alias="Mahler", @@ -1176,3 +1201,18 @@ def test_threshold(meet_threshold: bool, config: Dict[str, Any]): assert len(doc.ents) == 1 assert doc.ents[0].kb_id_ == entity_id if meet_threshold else EntityLinker.NIL + + +def test_span_maker_forward_with_empty(): + """The forward pass of the span maker may have a doc with no entities.""" + nlp = English() + doc1 = nlp("a b c") + ent = doc1[0:1] + ent.label_ = "X" + doc1.ents = [ent] + # no entities + doc2 = nlp("x y z") + + # just to get a model + span_maker = build_span_maker() + span_maker([doc1, doc2], False) diff --git a/spacy/tests/pipeline/test_pipe_methods.py b/spacy/tests/pipeline/test_pipe_methods.py index b946061f6..4dd7bae16 100644 --- a/spacy/tests/pipeline/test_pipe_methods.py +++ b/spacy/tests/pipeline/test_pipe_methods.py @@ -605,10 +605,33 @@ def test_update_with_annotates(): assert results[component] == "" -def test_load_disable_enable() -> None: - """ - Tests spacy.load() with dis-/enabling components. - """ +@pytest.mark.issue(11443) +def test_enable_disable_conflict_with_config(): + """Test conflict between enable/disable w.r.t. `nlp.disabled` set in the config.""" + nlp = English() + nlp.add_pipe("tagger") + nlp.add_pipe("senter") + nlp.add_pipe("sentencizer") + + with make_tempdir() as tmp_dir: + nlp.to_disk(tmp_dir) + # 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 fail due to conflict between enable and disabled. + with pytest.raises(ValueError): + spacy.load( + tmp_dir, + enable=["senter"], + config={"nlp": {"disabled": ["senter", "tagger"]}}, + ) + + +def test_load_disable_enable(): + """Tests spacy.load() with dis-/enabling components.""" base_nlp = English() for pipe in ("sentencizer", "tagger", "parser"): diff --git a/spacy/tests/pipeline/test_textcat.py b/spacy/tests/pipeline/test_textcat.py index 0bb036a33..d359b77db 100644 --- a/spacy/tests/pipeline/test_textcat.py +++ b/spacy/tests/pipeline/test_textcat.py @@ -823,10 +823,10 @@ 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 +849,7 @@ 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/pipeline/test_tok2vec.py b/spacy/tests/pipeline/test_tok2vec.py index 64faf133d..e423d9a19 100644 --- a/spacy/tests/pipeline/test_tok2vec.py +++ b/spacy/tests/pipeline/test_tok2vec.py @@ -230,6 +230,97 @@ def test_tok2vec_listener_callback(): assert get_dX(Y) is not None +def test_tok2vec_listener_overfitting(): + """Test that a pipeline with a listener properly overfits, even if 'tok2vec' is in the annotating components""" + orig_config = Config().from_str(cfg_string) + nlp = util.load_model_from_config(orig_config, auto_fill=True, validate=True) + train_examples = [] + for t in TRAIN_DATA: + train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1])) + optimizer = nlp.initialize(get_examples=lambda: train_examples) + + for i in range(50): + losses = {} + nlp.update(train_examples, sgd=optimizer, losses=losses, annotates=["tok2vec"]) + assert losses["tagger"] < 0.00001 + + # test the trained model + test_text = "I like blue eggs" + doc = nlp(test_text) + assert doc[0].tag_ == "N" + assert doc[1].tag_ == "V" + assert doc[2].tag_ == "J" + assert doc[3].tag_ == "N" + + # Also test the results are still the same after IO + with make_tempdir() as tmp_dir: + nlp.to_disk(tmp_dir) + nlp2 = util.load_model_from_path(tmp_dir) + doc2 = nlp2(test_text) + assert doc2[0].tag_ == "N" + assert doc2[1].tag_ == "V" + assert doc2[2].tag_ == "J" + assert doc2[3].tag_ == "N" + + +def test_tok2vec_frozen_not_annotating(): + """Test that a pipeline with a frozen tok2vec raises an error when the tok2vec is not annotating""" + orig_config = Config().from_str(cfg_string) + nlp = util.load_model_from_config(orig_config, auto_fill=True, validate=True) + train_examples = [] + for t in TRAIN_DATA: + train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1])) + optimizer = nlp.initialize(get_examples=lambda: train_examples) + + for i in range(2): + losses = {} + with pytest.raises( + ValueError, match=r"the tok2vec embedding layer is not updated" + ): + nlp.update( + train_examples, sgd=optimizer, losses=losses, exclude=["tok2vec"] + ) + + +def test_tok2vec_frozen_overfitting(): + """Test that a pipeline with a frozen & annotating tok2vec can still overfit""" + orig_config = Config().from_str(cfg_string) + nlp = util.load_model_from_config(orig_config, auto_fill=True, validate=True) + train_examples = [] + for t in TRAIN_DATA: + train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1])) + optimizer = nlp.initialize(get_examples=lambda: train_examples) + + for i in range(100): + losses = {} + nlp.update( + train_examples, + sgd=optimizer, + losses=losses, + exclude=["tok2vec"], + annotates=["tok2vec"], + ) + assert losses["tagger"] < 0.0001 + + # test the trained model + test_text = "I like blue eggs" + doc = nlp(test_text) + assert doc[0].tag_ == "N" + assert doc[1].tag_ == "V" + assert doc[2].tag_ == "J" + assert doc[3].tag_ == "N" + + # Also test the results are still the same after IO + with make_tempdir() as tmp_dir: + nlp.to_disk(tmp_dir) + nlp2 = util.load_model_from_path(tmp_dir) + doc2 = nlp2(test_text) + assert doc2[0].tag_ == "N" + assert doc2[1].tag_ == "V" + assert doc2[2].tag_ == "J" + assert doc2[3].tag_ == "N" + + def test_replace_listeners(): orig_config = Config().from_str(cfg_string) nlp = util.load_model_from_config(orig_config, auto_fill=True, validate=True) diff --git a/spacy/tests/serialize/test_resource_warning.py b/spacy/tests/serialize/test_resource_warning.py index a00b2a688..38701c6d9 100644 --- a/spacy/tests/serialize/test_resource_warning.py +++ b/spacy/tests/serialize/test_resource_warning.py @@ -3,7 +3,7 @@ from unittest import TestCase import pytest import srsly from numpy import zeros -from spacy.kb import KnowledgeBase, Writer +from spacy.kb.kb_in_memory import InMemoryLookupKB, Writer from spacy.vectors import Vectors from spacy.language import Language from spacy.pipeline import TrainablePipe @@ -71,7 +71,7 @@ def entity_linker(): nlp = Language() def create_kb(vocab): - kb = KnowledgeBase(vocab, entity_vector_length=1) + kb = InMemoryLookupKB(vocab, entity_vector_length=1) kb.add_entity("test", 0.0, zeros((1, 1), dtype="f")) return kb @@ -120,7 +120,7 @@ def test_writer_with_path_py35(): def test_save_and_load_knowledge_base(): nlp = Language() - kb = KnowledgeBase(nlp.vocab, entity_vector_length=1) + kb = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) with make_tempdir() as d: path = d / "kb" try: @@ -129,7 +129,7 @@ def test_save_and_load_knowledge_base(): pytest.fail(str(e)) try: - kb_loaded = KnowledgeBase(nlp.vocab, entity_vector_length=1) + kb_loaded = InMemoryLookupKB(nlp.vocab, entity_vector_length=1) kb_loaded.from_disk(path) except Exception as e: pytest.fail(str(e)) diff --git a/spacy/tests/serialize/test_serialize_kb.py b/spacy/tests/serialize/test_serialize_kb.py index 1e0ae3c76..8d3653ab1 100644 --- a/spacy/tests/serialize/test_serialize_kb.py +++ b/spacy/tests/serialize/test_serialize_kb.py @@ -2,7 +2,7 @@ from typing import Callable from spacy import util from spacy.util import ensure_path, registry, load_model_from_config -from spacy.kb import KnowledgeBase +from spacy.kb.kb_in_memory import InMemoryLookupKB from spacy.vocab import Vocab from thinc.api import Config @@ -22,7 +22,7 @@ def test_serialize_kb_disk(en_vocab): dir_path.mkdir() file_path = dir_path / "kb" kb1.to_disk(str(file_path)) - kb2 = KnowledgeBase(vocab=en_vocab, entity_vector_length=3) + kb2 = InMemoryLookupKB(vocab=en_vocab, entity_vector_length=3) kb2.from_disk(str(file_path)) # final assertions @@ -30,7 +30,7 @@ def test_serialize_kb_disk(en_vocab): def _get_dummy_kb(vocab): - kb = KnowledgeBase(vocab, entity_vector_length=3) + kb = InMemoryLookupKB(vocab, entity_vector_length=3) kb.add_entity(entity="Q53", freq=33, entity_vector=[0, 5, 3]) kb.add_entity(entity="Q17", freq=2, entity_vector=[7, 1, 0]) kb.add_entity(entity="Q007", freq=7, entity_vector=[0, 0, 7]) @@ -104,7 +104,7 @@ def test_serialize_subclassed_kb(): custom_field = 666 """ - class SubKnowledgeBase(KnowledgeBase): + class SubInMemoryLookupKB(InMemoryLookupKB): def __init__(self, vocab, entity_vector_length, custom_field): super().__init__(vocab, entity_vector_length) self.custom_field = custom_field @@ -112,9 +112,9 @@ def test_serialize_subclassed_kb(): @registry.misc("spacy.CustomKB.v1") def custom_kb( entity_vector_length: int, custom_field: int - ) -> Callable[[Vocab], KnowledgeBase]: + ) -> Callable[[Vocab], InMemoryLookupKB]: def custom_kb_factory(vocab): - kb = SubKnowledgeBase( + kb = SubInMemoryLookupKB( vocab=vocab, entity_vector_length=entity_vector_length, custom_field=custom_field, @@ -129,7 +129,7 @@ def test_serialize_subclassed_kb(): nlp.initialize() entity_linker = nlp.get_pipe("entity_linker") - assert type(entity_linker.kb) == SubKnowledgeBase + assert type(entity_linker.kb) == SubInMemoryLookupKB assert entity_linker.kb.entity_vector_length == 342 assert entity_linker.kb.custom_field == 666 @@ -139,6 +139,6 @@ def test_serialize_subclassed_kb(): nlp2 = util.load_model_from_path(tmp_dir) entity_linker2 = nlp2.get_pipe("entity_linker") # After IO, the KB is the standard one - assert type(entity_linker2.kb) == KnowledgeBase + assert type(entity_linker2.kb) == InMemoryLookupKB assert entity_linker2.kb.entity_vector_length == 342 assert not hasattr(entity_linker2.kb, "custom_field") diff --git a/spacy/tests/test_cli.py b/spacy/tests/test_cli.py index 838e00369..8225e14f1 100644 --- a/spacy/tests/test_cli.py +++ b/spacy/tests/test_cli.py @@ -1,5 +1,6 @@ import os import math +import pkg_resources from random import sample from typing import Counter @@ -25,6 +26,7 @@ from spacy.cli.download import get_compatibility, get_version from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config from spacy.cli.package import get_third_party_dependencies from spacy.cli.package import _is_permitted_package_name +from spacy.cli.project.run import _check_requirements from spacy.cli.validate import get_model_pkgs from spacy.lang.en import English from spacy.lang.nl import Dutch @@ -855,3 +857,42 @@ def test_span_length_freq_dist_output_must_be_correct(): span_freqs = _get_spans_length_freq_dist(sample_span_lengths, threshold) assert sum(span_freqs.values()) >= threshold assert list(span_freqs.keys()) == [3, 1, 4, 5, 2] + + +@pytest.mark.parametrize( + "reqs,output", + [ + [ + """ + spacy + + # comment + + thinc""", + (False, False), + ], + [ + """# comment + --some-flag + spacy""", + (False, False), + ], + [ + """# comment + --some-flag + spacy; python_version >= '3.6'""", + (False, False), + ], + [ + """# comment + spacyunknowndoesnotexist12345""", + (True, False), + ], + ], +) +def test_project_check_requirements(reqs, output): + # excessive guard against unlikely package name + try: + pkg_resources.require("spacyunknowndoesnotexist12345") + except pkg_resources.DistributionNotFound: + assert output == _check_requirements([req.strip() for req in reqs.split("\n")]) diff --git a/spacy/tests/test_models.py b/spacy/tests/test_models.py index 2306cabb7..d91ed1201 100644 --- a/spacy/tests/test_models.py +++ b/spacy/tests/test_models.py @@ -23,7 +23,7 @@ def get_textcat_bow_kwargs(): def get_textcat_cnn_kwargs(): - return {"tok2vec": test_tok2vec(), "exclusive_classes": False, "nO": 13} + return {"tok2vec": make_test_tok2vec(), "exclusive_classes": False, "nO": 13} def get_all_params(model): @@ -65,7 +65,7 @@ def get_tok2vec_kwargs(): } -def test_tok2vec(): +def make_test_tok2vec(): return build_Tok2Vec_model(**get_tok2vec_kwargs()) 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_augmenters.py b/spacy/tests/training/test_augmenters.py index e3639c5da..35860a199 100644 --- a/spacy/tests/training/test_augmenters.py +++ b/spacy/tests/training/test_augmenters.py @@ -31,7 +31,7 @@ def doc(nlp): words = ["Sarah", "'s", "sister", "flew", "to", "Silicon", "Valley", "via", "London", "."] tags = ["NNP", "POS", "NN", "VBD", "IN", "NNP", "NNP", "IN", "NNP", "."] pos = ["PROPN", "PART", "NOUN", "VERB", "ADP", "PROPN", "PROPN", "ADP", "PROPN", "PUNCT"] - ents = ["B-PERSON", "I-PERSON", "O", "O", "O", "B-LOC", "I-LOC", "O", "B-GPE", "O"] + ents = ["B-PERSON", "I-PERSON", "O", "", "O", "B-LOC", "I-LOC", "O", "B-GPE", "O"] cats = {"TRAVEL": 1.0, "BAKING": 0.0} # fmt: on doc = Doc(nlp.vocab, words=words, tags=tags, pos=pos, ents=ents) @@ -106,6 +106,7 @@ def test_lowercase_augmenter(nlp, doc): assert [(e.start, e.end, e.label) for e in eg.reference.ents] == ents for ref_ent, orig_ent in zip(eg.reference.ents, doc.ents): assert ref_ent.text == orig_ent.text.lower() + assert [t.ent_iob for t in doc] == [t.ent_iob for t in eg.reference] assert [t.pos_ for t in eg.reference] == [t.pos_ for t in doc] # check that augmentation works when lowercasing leads to different @@ -166,7 +167,7 @@ def test_make_whitespace_variant(nlp): lemmas = ["they", "fly", "to", "New", "York", "City", ".", "\n", "then", "they", "drive", "to", "Washington", ",", "D.C."] heads = [1, 1, 1, 4, 5, 2, 1, 10, 10, 10, 10, 10, 11, 12, 12] deps = ["nsubj", "ROOT", "prep", "compound", "compound", "pobj", "punct", "dep", "advmod", "nsubj", "ROOT", "prep", "pobj", "punct", "appos"] - ents = ["O", "O", "O", "B-GPE", "I-GPE", "I-GPE", "O", "O", "O", "O", "O", "O", "B-GPE", "O", "B-GPE"] + ents = ["O", "", "O", "B-GPE", "I-GPE", "I-GPE", "O", "O", "O", "O", "O", "O", "B-GPE", "O", "B-GPE"] # fmt: on doc = Doc( nlp.vocab, @@ -215,6 +216,8 @@ def test_make_whitespace_variant(nlp): assert mod_ex2.reference[j].head.i == j - 1 # entities are well-formed assert len(doc.ents) == len(mod_ex.reference.ents) + # there is one token with missing entity information + assert any(t.ent_iob == 0 for t in mod_ex.reference) for ent in mod_ex.reference.ents: assert not ent[0].is_space assert not ent[-1].is_space diff --git a/spacy/tokens/_dict_proxies.py b/spacy/tokens/_dict_proxies.py index 9630da261..6edcce13d 100644 --- a/spacy/tokens/_dict_proxies.py +++ b/spacy/tokens/_dict_proxies.py @@ -42,7 +42,8 @@ class SpanGroups(UserDict): def copy(self, doc: Optional["Doc"] = None) -> "SpanGroups": if doc is None: doc = self._ensure_doc() - return SpanGroups(doc).from_bytes(self.to_bytes()) + data_copy = ((k, v.copy(doc=doc)) for k, v in self.items()) + return SpanGroups(doc, items=data_copy) def setdefault(self, key, default=None): if not isinstance(default, SpanGroup): diff --git a/spacy/tokens/doc.pyi b/spacy/tokens/doc.pyi index a40fa74aa..f0cdaee87 100644 --- a/spacy/tokens/doc.pyi +++ b/spacy/tokens/doc.pyi @@ -72,7 +72,7 @@ class Doc: lemmas: Optional[List[str]] = ..., heads: Optional[List[int]] = ..., deps: Optional[List[str]] = ..., - sent_starts: Optional[List[Union[bool, None]]] = ..., + sent_starts: Optional[List[Union[bool, int, None]]] = ..., ents: Optional[List[str]] = ..., ) -> None: ... @property diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx index 7ba9a3341..f2621292c 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -217,9 +217,9 @@ cdef class Doc: head in the doc. Defaults to None. deps (Optional[List[str]]): A list of unicode strings, of the same length as words, to assign as token.dep. Defaults to None. - sent_starts (Optional[List[Union[bool, None]]]): A list of values, of - the same length as words, to assign as token.is_sent_start. Will be - overridden by heads if heads is provided. Defaults to None. + sent_starts (Optional[List[Union[bool, int, None]]]): A list of values, + of the same length as words, to assign as token.is_sent_start. Will + be overridden by heads if heads is provided. Defaults to None. ents (Optional[List[str]]): A list of unicode strings, of the same length as words, as IOB tags to assign as token.ent_iob and token.ent_type. Defaults to None. @@ -285,6 +285,7 @@ cdef class Doc: heads = [0] * len(deps) if heads and not deps: raise ValueError(Errors.E1017) + sent_starts = list(sent_starts) if sent_starts is not None else None if sent_starts is not None: for i in range(len(sent_starts)): if sent_starts[i] is True: @@ -300,12 +301,11 @@ cdef class Doc: ent_iobs = None ent_types = None if ents is not None: + ents = [ent if ent != "" else None for ent in ents] iob_strings = Token.iob_strings() # make valid IOB2 out of IOB1 or IOB2 for i, ent in enumerate(ents): - if ent is "": - ents[i] = None - elif ent is not None and not isinstance(ent, str): + if ent is not None and not isinstance(ent, str): raise ValueError(Errors.E177.format(tag=ent)) if i < len(ents) - 1: # OI -> OB @@ -1608,24 +1608,20 @@ cdef class Doc: Doc.set_extension(attr) self._.set(attr, doc_json["_"][attr]) - if doc_json.get("underscore_token", {}): - for token_attr in doc_json["underscore_token"]: - token_start = doc_json["underscore_token"][token_attr]["token_start"] - value = doc_json["underscore_token"][token_attr]["value"] - - if not Token.has_extension(token_attr): - Token.set_extension(token_attr) - self[token_start]._.set(token_attr, value) + for token_attr in doc_json.get("underscore_token", {}): + if not Token.has_extension(token_attr): + Token.set_extension(token_attr) + for token_data in doc_json["underscore_token"][token_attr]: + start = token_by_char(self.c, self.length, token_data["start"]) + value = token_data["value"] + self[start]._.set(token_attr, value) - if doc_json.get("underscore_span", {}): - for span_attr in doc_json["underscore_span"]: - token_start = doc_json["underscore_span"][span_attr]["token_start"] - token_end = doc_json["underscore_span"][span_attr]["token_end"] - value = doc_json["underscore_span"][span_attr]["value"] - - if not Span.has_extension(span_attr): - Span.set_extension(span_attr) - self[token_start:token_end]._.set(span_attr, value) + for span_attr in doc_json.get("underscore_span", {}): + if not Span.has_extension(span_attr): + Span.set_extension(span_attr) + for span_data in doc_json["underscore_span"][span_attr]: + value = span_data["value"] + self.char_span(span_data["start"], span_data["end"])._.set(span_attr, value) return self def to_json(self, underscore=None): @@ -1672,31 +1668,44 @@ 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: - data["_"] = {} - data["underscore_token"] = {} - data["underscore_span"] = {} - for data_key in 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] == "._.": attr = data_key[1] start = data_key[2] end = data_key[3] if attr in underscore: user_keys.add(attr) - value = self.user_data[data_key] 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: - 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] = {"token_start": start, "value": value} - # Else span attribute - else: + data["underscore_token"][attr] = [] + data["underscore_token"][attr].append({"start": start, "value": value}) + # 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"]: - data["underscore_span"][attr] = {"token_start": start, "token_end": end, "value": value} + data["underscore_span"][attr] = [] + data["underscore_span"][attr].append({"start": start, "end": end, "value": value}) for attr in underscore: if attr not in user_keys: 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/tokens/span_group.pyi b/spacy/tokens/span_group.pyi index 245eb4dbe..21cd124ab 100644 --- a/spacy/tokens/span_group.pyi +++ b/spacy/tokens/span_group.pyi @@ -1,4 +1,4 @@ -from typing import Any, Dict, Iterable +from typing import Any, Dict, Iterable, Optional from .doc import Doc from .span import Span @@ -24,4 +24,4 @@ class SpanGroup: def __getitem__(self, i: int) -> Span: ... def to_bytes(self) -> bytes: ... def from_bytes(self, bytes_data: bytes) -> SpanGroup: ... - def copy(self) -> SpanGroup: ... + def copy(self, doc: Optional[Doc] = ...) -> SpanGroup: ... diff --git a/spacy/tokens/span_group.pyx b/spacy/tokens/span_group.pyx index bb0fab24f..1aa3c0bc8 100644 --- a/spacy/tokens/span_group.pyx +++ b/spacy/tokens/span_group.pyx @@ -241,15 +241,18 @@ cdef class SpanGroup: cdef void push_back(self, SpanC span) nogil: self.c.push_back(span) - def copy(self) -> SpanGroup: + def copy(self, doc: Optional["Doc"] = None) -> SpanGroup: """Clones the span group. + doc (Doc): New reference document to which the copy is bound. RETURNS (SpanGroup): A copy of the span group. DOCS: https://spacy.io/api/spangroup#copy """ + if doc is None: + doc = self.doc return SpanGroup( - self.doc, + doc, name=self.name, attrs=deepcopy(self.attrs), spans=list(self), diff --git a/spacy/training/augment.py b/spacy/training/augment.py index 55d780ba4..2fe8c24fb 100644 --- a/spacy/training/augment.py +++ b/spacy/training/augment.py @@ -6,7 +6,7 @@ from functools import partial from ..util import registry from .example import Example -from .iob_utils import split_bilu_label +from .iob_utils import split_bilu_label, _doc_to_biluo_tags_with_partial if TYPE_CHECKING: from ..language import Language # noqa: F401 @@ -62,6 +62,9 @@ def combined_augmenter( if orth_variants and random.random() < orth_level: raw_text = example.text orig_dict = example.to_dict() + orig_dict["doc_annotation"]["entities"] = _doc_to_biluo_tags_with_partial( + example.reference + ) variant_text, variant_token_annot = make_orth_variants( nlp, raw_text, @@ -128,6 +131,9 @@ def lower_casing_augmenter( def make_lowercase_variant(nlp: "Language", example: Example): example_dict = example.to_dict() + example_dict["doc_annotation"]["entities"] = _doc_to_biluo_tags_with_partial( + example.reference + ) doc = nlp.make_doc(example.text.lower()) example_dict["token_annotation"]["ORTH"] = [t.lower_ for t in example.reference] return example.from_dict(doc, example_dict) @@ -146,6 +152,9 @@ def orth_variants_augmenter( else: raw_text = example.text orig_dict = example.to_dict() + orig_dict["doc_annotation"]["entities"] = _doc_to_biluo_tags_with_partial( + example.reference + ) variant_text, variant_token_annot = make_orth_variants( nlp, raw_text, @@ -248,6 +257,9 @@ def make_whitespace_variant( RETURNS (Example): Example with one additional space token. """ example_dict = example.to_dict() + example_dict["doc_annotation"]["entities"] = _doc_to_biluo_tags_with_partial( + example.reference + ) doc_dict = example_dict.get("doc_annotation", {}) token_dict = example_dict.get("token_annotation", {}) # returned unmodified if: diff --git a/spacy/training/iob_utils.py b/spacy/training/iob_utils.py index 61f83a1c3..0d4d246b0 100644 --- a/spacy/training/iob_utils.py +++ b/spacy/training/iob_utils.py @@ -60,6 +60,14 @@ def doc_to_biluo_tags(doc: Doc, missing: str = "O"): ) +def _doc_to_biluo_tags_with_partial(doc: Doc) -> List[str]: + ents = doc_to_biluo_tags(doc, missing="-") + for i, token in enumerate(doc): + if token.ent_iob == 2: + ents[i] = "O" + return ents + + def offsets_to_biluo_tags( doc: Doc, entities: Iterable[Tuple[int, int, Union[str, int]]], missing: str = "O" ) -> List[str]: diff --git a/spacy/util.py b/spacy/util.py index 4e1a62d05..76a1e0bfa 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -67,7 +67,6 @@ LEXEME_NORM_LANGS = ["cs", "da", "de", "el", "en", "id", "lb", "mk", "pt", "ru", CONFIG_SECTION_ORDER = ["paths", "variables", "system", "nlp", "components", "corpora", "training", "pretraining", "initialize"] # fmt: on - logger = logging.getLogger("spacy") logger_stream_handler = logging.StreamHandler() logger_stream_handler.setFormatter( @@ -394,13 +393,17 @@ def get_module_path(module: ModuleType) -> Path: return file_path.parent +# Default value for passed enable/disable values. +_DEFAULT_EMPTY_PIPES = SimpleFrozenList() + + def load_model( name: Union[str, Path], *, 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 a package or data path. @@ -440,9 +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. @@ -470,9 +473,9 @@ def load_model_from_path( *, meta: Optional[Dict[str, Any]] = None, 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 a data directory path. Creates Language class with @@ -516,9 +519,9 @@ def load_model_from_config( *, meta: Dict[str, Any] = SimpleFrozenDict(), 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, auto_fill: bool = False, validate: bool = True, ) -> "Language": @@ -616,9 +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/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/architectures.md b/website/docs/api/architectures.md index 2537faff6..4c5447f75 100644 --- a/website/docs/api/architectures.md +++ b/website/docs/api/architectures.md @@ -11,6 +11,7 @@ menu: - ['Text Classification', 'textcat'] - ['Span Classification', 'spancat'] - ['Entity Linking', 'entitylinker'] + - ['Coreference', 'coref-architectures'] --- A **model architecture** is a function that wires up a @@ -587,8 +588,8 @@ consists of either two or three subnetworks: run once for each batch. - **lower**: Construct a feature-specific vector for each `(token, feature)` pair. This is also run once for each batch. Constructing the state - representation is then a matter of summing the component features and - applying the non-linearity. + representation is then a matter of summing the component features and applying + the non-linearity. - **upper** (optional): A feed-forward network that predicts scores from the state representation. If not present, the output from the lower model is used as action scores directly. @@ -628,8 +629,8 @@ same signature, but the `use_upper` argument was `True` by default. > ``` Build a tagger model, using a provided token-to-vector component. The tagger -model adds a linear layer with softmax activation to predict scores given -the token vectors. +model adds a linear layer with softmax activation to predict scores given the +token vectors. | Name | Description | | ----------- | ------------------------------------------------------------------------------------------ | @@ -920,5 +921,84 @@ A function that reads an existing `KnowledgeBase` from file. A function that takes as input a [`KnowledgeBase`](/api/kb) and a [`Span`](/api/span) object denoting a named entity, and returns a list of plausible [`Candidate`](/api/kb/#candidate) objects. The default -`CandidateGenerator` uses the text of a mention to find its potential -aliases in the `KnowledgeBase`. Note that this function is case-dependent. +`CandidateGenerator` uses the text of a mention to find its potential aliases in +the `KnowledgeBase`. Note that this function is case-dependent. + +## Coreference {#coref-architectures tag="experimental"} + +A [`CoreferenceResolver`](/api/coref) component identifies tokens that refer to +the same entity. A [`SpanResolver`](/api/span-resolver) component infers spans +from single tokens. Together these components can be used to reproduce +traditional coreference models. You can also omit the `SpanResolver` if working +with only token-level clusters is acceptable. + +### spacy-experimental.Coref.v1 {#Coref tag="experimental"} + +> #### Example Config +> +> ```ini +> +> [model] +> @architectures = "spacy-experimental.Coref.v1" +> distance_embedding_size = 20 +> dropout = 0.3 +> hidden_size = 1024 +> depth = 2 +> antecedent_limit = 50 +> antecedent_batch_size = 512 +> +> [model.tok2vec] +> @architectures = "spacy-transformers.TransformerListener.v1" +> grad_factor = 1.0 +> upstream = "transformer" +> pooling = {"@layers":"reduce_mean.v1"} +> ``` + +The `Coref` model architecture is a Thinc `Model`. + +| Name | Description | +| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `tok2vec` | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~ | +| `distance_embedding_size` | A representation of the distance between candidates. ~~int~~ | +| `dropout` | The dropout to use internally. Unlike some Thinc models, this has separate dropout for the internal PyTorch layers. ~~float~~ | +| `hidden_size` | Size of the main internal layers. ~~int~~ | +| `depth` | Depth of the internal network. ~~int~~ | +| `antecedent_limit` | How many candidate antecedents to keep after rough scoring. This has a significant effect on memory usage. Typical values would be 50 to 200, or higher for very long documents. ~~int~~ | +| `antecedent_batch_size` | Internal batch size. ~~int~~ | +| **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~ | + +### spacy-experimental.SpanResolver.v1 {#SpanResolver tag="experimental"} + +> #### Example Config +> +> ```ini +> +> [model] +> @architectures = "spacy-experimental.SpanResolver.v1" +> hidden_size = 1024 +> distance_embedding_size = 64 +> conv_channels = 4 +> window_size = 1 +> max_distance = 128 +> prefix = "coref_head_clusters" +> +> [model.tok2vec] +> @architectures = "spacy-transformers.TransformerListener.v1" +> grad_factor = 1.0 +> upstream = "transformer" +> pooling = {"@layers":"reduce_mean.v1"} +> ``` + +The `SpanResolver` model architecture is a Thinc `Model`. Note that +`MentionClusters` is `List[List[Tuple[int, int]]]`. + +| Name | Description | +| ------------------------- | -------------------------------------------------------------------------------------------------------------------- | +| `tok2vec` | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~ | +| `hidden_size` | Size of the main internal layers. ~~int~~ | +| `distance_embedding_size` | A representation of the distance between two candidates. ~~int~~ | +| `conv_channels` | The number of channels in the internal CNN. ~~int~~ | +| `window_size` | The number of neighboring tokens to consider in the internal CNN. `1` means consider one token on each side. ~~int~~ | +| `max_distance` | The longest possible length of a predicted span. ~~int~~ | +| `prefix` | The prefix that indicates spans to use for input data. ~~string~~ | +| **CREATES** | The model using the architecture. ~~Model[List[Doc], List[MentionClusters]]~~ | diff --git a/website/docs/api/cli.md b/website/docs/api/cli.md index e5cd3089b..6e581b903 100644 --- a/website/docs/api/cli.md +++ b/website/docs/api/cli.md @@ -15,7 +15,6 @@ menu: - ['assemble', 'assemble'] - ['package', 'package'] - ['project', 'project'] - - ['ray', 'ray'] - ['huggingface-hub', 'huggingface-hub'] --- @@ -53,7 +52,7 @@ $ python -m spacy download [model] [--direct] [--sdist] [pip_args] | `--direct`, `-D` | Force direct download of exact package version. ~~bool (flag)~~ | | `--sdist`, `-S` 3 | Download the source package (`.tar.gz` archive) instead of the default pre-built binary wheel. ~~bool (flag)~~ | | `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| pip args 2.1 | Additional installation options to be passed to `pip install` when installing the pipeline package. For example, `--user` to install to the user home directory or `--no-deps` to not install package dependencies. ~~Any (option/flag)~~ | +| pip args | Additional installation options to be passed to `pip install` when installing the pipeline package. For example, `--user` to install to the user home directory or `--no-deps` to not install package dependencies. ~~Any (option/flag)~~ | | **CREATES** | The installed pipeline package in your `site-packages` directory. | ## info {#info tag="command"} @@ -77,15 +76,15 @@ $ python -m spacy info [--markdown] [--silent] [--exclude] $ python -m spacy info [model] [--markdown] [--silent] [--exclude] ``` -| Name | Description | -| ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------- | -| `model` | A trained pipeline, i.e. package name or path (optional). ~~Optional[str] \(option)~~ | -| `--markdown`, `-md` | Print information as Markdown. ~~bool (flag)~~ | -| `--silent`, `-s` 2.0.12 | Don't print anything, just return the values. ~~bool (flag)~~ | -| `--exclude`, `-e` | Comma-separated keys to exclude from the print-out. Defaults to `"labels"`. ~~Optional[str]~~ | -| `--url`, `-u` 3.5.0 | Print the URL to download the most recent compatible version of the pipeline. Requires a pipeline name. ~~bool (flag)~~ | -| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| **PRINTS** | Information about your spaCy installation. | +| Name | Description | +| -------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | +| `model` | A trained pipeline, i.e. package name or path (optional). ~~Optional[str] \(option)~~ | +| `--markdown`, `-md` | Print information as Markdown. ~~bool (flag)~~ | +| `--silent`, `-s` | Don't print anything, just return the values. ~~bool (flag)~~ | +| `--exclude`, `-e` | Comma-separated keys to exclude from the print-out. Defaults to `"labels"`. ~~Optional[str]~~ | +| `--url`, `-u` 3.5.0 | Print the URL to download the most recent compatible version of the pipeline. Requires a pipeline name. ~~bool (flag)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | +| **PRINTS** | Information about your spaCy installation. | ## validate {#validate new="2" tag="command"} @@ -260,22 +259,22 @@ chosen based on the file extension of the input file. $ python -m spacy convert [input_file] [output_dir] [--converter] [--file-type] [--n-sents] [--seg-sents] [--base] [--morphology] [--merge-subtokens] [--ner-map] [--lang] ``` -| Name | Description | -| ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------- | -| `input_path` | Input file or directory. ~~Path (positional)~~ | -| `output_dir` | Output directory for converted file. Defaults to `"-"`, meaning data will be written to `stdout`. ~~Optional[Path] \(option)~~ | -| `--converter`, `-c` 2 | Name of converter to use (see below). ~~str (option)~~ | -| `--file-type`, `-t` 2.1 | Type of file to create. Either `spacy` (default) for binary [`DocBin`](/api/docbin) data or `json` for v2.x JSON format. ~~str (option)~~ | -| `--n-sents`, `-n` | Number of sentences per document. Supported for: `conll`, `conllu`, `iob`, `ner` ~~int (option)~~ | -| `--seg-sents`, `-s` 2.2 | Segment sentences. Supported for: `conll`, `ner` ~~bool (flag)~~ | -| `--base`, `-b`, `--model` | Trained spaCy pipeline for sentence segmentation to use as base (for `--seg-sents`). ~~Optional[str](option)~~ | -| `--morphology`, `-m` | Enable appending morphology to tags. Supported for: `conllu` ~~bool (flag)~~ | -| `--merge-subtokens`, `-T` | Merge CoNLL-U subtokens ~~bool (flag)~~ | -| `--ner-map`, `-nm` | NER tag mapping (as JSON-encoded dict of entity types). Supported for: `conllu` ~~Optional[Path](option)~~ | -| `--lang`, `-l` 2.1 | Language code (if tokenizer required). ~~Optional[str] \(option)~~ | -| `--concatenate`, `-C` | Concatenate output to a single file ~~bool (flag)~~ | -| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| **CREATES** | Binary [`DocBin`](/api/docbin) training data that can be used with [`spacy train`](/api/cli#train). | +| Name | Description | +| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | +| `input_path` | Input file or directory. ~~Path (positional)~~ | +| `output_dir` | Output directory for converted file. Defaults to `"-"`, meaning data will be written to `stdout`. ~~Optional[Path] \(option)~~ | +| `--converter`, `-c` | Name of converter to use (see below). ~~str (option)~~ | +| `--file-type`, `-t` | Type of file to create. Either `spacy` (default) for binary [`DocBin`](/api/docbin) data or `json` for v2.x JSON format. ~~str (option)~~ | +| `--n-sents`, `-n` | Number of sentences per document. Supported for: `conll`, `conllu`, `iob`, `ner` ~~int (option)~~ | +| `--seg-sents`, `-s` | Segment sentences. Supported for: `conll`, `ner` ~~bool (flag)~~ | +| `--base`, `-b`, `--model` | Trained spaCy pipeline for sentence segmentation to use as base (for `--seg-sents`). ~~Optional[str](option)~~ | +| `--morphology`, `-m` | Enable appending morphology to tags. Supported for: `conllu` ~~bool (flag)~~ | +| `--merge-subtokens`, `-T` | Merge CoNLL-U subtokens ~~bool (flag)~~ | +| `--ner-map`, `-nm` | NER tag mapping (as JSON-encoded dict of entity types). Supported for: `conllu` ~~Optional[Path](option)~~ | +| `--lang`, `-l` | Language code (if tokenizer required). ~~Optional[str] \(option)~~ | +| `--concatenate`, `-C` | Concatenate output to a single file ~~bool (flag)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | +| **CREATES** | Binary [`DocBin`](/api/docbin) training data that can be used with [`spacy train`](/api/cli#train). | ### Converters {#converters} @@ -474,8 +473,7 @@ report span characteristics such as the average span length and the span (or span boundary) distinctiveness. The distinctiveness measure shows how different the tokens are with respect to the rest of the corpus using the KL-divergence of the token distributions. To learn more, you can check out Papay et al.'s work on -[*Dissecting Span Identification Tasks with Performance Prediction* (EMNLP -2020)](https://aclanthology.org/2020.emnlp-main.396/). +[*Dissecting Span Identification Tasks with Performance Prediction* (EMNLP 2020)](https://aclanthology.org/2020.emnlp-main.396/). @@ -1229,19 +1227,19 @@ $ python -m spacy package [input_dir] [output_dir] [--code] [--meta-path] [--cre > $ pip install dist/en_pipeline-0.0.0.tar.gz > ``` -| Name | Description | -| ------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `input_dir` | Path to directory containing pipeline data. ~~Path (positional)~~ | -| `output_dir` | Directory to create package folder in. ~~Path (positional)~~ | -| `--code`, `-c` 3 | Comma-separated paths to Python files to be included in the package and imported in its `__init__.py`. This allows including [registering functions](/usage/training#custom-functions) and [custom components](/usage/processing-pipelines#custom-components). ~~str (option)~~ | -| `--meta-path`, `-m` 2 | Path to [`meta.json`](/api/data-formats#meta) file (optional). ~~Optional[Path] \(option)~~ | -| `--create-meta`, `-C` 2 | Create a `meta.json` file on the command line, even if one already exists in the directory. If an existing file is found, its entries will be shown as the defaults in the command line prompt. ~~bool (flag)~~ | -| `--build`, `-b` 3 | Comma-separated artifact formats to build. Can be `sdist` (for a `.tar.gz` archive) and/or `wheel` (for a binary `.whl` file), or `none` if you want to run this step manually. The generated artifacts can be installed by `pip install`. Defaults to `sdist`. ~~str (option)~~ | -| `--name`, `-n` 3 | Package name to override in meta. ~~Optional[str] \(option)~~ | -| `--version`, `-v` 3 | Package version to override in meta. Useful when training new versions, as it doesn't require editing the meta template. ~~Optional[str] \(option)~~ | -| `--force`, `-f` | Force overwriting of existing folder in output directory. ~~bool (flag)~~ | -| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| **CREATES** | A Python package containing the spaCy pipeline. | +| Name | Description | +| -------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `input_dir` | Path to directory containing pipeline data. ~~Path (positional)~~ | +| `output_dir` | Directory to create package folder in. ~~Path (positional)~~ | +| `--code`, `-c` 3 | Comma-separated paths to Python files to be included in the package and imported in its `__init__.py`. This allows including [registering functions](/usage/training#custom-functions) and [custom components](/usage/processing-pipelines#custom-components). ~~str (option)~~ | +| `--meta-path`, `-m` | Path to [`meta.json`](/api/data-formats#meta) file (optional). ~~Optional[Path] \(option)~~ | +| `--create-meta`, `-C` | Create a `meta.json` file on the command line, even if one already exists in the directory. If an existing file is found, its entries will be shown as the defaults in the command line prompt. ~~bool (flag)~~ | +| `--build`, `-b` 3 | Comma-separated artifact formats to build. Can be `sdist` (for a `.tar.gz` archive) and/or `wheel` (for a binary `.whl` file), or `none` if you want to run this step manually. The generated artifacts can be installed by `pip install`. Defaults to `sdist`. ~~str (option)~~ | +| `--name`, `-n` 3 | Package name to override in meta. ~~Optional[str] \(option)~~ | +| `--version`, `-v` 3 | Package version to override in meta. Useful when training new versions, as it doesn't require editing the meta template. ~~Optional[str] \(option)~~ | +| `--force`, `-f` | Force overwriting of existing folder in output directory. ~~bool (flag)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | +| **CREATES** | A Python package containing the spaCy pipeline. | ## project {#project new="3"} @@ -1482,7 +1480,7 @@ You'll also need to add the assets you want to track with ```cli -$ python -m spacy project dvc [project_dir] [workflow] [--force] [--verbose] +$ python -m spacy project dvc [project_dir] [workflow] [--force] [--verbose] [--quiet] ``` > #### Example @@ -1499,53 +1497,10 @@ $ python -m spacy project dvc [project_dir] [workflow] [--force] [--verbose] | `workflow` | Name of workflow defined in `project.yml`. Defaults to first workflow if not set. ~~Optional[str] \(option)~~ | | `--force`, `-F` | Force-updating config file. ~~bool (flag)~~ | | `--verbose`, `-V` | Print more output generated by DVC. ~~bool (flag)~~ | +| `--quiet`, `-q` | Print no output generated by DVC. ~~bool (flag)~~ | | `--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/coref.md b/website/docs/api/coref.md new file mode 100644 index 000000000..8f54422d6 --- /dev/null +++ b/website/docs/api/coref.md @@ -0,0 +1,353 @@ +--- +title: CoreferenceResolver +tag: class,experimental +source: spacy-experimental/coref/coref_component.py +teaser: 'Pipeline component for word-level coreference resolution' +api_base_class: /api/pipe +api_string_name: coref +api_trainable: true +--- + +> #### Installation +> +> ```bash +> $ pip install -U spacy-experimental +> ``` + + + +This component is not yet integrated into spaCy core, and is available via the +extension package +[`spacy-experimental`](https://github.com/explosion/spacy-experimental) starting +in version 0.6.0. It exposes the component via +[entry points](/usage/saving-loading/#entry-points), so if you have the package +installed, using `factory = "experimental_coref"` in your +[training config](/usage/training#config) or +`nlp.add_pipe("experimental_coref")` will work out-of-the-box. + + + +A `CoreferenceResolver` component groups tokens into clusters that refer to the +same thing. Clusters are represented as SpanGroups that start with a prefix +(`coref_clusters` by default). + +A `CoreferenceResolver` component can be paired with a +[`SpanResolver`](/api/span-resolver) to expand single tokens to spans. + +## Assigned Attributes {#assigned-attributes} + +Predictions will be saved to `Doc.spans` as a [`SpanGroup`](/api/spangroup). The +span key will be a prefix plus a serial number referring to the coreference +cluster, starting from zero. + +The span key prefix defaults to `"coref_clusters"`, but can be passed as a +parameter. + +| Location | Value | +| ------------------------------------------ | ------------------------------------------------------------------------------------------------------- | +| `Doc.spans[prefix + "_" + cluster_number]` | One coreference cluster, represented as single-token spans. Cluster numbers start from 1. ~~SpanGroup~~ | + +## Config and implementation {#config} + +The default config is defined by the pipeline component factory and describes +how the component should be configured. You can override its settings via the +`config` argument on [`nlp.add_pipe`](/api/language#add_pipe) or in your +[`config.cfg` for training](/usage/training#config). See the +[model architectures](/api/architectures#coref-architectures) documentation for +details on the architectures and their arguments and hyperparameters. + +> #### Example +> +> ```python +> from spacy_experimental.coref.coref_component import DEFAULT_COREF_MODEL +> from spacy_experimental.coref.coref_util import DEFAULT_CLUSTER_PREFIX +> config={ +> "model": DEFAULT_COREF_MODEL, +> "span_cluster_prefix": DEFAULT_CLUSTER_PREFIX, +> }, +> nlp.add_pipe("experimental_coref", config=config) +> ``` + +| Setting | Description | +| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | +| `model` | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. Defaults to [Coref](/api/architectures#Coref). ~~Model~~ | +| `span_cluster_prefix` | The prefix for the keys for clusters saved to `doc.spans`. Defaults to `coref_clusters`. ~~str~~ | + +## CoreferenceResolver.\_\_init\_\_ {#init tag="method"} + +> #### Example +> +> ```python +> # Construction via add_pipe with default model +> coref = nlp.add_pipe("experimental_coref") +> +> # Construction via add_pipe with custom model +> config = {"model": {"@architectures": "my_coref.v1"}} +> coref = nlp.add_pipe("experimental_coref", config=config) +> +> # Construction from class +> from spacy_experimental.coref.coref_component import CoreferenceResolver +> coref = CoreferenceResolver(nlp.vocab, model) +> ``` + +Create a new pipeline instance. In your application, you would normally use a +shortcut for this and instantiate the component using its string name and +[`nlp.add_pipe`](/api/language#add_pipe). + +| Name | Description | +| --------------------- | --------------------------------------------------------------------------------------------------- | +| `vocab` | The shared vocabulary. ~~Vocab~~ | +| `model` | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. ~~Model~~ | +| `name` | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~ | +| _keyword-only_ | | +| `span_cluster_prefix` | The prefix for the key for saving clusters of spans. ~~bool~~ | + +## CoreferenceResolver.\_\_call\_\_ {#call tag="method"} + +Apply the pipe to one document. The document is modified in place and returned. +This usually happens under the hood when the `nlp` object is called on a text +and all pipeline components are applied to the `Doc` in order. Both +[`__call__`](/api/coref#call) and [`pipe`](/api/coref#pipe) delegate to the +[`predict`](/api/coref#predict) and +[`set_annotations`](/api/coref#set_annotations) methods. + +> #### Example +> +> ```python +> doc = nlp("This is a sentence.") +> coref = nlp.add_pipe("experimental_coref") +> # This usually happens under the hood +> processed = coref(doc) +> ``` + +| Name | Description | +| ----------- | -------------------------------- | +| `doc` | The document to process. ~~Doc~~ | +| **RETURNS** | The processed document. ~~Doc~~ | + +## CoreferenceResolver.pipe {#pipe tag="method"} + +Apply the pipe to a stream of documents. This usually happens under the hood +when the `nlp` object is called on a text and all pipeline components are +applied to the `Doc` in order. Both [`__call__`](/api/coref#call) and +[`pipe`](/api/coref#pipe) delegate to the [`predict`](/api/coref#predict) and +[`set_annotations`](/api/coref#set_annotations) methods. + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> for doc in coref.pipe(docs, batch_size=50): +> pass +> ``` + +| Name | Description | +| -------------- | ------------------------------------------------------------- | +| `stream` | A stream of documents. ~~Iterable[Doc]~~ | +| _keyword-only_ | | +| `batch_size` | The number of documents to buffer. Defaults to `128`. ~~int~~ | +| **YIELDS** | The processed documents in order. ~~Doc~~ | + +## CoreferenceResolver.initialize {#initialize tag="method"} + +Initialize the component for training. `get_examples` should be a function that +returns an iterable of [`Example`](/api/example) objects. **At least one example +should be supplied.** The data examples are used to **initialize the model** of +the component and can either be the full training data or a representative +sample. Initialization includes validating the network, +[inferring missing shapes](https://thinc.ai/docs/usage-models#validation) and +setting up the label scheme based on the data. This method is typically called +by [`Language.initialize`](/api/language#initialize). + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> coref.initialize(lambda: examples, nlp=nlp) +> ``` + +| Name | Description | +| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `get_examples` | Function that returns gold-standard annotations in the form of [`Example`](/api/example) objects. Must contain at least one `Example`. ~~Callable[[], Iterable[Example]]~~ | +| _keyword-only_ | | +| `nlp` | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~ | + +## CoreferenceResolver.predict {#predict tag="method"} + +Apply the component's model to a batch of [`Doc`](/api/doc) objects, without +modifying them. Clusters are returned as a list of `MentionClusters`, one for +each input `Doc`. A `MentionClusters` instance is just a list of lists of pairs +of `int`s, where each item corresponds to a cluster, and the `int`s correspond +to token indices. + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> clusters = coref.predict([doc1, doc2]) +> ``` + +| Name | Description | +| ----------- | ---------------------------------------------------------------------------- | +| `docs` | The documents to predict. ~~Iterable[Doc]~~ | +| **RETURNS** | The predicted coreference clusters for the `docs`. ~~List[MentionClusters]~~ | + +## CoreferenceResolver.set_annotations {#set_annotations tag="method"} + +Modify a batch of documents, saving coreference clusters in `Doc.spans`. + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> clusters = coref.predict([doc1, doc2]) +> coref.set_annotations([doc1, doc2], clusters) +> ``` + +| Name | Description | +| ---------- | ---------------------------------------------------------------------------- | +| `docs` | The documents to modify. ~~Iterable[Doc]~~ | +| `clusters` | The predicted coreference clusters for the `docs`. ~~List[MentionClusters]~~ | + +## CoreferenceResolver.update {#update tag="method"} + +Learn from a batch of [`Example`](/api/example) objects. Delegates to +[`predict`](/api/coref#predict). + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> optimizer = nlp.initialize() +> losses = coref.update(examples, sgd=optimizer) +> ``` + +| Name | Description | +| -------------- | ------------------------------------------------------------------------------------------------------------------------ | +| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ | +| _keyword-only_ | | +| `drop` | The dropout rate. ~~float~~ | +| `sgd` | An optimizer. Will be created via [`create_optimizer`](#create_optimizer) if not set. ~~Optional[Optimizer]~~ | +| `losses` | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ | +| **RETURNS** | The updated `losses` dictionary. ~~Dict[str, float]~~ | + +## CoreferenceResolver.create_optimizer {#create_optimizer tag="method"} + +Create an optimizer for the pipeline component. + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> optimizer = coref.create_optimizer() +> ``` + +| Name | Description | +| ----------- | ---------------------------- | +| **RETURNS** | The optimizer. ~~Optimizer~~ | + +## CoreferenceResolver.use_params {#use_params tag="method, contextmanager"} + +Modify the pipe's model, to use the given parameter values. At the end of the +context, the original parameters are restored. + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> with coref.use_params(optimizer.averages): +> coref.to_disk("/best_model") +> ``` + +| Name | Description | +| -------- | -------------------------------------------------- | +| `params` | The parameter values to use in the model. ~~dict~~ | + +## CoreferenceResolver.to_disk {#to_disk tag="method"} + +Serialize the pipe to disk. + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> coref.to_disk("/path/to/coref") +> ``` + +| Name | Description | +| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | +| `path` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| _keyword-only_ | | +| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ | + +## CoreferenceResolver.from_disk {#from_disk tag="method"} + +Load the pipe from disk. Modifies the object in place and returns it. + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> coref.from_disk("/path/to/coref") +> ``` + +| Name | Description | +| -------------- | ----------------------------------------------------------------------------------------------- | +| `path` | A path to a directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| _keyword-only_ | | +| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ | +| **RETURNS** | The modified `CoreferenceResolver` object. ~~CoreferenceResolver~~ | + +## CoreferenceResolver.to_bytes {#to_bytes tag="method"} + +> #### Example +> +> ```python +> coref = nlp.add_pipe("experimental_coref") +> coref_bytes = coref.to_bytes() +> ``` + +Serialize the pipe to a bytestring, including the `KnowledgeBase`. + +| Name | Description | +| -------------- | ------------------------------------------------------------------------------------------- | +| _keyword-only_ | | +| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ | +| **RETURNS** | The serialized form of the `CoreferenceResolver` object. ~~bytes~~ | + +## CoreferenceResolver.from_bytes {#from_bytes tag="method"} + +Load the pipe from a bytestring. Modifies the object in place and returns it. + +> #### Example +> +> ```python +> coref_bytes = coref.to_bytes() +> coref = nlp.add_pipe("experimental_coref") +> coref.from_bytes(coref_bytes) +> ``` + +| Name | Description | +| -------------- | ------------------------------------------------------------------------------------------- | +| `bytes_data` | The data to load from. ~~bytes~~ | +| _keyword-only_ | | +| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ | +| **RETURNS** | The `CoreferenceResolver` object. ~~CoreferenceResolver~~ | + +## Serialization fields {#serialization-fields} + +During serialization, spaCy will export several data fields used to restore +different aspects of the object. If needed, you can exclude them from +serialization by passing in the string names via the `exclude` argument. + +> #### Example +> +> ```python +> data = coref.to_disk("/path", exclude=["vocab"]) +> ``` + +| Name | Description | +| ------- | -------------------------------------------------------------- | +| `vocab` | The shared [`Vocab`](/api/vocab). | +| `cfg` | The config file. You usually don't want to exclude this. | +| `model` | The binary model data. You usually don't want to exclude this. | diff --git a/website/docs/api/doc.md b/website/docs/api/doc.md index f97f4ad83..090489d83 100644 --- a/website/docs/api/doc.md +++ b/website/docs/api/doc.md @@ -31,21 +31,21 @@ Construct a `Doc` object. The most common way to get a `Doc` object is via the > doc = Doc(nlp.vocab, words=words, spaces=spaces) > ``` -| Name | Description | -| ---------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `vocab` | A storage container for lexical types. ~~Vocab~~ | -| `words` | A list of strings or integer hash values to add to the document as words. ~~Optional[List[Union[str,int]]]~~ | -| `spaces` | A list of boolean values indicating whether each word has a subsequent space. Must have the same length as `words`, if specified. Defaults to a sequence of `True`. ~~Optional[List[bool]]~~ | -| _keyword-only_ | | -| `user\_data` | Optional extra data to attach to the Doc. ~~Dict~~ | -| `tags` 3 | A list of strings, of the same length as `words`, to assign as `token.tag` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | -| `pos` 3 | A list of strings, of the same length as `words`, to assign as `token.pos` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | -| `morphs` 3 | A list of strings, of the same length as `words`, to assign as `token.morph` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | -| `lemmas` 3 | A list of strings, of the same length as `words`, to assign as `token.lemma` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | -| `heads` 3 | A list of values, of the same length as `words`, to assign as the head for each word. Head indices are the absolute position of the head in the `Doc`. Defaults to `None`. ~~Optional[List[int]]~~ | -| `deps` 3 | A list of strings, of the same length as `words`, to assign as `token.dep` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | -| `sent_starts` 3 | A list of values, of the same length as `words`, to assign as `token.is_sent_start`. Will be overridden by heads if `heads` is provided. Defaults to `None`. ~~Optional[List[Optional[bool]]]~~ | -| `ents` 3 | A list of strings, of the same length of `words`, to assign the token-based IOB tag. Defaults to `None`. ~~Optional[List[str]]~~ | +| Name | Description | +| ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `vocab` | A storage container for lexical types. ~~Vocab~~ | +| `words` | A list of strings or integer hash values to add to the document as words. ~~Optional[List[Union[str,int]]]~~ | +| `spaces` | A list of boolean values indicating whether each word has a subsequent space. Must have the same length as `words`, if specified. Defaults to a sequence of `True`. ~~Optional[List[bool]]~~ | +| _keyword-only_ | | +| `user\_data` | Optional extra data to attach to the Doc. ~~Dict~~ | +| `tags` 3 | A list of strings, of the same length as `words`, to assign as `token.tag` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | +| `pos` 3 | A list of strings, of the same length as `words`, to assign as `token.pos` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | +| `morphs` 3 | A list of strings, of the same length as `words`, to assign as `token.morph` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | +| `lemmas` 3 | A list of strings, of the same length as `words`, to assign as `token.lemma` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | +| `heads` 3 | A list of values, of the same length as `words`, to assign as the head for each word. Head indices are the absolute position of the head in the `Doc`. Defaults to `None`. ~~Optional[List[int]]~~ | +| `deps` 3 | A list of strings, of the same length as `words`, to assign as `token.dep` for each word. Defaults to `None`. ~~Optional[List[str]]~~ | +| `sent_starts` 3 | A list of values, of the same length as `words`, to assign as `token.is_sent_start`. Will be overridden by heads if `heads` is provided. Defaults to `None`. ~~Optional[List[Union[bool, int, None]]]~~ | +| `ents` 3 | A list of strings, of the same length of `words`, to assign the token-based IOB tag. Defaults to `None`. ~~Optional[List[str]]~~ | ## Doc.\_\_getitem\_\_ {#getitem tag="method"} @@ -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/entitylinker.md b/website/docs/api/entitylinker.md index 43e08a39c..40ec8afb5 100644 --- a/website/docs/api/entitylinker.md +++ b/website/docs/api/entitylinker.md @@ -14,7 +14,8 @@ entities) to unique identifiers, grounding the named entities into the "real world". It requires a `KnowledgeBase`, as well as a function to generate plausible candidates from that `KnowledgeBase` given a certain textual mention, and a machine learning model to pick the right candidate, given the local -context of the mention. +context of the mention. `EntityLinker` defaults to using the +[`InMemoryLookupKB`](/api/kb_in_memory) implementation. ## Assigned Attributes {#assigned-attributes} @@ -170,7 +171,7 @@ with the current vocab. > > ```python > def create_kb(vocab): -> kb = KnowledgeBase(vocab, entity_vector_length=128) +> kb = InMemoryLookupKB(vocab, entity_vector_length=128) > kb.add_entity(...) > kb.add_alias(...) > return kb diff --git a/website/docs/api/kb.md b/website/docs/api/kb.md index e7a8fcd6f..b217a1678 100644 --- a/website/docs/api/kb.md +++ b/website/docs/api/kb.md @@ -4,27 +4,45 @@ teaser: A storage class for entities and aliases of a specific knowledge base (ontology) tag: class -source: spacy/kb.pyx +source: spacy/kb/kb.pyx new: 2.2 --- -The `KnowledgeBase` object provides a method to generate -[`Candidate`](/api/kb/#candidate) objects, which are plausible external +The `KnowledgeBase` object is an abstract class providing a method to generate +[`Candidate`](/api/kb#candidate) objects, which are plausible external identifiers given a certain textual mention. Each such `Candidate` holds information from the relevant KB entities, such as its frequency in text and possible aliases. Each entity in the knowledge base also has a pretrained entity vector of a fixed size. +Beyond that, `KnowledgeBase` classes have to implement a number of utility +functions called by the [`EntityLinker`](/api/entitylinker) component. + + + +This class was not abstract up to spaCy version 3.5. The `KnowledgeBase` +implementation up to that point is available as `InMemoryLookupKB` from 3.5 +onwards. + + + ## KnowledgeBase.\_\_init\_\_ {#init tag="method"} -Create the knowledge base. +`KnowledgeBase` is an abstract class and cannot be instantiated. Its child +classes should call `__init__()` to set up some necessary attributes. > #### Example > > ```python > from spacy.kb import KnowledgeBase +> from spacy.vocab import Vocab +> +> class FullyImplementedKB(KnowledgeBase): +> def __init__(self, vocab: Vocab, entity_vector_length: int): +> super().__init__(vocab, entity_vector_length) +> ... > vocab = nlp.vocab -> kb = KnowledgeBase(vocab=vocab, entity_vector_length=64) +> kb = FullyImplementedKB(vocab=vocab, entity_vector_length=64) > ``` | Name | Description | @@ -40,133 +58,66 @@ The length of the fixed-size entity vectors in the knowledge base. | ----------- | ------------------------------------------------ | | **RETURNS** | Length of the fixed-size entity vectors. ~~int~~ | -## KnowledgeBase.add_entity {#add_entity tag="method"} +## KnowledgeBase.get_candidates {#get_candidates tag="method"} -Add an entity to the knowledge base, specifying its corpus frequency and entity -vector, which should be of length -[`entity_vector_length`](/api/kb#entity_vector_length). +Given a certain textual mention as input, retrieve a list of candidate entities +of type [`Candidate`](/api/kb#candidate). > #### Example > > ```python -> kb.add_entity(entity="Q42", freq=32, entity_vector=vector1) -> kb.add_entity(entity="Q463035", freq=111, entity_vector=vector2) +> from spacy.lang.en import English +> nlp = English() +> doc = nlp("Douglas Adams wrote 'The Hitchhiker's Guide to the Galaxy'.") +> candidates = kb.get_candidates(doc[0:2]) > ``` -| Name | Description | -| --------------- | ---------------------------------------------------------- | -| `entity` | The unique entity identifier. ~~str~~ | -| `freq` | The frequency of the entity in a typical corpus. ~~float~~ | -| `entity_vector` | The pretrained vector of the entity. ~~numpy.ndarray~~ | +| Name | Description | +| ----------- | -------------------------------------------------------------------- | +| `mention` | The textual mention or alias. ~~Span~~ | +| **RETURNS** | An iterable of relevant `Candidate` objects. ~~Iterable[Candidate]~~ | -## KnowledgeBase.set_entities {#set_entities tag="method"} +## KnowledgeBase.get_candidates_batch {#get_candidates_batch tag="method"} -Define the full list of entities in the knowledge base, specifying the corpus -frequency and entity vector for each entity. +Same as [`get_candidates()`](/api/kb#get_candidates), but for an arbitrary +number of mentions. The [`EntityLinker`](/api/entitylinker) component will call +`get_candidates_batch()` instead of `get_candidates()`, if the config parameter +`candidates_batch_size` is greater or equal than 1. + +The default implementation of `get_candidates_batch()` executes +`get_candidates()` in a loop. We recommend implementing a more efficient way to +retrieve candidates for multiple mentions at once, if performance is of concern +to you. > #### Example > > ```python -> kb.set_entities(entity_list=["Q42", "Q463035"], freq_list=[32, 111], vector_list=[vector1, vector2]) +> from spacy.lang.en import English +> nlp = English() +> doc = nlp("Douglas Adams wrote 'The Hitchhiker's Guide to the Galaxy'.") +> candidates = kb.get_candidates((doc[0:2], doc[3:])) > ``` -| Name | Description | -| ------------- | ---------------------------------------------------------------- | -| `entity_list` | List of unique entity identifiers. ~~Iterable[Union[str, int]]~~ | -| `freq_list` | List of entity frequencies. ~~Iterable[int]~~ | -| `vector_list` | List of entity vectors. ~~Iterable[numpy.ndarray]~~ | - -## KnowledgeBase.add_alias {#add_alias tag="method"} - -Add an alias or mention to the knowledge base, specifying its potential KB -identifiers and their prior probabilities. The entity identifiers should refer -to entities previously added with [`add_entity`](/api/kb#add_entity) or -[`set_entities`](/api/kb#set_entities). The sum of the prior probabilities -should not exceed 1. Note that an empty string can not be used as alias. - -> #### Example -> -> ```python -> kb.add_alias(alias="Douglas", entities=["Q42", "Q463035"], probabilities=[0.6, 0.3]) -> ``` - -| Name | Description | -| --------------- | --------------------------------------------------------------------------------- | -| `alias` | The textual mention or alias. Can not be the empty string. ~~str~~ | -| `entities` | The potential entities that the alias may refer to. ~~Iterable[Union[str, int]]~~ | -| `probabilities` | The prior probabilities of each entity. ~~Iterable[float]~~ | - -## KnowledgeBase.\_\_len\_\_ {#len tag="method"} - -Get the total number of entities in the knowledge base. - -> #### Example -> -> ```python -> total_entities = len(kb) -> ``` - -| Name | Description | -| ----------- | ----------------------------------------------------- | -| **RETURNS** | The number of entities in the knowledge base. ~~int~~ | - -## KnowledgeBase.get_entity_strings {#get_entity_strings tag="method"} - -Get a list of all entity IDs in the knowledge base. - -> #### Example -> -> ```python -> all_entities = kb.get_entity_strings() -> ``` - -| Name | Description | -| ----------- | --------------------------------------------------------- | -| **RETURNS** | The list of entities in the knowledge base. ~~List[str]~~ | - -## KnowledgeBase.get_size_aliases {#get_size_aliases tag="method"} - -Get the total number of aliases in the knowledge base. - -> #### Example -> -> ```python -> total_aliases = kb.get_size_aliases() -> ``` - -| Name | Description | -| ----------- | ---------------------------------------------------- | -| **RETURNS** | The number of aliases in the knowledge base. ~~int~~ | - -## KnowledgeBase.get_alias_strings {#get_alias_strings tag="method"} - -Get a list of all aliases in the knowledge base. - -> #### Example -> -> ```python -> all_aliases = kb.get_alias_strings() -> ``` - -| Name | Description | -| ----------- | -------------------------------------------------------- | -| **RETURNS** | The list of aliases in the knowledge base. ~~List[str]~~ | +| Name | Description | +| ----------- | -------------------------------------------------------------------------------------------- | +| `mentions` | The textual mention or alias. ~~Iterable[Span]~~ | +| **RETURNS** | An iterable of iterable with relevant `Candidate` objects. ~~Iterable[Iterable[Candidate]]~~ | ## KnowledgeBase.get_alias_candidates {#get_alias_candidates tag="method"} -Given a certain textual mention as input, retrieve a list of candidate entities -of type [`Candidate`](/api/kb/#candidate). + +This method is _not_ available from spaCy 3.5 onwards. + -> #### Example -> -> ```python -> candidates = kb.get_alias_candidates("Douglas") -> ``` - -| Name | Description | -| ----------- | ------------------------------------------------------------- | -| `alias` | The textual mention or alias. ~~str~~ | -| **RETURNS** | The list of relevant `Candidate` objects. ~~List[Candidate]~~ | +From spaCy 3.5 on `KnowledgeBase` is an abstract class (with +[`InMemoryLookupKB`](/api/kb_in_memory) being a drop-in replacement) to allow +more flexibility in customizing knowledge bases. Some of its methods were moved +to [`InMemoryLookupKB`](/api/kb_in_memory) during this refactoring, one of those +being `get_alias_candidates()`. This method is now available as +[`InMemoryLookupKB.get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates). +Note: [`InMemoryLookupKB.get_candidates()`](/api/kb_in_memory#get_candidates) +defaults to +[`InMemoryLookupKB.get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates). ## KnowledgeBase.get_vector {#get_vector tag="method"} @@ -178,27 +129,30 @@ Given a certain entity ID, retrieve its pretrained entity vector. > vector = kb.get_vector("Q42") > ``` -| Name | Description | -| ----------- | ------------------------------------ | -| `entity` | The entity ID. ~~str~~ | -| **RETURNS** | The entity vector. ~~numpy.ndarray~~ | +| Name | Description | +| ----------- | -------------------------------------- | +| `entity` | The entity ID. ~~str~~ | +| **RETURNS** | The entity vector. ~~Iterable[float]~~ | -## KnowledgeBase.get_prior_prob {#get_prior_prob tag="method"} +## KnowledgeBase.get_vectors {#get_vectors tag="method"} -Given a certain entity ID and a certain textual mention, retrieve the prior -probability of the fact that the mention links to the entity ID. +Same as [`get_vector()`](/api/kb#get_vector), but for an arbitrary number of +entity IDs. + +The default implementation of `get_vectors()` executes `get_vector()` in a loop. +We recommend implementing a more efficient way to retrieve vectors for multiple +entities at once, if performance is of concern to you. > #### Example > > ```python -> probability = kb.get_prior_prob("Q42", "Douglas") +> vectors = kb.get_vectors(("Q42", "Q3107329")) > ``` -| Name | Description | -| ----------- | ------------------------------------------------------------------------- | -| `entity` | The entity ID. ~~str~~ | -| `alias` | The textual mention or alias. ~~str~~ | -| **RETURNS** | The prior probability of the `alias` referring to the `entity`. ~~float~~ | +| Name | Description | +| ----------- | --------------------------------------------------------- | +| `entities` | The entity IDs. ~~Iterable[str]~~ | +| **RETURNS** | The entity vectors. ~~Iterable[Iterable[numpy.ndarray]]~~ | ## KnowledgeBase.to_disk {#to_disk tag="method"} @@ -207,12 +161,13 @@ Save the current state of the knowledge base to a directory. > #### Example > > ```python -> kb.to_disk(loc) +> kb.to_disk(path) > ``` -| Name | Description | -| ----- | ------------------------------------------------------------------------------------------------------------------------------------------ | -| `loc` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| Name | Description | +| --------- | ------------------------------------------------------------------------------------------------------------------------------------------ | +| `path` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| `exclude` | List of components to exclude. ~~Iterable[str]~~ | ## KnowledgeBase.from_disk {#from_disk tag="method"} @@ -222,16 +177,16 @@ Restore the state of the knowledge base from a given directory. Note that the > #### Example > > ```python -> from spacy.kb import KnowledgeBase > from spacy.vocab import Vocab > vocab = Vocab().from_disk("/path/to/vocab") -> kb = KnowledgeBase(vocab=vocab, entity_vector_length=64) +> kb = FullyImplementedKB(vocab=vocab, entity_vector_length=64) > kb.from_disk("/path/to/kb") > ``` | Name | Description | | ----------- | ----------------------------------------------------------------------------------------------- | | `loc` | A path to a directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| `exclude` | List of components to exclude. ~~Iterable[str]~~ | | **RETURNS** | The modified `KnowledgeBase` object. ~~KnowledgeBase~~ | ## Candidate {#candidate tag="class"} diff --git a/website/docs/api/kb_in_memory.md b/website/docs/api/kb_in_memory.md new file mode 100644 index 000000000..9e3279e6a --- /dev/null +++ b/website/docs/api/kb_in_memory.md @@ -0,0 +1,302 @@ +--- +title: InMemoryLookupKB +teaser: + The default implementation of the KnowledgeBase interface. Stores all + information in-memory. +tag: class +source: spacy/kb/kb_in_memory.pyx +new: 3.5 +--- + +The `InMemoryLookupKB` class inherits from [`KnowledgeBase`](/api/kb) and +implements all of its methods. It stores all KB data in-memory and generates +[`Candidate`](/api/kb#candidate) objects by exactly matching mentions with +entity names. It's highly optimized for both a low memory footprint and speed of +retrieval. + +## InMemoryLookupKB.\_\_init\_\_ {#init tag="method"} + +Create the knowledge base. + +> #### Example +> +> ```python +> from spacy.kb import InMemoryLookupKB +> vocab = nlp.vocab +> kb = InMemoryLookupKB(vocab=vocab, entity_vector_length=64) +> ``` + +| Name | Description | +| ---------------------- | ------------------------------------------------ | +| `vocab` | The shared vocabulary. ~~Vocab~~ | +| `entity_vector_length` | Length of the fixed-size entity vectors. ~~int~~ | + +## InMemoryLookupKB.entity_vector_length {#entity_vector_length tag="property"} + +The length of the fixed-size entity vectors in the knowledge base. + +| Name | Description | +| ----------- | ------------------------------------------------ | +| **RETURNS** | Length of the fixed-size entity vectors. ~~int~~ | + +## InMemoryLookupKB.add_entity {#add_entity tag="method"} + +Add an entity to the knowledge base, specifying its corpus frequency and entity +vector, which should be of length +[`entity_vector_length`](/api/kb_in_memory#entity_vector_length). + +> #### Example +> +> ```python +> kb.add_entity(entity="Q42", freq=32, entity_vector=vector1) +> kb.add_entity(entity="Q463035", freq=111, entity_vector=vector2) +> ``` + +| Name | Description | +| --------------- | ---------------------------------------------------------- | +| `entity` | The unique entity identifier. ~~str~~ | +| `freq` | The frequency of the entity in a typical corpus. ~~float~~ | +| `entity_vector` | The pretrained vector of the entity. ~~numpy.ndarray~~ | + +## InMemoryLookupKB.set_entities {#set_entities tag="method"} + +Define the full list of entities in the knowledge base, specifying the corpus +frequency and entity vector for each entity. + +> #### Example +> +> ```python +> kb.set_entities(entity_list=["Q42", "Q463035"], freq_list=[32, 111], vector_list=[vector1, vector2]) +> ``` + +| Name | Description | +| ------------- | ---------------------------------------------------------------- | +| `entity_list` | List of unique entity identifiers. ~~Iterable[Union[str, int]]~~ | +| `freq_list` | List of entity frequencies. ~~Iterable[int]~~ | +| `vector_list` | List of entity vectors. ~~Iterable[numpy.ndarray]~~ | + +## InMemoryLookupKB.add_alias {#add_alias tag="method"} + +Add an alias or mention to the knowledge base, specifying its potential KB +identifiers and their prior probabilities. The entity identifiers should refer +to entities previously added with [`add_entity`](/api/kb_in_memory#add_entity) +or [`set_entities`](/api/kb_in_memory#set_entities). The sum of the prior +probabilities should not exceed 1. Note that an empty string can not be used as +alias. + +> #### Example +> +> ```python +> kb.add_alias(alias="Douglas", entities=["Q42", "Q463035"], probabilities=[0.6, 0.3]) +> ``` + +| Name | Description | +| --------------- | --------------------------------------------------------------------------------- | +| `alias` | The textual mention or alias. Can not be the empty string. ~~str~~ | +| `entities` | The potential entities that the alias may refer to. ~~Iterable[Union[str, int]]~~ | +| `probabilities` | The prior probabilities of each entity. ~~Iterable[float]~~ | + +## InMemoryLookupKB.\_\_len\_\_ {#len tag="method"} + +Get the total number of entities in the knowledge base. + +> #### Example +> +> ```python +> total_entities = len(kb) +> ``` + +| Name | Description | +| ----------- | ----------------------------------------------------- | +| **RETURNS** | The number of entities in the knowledge base. ~~int~~ | + +## InMemoryLookupKB.get_entity_strings {#get_entity_strings tag="method"} + +Get a list of all entity IDs in the knowledge base. + +> #### Example +> +> ```python +> all_entities = kb.get_entity_strings() +> ``` + +| Name | Description | +| ----------- | --------------------------------------------------------- | +| **RETURNS** | The list of entities in the knowledge base. ~~List[str]~~ | + +## InMemoryLookupKB.get_size_aliases {#get_size_aliases tag="method"} + +Get the total number of aliases in the knowledge base. + +> #### Example +> +> ```python +> total_aliases = kb.get_size_aliases() +> ``` + +| Name | Description | +| ----------- | ---------------------------------------------------- | +| **RETURNS** | The number of aliases in the knowledge base. ~~int~~ | + +## InMemoryLookupKB.get_alias_strings {#get_alias_strings tag="method"} + +Get a list of all aliases in the knowledge base. + +> #### Example +> +> ```python +> all_aliases = kb.get_alias_strings() +> ``` + +| Name | Description | +| ----------- | -------------------------------------------------------- | +| **RETURNS** | The list of aliases in the knowledge base. ~~List[str]~~ | + +## InMemoryLookupKB.get_candidates {#get_candidates tag="method"} + +Given a certain textual mention as input, retrieve a list of candidate entities +of type [`Candidate`](/api/kb#candidate). Wraps +[`get_alias_candidates()`](/api/kb_in_memory#get_alias_candidates). + +> #### Example +> +> ```python +> from spacy.lang.en import English +> nlp = English() +> doc = nlp("Douglas Adams wrote 'The Hitchhiker's Guide to the Galaxy'.") +> candidates = kb.get_candidates(doc[0:2]) +> ``` + +| Name | Description | +| ----------- | -------------------------------------------------------------------- | +| `mention` | The textual mention or alias. ~~Span~~ | +| **RETURNS** | An iterable of relevant `Candidate` objects. ~~Iterable[Candidate]~~ | + +## InMemoryLookupKB.get_candidates_batch {#get_candidates_batch tag="method"} + +Same as [`get_candidates()`](/api/kb_in_memory#get_candidates), but for an +arbitrary number of mentions. The [`EntityLinker`](/api/entitylinker) component +will call `get_candidates_batch()` instead of `get_candidates()`, if the config +parameter `candidates_batch_size` is greater or equal than 1. + +The default implementation of `get_candidates_batch()` executes +`get_candidates()` in a loop. We recommend implementing a more efficient way to +retrieve candidates for multiple mentions at once, if performance is of concern +to you. + +> #### Example +> +> ```python +> from spacy.lang.en import English +> nlp = English() +> doc = nlp("Douglas Adams wrote 'The Hitchhiker's Guide to the Galaxy'.") +> candidates = kb.get_candidates((doc[0:2], doc[3:])) +> ``` + +| Name | Description | +| ----------- | -------------------------------------------------------------------------------------------- | +| `mentions` | The textual mention or alias. ~~Iterable[Span]~~ | +| **RETURNS** | An iterable of iterable with relevant `Candidate` objects. ~~Iterable[Iterable[Candidate]]~~ | + +## InMemoryLookupKB.get_alias_candidates {#get_alias_candidates tag="method"} + +Given a certain textual mention as input, retrieve a list of candidate entities +of type [`Candidate`](/api/kb#candidate). + +> #### Example +> +> ```python +> candidates = kb.get_alias_candidates("Douglas") +> ``` + +| Name | Description | +| ----------- | ------------------------------------------------------------- | +| `alias` | The textual mention or alias. ~~str~~ | +| **RETURNS** | The list of relevant `Candidate` objects. ~~List[Candidate]~~ | + +## InMemoryLookupKB.get_vector {#get_vector tag="method"} + +Given a certain entity ID, retrieve its pretrained entity vector. + +> #### Example +> +> ```python +> vector = kb.get_vector("Q42") +> ``` + +| Name | Description | +| ----------- | ------------------------------------ | +| `entity` | The entity ID. ~~str~~ | +| **RETURNS** | The entity vector. ~~numpy.ndarray~~ | + +## InMemoryLookupKB.get_vectors {#get_vectors tag="method"} + +Same as [`get_vector()`](/api/kb_in_memory#get_vector), but for an arbitrary +number of entity IDs. + +The default implementation of `get_vectors()` executes `get_vector()` in a loop. +We recommend implementing a more efficient way to retrieve vectors for multiple +entities at once, if performance is of concern to you. + +> #### Example +> +> ```python +> vectors = kb.get_vectors(("Q42", "Q3107329")) +> ``` + +| Name | Description | +| ----------- | --------------------------------------------------------- | +| `entities` | The entity IDs. ~~Iterable[str]~~ | +| **RETURNS** | The entity vectors. ~~Iterable[Iterable[numpy.ndarray]]~~ | + +## InMemoryLookupKB.get_prior_prob {#get_prior_prob tag="method"} + +Given a certain entity ID and a certain textual mention, retrieve the prior +probability of the fact that the mention links to the entity ID. + +> #### Example +> +> ```python +> probability = kb.get_prior_prob("Q42", "Douglas") +> ``` + +| Name | Description | +| ----------- | ------------------------------------------------------------------------- | +| `entity` | The entity ID. ~~str~~ | +| `alias` | The textual mention or alias. ~~str~~ | +| **RETURNS** | The prior probability of the `alias` referring to the `entity`. ~~float~~ | + +## InMemoryLookupKB.to_disk {#to_disk tag="method"} + +Save the current state of the knowledge base to a directory. + +> #### Example +> +> ```python +> kb.to_disk(path) +> ``` + +| Name | Description | +| --------- | ------------------------------------------------------------------------------------------------------------------------------------------ | +| `path` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| `exclude` | List of components to exclude. ~~Iterable[str]~~ | + +## InMemoryLookupKB.from_disk {#from_disk tag="method"} + +Restore the state of the knowledge base from a given directory. Note that the +[`Vocab`](/api/vocab) should also be the same as the one used to create the KB. + +> #### Example +> +> ```python +> from spacy.vocab import Vocab +> vocab = Vocab().from_disk("/path/to/vocab") +> kb = FullyImplementedKB(vocab=vocab, entity_vector_length=64) +> kb.from_disk("/path/to/kb") +> ``` + +| Name | Description | +| ----------- | ----------------------------------------------------------------------------------------------- | +| `loc` | A path to a directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| `exclude` | List of components to exclude. ~~Iterable[str]~~ | +| **RETURNS** | The modified `KnowledgeBase` object. ~~KnowledgeBase~~ | diff --git a/website/docs/api/language.md b/website/docs/api/language.md index ed763e36a..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"} @@ -164,6 +164,9 @@ examples, see the Apply the pipeline to some text. The text can span multiple sentences, and can contain arbitrary whitespace. Alignment into the original string is preserved. +Instead of text, a `Doc` can be passed as input, in which case tokenization is +skipped, but the rest of the pipeline is run. + > #### Example > > ```python @@ -173,7 +176,7 @@ contain arbitrary whitespace. Alignment into the original string is preserved. | Name | Description | | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | -| `text` | The text to be processed. ~~str~~ | +| `text` | The text to be processed, or a Doc. ~~Union[str, Doc]~~ | | _keyword-only_ | | | `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]]]~~ | @@ -184,6 +187,9 @@ contain arbitrary whitespace. Alignment into the original string is preserved. Process texts as a stream, and yield `Doc` objects in order. This is usually more efficient than processing texts one-by-one. +Instead of text, a `Doc` object can be passed as input. In this case +tokenization is skipped but the rest of the pipeline is run. + > #### Example > > ```python @@ -192,16 +198,16 @@ more efficient than processing texts one-by-one. > assert doc.has_annotation("DEP") > ``` -| Name | Description | -| ------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `texts` | A sequence of strings. ~~Iterable[str]~~ | -| _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"} @@ -1024,21 +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/lemmatizer.md b/website/docs/api/lemmatizer.md index 422f34040..905096338 100644 --- a/website/docs/api/lemmatizer.md +++ b/website/docs/api/lemmatizer.md @@ -70,7 +70,7 @@ lemmatizer is available. The lemmatizer modes `rule` and `pos_lookup` require [`token.pos`](/api/token) from a previous pipeline component (see example pipeline configurations in the [pretrained pipeline design details](/models#design-cnn)) or rely on third-party -libraries (`pymorphy2`). +libraries (`pymorphy3`). | Language | Default Mode | | -------- | ------------ | @@ -86,9 +86,9 @@ libraries (`pymorphy2`). | `nb` | `rule` | | `nl` | `rule` | | `pl` | `pos_lookup` | -| `ru` | `pymorphy2` | +| `ru` | `pymorphy3` | | `sv` | `rule` | -| `uk` | `pymorphy2` | +| `uk` | `pymorphy3` | ```python %%GITHUB_SPACY/spacy/pipeline/lemmatizer.py 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/pipeline-functions.md b/website/docs/api/pipeline-functions.md index 1b7017ca7..070292782 100644 --- a/website/docs/api/pipeline-functions.md +++ b/website/docs/api/pipeline-functions.md @@ -153,3 +153,36 @@ whole pipeline has run. | `attrs` | A dict of the `Doc` attributes and the values to set them to. Defaults to `{"tensor": None, "_.trf_data": None}` to clean up after `tok2vec` and `transformer` components. ~~dict~~ | | `silent` | If `False`, show warnings if attributes aren't found or can't be set. Defaults to `True`. ~~bool~~ | | **RETURNS** | The modified `Doc` with the modified attributes. ~~Doc~~ | + +## span_cleaner {#span_cleaner tag="function,experimental"} + +Remove `SpanGroup`s from `doc.spans` based on a key prefix. This is used to +clean up after the [`CoreferenceResolver`](/api/coref) when it's paired with a +[`SpanResolver`](/api/span-resolver). + + + +This pipeline function is not yet integrated into spaCy core, and is available +via the extension package +[`spacy-experimental`](https://github.com/explosion/spacy-experimental) starting +in version 0.6.0. It exposes the component via +[entry points](/usage/saving-loading/#entry-points), so if you have the package +installed, using `factory = "span_cleaner"` in your +[training config](/usage/training#config) or `nlp.add_pipe("span_cleaner")` will +work out-of-the-box. + + + +> #### Example +> +> ```python +> config = {"prefix": "coref_head_clusters"} +> nlp.add_pipe("span_cleaner", config=config) +> doc = nlp("text") +> assert "coref_head_clusters_1" not in doc.spans +> ``` + +| Setting | Description | +| ----------- | ------------------------------------------------------------------------------------------------------------------------- | +| `prefix` | A prefix to check `SpanGroup` keys for. Any matching groups will be removed. Defaults to `"coref_head_clusters"`. ~~str~~ | +| **RETURNS** | The modified `Doc` with any matching spans removed. ~~Doc~~ | diff --git a/website/docs/api/scorer.md b/website/docs/api/scorer.md index 8dbe3b276..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"} @@ -270,3 +271,62 @@ Compute micro-PRF and per-entity PRF scores. | Name | Description | | ---------- | ------------------------------------------------------------------------------------------------------------------- | | `examples` | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ | + +## score_coref_clusters {#score_coref_clusters tag="experimental"} + +Returns LEA ([Moosavi and Strube, 2016](https://aclanthology.org/P16-1060/)) PRF +scores for coreference clusters. + + + +Note this scoring function is not yet included in spaCy core - for details, see +the [CoreferenceResolver](/api/coref) docs. + + + +> #### Example +> +> ```python +> scores = score_coref_clusters( +> examples, +> span_cluster_prefix="coref_clusters", +> ) +> print(scores["coref_f"]) +> ``` + +| Name | Description | +| --------------------- | ------------------------------------------------------------------------------------------------------------------- | +| `examples` | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ | +| _keyword-only_ | | +| `span_cluster_prefix` | The prefix used for spans representing coreference clusters. ~~str~~ | +| **RETURNS** | A dictionary containing the scores. ~~Dict[str, Optional[float]]~~ | + +## score_span_predictions {#score_span_predictions tag="experimental"} + +Return accuracy for reconstructions of spans from single tokens. Only exactly +correct predictions are counted as correct, there is no partial credit for near +answers. Used by the [SpanResolver](/api/span-resolver). + + + +Note this scoring function is not yet included in spaCy core - for details, see +the [SpanResolver](/api/span-resolver) docs. + + + +> #### Example +> +> ```python +> scores = score_span_predictions( +> examples, +> output_prefix="coref_clusters", +> ) +> print(scores["span_coref_clusters_accuracy"]) +> ``` + +| Name | Description | +| --------------- | ------------------------------------------------------------------------------------------------------------------- | +| `examples` | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ | +| _keyword-only_ | | +| `output_prefix` | The prefix used for spans representing the final predicted spans. ~~str~~ | +| **RETURNS** | A dictionary containing the scores. ~~Dict[str, Optional[float]]~~ | diff --git a/website/docs/api/span-resolver.md b/website/docs/api/span-resolver.md new file mode 100644 index 000000000..3e992cd03 --- /dev/null +++ b/website/docs/api/span-resolver.md @@ -0,0 +1,356 @@ +--- +title: SpanResolver +tag: class,experimental +source: spacy-experimental/coref/span_resolver_component.py +teaser: 'Pipeline component for resolving tokens into spans' +api_base_class: /api/pipe +api_string_name: span_resolver +api_trainable: true +--- + +> #### Installation +> +> ```bash +> $ pip install -U spacy-experimental +> ``` + + + +This component not yet integrated into spaCy core, and is available via the +extension package +[`spacy-experimental`](https://github.com/explosion/spacy-experimental) starting +in version 0.6.0. It exposes the component via +[entry points](/usage/saving-loading/#entry-points), so if you have the package +installed, using `factory = "experimental_span_resolver"` in your +[training config](/usage/training#config) or +`nlp.add_pipe("experimental_span_resolver")` will work out-of-the-box. + + + +A `SpanResolver` component takes in tokens (represented as `Span` objects of +length 1) and resolves them into `Span` objects of arbitrary length. The initial +use case is as a post-processing step on word-level +[coreference resolution](/api/coref). The input and output keys used to store +`Span` objects are configurable. + +## Assigned Attributes {#assigned-attributes} + +Predictions will be saved to `Doc.spans` as [`SpanGroup`s](/api/spangroup). + +Input token spans will be read in using an input prefix, by default +`"coref_head_clusters"`, and output spans will be saved using an output prefix +(default `"coref_clusters"`) plus a serial number starting from one. The +prefixes are configurable. + +| Location | Value | +| ------------------------------------------------- | ------------------------------------------------------------------------- | +| `Doc.spans[output_prefix + "_" + cluster_number]` | One group of predicted spans. Cluster number starts from 1. ~~SpanGroup~~ | + +## Config and implementation {#config} + +The default config is defined by the pipeline component factory and describes +how the component should be configured. You can override its settings via the +`config` argument on [`nlp.add_pipe`](/api/language#add_pipe) or in your +[`config.cfg` for training](/usage/training#config). See the +[model architectures](/api/architectures#coref-architectures) documentation for +details on the architectures and their arguments and hyperparameters. + +> #### Example +> +> ```python +> from spacy_experimental.coref.span_resolver_component import DEFAULT_SPAN_RESOLVER_MODEL +> from spacy_experimental.coref.coref_util import DEFAULT_CLUSTER_PREFIX, DEFAULT_CLUSTER_HEAD_PREFIX +> config={ +> "model": DEFAULT_SPAN_RESOLVER_MODEL, +> "input_prefix": DEFAULT_CLUSTER_HEAD_PREFIX, +> "output_prefix": DEFAULT_CLUSTER_PREFIX, +> }, +> nlp.add_pipe("experimental_span_resolver", config=config) +> ``` + +| Setting | Description | +| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `model` | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. Defaults to [SpanResolver](/api/architectures#SpanResolver). ~~Model~~ | +| `input_prefix` | The prefix to use for input `SpanGroup`s. Defaults to `coref_head_clusters`. ~~str~~ | +| `output_prefix` | The prefix for predicted `SpanGroup`s. Defaults to `coref_clusters`. ~~str~~ | + +## SpanResolver.\_\_init\_\_ {#init tag="method"} + +> #### Example +> +> ```python +> # Construction via add_pipe with default model +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> +> # Construction via add_pipe with custom model +> config = {"model": {"@architectures": "my_span_resolver.v1"}} +> span_resolver = nlp.add_pipe("experimental_span_resolver", config=config) +> +> # Construction from class +> from spacy_experimental.coref.span_resolver_component import SpanResolver +> span_resolver = SpanResolver(nlp.vocab, model) +> ``` + +Create a new pipeline instance. In your application, you would normally use a +shortcut for this and instantiate the component using its string name and +[`nlp.add_pipe`](/api/language#add_pipe). + +| Name | Description | +| --------------- | --------------------------------------------------------------------------------------------------- | +| `vocab` | The shared vocabulary. ~~Vocab~~ | +| `model` | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. ~~Model~~ | +| `name` | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~ | +| _keyword-only_ | | +| `input_prefix` | The prefix to use for input `SpanGroup`s. Defaults to `coref_head_clusters`. ~~str~~ | +| `output_prefix` | The prefix for predicted `SpanGroup`s. Defaults to `coref_clusters`. ~~str~~ | + +## SpanResolver.\_\_call\_\_ {#call tag="method"} + +Apply the pipe to one document. The document is modified in place and returned. +This usually happens under the hood when the `nlp` object is called on a text +and all pipeline components are applied to the `Doc` in order. Both +[`__call__`](#call) and [`pipe`](#pipe) delegate to the [`predict`](#predict) +and [`set_annotations`](#set_annotations) methods. + +> #### Example +> +> ```python +> doc = nlp("This is a sentence.") +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> # This usually happens under the hood +> processed = span_resolver(doc) +> ``` + +| Name | Description | +| ----------- | -------------------------------- | +| `doc` | The document to process. ~~Doc~~ | +| **RETURNS** | The processed document. ~~Doc~~ | + +## SpanResolver.pipe {#pipe tag="method"} + +Apply the pipe to a stream of documents. This usually happens under the hood +when the `nlp` object is called on a text and all pipeline components are +applied to the `Doc` in order. Both [`__call__`](/api/span-resolver#call) and +[`pipe`](/api/span-resolver#pipe) delegate to the +[`predict`](/api/span-resolver#predict) and +[`set_annotations`](/api/span-resolver#set_annotations) methods. + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> for doc in span_resolver.pipe(docs, batch_size=50): +> pass +> ``` + +| Name | Description | +| -------------- | ------------------------------------------------------------- | +| `stream` | A stream of documents. ~~Iterable[Doc]~~ | +| _keyword-only_ | | +| `batch_size` | The number of documents to buffer. Defaults to `128`. ~~int~~ | +| **YIELDS** | The processed documents in order. ~~Doc~~ | + +## SpanResolver.initialize {#initialize tag="method"} + +Initialize the component for training. `get_examples` should be a function that +returns an iterable of [`Example`](/api/example) objects. **At least one example +should be supplied.** The data examples are used to **initialize the model** of +the component and can either be the full training data or a representative +sample. Initialization includes validating the network, +[inferring missing shapes](https://thinc.ai/docs/usage-models#validation) and +setting up the label scheme based on the data. This method is typically called +by [`Language.initialize`](/api/language#initialize). + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> span_resolver.initialize(lambda: examples, nlp=nlp) +> ``` + +| Name | Description | +| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `get_examples` | Function that returns gold-standard annotations in the form of [`Example`](/api/example) objects. Must contain at least one `Example`. ~~Callable[[], Iterable[Example]]~~ | +| _keyword-only_ | | +| `nlp` | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~ | + +## SpanResolver.predict {#predict tag="method"} + +Apply the component's model to a batch of [`Doc`](/api/doc) objects, without +modifying them. Predictions are returned as a list of `MentionClusters`, one for +each input `Doc`. A `MentionClusters` instance is just a list of lists of pairs +of `int`s, where each item corresponds to an input `SpanGroup`, and the `int`s +correspond to token indices. + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> spans = span_resolver.predict([doc1, doc2]) +> ``` + +| Name | Description | +| ----------- | ------------------------------------------------------------- | +| `docs` | The documents to predict. ~~Iterable[Doc]~~ | +| **RETURNS** | The predicted spans for the `Doc`s. ~~List[MentionClusters]~~ | + +## SpanResolver.set_annotations {#set_annotations tag="method"} + +Modify a batch of documents, saving predictions using the output prefix in +`Doc.spans`. + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> spans = span_resolver.predict([doc1, doc2]) +> span_resolver.set_annotations([doc1, doc2], spans) +> ``` + +| Name | Description | +| ------- | ------------------------------------------------------------- | +| `docs` | The documents to modify. ~~Iterable[Doc]~~ | +| `spans` | The predicted spans for the `docs`. ~~List[MentionClusters]~~ | + +## SpanResolver.update {#update tag="method"} + +Learn from a batch of [`Example`](/api/example) objects. Delegates to +[`predict`](/api/span-resolver#predict). + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> optimizer = nlp.initialize() +> losses = span_resolver.update(examples, sgd=optimizer) +> ``` + +| Name | Description | +| -------------- | ------------------------------------------------------------------------------------------------------------------------ | +| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ | +| _keyword-only_ | | +| `drop` | The dropout rate. ~~float~~ | +| `sgd` | An optimizer. Will be created via [`create_optimizer`](#create_optimizer) if not set. ~~Optional[Optimizer]~~ | +| `losses` | Optional record of the loss during training. Updated using the component name as the key. ~~Optional[Dict[str, float]]~~ | +| **RETURNS** | The updated `losses` dictionary. ~~Dict[str, float]~~ | + +## SpanResolver.create_optimizer {#create_optimizer tag="method"} + +Create an optimizer for the pipeline component. + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> optimizer = span_resolver.create_optimizer() +> ``` + +| Name | Description | +| ----------- | ---------------------------- | +| **RETURNS** | The optimizer. ~~Optimizer~~ | + +## SpanResolver.use_params {#use_params tag="method, contextmanager"} + +Modify the pipe's model, to use the given parameter values. At the end of the +context, the original parameters are restored. + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> with span_resolver.use_params(optimizer.averages): +> span_resolver.to_disk("/best_model") +> ``` + +| Name | Description | +| -------- | -------------------------------------------------- | +| `params` | The parameter values to use in the model. ~~dict~~ | + +## SpanResolver.to_disk {#to_disk tag="method"} + +Serialize the pipe to disk. + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> span_resolver.to_disk("/path/to/span_resolver") +> ``` + +| Name | Description | +| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | +| `path` | A path to a directory, which will be created if it doesn't exist. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| _keyword-only_ | | +| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ | + +## SpanResolver.from_disk {#from_disk tag="method"} + +Load the pipe from disk. Modifies the object in place and returns it. + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> span_resolver.from_disk("/path/to/span_resolver") +> ``` + +| Name | Description | +| -------------- | ----------------------------------------------------------------------------------------------- | +| `path` | A path to a directory. Paths may be either strings or `Path`-like objects. ~~Union[str, Path]~~ | +| _keyword-only_ | | +| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ | +| **RETURNS** | The modified `SpanResolver` object. ~~SpanResolver~~ | + +## SpanResolver.to_bytes {#to_bytes tag="method"} + +> #### Example +> +> ```python +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> span_resolver_bytes = span_resolver.to_bytes() +> ``` + +Serialize the pipe to a bytestring. + +| Name | Description | +| -------------- | ------------------------------------------------------------------------------------------- | +| _keyword-only_ | | +| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ | +| **RETURNS** | The serialized form of the `SpanResolver` object. ~~bytes~~ | + +## SpanResolver.from_bytes {#from_bytes tag="method"} + +Load the pipe from a bytestring. Modifies the object in place and returns it. + +> #### Example +> +> ```python +> span_resolver_bytes = span_resolver.to_bytes() +> span_resolver = nlp.add_pipe("experimental_span_resolver") +> span_resolver.from_bytes(span_resolver_bytes) +> ``` + +| Name | Description | +| -------------- | ------------------------------------------------------------------------------------------- | +| `bytes_data` | The data to load from. ~~bytes~~ | +| _keyword-only_ | | +| `exclude` | String names of [serialization fields](#serialization-fields) to exclude. ~~Iterable[str]~~ | +| **RETURNS** | The `SpanResolver` object. ~~SpanResolver~~ | + +## Serialization fields {#serialization-fields} + +During serialization, spaCy will export several data fields used to restore +different aspects of the object. If needed, you can exclude them from +serialization by passing in the string names via the `exclude` argument. + +> #### Example +> +> ```python +> data = span_resolver.to_disk("/path", exclude=["vocab"]) +> ``` + +| Name | Description | +| ------- | -------------------------------------------------------------- | +| `vocab` | The shared [`Vocab`](/api/vocab). | +| `cfg` | The config file. You usually don't want to exclude this. | +| `model` | The binary model data. You usually don't want to exclude this. | 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/spangroup.md b/website/docs/api/spangroup.md index 8dbdefc01..2d1cf73c4 100644 --- a/website/docs/api/spangroup.md +++ b/website/docs/api/spangroup.md @@ -255,9 +255,10 @@ Return a copy of the span group. > new_group = doc.spans["errors"].copy() > ``` -| Name | Description | -| ----------- | ----------------------------------------------- | -| **RETURNS** | A copy of the `SpanGroup` object. ~~SpanGroup~~ | +| Name | Description | +| ----------- | -------------------------------------------------------------------------------------------------- | +| `doc` | The document to which the copy is bound. Defaults to `None` for the current doc. ~~Optional[Doc]~~ | +| **RETURNS** | A copy of the `SpanGroup` object. ~~SpanGroup~~ | ## SpanGroup.to_bytes {#to_bytes tag="method"} 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/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/101/_architecture.md b/website/docs/usage/101/_architecture.md index 22e2b961e..4ebca2756 100644 --- a/website/docs/usage/101/_architecture.md +++ b/website/docs/usage/101/_architecture.md @@ -78,7 +78,9 @@ operates on a `Doc` and gives you access to the matched tokens **in context**. | Name | Description | | ------------------------------------------------ | -------------------------------------------------------------------------------------------------- | | [`Corpus`](/api/corpus) | Class for managing annotated corpora for training and evaluation data. | -| [`KnowledgeBase`](/api/kb) | Storage for entities and aliases of a knowledge base for entity linking. | +| [`KnowledgeBase`](/api/kb) | Abstract base class for storage and retrieval of data for entity linking. | +| [`InMemoryLookupKB`](/api/kb_in_memory) | Implementation of `KnowledgeBase` storing all data in memory. | +| [`Candidate`](/api/kb#candidate) | Object associating a textual mention with a specific entity contained in a `KnowledgeBase`. | | [`Lookups`](/api/lookups) | Container for convenient access to large lookup tables and dictionaries. | | [`MorphAnalysis`](/api/morphology#morphanalysis) | A morphological analysis. | | [`Morphology`](/api/morphology) | Store morphological analyses and map them to and from hash values. | 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 35150035a..34315e4e7 100644 --- a/website/docs/usage/projects.md +++ b/website/docs/usage/projects.md @@ -148,6 +148,13 @@ skipped. You can also set `--force` to force re-running a command, or `--dry` to perform a "dry run" and see what would happen (without actually running the script). +Since spaCy v3.4.2, `spacy projects run` checks your installed dependencies to +verify that your environment is properly set up and aligns with the project's +`requirements.txt`, if there is one. If missing or conflicting dependencies are +detected, a corresponding warning is displayed. If you'd like to disable the +dependency check, set `check_requirements: false` in your project's +`project.yml`. + ### 4. Run a workflow {#run-workfow} > #### project.yml @@ -226,26 +233,49 @@ pipelines. ```yaml %%GITHUB_PROJECTS/pipelines/tagger_parser_ud/project.yml ``` + > #### Tip: Overriding variables on the CLI > -> If you want to override one or more variables on the CLI and are not already specifying a -> project directory, you need to add `.` as a placeholder: +> If you want to override one or more variables on the CLI and are not already +> specifying a project directory, you need to add `.` as a placeholder: > > ``` > python -m spacy project run test . --vars.foo bar > ``` -| Section | Description | -| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| `title` | An optional project title used in `--help` message and [auto-generated docs](#custom-docs). | -| `description` | An optional project description used in [auto-generated docs](#custom-docs). | -| `vars` | A dictionary of variables that can be referenced in paths, URLs and scripts and overriden on the CLI, just like [`config.cfg` variables](/usage/training#config-interpolation). For example, `${vars.name}` will use the value of the variable `name`. Variables need to be defined in the section `vars`, but can be a nested dict, so you're able to reference `${vars.model.name}`. | -| `env` | A dictionary of variables, mapped to the names of environment variables that will be read in when running the project. For example, `${env.name}` will use the value of the environment variable defined as `name`. | -| `directories` | An optional list of [directories](#project-files) that should be created in the project for assets, training outputs, metrics etc. spaCy will make sure that these directories always exist. | -| `assets` | A list of assets that can be fetched with the [`project assets`](/api/cli#project-assets) command. `url` defines a URL or local path, `dest` is the destination file relative to the project directory, and an optional `checksum` ensures that an error is raised if the file's checksum doesn't match. Instead of `url`, you can also provide a `git` block with the keys `repo`, `branch` and `path`, to download from a Git repo. | -| `workflows` | A dictionary of workflow names, mapped to a list of command names, to execute in order. Workflows can be run with the [`project run`](/api/cli#project-run) command. | -| `commands` | A list of named commands. A command can define an optional help message (shown in the CLI when the user adds `--help`) and the `script`, a list of commands to run. The `deps` and `outputs` let you define the created file the command depends on and produces, respectively. This lets spaCy determine whether a command needs to be re-run because its dependencies or outputs changed. Commands can be run as part of a workflow, or separately with the [`project run`](/api/cli#project-run) command. | -| `spacy_version` | Optional spaCy version range like `>=3.0.0,<3.1.0` that the project is compatible with. If it's loaded with an incompatible version, an error is raised when the project is loaded. | +> #### Tip: Environment Variables +> +> Commands in a project file are not executed in a shell, so they don't have +> direct access to environment variables. But you can insert environment +> variables using the `env` dictionary to make values available for +> interpolation, just like values in `vars`. Here's an example `env` dict that +> makes `$PATH` available as `ENV_PATH`: +> +> ```yaml +> env: +> ENV_PATH: PATH +> ``` +> +> This can be used in a project command like so: +> +> ```yaml +> - name: "echo-path" +> script: +> - "echo ${env.ENV_PATH}" +> ``` + +| Section | Description | +| --------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `title` | An optional project title used in `--help` message and [auto-generated docs](#custom-docs). | +| `description` | An optional project description used in [auto-generated docs](#custom-docs). | +| `vars` | A dictionary of variables that can be referenced in paths, URLs and scripts and overriden on the CLI, just like [`config.cfg` variables](/usage/training#config-interpolation). For example, `${vars.name}` will use the value of the variable `name`. Variables need to be defined in the section `vars`, but can be a nested dict, so you're able to reference `${vars.model.name}`. | +| `env` | A dictionary of variables, mapped to the names of environment variables that will be read in when running the project. For example, `${env.name}` will use the value of the environment variable defined as `name`. | +| `directories` | An optional list of [directories](#project-files) that should be created in the project for assets, training outputs, metrics etc. spaCy will make sure that these directories always exist. | +| `assets` | A list of assets that can be fetched with the [`project assets`](/api/cli#project-assets) command. `url` defines a URL or local path, `dest` is the destination file relative to the project directory, and an optional `checksum` ensures that an error is raised if the file's checksum doesn't match. Instead of `url`, you can also provide a `git` block with the keys `repo`, `branch` and `path`, to download from a Git repo. | +| `workflows` | A dictionary of workflow names, mapped to a list of command names, to execute in order. Workflows can be run with the [`project run`](/api/cli#project-run) command. | +| `commands` | A list of named commands. A command can define an optional help message (shown in the CLI when the user adds `--help`) and the `script`, a list of commands to run. The `deps` and `outputs` let you define the created file the command depends on and produces, respectively. This lets spaCy determine whether a command needs to be re-run because its dependencies or outputs changed. Commands can be run as part of a workflow, or separately with the [`project run`](/api/cli#project-run) command. | +| `spacy_version` | Optional spaCy version range like `>=3.0.0,<3.1.0` that the project is compatible with. If it's loaded with an incompatible version, an error is raised when the project is loaded. | +| `check_requirements` 3.4.2 | A flag determining whether to verify that the installed dependencies align with the project's `requirements.txt`. Defaults to `true`. | ### Data assets {#data-assets} @@ -984,54 +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 5e064b269..e40a395c4 100644 --- a/website/docs/usage/training.md +++ b/website/docs/usage/training.md @@ -480,7 +480,7 @@ as-is. They are also excluded when calling > parse. So the evaluation results should always reflect what your pipeline will > produce at runtime. If you want a frozen component to run (without updating) > during training as well, so that downstream components can use its -> **predictions**, you can add it to the list of +> **predictions**, you should add it to the list of > [`annotating_components`](/usage/training#annotating-components). ```ini @@ -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/v3-4.md b/website/docs/usage/v3-4.md index 7cc4570d5..597fc3cc8 100644 --- a/website/docs/usage/v3-4.md +++ b/website/docs/usage/v3-4.md @@ -65,10 +65,10 @@ The English CNN pipelines have new word vectors: | Package | Model Version | TAG | Parser LAS | NER F | | ----------------------------------------------- | ------------- | ---: | ---------: | ----: | -| [`en_core_news_md`](/models/en#en_core_news_md) | v3.3.0 | 97.3 | 90.1 | 84.6 | -| [`en_core_news_md`](/models/en#en_core_news_lg) | v3.4.0 | 97.2 | 90.3 | 85.5 | -| [`en_core_news_lg`](/models/en#en_core_news_md) | v3.3.0 | 97.4 | 90.1 | 85.3 | -| [`en_core_news_lg`](/models/en#en_core_news_lg) | v3.4.0 | 97.3 | 90.2 | 85.6 | +| [`en_core_web_md`](/models/en#en_core_web_md) | v3.3.0 | 97.3 | 90.1 | 84.6 | +| [`en_core_web_md`](/models/en#en_core_web_lg) | v3.4.0 | 97.2 | 90.3 | 85.5 | +| [`en_core_web_lg`](/models/en#en_core_web_md) | v3.3.0 | 97.4 | 90.1 | 85.3 | +| [`en_core_web_lg`](/models/en#en_core_web_lg) | v3.4.0 | 97.3 | 90.2 | 85.6 | ## Notes about upgrading from v3.3 {#upgrading} diff --git a/website/meta/languages.json b/website/meta/languages.json index 79e1fc5d5..bd1535c90 100644 --- a/website/meta/languages.json +++ b/website/meta/languages.json @@ -4,12 +4,22 @@ "code": "af", "name": "Afrikaans" }, + { + "code": "am", + "name": "Amharic", + "has_examples": true + }, { "code": "ar", "name": "Arabic", "example": "هذه جملة", "has_examples": true }, + { + "code": "az", + "name": "Azerbaijani", + "has_examples": true + }, { "code": "bg", "name": "Bulgarian", @@ -65,7 +75,7 @@ { "code": "dsb", "name": "Lower Sorbian", - "has_examples": true + "has_examples": true }, { "code": "el", @@ -142,6 +152,11 @@ "code": "ga", "name": "Irish" }, + { + "code": "grc", + "name": "Ancient Greek", + "has_examples": true + }, { "code": "gu", "name": "Gujarati", @@ -172,7 +187,7 @@ { "code": "hsb", "name": "Upper Sorbian", - "has_examples": true + "has_examples": true }, { "code": "hu", @@ -260,6 +275,10 @@ "example": "Адамга эң кыйыны — күн сайын адам болуу", "has_examples": true }, + { + "code": "la", + "name": "Latin" + }, { "code": "lb", "name": "Luxembourgish", @@ -374,8 +393,8 @@ "has_examples": true, "dependencies": [ { - "name": "pymorphy2", - "url": "https://github.com/kmike/pymorphy2" + "name": "pymorphy3", + "url": "https://github.com/no-plagiarism/pymorphy3" } ], "models": [ @@ -448,6 +467,11 @@ "example": "นี่คือประโยค", "has_examples": true }, + { + "code": "ti", + "name": "Tigrinya", + "has_examples": true + }, { "code": "tl", "name": "Tagalog" @@ -480,12 +504,12 @@ ], "dependencies": [ { - "name": "pymorphy2", - "url": "https://github.com/kmike/pymorphy2" + "name": "pymorphy3", + "url": "https://github.com/no-plagiarism/pymorphy3" }, { - "name": "pymorphy2-dicts-uk", - "url": "https://github.com/kmike/pymorphy2-dicts/" + "name": "pymorphy3-dicts-uk", + "url": "https://github.com/no-plagiarism/pymorphy3-dicts" } ] }, diff --git a/website/meta/sidebars.json b/website/meta/sidebars.json index 1b743636c..2d8745d77 100644 --- a/website/meta/sidebars.json +++ b/website/meta/sidebars.json @@ -12,7 +12,6 @@ { "text": "New in v3.0", "url": "/usage/v3" }, { "text": "New in v3.1", "url": "/usage/v3-1" }, { "text": "New in v3.2", "url": "/usage/v3-2" }, - { "text": "New in v3.2", "url": "/usage/v3-2" }, { "text": "New in v3.3", "url": "/usage/v3-3" }, { "text": "New in v3.4", "url": "/usage/v3-4" } ] @@ -95,6 +94,7 @@ "label": "Pipeline", "items": [ { "text": "AttributeRuler", "url": "/api/attributeruler" }, + { "text": "CoreferenceResolver", "url": "/api/coref" }, { "text": "DependencyParser", "url": "/api/dependencyparser" }, { "text": "EditTreeLemmatizer", "url": "/api/edittreelemmatizer" }, { "text": "EntityLinker", "url": "/api/entitylinker" }, @@ -105,6 +105,7 @@ { "text": "SentenceRecognizer", "url": "/api/sentencerecognizer" }, { "text": "Sentencizer", "url": "/api/sentencizer" }, { "text": "SpanCategorizer", "url": "/api/spancategorizer" }, + { "text": "SpanResolver", "url": "/api/span-resolver" }, { "text": "SpanRuler", "url": "/api/spanruler" }, { "text": "Tagger", "url": "/api/tagger" }, { "text": "TextCategorizer", "url": "/api/textcategorizer" }, diff --git a/website/meta/universe.json b/website/meta/universe.json index 9145855c6..661f5da12 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -1,5 +1,129 @@ { "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", + "slogan": "Easily clean text with spaCy!", + "description": "**spacy-cleaner** utilises spaCy `Language` models to replace, remove, and \n mutate spaCy tokens. Cleaning actions available are:\n\n* Remove/replace stopwords.\n* Remove/replace punctuation.\n* Remove/replace numbers.\n* Remove/replace emails.\n* Remove/replace URLs.\n* Perform lemmatisation.\n\nSee our [docs](https://ce11an.github.io/spacy-cleaner/) for more information.", + "github": "Ce11an/spacy-cleaner", + "pip": "spacy-cleaner", + "code_example": [ + "import spacy", + "import spacy_cleaner", + "from spacy_cleaner.processing import removers, replacers, mutators", + "", + "model = spacy.load(\"en_core_web_sm\")", + "pipeline = spacy_cleaner.Pipeline(", + " model,", + " removers.remove_stopword_token,", + " replacers.replace_punctuation_token,", + " mutators.mutate_lemma_token,", + ")", + "", + "texts = [\"Hello, my name is Cellan! I love to swim!\"]", + "", + "pipeline.clean(texts)", + "# ['hello _IS_PUNCT_ Cellan _IS_PUNCT_ love swim _IS_PUNCT_']" + ], + "code_language": "python", + "url": "https://ce11an.github.io/spacy-cleaner/", + "image": "https://raw.githubusercontent.com/Ce11an/spacy-cleaner/main/docs/assets/images/spacemen.png", + "author": "Cellan Hall", + "author_links": { + "twitter": "Ce11an", + "github": "Ce11an", + "website": "https://www.linkedin.com/in/cellan-hall/" + }, + "category": [ + "extension" + ], + "tags": [ + "text-processing" + ] + }, + { + "id": "Zshot", + "title": "Zshot", + "slogan": "Zero and Few shot named entity & relationships recognition", + "github": "ibm/zshot", + "pip": "zshot", + "code_example": [ + "import spacy", + "from zshot import PipelineConfig, displacy", + "from zshot.linker import LinkerRegen", + "from zshot.mentions_extractor import MentionsExtractorSpacy", + "from zshot.utils.data_models import Entity", + "", + "nlp = spacy.load('en_core_web_sm')", + "# zero shot definition of entities", + "nlp_config = PipelineConfig(", + " mentions_extractor=MentionsExtractorSpacy(),", + " linker=LinkerRegen(),", + " entities=[", + " Entity(name='Paris',", + " description='Paris is located in northern central France, in a north-bending arc of the river Seine'),", + " Entity(name='IBM',", + " description='International Business Machines Corporation (IBM) is an American multinational technology corporation headquartered in Armonk, New York'),", + " Entity(name='New York', description='New York is a city in U.S. state'),", + " Entity(name='Florida', description='southeasternmost U.S. state'),", + " Entity(name='American',", + " description='American, something of, from, or related to the United States of America, commonly known as the United States or America'),", + " Entity(name='Chemical formula',", + " description='In chemistry, a chemical formula is a way of presenting information about the chemical proportions of atoms that constitute a particular chemical compound or molecul'),", + " Entity(name='Acetamide',", + " description='Acetamide (systematic name: ethanamide) is an organic compound with the formula CH3CONH2. It is the simplest amide derived from acetic acid. It finds some use as a plasticizer and as an industrial solvent.'),", + " Entity(name='Armonk',", + " description='Armonk is a hamlet and census-designated place (CDP) in the town of North Castle, located in Westchester County, New York, United States.'),", + " Entity(name='Acetic Acid',", + " description='Acetic acid, systematically named ethanoic acid, is an acidic, colourless liquid and organic compound with the chemical formula CH3COOH'),", + " Entity(name='Industrial solvent',", + " description='Acetamide (systematic name: ethanamide) is an organic compound with the formula CH3CONH2. It is the simplest amide derived from acetic acid. It finds some use as a plasticizer and as an industrial solvent.'),", + " ]", + ")", + "nlp.add_pipe('zshot', config=nlp_config, last=True)", + "", + "text = 'International Business Machines Corporation (IBM) is an American multinational technology corporation' \\", + " ' headquartered in Armonk, New York, with operations in over 171 countries.'", + "", + "doc = nlp(text)", + "displacy.serve(doc, style='ent')" + ], + "thumb": "https://ibm.github.io/zshot/img/graph.png", + "url": "https://ibm.github.io/zshot/", + "author": "IBM Research", + "author_links": { + "github": "ibm", + "twitter": "IBMResearch", + "website": "https://research.ibm.com/labs/ireland/" + }, + "category": ["scientific", "models", "research"] + }, { "id": "concepcy", "title": "concepCy", @@ -433,17 +557,6 @@ "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", @@ -2403,20 +2516,20 @@ "import spacy", "from spacy_wordnet.wordnet_annotator import WordnetAnnotator ", "", - "# Load an spacy model (supported models are \"es\" and \"en\") ", - "nlp = spacy.load('en')", - "# Spacy 3.x", - "nlp.add_pipe(\"spacy_wordnet\", after='tagger', config={'lang': nlp.lang})", - "# Spacy 2.x", + "# Load a spaCy model (supported languages are \"es\" and \"en\") ", + "nlp = spacy.load('en_core_web_sm')", + "# spaCy 3.x", + "nlp.add_pipe(\"spacy_wordnet\", after='tagger')", + "# spaCy 2.x", "# nlp.add_pipe(WordnetAnnotator(nlp.lang), after='tagger')", "token = nlp('prices')[0]", "", - "# wordnet object link spacy token with nltk wordnet interface by giving acces to", + "# WordNet object links spaCy token with NLTK WordNet interface by giving access to", "# synsets and lemmas ", "token._.wordnet.synsets()", "token._.wordnet.lemmas()", "", - "# And automatically tags with wordnet domains", + "# And automatically add info about WordNet domains", "token._.wordnet.wordnet_domains()" ], "author": "recognai", @@ -3984,7 +4097,21 @@ }, "category": ["pipeline"], "tags": ["interpretation", "ja"] + }, + { + "id": "spacy-partial-tagger", + "title": "spaCy - Partial Tagger", + "slogan": "Sequence Tagger for Partially Annotated Dataset in spaCy", + "description": "This is a library to build a CRF tagger with a partially annotated dataset in spaCy. You can build your own tagger only from dictionary.", + "github": "doccano/spacy-partial-tagger", + "pip": "spacy-partial-tagger", + "category": ["pipeline", "training"], + "author": "Yasufumi Taniguchi", + "author_links": { + "github": "yasufumy" + } } + ], "categories": [ diff --git a/website/src/styles/quickstart.module.sass b/website/src/styles/quickstart.module.sass index 8ad106a78..d0f9db551 100644 --- a/website/src/styles/quickstart.module.sass +++ b/website/src/styles/quickstart.module.sass @@ -149,6 +149,9 @@ & > span display: block + a + text-decoration: underline + .small font-size: var(--font-size-code) line-height: 1.65 diff --git a/website/src/widgets/quickstart-install.js b/website/src/widgets/quickstart-install.js index 0d2186acb..28dd14ecc 100644 --- a/website/src/widgets/quickstart-install.js +++ b/website/src/widgets/quickstart-install.js @@ -159,6 +159,9 @@ const QuickstartInstall = ({ id, title }) => { setters={setters} showDropdown={showDropdown} > + + # Note M1 GPU support is experimental, see Thinc issue #792 + python -m venv .env @@ -198,7 +201,13 @@ const QuickstartInstall = ({ id, title }) => { {nightly ? ' --pre' : ''} conda install -c conda-forge spacy - + + conda install -c conda-forge cupy + + + conda install -c conda-forge cupy + + conda install -c conda-forge cupy