diff --git a/.github/azure-steps.yml b/.github/azure-steps.yml index 2f77706b8..d0db75f9a 100644 --- a/.github/azure-steps.yml +++ b/.github/azure-steps.yml @@ -107,7 +107,7 @@ steps: displayName: "Run CPU tests" - script: | - python -m pip install --pre thinc-apple-ops + python -m pip install 'spacy[apple]' 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')) diff --git a/.github/workflows/lock.yml b/.github/workflows/lock.yml index c9833cdba..794adee85 100644 --- a/.github/workflows/lock.yml +++ b/.github/workflows/lock.yml @@ -15,11 +15,11 @@ jobs: action: runs-on: ubuntu-latest steps: - - uses: dessant/lock-threads@v3 + - uses: dessant/lock-threads@v4 with: process-only: 'issues' issue-inactive-days: '30' - issue-comment: > - This thread has been automatically locked since there - has not been any recent activity after it was closed. + issue-comment: > + This thread has been automatically locked since there + has not been any recent activity after it was closed. Please open a new issue for related bugs. diff --git a/README.md b/README.md index abfc3da67..195424551 100644 --- a/README.md +++ b/README.md @@ -14,7 +14,7 @@ parsing, **named entity recognition**, **text classification** and more, multi-task learning with pretrained **transformers** like BERT, as well as a 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. +open-source software, released under the [MIT license](https://github.com/explosion/spaCy/blob/master/LICENSE). 💫 **Version 3.4 out now!** [Check out the release notes here.](https://github.com/explosion/spaCy/releases) @@ -46,6 +46,7 @@ open-source software, released under the MIT license. | 🛠 **[Changelog]** | Changes and version history. | | 💝 **[Contribute]** | How to contribute to the spaCy project and code base. | | spaCy Tailored Pipelines | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more →](https://explosion.ai/spacy-tailored-pipelines)** | +| spaCy Tailored Pipelines | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more →](https://explosion.ai/spacy-tailored-analysis)** | [spacy 101]: https://spacy.io/usage/spacy-101 [new in v3.0]: https://spacy.io/usage/v3 @@ -59,6 +60,7 @@ open-source software, released under the MIT license. [changelog]: https://spacy.io/usage#changelog [contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md + ## 💬 Where to ask questions The spaCy project is maintained by the [spaCy team](https://explosion.ai/about). diff --git a/azure-pipelines.yml b/azure-pipelines.yml index 9c3b92f06..0f7ea91f9 100644 --- a/azure-pipelines.yml +++ b/azure-pipelines.yml @@ -41,7 +41,7 @@ jobs: matrix: # We're only running one platform per Python version to speed up builds Python36Linux: - imageName: "ubuntu-latest" + imageName: "ubuntu-20.04" python.version: "3.6" # Python36Windows: # imageName: "windows-latest" @@ -50,7 +50,7 @@ jobs: # imageName: "macos-latest" # python.version: "3.6" # Python37Linux: - # imageName: "ubuntu-latest" + # imageName: "ubuntu-20.04" # python.version: "3.7" Python37Windows: imageName: "windows-latest" diff --git a/build-constraints.txt b/build-constraints.txt index 956973abf..c1e82f1b0 100644 --- a/build-constraints.txt +++ b/build-constraints.txt @@ -5,4 +5,5 @@ numpy==1.17.3; python_version=='3.8' and platform_machine!='aarch64' numpy==1.19.2; python_version=='3.8' and platform_machine=='aarch64' numpy==1.19.3; python_version=='3.9' numpy==1.21.3; python_version=='3.10' -numpy; python_version>='3.11' +numpy==1.23.2; python_version=='3.11' +numpy; python_version>='3.12' diff --git a/requirements.txt b/requirements.txt index 778c05e21..5bc1c8684 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,12 +1,12 @@ # Our libraries -spacy-legacy>=3.0.10,<3.1.0 +spacy-legacy>=3.0.11,<3.1.0 spacy-loggers>=1.0.0,<2.0.0 cymem>=2.0.2,<2.1.0 preshed>=3.0.2,<3.1.0 thinc>=8.1.0,<8.2.0 ml_datasets>=0.2.0,<0.3.0 murmurhash>=0.28.0,<1.1.0 -wasabi>=0.9.1,<1.1.0 +wasabi>=0.9.1,<1.2.0 srsly>=2.4.3,<3.0.0 catalogue>=2.0.6,<2.1.0 typer>=0.3.0,<0.8.0 diff --git a/setup.cfg b/setup.cfg index 5768c9d3e..cee8c0c33 100644 --- a/setup.cfg +++ b/setup.cfg @@ -22,6 +22,7 @@ classifiers = Programming Language :: Python :: 3.8 Programming Language :: Python :: 3.9 Programming Language :: Python :: 3.10 + Programming Language :: Python :: 3.11 Topic :: Scientific/Engineering project_urls = Release notes = https://github.com/explosion/spaCy/releases @@ -41,13 +42,13 @@ setup_requires = thinc>=8.1.0,<8.2.0 install_requires = # Our libraries - spacy-legacy>=3.0.10,<3.1.0 + spacy-legacy>=3.0.11,<3.1.0 spacy-loggers>=1.0.0,<2.0.0 murmurhash>=0.28.0,<1.1.0 cymem>=2.0.2,<2.1.0 preshed>=3.0.2,<3.1.0 thinc>=8.1.0,<8.2.0 - wasabi>=0.9.1,<1.1.0 + wasabi>=0.9.1,<1.2.0 srsly>=2.4.3,<3.0.0 catalogue>=2.0.6,<2.1.0 # Third-party dependencies diff --git a/spacy/cli/__init__.py b/spacy/cli/__init__.py index 43473c590..868526b42 100644 --- a/spacy/cli/__init__.py +++ b/spacy/cli/__init__.py @@ -17,6 +17,7 @@ from .debug_config import debug_config # noqa: F401 from .debug_model import debug_model # noqa: F401 from .debug_diff import debug_diff # noqa: F401 from .evaluate import evaluate # noqa: F401 +from .apply import apply # noqa: F401 from .convert import convert # noqa: F401 from .init_pipeline import init_pipeline_cli # noqa: F401 from .init_config import init_config, fill_config # noqa: F401 diff --git a/spacy/cli/_util.py b/spacy/cli/_util.py index 0da9c4626..ba3892b1d 100644 --- a/spacy/cli/_util.py +++ b/spacy/cli/_util.py @@ -161,15 +161,15 @@ def load_project_config( sys.exit(1) validate_project_version(config) validate_project_commands(config) + if interpolate: + err = f"{PROJECT_FILE} validation error" + with show_validation_error(title=err, hint_fill=False): + config = substitute_project_variables(config, overrides) # Make sure directories defined in config exist for subdir in config.get("directories", []): dir_path = path / subdir if not dir_path.exists(): dir_path.mkdir(parents=True) - if interpolate: - err = f"{PROJECT_FILE} validation error" - with show_validation_error(title=err, hint_fill=False): - config = substitute_project_variables(config, overrides) return config @@ -585,6 +585,33 @@ def setup_gpu(use_gpu: int, silent=None) -> None: local_msg.info("To switch to GPU 0, use the option: --gpu-id 0") +def walk_directory(path: Path, suffix: Optional[str] = None) -> List[Path]: + """Given a directory and a suffix, recursively find all files matching the suffix. + Directories or files with names beginning with a . are ignored, but hidden flags on + filesystems are not checked. + When provided with a suffix `None`, there is no suffix-based filtering.""" + if not path.is_dir(): + return [path] + paths = [path] + locs = [] + seen = set() + for path in paths: + if str(path) in seen: + continue + seen.add(str(path)) + if path.parts[-1].startswith("."): + continue + elif path.is_dir(): + paths.extend(path.iterdir()) + elif suffix is not None and not path.parts[-1].endswith(suffix): + continue + else: + locs.append(path) + # It's good to sort these, in case the ordering messes up cache. + locs.sort() + return locs + + 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)`""" diff --git a/spacy/cli/apply.py b/spacy/cli/apply.py new file mode 100644 index 000000000..f0df4e757 --- /dev/null +++ b/spacy/cli/apply.py @@ -0,0 +1,143 @@ +import tqdm +import srsly + +from itertools import chain +from pathlib import Path +from typing import Optional, List, Iterable, cast, Union + +from wasabi import msg + +from ._util import app, Arg, Opt, setup_gpu, import_code, walk_directory + +from ..tokens import Doc, DocBin +from ..vocab import Vocab +from ..util import ensure_path, load_model + + +path_help = """Location of the documents to predict on. +Can be a single file in .spacy format or a .jsonl file. +Files with other extensions are treated as single plain text documents. +If a directory is provided it is traversed recursively to grab +all files to be processed. +The files can be a mixture of .spacy, .jsonl and text files. +If .jsonl is provided the specified field is going +to be grabbed ("text" by default).""" + +out_help = "Path to save the resulting .spacy file" +code_help = ( + "Path to Python file with additional " "code (registered functions) to be imported" +) +gold_help = "Use gold preprocessing provided in the .spacy files" +force_msg = ( + "The provided output file already exists. " + "To force overwriting the output file, set the --force or -F flag." +) + + +DocOrStrStream = Union[Iterable[str], Iterable[Doc]] + + +def _stream_docbin(path: Path, vocab: Vocab) -> Iterable[Doc]: + """ + Stream Doc objects from DocBin. + """ + docbin = DocBin().from_disk(path) + for doc in docbin.get_docs(vocab): + yield doc + + +def _stream_jsonl(path: Path, field: str) -> Iterable[str]: + """ + Stream "text" field from JSONL. If the field "text" is + not found it raises error. + """ + for entry in srsly.read_jsonl(path): + if field not in entry: + msg.fail(f"{path} does not contain the required '{field}' field.", exits=1) + else: + yield entry[field] + + +def _stream_texts(paths: Iterable[Path]) -> Iterable[str]: + """ + Yields strings from text files in paths. + """ + for path in paths: + with open(path, "r") as fin: + text = fin.read() + yield text + + +@app.command("apply") +def apply_cli( + # fmt: off + model: str = Arg(..., help="Model name or path"), + data_path: Path = Arg(..., help=path_help, exists=True), + output_file: Path = Arg(..., help=out_help, dir_okay=False), + code_path: Optional[Path] = Opt(None, "--code", "-c", help=code_help), + text_key: str = Opt("text", "--text-key", "-tk", help="Key containing text string for JSONL"), + force_overwrite: bool = Opt(False, "--force", "-F", help="Force overwriting the output file"), + use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU."), + batch_size: int = Opt(1, "--batch-size", "-b", help="Batch size."), + n_process: int = Opt(1, "--n-process", "-n", help="number of processors to use.") +): + """ + Apply a trained pipeline to documents to get predictions. + Expects a loadable spaCy pipeline and path to the data, which + can be a directory or a file. + The data files can be provided in multiple formats: + 1. .spacy files + 2. .jsonl files with a specified "field" to read the text from. + 3. Files with any other extension are assumed to be containing + a single document. + DOCS: https://spacy.io/api/cli#apply + """ + data_path = ensure_path(data_path) + output_file = ensure_path(output_file) + code_path = ensure_path(code_path) + if output_file.exists() and not force_overwrite: + msg.fail(force_msg, exits=1) + if not data_path.exists(): + msg.fail(f"Couldn't find data path: {data_path}", exits=1) + import_code(code_path) + setup_gpu(use_gpu) + apply(data_path, output_file, model, text_key, batch_size, n_process) + + +def apply( + data_path: Path, + output_file: Path, + model: str, + json_field: str, + batch_size: int, + n_process: int, +): + docbin = DocBin(store_user_data=True) + paths = walk_directory(data_path) + if len(paths) == 0: + docbin.to_disk(output_file) + msg.warn( + "Did not find data to process," + f" {data_path} seems to be an empty directory." + ) + return + nlp = load_model(model) + msg.good(f"Loaded model {model}") + vocab = nlp.vocab + streams: List[DocOrStrStream] = [] + text_files = [] + for path in paths: + if path.suffix == ".spacy": + streams.append(_stream_docbin(path, vocab)) + elif path.suffix == ".jsonl": + streams.append(_stream_jsonl(path, json_field)) + else: + text_files.append(path) + if len(text_files) > 0: + streams.append(_stream_texts(text_files)) + datagen = cast(DocOrStrStream, chain(*streams)) + for doc in tqdm.tqdm(nlp.pipe(datagen, batch_size=batch_size, n_process=n_process)): + docbin.add(doc) + if output_file.suffix == "": + output_file = output_file.with_suffix(".spacy") + docbin.to_disk(output_file) diff --git a/spacy/cli/convert.py b/spacy/cli/convert.py index 04eb7078f..68d454b3e 100644 --- a/spacy/cli/convert.py +++ b/spacy/cli/convert.py @@ -1,4 +1,4 @@ -from typing import Callable, Iterable, Mapping, Optional, Any, List, Union +from typing import Callable, Iterable, Mapping, Optional, Any, Union from enum import Enum from pathlib import Path from wasabi import Printer @@ -7,7 +7,7 @@ import re import sys import itertools -from ._util import app, Arg, Opt +from ._util import app, Arg, Opt, walk_directory from ..training import docs_to_json from ..tokens import Doc, DocBin from ..training.converters import iob_to_docs, conll_ner_to_docs, json_to_docs @@ -28,6 +28,8 @@ CONVERTERS: Mapping[str, Callable[..., Iterable[Doc]]] = { "json": json_to_docs, } +AUTO = "auto" + # File types that can be written to stdout FILE_TYPES_STDOUT = ("json",) @@ -49,7 +51,7 @@ def convert_cli( model: Optional[str] = Opt(None, "--model", "--base", "-b", help="Trained spaCy pipeline for sentence segmentation to use as base (for --seg-sents)"), morphology: bool = Opt(False, "--morphology", "-m", help="Enable appending morphology to tags"), merge_subtokens: bool = Opt(False, "--merge-subtokens", "-T", help="Merge CoNLL-U subtokens"), - converter: str = Opt("auto", "--converter", "-c", help=f"Converter: {tuple(CONVERTERS.keys())}"), + converter: str = Opt(AUTO, "--converter", "-c", help=f"Converter: {tuple(CONVERTERS.keys())}"), ner_map: Optional[Path] = Opt(None, "--ner-map", "-nm", help="NER tag mapping (as JSON-encoded dict of entity types)", exists=True), lang: Optional[str] = Opt(None, "--lang", "-l", help="Language (if tokenizer required)"), concatenate: bool = Opt(None, "--concatenate", "-C", help="Concatenate output to a single file"), @@ -70,8 +72,8 @@ def convert_cli( output_dir: Union[str, Path] = "-" if output_dir == Path("-") else output_dir silent = output_dir == "-" msg = Printer(no_print=silent) - verify_cli_args(msg, input_path, output_dir, file_type.value, converter, ner_map) converter = _get_converter(msg, converter, input_path) + verify_cli_args(msg, input_path, output_dir, file_type.value, converter, ner_map) convert( input_path, output_dir, @@ -100,7 +102,7 @@ def convert( model: Optional[str] = None, morphology: bool = False, merge_subtokens: bool = False, - converter: str = "auto", + converter: str, ner_map: Optional[Path] = None, lang: Optional[str] = None, concatenate: bool = False, @@ -189,33 +191,6 @@ def autodetect_ner_format(input_data: str) -> Optional[str]: return None -def walk_directory(path: Path, converter: str) -> List[Path]: - if not path.is_dir(): - return [path] - paths = [path] - locs = [] - seen = set() - for path in paths: - if str(path) in seen: - continue - seen.add(str(path)) - if path.parts[-1].startswith("."): - continue - elif path.is_dir(): - paths.extend(path.iterdir()) - elif converter == "json" and not path.parts[-1].endswith("json"): - continue - elif converter == "conll" and not path.parts[-1].endswith("conll"): - continue - elif converter == "iob" and not path.parts[-1].endswith("iob"): - continue - else: - locs.append(path) - # It's good to sort these, in case the ordering messes up cache. - locs.sort() - return locs - - def verify_cli_args( msg: Printer, input_path: Path, @@ -239,18 +214,22 @@ def verify_cli_args( input_locs = walk_directory(input_path, converter) if len(input_locs) == 0: msg.fail("No input files in directory", input_path, exits=1) - file_types = list(set([loc.suffix[1:] for loc in input_locs])) - if converter == "auto" and len(file_types) >= 2: - file_types_str = ",".join(file_types) - msg.fail("All input files must be same type", file_types_str, exits=1) - if converter != "auto" and converter not in CONVERTERS: + if converter not in CONVERTERS: msg.fail(f"Can't find converter for {converter}", exits=1) def _get_converter(msg, converter, input_path: Path): if input_path.is_dir(): - input_path = walk_directory(input_path, converter)[0] - if converter == "auto": + if converter == AUTO: + input_locs = walk_directory(input_path, suffix=None) + file_types = list(set([loc.suffix[1:] for loc in input_locs])) + if len(file_types) >= 2: + file_types_str = ",".join(file_types) + msg.fail("All input files must be same type", file_types_str, exits=1) + input_path = input_locs[0] + else: + input_path = walk_directory(input_path, suffix=converter)[0] + if converter == AUTO: converter = input_path.suffix[1:] if converter == "ner" or converter == "iob": with input_path.open(encoding="utf8") as file_: diff --git a/spacy/cli/project/run.py b/spacy/cli/project/run.py index a109c4a5a..6dd174902 100644 --- a/spacy/cli/project/run.py +++ b/spacy/cli/project/run.py @@ -101,8 +101,8 @@ def project_run( if not (project_dir / dep).exists(): err = f"Missing dependency specified by command '{subcommand}': {dep}" err_help = "Maybe you forgot to run the 'project assets' command or a previous step?" - err_kwargs = {"exits": 1} if not dry else {} - msg.fail(err, err_help, **err_kwargs) + err_exits = 1 if not dry else None + msg.fail(err, err_help, exits=err_exits) check_spacy_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION) with working_dir(project_dir) as current_dir: msg.divider(subcommand) diff --git a/spacy/cli/templates/quickstart_training.jinja b/spacy/cli/templates/quickstart_training.jinja index 58864883a..b961ac892 100644 --- a/spacy/cli/templates/quickstart_training.jinja +++ b/spacy/cli/templates/quickstart_training.jinja @@ -1,7 +1,7 @@ {# This is a template for training configs used for the quickstart widget in the docs and the init config command. It encodes various best practices and can help generate the best possible configuration, given a user's requirements. #} -{%- set use_transformer = hardware != "cpu" -%} +{%- set use_transformer = hardware != "cpu" and transformer_data -%} {%- set transformer = transformer_data[optimize] if use_transformer else {} -%} {%- set listener_components = ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker", "spancat", "trainable_lemmatizer"] -%} [paths] diff --git a/spacy/displacy/__init__.py b/spacy/displacy/__init__.py index bc32001d7..2f2058b8e 100644 --- a/spacy/displacy/__init__.py +++ b/spacy/displacy/__init__.py @@ -36,7 +36,7 @@ def render( jupyter (bool): Override Jupyter auto-detection. options (dict): Visualiser-specific options, e.g. colors. manual (bool): Don't parse `Doc` and instead expect a dict/list of dicts. - RETURNS (str): Rendered HTML markup. + RETURNS (str): Rendered SVG or HTML markup. DOCS: https://spacy.io/api/top-level#displacy.render USAGE: https://spacy.io/usage/visualizers diff --git a/spacy/displacy/render.py b/spacy/displacy/render.py index 50dc3466c..f74222dc2 100644 --- a/spacy/displacy/render.py +++ b/spacy/displacy/render.py @@ -94,7 +94,7 @@ class SpanRenderer: parsed (list): Dependency parses to render. page (bool): Render parses wrapped as full HTML page. minify (bool): Minify HTML markup. - RETURNS (str): Rendered HTML markup. + RETURNS (str): Rendered SVG or HTML markup. """ rendered = [] for i, p in enumerate(parsed): @@ -510,7 +510,7 @@ class EntityRenderer: parsed (list): Dependency parses to render. page (bool): Render parses wrapped as full HTML page. minify (bool): Minify HTML markup. - RETURNS (str): Rendered HTML markup. + RETURNS (str): Rendered SVG or HTML markup. """ rendered = [] for i, p in enumerate(parsed): diff --git a/spacy/errors.py b/spacy/errors.py index e34614b0f..cd9281e91 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -345,6 +345,11 @@ class Errors(metaclass=ErrorsWithCodes): "clear the existing vectors and resize the table.") E074 = ("Error interpreting compiled match pattern: patterns are expected " "to end with the attribute {attr}. Got: {bad_attr}.") + E079 = ("Error computing states in beam: number of predicted beams " + "({pbeams}) does not equal number of gold beams ({gbeams}).") + E080 = ("Duplicate state found in beam: {key}.") + E081 = ("Error getting gradient in beam: number of histories ({n_hist}) " + "does not equal number of losses ({losses}).") E082 = ("Error deprojectivizing parse: number of heads ({n_heads}), " "projective heads ({n_proj_heads}) and labels ({n_labels}) do not " "match.") @@ -957,6 +962,7 @@ class Errors(metaclass=ErrorsWithCodes): E1046 = ("{cls_name} is an abstract class and cannot be instantiated. If you are looking for spaCy's default " "knowledge base, use `InMemoryLookupKB`.") E1047 = ("`find_threshold()` only supports components with a `scorer` attribute.") + E1048 = ("Got '{unexpected}' as console progress bar type, but expected one of the following: {expected}") # Deprecated model shortcuts, only used in errors and warnings diff --git a/spacy/lang/nl/stop_words.py b/spacy/lang/nl/stop_words.py index a2c6198e7..cd4fdefdf 100644 --- a/spacy/lang/nl/stop_words.py +++ b/spacy/lang/nl/stop_words.py @@ -15,7 +15,7 @@ STOP_WORDS = set( """ -aan af al alle alles allebei alleen allen als altijd ander anders andere anderen aangaangde aangezien achter achterna +aan af al alle alles allebei alleen allen als altijd ander anders andere anderen aangaande aangezien achter achterna afgelopen aldus alhoewel anderzijds ben bij bijna bijvoorbeeld behalve beide beiden beneden bent bepaald beter betere betreffende binnen binnenin boven diff --git a/spacy/pipeline/edit_tree_lemmatizer.py b/spacy/pipeline/edit_tree_lemmatizer.py index 12f9b73a3..a56c9975e 100644 --- a/spacy/pipeline/edit_tree_lemmatizer.py +++ b/spacy/pipeline/edit_tree_lemmatizer.py @@ -328,9 +328,9 @@ class EditTreeLemmatizer(TrainablePipe): tree = dict(tree) if "orig" in tree: - tree["orig"] = self.vocab.strings[tree["orig"]] + tree["orig"] = self.vocab.strings.add(tree["orig"]) if "orig" in tree: - tree["subst"] = self.vocab.strings[tree["subst"]] + tree["subst"] = self.vocab.strings.add(tree["subst"]) trees.append(tree) diff --git a/spacy/pipeline/span_ruler.py b/spacy/pipeline/span_ruler.py index 807a4ffe5..0e7e9ebf7 100644 --- a/spacy/pipeline/span_ruler.py +++ b/spacy/pipeline/span_ruler.py @@ -170,7 +170,7 @@ def prioritize_existing_ents_filter( @registry.misc("spacy.prioritize_existing_ents_filter.v1") -def make_preverse_existing_ents_filter(): +def make_preserve_existing_ents_filter(): return prioritize_existing_ents_filter diff --git a/spacy/pipeline/spancat.py b/spacy/pipeline/spancat.py index 0a84c72fd..a3388e81a 100644 --- a/spacy/pipeline/spancat.py +++ b/spacy/pipeline/spancat.py @@ -272,7 +272,10 @@ class SpanCategorizer(TrainablePipe): DOCS: https://spacy.io/api/spancategorizer#predict """ indices = self.suggester(docs, ops=self.model.ops) - scores = self.model.predict((docs, indices)) # type: ignore + if indices.lengths.sum() == 0: + scores = self.model.ops.alloc2f(0, 0) + else: + scores = self.model.predict((docs, indices)) # type: ignore return indices, scores def set_candidates( diff --git a/spacy/pipeline/textcat.py b/spacy/pipeline/textcat.py index 65121114d..650a01949 100644 --- a/spacy/pipeline/textcat.py +++ b/spacy/pipeline/textcat.py @@ -74,7 +74,7 @@ subword_features = true default_config={ "threshold": 0.0, "model": DEFAULT_SINGLE_TEXTCAT_MODEL, - "scorer": {"@scorers": "spacy.textcat_scorer.v1"}, + "scorer": {"@scorers": "spacy.textcat_scorer.v2"}, }, default_score_weights={ "cats_score": 1.0, @@ -117,7 +117,7 @@ def textcat_score(examples: Iterable[Example], **kwargs) -> Dict[str, Any]: ) -@registry.scorers("spacy.textcat_scorer.v1") +@registry.scorers("spacy.textcat_scorer.v2") def make_textcat_scorer(): return textcat_score diff --git a/spacy/pipeline/textcat_multilabel.py b/spacy/pipeline/textcat_multilabel.py index 328cee723..41c0e2f63 100644 --- a/spacy/pipeline/textcat_multilabel.py +++ b/spacy/pipeline/textcat_multilabel.py @@ -74,7 +74,7 @@ subword_features = true default_config={ "threshold": 0.5, "model": DEFAULT_MULTI_TEXTCAT_MODEL, - "scorer": {"@scorers": "spacy.textcat_multilabel_scorer.v1"}, + "scorer": {"@scorers": "spacy.textcat_multilabel_scorer.v2"}, }, default_score_weights={ "cats_score": 1.0, @@ -120,7 +120,7 @@ def textcat_multilabel_score(examples: Iterable[Example], **kwargs) -> Dict[str, ) -@registry.scorers("spacy.textcat_multilabel_scorer.v1") +@registry.scorers("spacy.textcat_multilabel_scorer.v2") def make_textcat_multilabel_scorer(): return textcat_multilabel_score diff --git a/spacy/scorer.py b/spacy/scorer.py index 16fc303a0..d8c383ab8 100644 --- a/spacy/scorer.py +++ b/spacy/scorer.py @@ -476,14 +476,12 @@ class Scorer: f_per_type = {label: PRFScore() for label in labels} auc_per_type = {label: ROCAUCScore() for label in labels} labels = set(labels) - if labels: - for eg in examples: - labels.update(eg.predicted.cats.keys()) - labels.update(eg.reference.cats.keys()) for example in examples: # Through this loop, None in the gold_cats indicates missing label. pred_cats = getter(example.predicted, attr) + pred_cats = {k: v for k, v in pred_cats.items() if k in labels} gold_cats = getter(example.reference, attr) + gold_cats = {k: v for k, v in gold_cats.items() if k in labels} for label in labels: pred_score = pred_cats.get(label, 0.0) diff --git a/spacy/tests/doc/test_array.py b/spacy/tests/doc/test_array.py index c334cc6eb..1f2d7d999 100644 --- a/spacy/tests/doc/test_array.py +++ b/spacy/tests/doc/test_array.py @@ -123,14 +123,14 @@ def test_doc_from_array_heads_in_bounds(en_vocab): # head before start arr = doc.to_array(["HEAD"]) - arr[0] = -1 + arr[0] = numpy.int32(-1).astype(numpy.uint64) doc_from_array = Doc(en_vocab, words=words) with pytest.raises(ValueError): doc_from_array.from_array(["HEAD"], arr) # head after end arr = doc.to_array(["HEAD"]) - arr[0] = 5 + arr[0] = numpy.int32(5).astype(numpy.uint64) doc_from_array = Doc(en_vocab, words=words) with pytest.raises(ValueError): doc_from_array.from_array(["HEAD"], arr) diff --git a/spacy/tests/doc/test_span_group.py b/spacy/tests/doc/test_span_group.py index 8c70a83e1..818569c64 100644 --- a/spacy/tests/doc/test_span_group.py +++ b/spacy/tests/doc/test_span_group.py @@ -1,7 +1,10 @@ +from typing import List + import pytest from random import Random from spacy.matcher import Matcher -from spacy.tokens import Span, SpanGroup +from spacy.tokens import Span, SpanGroup, Doc +from spacy.util import filter_spans @pytest.fixture @@ -240,3 +243,13 @@ def test_span_group_extend(doc): def test_span_group_dealloc(span_group): with pytest.raises(AttributeError): print(span_group.doc) + + +@pytest.mark.issue(11975) +def test_span_group_typing(doc: Doc): + """Tests whether typing of `SpanGroup` as `Iterable[Span]`-like object is accepted by mypy.""" + span_group: SpanGroup = doc.spans["SPANS"] + spans: List[Span] = list(span_group) + for i, span in enumerate(span_group): + assert span == span_group[i] == spans[i] + filter_spans(span_group) diff --git a/spacy/tests/pipeline/test_edit_tree_lemmatizer.py b/spacy/tests/pipeline/test_edit_tree_lemmatizer.py index cf541e301..b12ca5dd4 100644 --- a/spacy/tests/pipeline/test_edit_tree_lemmatizer.py +++ b/spacy/tests/pipeline/test_edit_tree_lemmatizer.py @@ -60,10 +60,45 @@ def test_initialize_from_labels(): nlp2 = Language() lemmatizer2 = nlp2.add_pipe("trainable_lemmatizer") lemmatizer2.initialize( - get_examples=lambda: train_examples, + # We want to check that the strings in replacement nodes are + # added to the string store. Avoid that they get added through + # the examples. + get_examples=lambda: train_examples[:1], labels=lemmatizer.label_data, ) assert lemmatizer2.tree2label == {1: 0, 3: 1, 4: 2, 6: 3} + assert lemmatizer2.label_data == { + "trees": [ + {"orig": "S", "subst": "s"}, + { + "prefix_len": 1, + "suffix_len": 0, + "prefix_tree": 0, + "suffix_tree": 4294967295, + }, + {"orig": "s", "subst": ""}, + { + "prefix_len": 0, + "suffix_len": 1, + "prefix_tree": 4294967295, + "suffix_tree": 2, + }, + { + "prefix_len": 0, + "suffix_len": 0, + "prefix_tree": 4294967295, + "suffix_tree": 4294967295, + }, + {"orig": "E", "subst": "e"}, + { + "prefix_len": 1, + "suffix_len": 0, + "prefix_tree": 5, + "suffix_tree": 4294967295, + }, + ], + "labels": (1, 3, 4, 6), + } def test_no_data(): diff --git a/spacy/tests/pipeline/test_spancat.py b/spacy/tests/pipeline/test_spancat.py index 15256a763..e9db983d3 100644 --- a/spacy/tests/pipeline/test_spancat.py +++ b/spacy/tests/pipeline/test_spancat.py @@ -372,24 +372,39 @@ def test_overfitting_IO_overlapping(): def test_zero_suggestions(): - # Test with a suggester that returns 0 suggestions + # Test with a suggester that can return 0 suggestions - @registry.misc("test_zero_suggester") - def make_zero_suggester(): - def zero_suggester(docs, *, ops=None): + @registry.misc("test_mixed_zero_suggester") + def make_mixed_zero_suggester(): + def mixed_zero_suggester(docs, *, ops=None): if ops is None: ops = get_current_ops() - return Ragged( - ops.xp.zeros((0, 0), dtype="i"), ops.xp.zeros((len(docs),), dtype="i") - ) + spans = [] + lengths = [] + for doc in docs: + if len(doc) > 0 and len(doc) % 2 == 0: + spans.append((0, 1)) + lengths.append(1) + else: + lengths.append(0) + spans = ops.asarray2i(spans) + lengths_array = ops.asarray1i(lengths) + if len(spans) > 0: + output = Ragged(ops.xp.vstack(spans), lengths_array) + else: + output = Ragged(ops.xp.zeros((0, 0), dtype="i"), lengths_array) + return output - return zero_suggester + return mixed_zero_suggester fix_random_seed(0) nlp = English() spancat = nlp.add_pipe( "spancat", - config={"suggester": {"@misc": "test_zero_suggester"}, "spans_key": SPAN_KEY}, + config={ + "suggester": {"@misc": "test_mixed_zero_suggester"}, + "spans_key": SPAN_KEY, + }, ) train_examples = make_examples(nlp) optimizer = nlp.initialize(get_examples=lambda: train_examples) @@ -397,6 +412,16 @@ def test_zero_suggestions(): assert set(spancat.labels) == {"LOC", "PERSON"} nlp.update(train_examples, sgd=optimizer) + # empty doc + nlp("") + # single doc with zero suggestions + nlp("one") + # single doc with one suggestion + nlp("two two") + # batch with mixed zero/one suggestions + list(nlp.pipe(["one", "two two", "three three three", "", "four four four four"])) + # batch with no suggestions + list(nlp.pipe(["", "one", "three three three"])) def test_set_candidates(): diff --git a/spacy/tests/pipeline/test_textcat.py b/spacy/tests/pipeline/test_textcat.py index 155ce99a2..d042f3445 100644 --- a/spacy/tests/pipeline/test_textcat.py +++ b/spacy/tests/pipeline/test_textcat.py @@ -895,3 +895,26 @@ def test_textcat_multi_threshold(): scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 0}) assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 1.0 + + +@pytest.mark.parametrize( + "component_name,scorer", + [ + ("textcat", "spacy.textcat_scorer.v1"), + ("textcat_multilabel", "spacy.textcat_multilabel_scorer.v1"), + ], +) +def test_textcat_legacy_scorers(component_name, scorer): + """Check that legacy scorers are registered and produce the expected score + keys.""" + nlp = English() + nlp.add_pipe(component_name, config={"scorer": {"@scorers": scorer}}) + + train_examples = [] + for text, annotations in TRAIN_DATA_SINGLE_LABEL: + train_examples.append(Example.from_dict(nlp.make_doc(text), annotations)) + nlp.initialize(get_examples=lambda: train_examples) + + # score the model (it's not actually trained but that doesn't matter) + scores = nlp.evaluate(train_examples) + assert 0 <= scores["cats_score"] <= 1 diff --git a/spacy/tests/test_cli.py b/spacy/tests/test_cli.py index 2e706458f..c88e20de2 100644 --- a/spacy/tests/test_cli.py +++ b/spacy/tests/test_cli.py @@ -4,7 +4,9 @@ from collections import Counter from typing import Tuple, List, Dict, Any import pkg_resources import time +from pathlib import Path +import spacy import numpy import pytest import srsly @@ -14,7 +16,7 @@ from thinc.api import Config, ConfigValidationError from spacy import about from spacy.cli import info -from spacy.cli._util import is_subpath_of, load_project_config +from spacy.cli._util import is_subpath_of, load_project_config, walk_directory from spacy.cli._util import parse_config_overrides, string_to_list from spacy.cli._util import substitute_project_variables from spacy.cli._util import validate_project_commands @@ -32,6 +34,7 @@ from spacy.cli.package import _is_permitted_package_name from spacy.cli.project.remote_storage import RemoteStorage from spacy.cli.project.run import _check_requirements from spacy.cli.validate import get_model_pkgs +from spacy.cli.apply import apply from spacy.cli.find_threshold import find_threshold from spacy.lang.en import English from spacy.lang.nl import Dutch @@ -123,6 +126,25 @@ def test_issue7055(): assert "model" in filled_cfg["components"]["ner"] +@pytest.mark.issue(11235) +def test_issue11235(): + """ + Test that the cli handles interpolation in the directory names correctly when loading project config. + """ + lang_var = "en" + variables = {"lang": lang_var} + commands = [{"name": "x", "script": ["hello ${vars.lang}"]}] + directories = ["cfg", "${vars.lang}_model"] + project = {"commands": commands, "vars": variables, "directories": directories} + with make_tempdir() as d: + srsly.write_yaml(d / "project.yml", project) + cfg = load_project_config(d) + # Check that the directories are interpolated and created correctly + assert os.path.exists(d / "cfg") + assert os.path.exists(d / f"{lang_var}_model") + assert cfg["commands"][0]["script"][0] == f"hello {lang_var}" + + def test_cli_info(): nlp = Dutch() nlp.add_pipe("textcat") @@ -866,6 +888,82 @@ def test_span_length_freq_dist_output_must_be_correct(): assert list(span_freqs.keys()) == [3, 1, 4, 5, 2] +def test_applycli_empty_dir(): + with make_tempdir() as data_path: + output = data_path / "test.spacy" + apply(data_path, output, "blank:en", "text", 1, 1) + + +def test_applycli_docbin(): + with make_tempdir() as data_path: + output = data_path / "testout.spacy" + nlp = spacy.blank("en") + doc = nlp("testing apply cli.") + # test empty DocBin case + docbin = DocBin() + docbin.to_disk(data_path / "testin.spacy") + apply(data_path, output, "blank:en", "text", 1, 1) + docbin.add(doc) + docbin.to_disk(data_path / "testin.spacy") + apply(data_path, output, "blank:en", "text", 1, 1) + + +def test_applycli_jsonl(): + with make_tempdir() as data_path: + output = data_path / "testout.spacy" + data = [{"field": "Testing apply cli.", "key": 234}] + data2 = [{"field": "234"}] + srsly.write_jsonl(data_path / "test.jsonl", data) + apply(data_path, output, "blank:en", "field", 1, 1) + srsly.write_jsonl(data_path / "test2.jsonl", data2) + apply(data_path, output, "blank:en", "field", 1, 1) + + +def test_applycli_txt(): + with make_tempdir() as data_path: + output = data_path / "testout.spacy" + with open(data_path / "test.foo", "w") as ftest: + ftest.write("Testing apply cli.") + apply(data_path, output, "blank:en", "text", 1, 1) + + +def test_applycli_mixed(): + with make_tempdir() as data_path: + output = data_path / "testout.spacy" + text = "Testing apply cli" + nlp = spacy.blank("en") + doc = nlp(text) + jsonl_data = [{"text": text}] + srsly.write_jsonl(data_path / "test.jsonl", jsonl_data) + docbin = DocBin() + docbin.add(doc) + docbin.to_disk(data_path / "testin.spacy") + with open(data_path / "test.txt", "w") as ftest: + ftest.write(text) + apply(data_path, output, "blank:en", "text", 1, 1) + # Check whether it worked + result = list(DocBin().from_disk(output).get_docs(nlp.vocab)) + assert len(result) == 3 + for doc in result: + assert doc.text == text + + +def test_applycli_user_data(): + Doc.set_extension("ext", default=0) + val = ("ext", 0) + with make_tempdir() as data_path: + output = data_path / "testout.spacy" + nlp = spacy.blank("en") + doc = nlp("testing apply cli.") + doc._.ext = val + docbin = DocBin(store_user_data=True) + docbin.add(doc) + docbin.to_disk(data_path / "testin.spacy") + apply(data_path, output, "blank:en", "", 1, 1) + result = list(DocBin().from_disk(output).get_docs(nlp.vocab)) + assert result[0]._.ext == val + + def test_local_remote_storage(): with make_tempdir() as d: filename = "a.txt" @@ -1088,3 +1186,26 @@ def test_upload_download_local_file(): download_file(remote_file, local_file) with local_file.open(mode="r") as file_: assert file_.read() == content + + +def test_walk_directory(): + with make_tempdir() as d: + files = [ + "data1.iob", + "data2.iob", + "data3.json", + "data4.conll", + "data5.conll", + "data6.conll", + "data7.txt", + ] + + for f in files: + Path(d / f).touch() + + assert (len(walk_directory(d))) == 7 + assert (len(walk_directory(d, suffix=None))) == 7 + assert (len(walk_directory(d, suffix="json"))) == 1 + assert (len(walk_directory(d, suffix="iob"))) == 2 + assert (len(walk_directory(d, suffix="conll"))) == 3 + assert (len(walk_directory(d, suffix="pdf"))) == 0 diff --git a/spacy/tests/test_cli_app.py b/spacy/tests/test_cli_app.py new file mode 100644 index 000000000..873a3ff66 --- /dev/null +++ b/spacy/tests/test_cli_app.py @@ -0,0 +1,33 @@ +import os +from pathlib import Path +from typer.testing import CliRunner + +from spacy.cli._util import app +from .util import make_tempdir + + +def test_convert_auto(): + with make_tempdir() as d_in, make_tempdir() as d_out: + for f in ["data1.iob", "data2.iob", "data3.iob"]: + Path(d_in / f).touch() + + # ensure that "automatic" suffix detection works + result = CliRunner().invoke(app, ["convert", str(d_in), str(d_out)]) + assert "Generated output file" in result.stdout + out_files = os.listdir(d_out) + assert len(out_files) == 3 + assert "data1.spacy" in out_files + assert "data2.spacy" in out_files + assert "data3.spacy" in out_files + + +def test_convert_auto_conflict(): + with make_tempdir() as d_in, make_tempdir() as d_out: + for f in ["data1.iob", "data2.iob", "data3.json"]: + Path(d_in / f).touch() + + # ensure that "automatic" suffix detection warns when there are different file types + result = CliRunner().invoke(app, ["convert", str(d_in), str(d_out)]) + assert "All input files must be same type" in result.stdout + out_files = os.listdir(d_out) + assert len(out_files) == 0 diff --git a/spacy/tests/test_language.py b/spacy/tests/test_language.py index 03a98d32f..03790eb86 100644 --- a/spacy/tests/test_language.py +++ b/spacy/tests/test_language.py @@ -3,6 +3,7 @@ import logging from unittest import mock import pytest from spacy.language import Language +from spacy.scorer import Scorer from spacy.tokens import Doc, Span from spacy.vocab import Vocab from spacy.training import Example @@ -126,6 +127,112 @@ def test_evaluate_no_pipe(nlp): nlp.evaluate([Example.from_dict(doc, annots)]) +def test_evaluate_textcat_multilabel(en_vocab): + """Test that evaluate works with a multilabel textcat pipe.""" + nlp = Language(en_vocab) + textcat_multilabel = nlp.add_pipe("textcat_multilabel") + for label in ("FEATURE", "REQUEST", "BUG", "QUESTION"): + textcat_multilabel.add_label(label) + nlp.initialize() + + annots = {"cats": {"FEATURE": 1.0, "QUESTION": 1.0}} + doc = nlp.make_doc("hello world") + example = Example.from_dict(doc, annots) + scores = nlp.evaluate([example]) + labels = nlp.get_pipe("textcat_multilabel").labels + for label in labels: + assert scores["cats_f_per_type"].get(label) is not None + for key in example.reference.cats.keys(): + if key not in labels: + assert scores["cats_f_per_type"].get(key) is None + + +def test_evaluate_multiple_textcat_final(en_vocab): + """Test that evaluate evaluates the final textcat component in a pipeline + with more than one textcat or textcat_multilabel.""" + nlp = Language(en_vocab) + textcat = nlp.add_pipe("textcat") + for label in ("POSITIVE", "NEGATIVE"): + textcat.add_label(label) + textcat_multilabel = nlp.add_pipe("textcat_multilabel") + for label in ("FEATURE", "REQUEST", "BUG", "QUESTION"): + textcat_multilabel.add_label(label) + nlp.initialize() + + annots = { + "cats": { + "POSITIVE": 1.0, + "NEGATIVE": 0.0, + "FEATURE": 1.0, + "QUESTION": 1.0, + "POSITIVE": 1.0, + "NEGATIVE": 0.0, + } + } + doc = nlp.make_doc("hello world") + example = Example.from_dict(doc, annots) + scores = nlp.evaluate([example]) + # get the labels from the final pipe + labels = nlp.get_pipe(nlp.pipe_names[-1]).labels + for label in labels: + assert scores["cats_f_per_type"].get(label) is not None + for key in example.reference.cats.keys(): + if key not in labels: + assert scores["cats_f_per_type"].get(key) is None + + +def test_evaluate_multiple_textcat_separate(en_vocab): + """Test that evaluate can evaluate multiple textcat components separately + with custom scorers.""" + + def custom_textcat_score(examples, **kwargs): + scores = Scorer.score_cats( + examples, + "cats", + multi_label=False, + **kwargs, + ) + return {f"custom_{k}": v for k, v in scores.items()} + + @spacy.registry.scorers("test_custom_textcat_scorer") + def make_custom_textcat_scorer(): + return custom_textcat_score + + nlp = Language(en_vocab) + textcat = nlp.add_pipe( + "textcat", + config={"scorer": {"@scorers": "test_custom_textcat_scorer"}}, + ) + for label in ("POSITIVE", "NEGATIVE"): + textcat.add_label(label) + textcat_multilabel = nlp.add_pipe("textcat_multilabel") + for label in ("FEATURE", "REQUEST", "BUG", "QUESTION"): + textcat_multilabel.add_label(label) + nlp.initialize() + + annots = { + "cats": { + "POSITIVE": 1.0, + "NEGATIVE": 0.0, + "FEATURE": 1.0, + "QUESTION": 1.0, + "POSITIVE": 1.0, + "NEGATIVE": 0.0, + } + } + doc = nlp.make_doc("hello world") + example = Example.from_dict(doc, annots) + scores = nlp.evaluate([example]) + # check custom scores for the textcat pipe + assert "custom_cats_f_per_type" in scores + labels = nlp.get_pipe("textcat").labels + assert set(scores["custom_cats_f_per_type"].keys()) == set(labels) + # check default scores for the textcat_multilabel pipe + assert "cats_f_per_type" in scores + labels = nlp.get_pipe("textcat_multilabel").labels + assert set(scores["cats_f_per_type"].keys()) == set(labels) + + def vector_modification_pipe(doc): doc.vector += 1 return doc diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx index f2621292c..075bc4d15 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -359,6 +359,7 @@ cdef class Doc: for annot in annotations: if annot: if annot is heads or annot is sent_starts or annot is ent_iobs: + annot = numpy.array(annot, dtype=numpy.int32).astype(numpy.uint64) for i in range(len(words)): if attrs.ndim == 1: attrs[i] = annot[i] @@ -1558,6 +1559,7 @@ cdef class Doc: for j, (attr, annot) in enumerate(token_annotations.items()): if attr is HEAD: + annot = numpy.array(annot, dtype=numpy.int32).astype(numpy.uint64) for i in range(len(words)): array[i, j] = annot[i] elif attr is MORPH: diff --git a/spacy/tokens/span.pyi b/spacy/tokens/span.pyi index 0a6f306a6..9986a90e6 100644 --- a/spacy/tokens/span.pyi +++ b/spacy/tokens/span.pyi @@ -95,8 +95,8 @@ class Span: self, start_idx: int, end_idx: int, - label: int = ..., - kb_id: int = ..., + label: Union[int, str] = ..., + kb_id: Union[int, str] = ..., vector: Optional[Floats1d] = ..., ) -> Span: ... @property diff --git a/spacy/tokens/span.pyx b/spacy/tokens/span.pyx index c3495f497..99a5f43bd 100644 --- a/spacy/tokens/span.pyx +++ b/spacy/tokens/span.pyx @@ -299,7 +299,7 @@ cdef class Span: for ancestor in ancestors: ancestor_i = ancestor.i - self.c.start if ancestor_i in range(length): - array[i, head_col] = ancestor_i - i + array[i, head_col] = numpy.int32(ancestor_i - i).astype(numpy.uint64) # if there is no appropriate ancestor, define a new artificial root value = array[i, head_col] @@ -307,7 +307,7 @@ cdef class Span: new_root = old_to_new_root.get(ancestor_i, None) if new_root is not None: # take the same artificial root as a previous token from the same sentence - array[i, head_col] = new_root - i + array[i, head_col] = numpy.int32(new_root - i).astype(numpy.uint64) else: # set this token as the new artificial root array[i, head_col] = 0 diff --git a/spacy/tokens/span_group.pyi b/spacy/tokens/span_group.pyi index 21cd124ab..0b4aa83aa 100644 --- a/spacy/tokens/span_group.pyi +++ b/spacy/tokens/span_group.pyi @@ -18,6 +18,7 @@ class SpanGroup: def doc(self) -> Doc: ... @property def has_overlap(self) -> bool: ... + def __iter__(self): ... def __len__(self) -> int: ... def append(self, span: Span) -> None: ... def extend(self, spans: Iterable[Span]) -> None: ... diff --git a/spacy/tokens/span_group.pyx b/spacy/tokens/span_group.pyx index 1aa3c0bc8..608dda283 100644 --- a/spacy/tokens/span_group.pyx +++ b/spacy/tokens/span_group.pyx @@ -158,6 +158,16 @@ cdef class SpanGroup: return self._concat(other) return NotImplemented + def __iter__(self): + """ + Iterate over the spans in this SpanGroup. + YIELDS (Span): A span in this SpanGroup. + + DOCS: https://spacy.io/api/spangroup#iter + """ + for i in range(self.c.size()): + yield self[i] + def append(self, Span span): """Add a span to the group. The span must refer to the same Doc object as the span group. diff --git a/spacy/training/example.pyx b/spacy/training/example.pyx index dfd337b9e..95b0f0de9 100644 --- a/spacy/training/example.pyx +++ b/spacy/training/example.pyx @@ -443,26 +443,27 @@ def _annot2array(vocab, tok_annot, doc_annot): if key not in IDS: raise ValueError(Errors.E974.format(obj="token", key=key)) elif key in ["ORTH", "SPACY"]: - pass + continue elif key == "HEAD": attrs.append(key) - values.append([h-i if h is not None else 0 for i, h in enumerate(value)]) + row = [h-i if h is not None else 0 for i, h in enumerate(value)] elif key == "DEP": attrs.append(key) - values.append([vocab.strings.add(h) if h is not None else MISSING_DEP for h in value]) + row = [vocab.strings.add(h) if h is not None else MISSING_DEP for h in value] elif key == "SENT_START": attrs.append(key) - values.append([to_ternary_int(v) for v in value]) + row = [to_ternary_int(v) for v in value] elif key == "MORPH": attrs.append(key) - values.append([vocab.morphology.add(v) for v in value]) + row = [vocab.morphology.add(v) for v in value] else: attrs.append(key) if not all(isinstance(v, str) for v in value): types = set([type(v) for v in value]) raise TypeError(Errors.E969.format(field=key, types=types)) from None - values.append([vocab.strings.add(v) for v in value]) - array = numpy.asarray(values, dtype="uint64") + row = [vocab.strings.add(v) for v in value] + values.append([numpy.array(v, dtype=numpy.int32).astype(numpy.uint64) if v < 0 else v for v in row]) + array = numpy.array(values, dtype=numpy.uint64) return attrs, array.T diff --git a/spacy/training/loggers.py b/spacy/training/loggers.py index 408ea7140..7de31822e 100644 --- a/spacy/training/loggers.py +++ b/spacy/training/loggers.py @@ -26,6 +26,8 @@ def setup_table( return final_cols, final_widths, ["r" for _ in final_widths] +# We cannot rename this method as it's directly imported +# and used by external packages such as spacy-loggers. @registry.loggers("spacy.ConsoleLogger.v2") def console_logger( progress_bar: bool = False, @@ -33,7 +35,27 @@ def console_logger( output_file: Optional[Union[str, Path]] = None, ): """The ConsoleLogger.v2 prints out training logs in the console and/or saves them to a jsonl file. - progress_bar (bool): Whether the logger should print the progress bar. + progress_bar (bool): Whether the logger should print a progress bar tracking the steps till the next evaluation pass. + console_output (bool): Whether the logger should print the logs on the console. + output_file (Optional[Union[str, Path]]): The file to save the training logs to. + """ + return console_logger_v3( + progress_bar=None if progress_bar is False else "eval", + console_output=console_output, + output_file=output_file, + ) + + +@registry.loggers("spacy.ConsoleLogger.v3") +def console_logger_v3( + progress_bar: Optional[str] = None, + console_output: bool = True, + output_file: Optional[Union[str, Path]] = None, +): + """The ConsoleLogger.v3 prints out training logs in the console and/or saves them to a jsonl file. + progress_bar (Optional[str]): Type of progress bar to show in the console. Allowed values: + train - Tracks the number of steps from the beginning of training until the full training run is complete (training.max_steps is reached). + eval - Tracks the number of steps between the previous and next evaluation (training.eval_frequency is reached). console_output (bool): Whether the logger should print the logs on the console. output_file (Optional[Union[str, Path]]): The file to save the training logs to. """ @@ -70,6 +92,7 @@ def console_logger( for name, proc in nlp.pipeline if hasattr(proc, "is_trainable") and proc.is_trainable ] + max_steps = nlp.config["training"]["max_steps"] eval_frequency = nlp.config["training"]["eval_frequency"] score_weights = nlp.config["training"]["score_weights"] score_cols = [col for col, value in score_weights.items() if value is not None] @@ -84,6 +107,13 @@ def console_logger( write(msg.row(table_header, widths=table_widths, spacing=spacing)) write(msg.row(["-" * width for width in table_widths], spacing=spacing)) progress = None + expected_progress_types = ("train", "eval") + if progress_bar is not None and progress_bar not in expected_progress_types: + raise ValueError( + Errors.E1048.format( + unexpected=progress_bar, expected=expected_progress_types + ) + ) def log_step(info: Optional[Dict[str, Any]]) -> None: nonlocal progress @@ -141,11 +171,23 @@ def console_logger( ) ) if progress_bar: + if progress_bar == "train": + total = max_steps + desc = f"Last Eval Epoch: {info['epoch']}" + initial = info["step"] + else: + total = eval_frequency + desc = f"Epoch {info['epoch']+1}" + initial = 0 # Set disable=None, so that it disables on non-TTY progress = tqdm.tqdm( - total=eval_frequency, disable=None, leave=False, file=stderr + total=total, + disable=None, + leave=False, + file=stderr, + initial=initial, ) - progress.set_description(f"Epoch {info['epoch']+1}") + progress.set_description(desc) def finalize() -> None: if output_stream: diff --git a/spacy/util.py b/spacy/util.py index cba403361..8d211a9a5 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -1643,7 +1643,9 @@ def _pipe( docs: Iterable["Doc"], proc: "PipeCallable", name: str, - default_error_handler: Callable[[str, "PipeCallable", List["Doc"], Exception], NoReturn], + default_error_handler: Callable[ + [str, "PipeCallable", List["Doc"], Exception], NoReturn + ], kwargs: Mapping[str, Any], ) -> Iterator["Doc"]: if hasattr(proc, "pipe"): diff --git a/website/docs/api/cli.md b/website/docs/api/cli.md index 798d75ae2..f54809e7b 100644 --- a/website/docs/api/cli.md +++ b/website/docs/api/cli.md @@ -13,6 +13,7 @@ menu: - ['pretrain', 'pretrain'] - ['evaluate', 'evaluate'] - ['benchmark', 'benchmark'] + - ['apply', 'apply'] - ['find-threshold', 'find-threshold'] - ['assemble', 'assemble'] - ['package', 'package'] @@ -475,7 +476,7 @@ 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/). @@ -1195,6 +1196,37 @@ $ python -m spacy benchmark speed [model] [data_path] [--batch_size] [--no-shuff | `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | | **CREATES** | Pipeline speed with 95% confidence interval. | +## apply {#apply new="3.5" tag="command"} + +Applies a trained pipeline to data and stores the resulting annotated documents +in a `DocBin`. The input can be a single file or a directory. The recognized +input formats are: + +1. `.spacy` +2. `.jsonl` containing a user specified `text_key` +3. Files with any other extension are assumed to be plain text files containing + a single document. + +When a directory is provided it is traversed recursively to collect all files. + +```cli +$ python -m spacy apply [model] [data-path] [output-file] [--code] [--text-key] [--force-overwrite] [--gpu-id] [--batch-size] [--n-process] +``` + +| Name | Description | +| ----------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `model` | Pipeline to apply to the data. Can be a package or a path to a data directory. ~~str (positional)~~ | +| `data_path` | Location of data to be evaluated in spaCy's [binary format](/api/data-formats#training), jsonl, or plain text. ~~Path (positional)~~ | +| `output-file`, `-o` | Output `DocBin` path. ~~str (positional)~~ | +| `--code`, `-c` 3 | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ | +| `--text-key`, `-tk` | The key for `.jsonl` files to use to grab the texts from. Defaults to `text`. ~~Optional[str] \(option)~~ | +| `--force-overwrite`, `-F` | If the provided `output-file` already exists, then force `apply` to overwrite it. If this is `False` (default) then quits with a warning instead. ~~bool (flag)~~ | +| `--gpu-id`, `-g` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~ | +| `--batch-size`, `-b` | Batch size to use for prediction. Defaults to `1`. ~~int (option)~~ | +| `--n-process`, `-n` | Number of processes to use for prediction. Defaults to `1`. ~~int (option)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | +| **CREATES** | A `DocBin` with the annotations from the `model` for all the files found in `data-path`. | + ## find-threshold {#find-threshold new="3.5" tag="command"} Runs prediction trials for a trained model with varying tresholds to maximize @@ -1220,7 +1252,6 @@ be provided. > $ python -m spacy find-threshold my_nlp data.spacy spancat threshold spans_sc_f > ``` - | Name | Description | | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `model` | Pipeline to evaluate. Can be a package or a path to a data directory. ~~str (positional)~~ | diff --git a/website/docs/api/data-formats.md b/website/docs/api/data-formats.md index 768844cf3..420e827a0 100644 --- a/website/docs/api/data-formats.md +++ b/website/docs/api/data-formats.md @@ -186,7 +186,7 @@ process that are used when you run [`spacy train`](/api/cli#train). | `accumulate_gradient` | Whether to divide the batch up into substeps. Defaults to `1`. ~~int~~ | | `batcher` | Callable that takes an iterator of [`Doc`](/api/doc) objects and yields batches of `Doc`s. Defaults to [`batch_by_words`](/api/top-level#batch_by_words). ~~Callable[[Iterator[Doc], Iterator[List[Doc]]]]~~ | | `before_to_disk` | Optional callback to modify `nlp` object right before it is saved to disk during and after training. Can be used to remove or reset config values or disable components. Defaults to `null`. ~~Optional[Callable[[Language], Language]]~~ | -| `before_update` | Optional callback that is invoked at the start of each training step with the `nlp` object and a `Dict` containing the following entries: `step`, `epoch`. Can be used to make deferred changes to components. Defaults to `null`. ~~Optional[Callable[[Language, Dict[str, Any]], None]]~~ | +| `before_update` 3.5 | Optional callback that is invoked at the start of each training step with the `nlp` object and a `Dict` containing the following entries: `step`, `epoch`. Can be used to make deferred changes to components. Defaults to `null`. ~~Optional[Callable[[Language, Dict[str, Any]], None]]~~ | | `dev_corpus` | Dot notation of the config location defining the dev corpus. Defaults to `corpora.dev`. ~~str~~ | | `dropout` | The dropout rate. Defaults to `0.1`. ~~float~~ | | `eval_frequency` | How often to evaluate during training (steps). Defaults to `200`. ~~int~~ | diff --git a/website/docs/api/lexeme.md b/website/docs/api/lexeme.md index eb76afa90..557d04cce 100644 --- a/website/docs/api/lexeme.md +++ b/website/docs/api/lexeme.md @@ -138,7 +138,7 @@ The L2 norm of the lexeme's vector representation. | `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~~ | +| `suffix_` | Length-N substring from the end 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~~ | diff --git a/website/docs/api/spangroup.md b/website/docs/api/spangroup.md index 2d1cf73c4..bd9659acb 100644 --- a/website/docs/api/spangroup.md +++ b/website/docs/api/spangroup.md @@ -202,6 +202,23 @@ already present in the current span group. | `other` | The span group or spans to append. ~~Union[SpanGroup, Iterable[Span]]~~ | | **RETURNS** | The span group. ~~SpanGroup~~ | +## SpanGroup.\_\_iter\_\_ {#iter tag="method" new="3.5"} + +Iterate over the spans in this span group. + +> #### Example +> +> ```python +> doc = nlp("Their goi ng home") +> doc.spans["errors"] = [doc[0:1], doc[1:3]] +> for error_span in doc.spans["errors"]: +> print(error_span) +> ``` + +| Name | Description | +| ---------- | ----------------------------------- | +| **YIELDS** | A span in this span group. ~~Span~~ | + ## SpanGroup.append {#append tag="method"} Add a [`Span`](/api/span) object to the group. The span must refer to the same diff --git a/website/docs/api/top-level.md b/website/docs/api/top-level.md index 211affa4a..6a63e07da 100644 --- a/website/docs/api/top-level.md +++ b/website/docs/api/top-level.md @@ -266,7 +266,7 @@ Render a dependency parse tree or named entity visualization. | ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `docs` | Document(s) or span(s) to visualize. ~~Union[Iterable[Union[Doc, Span, dict]], Doc, Span, dict]~~ | | `style` | Visualization style, `"dep"`, `"ent"` or `"span"` 3.3. Defaults to `"dep"`. ~~str~~ | -| `page` | Render markup as full HTML page. Defaults to `True`. ~~bool~~ | +| `page` | Render markup as full HTML page. Defaults to `False`. ~~bool~~ | | `minify` | Minify HTML markup. Defaults to `False`. ~~bool~~ | | `options` | [Visualizer-specific options](#displacy_options), e.g. colors. ~~Dict[str, Any]~~ | | `manual` | Don't parse `Doc` and instead expect a dict or list of dicts. [See here](/usage/visualizers#manual-usage) for formats and examples. Defaults to `False`. ~~bool~~ | @@ -513,7 +513,7 @@ a [Weights & Biases](https://www.wandb.com/) dashboard. Instead of using one of the built-in loggers, you can [implement your own](/usage/training#custom-logging). -#### spacy.ConsoleLogger.v2 {#ConsoleLogger tag="registered function"} +#### spacy.ConsoleLogger.v2 {tag="registered function"} > #### Example config > @@ -564,11 +564,33 @@ start decreasing across epochs. -| Name | Description | -| ---------------- | --------------------------------------------------------------------- | -| `progress_bar` | Whether the logger should print the progress bar ~~bool~~ | -| `console_output` | Whether the logger should print the logs on the console. ~~bool~~ | -| `output_file` | The file to save the training logs to. ~~Optional[Union[str, Path]]~~ | +| Name | Description | +| ---------------- | ---------------------------------------------------------------------------------------------------------------------------- | +| `progress_bar` | Whether the logger should print a progress bar tracking the steps till the next evaluation pass (default: `False`). ~~bool~~ | +| `console_output` | Whether the logger should print the logs in the console (default: `True`). ~~bool~~ | +| `output_file` | The file to save the training logs to (default: `None`). ~~Optional[Union[str, Path]]~~ | + +#### spacy.ConsoleLogger.v3 {#ConsoleLogger tag="registered function"} + +> #### Example config +> +> ```ini +> [training.logger] +> @loggers = "spacy.ConsoleLogger.v3" +> progress_bar = "all_steps" +> console_output = true +> output_file = "training_log.jsonl" +> ``` + +Writes the results of a training step to the console in a tabular format and +optionally saves them to a `jsonl` file. + +| Name | Description | +| ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `progress_bar` | Type of progress bar to show in the console: `"train"`, `"eval"` or `None`. | +| | The bar tracks the number of steps until `training.max_steps` and `training.eval_frequency` are reached respectively (default: `None`). ~~Optional[str]~~ | +| `console_output` | Whether the logger should print the logs in the console (default: `True`). ~~bool~~ | +| `output_file` | The file to save the training logs to (default: `None`). ~~Optional[Union[str, Path]]~~ | ## Readers {#readers} @@ -1004,6 +1026,54 @@ This method was previously available as `spacy.gold.spans_from_biluo_tags`. | `tags` | A sequence of [BILUO](/usage/linguistic-features#accessing-ner) tags with each tag describing one token. Each tag string will be of the form of either `""`, `"O"` or `"{action}-{label}"`, where action is one of `"B"`, `"I"`, `"L"`, `"U"`. ~~List[str]~~ | | **RETURNS** | A sequence of `Span` objects with added entity labels. ~~List[Span]~~ | +### training.biluo_to_iob {#biluo_to_iob tag="function"} + +Convert a sequence of [BILUO](/usage/linguistic-features#accessing-ner) tags to +[IOB](/usage/linguistic-features#accessing-ner) tags. This is useful if you want +use the BILUO tags with a model that only supports IOB tags. + +> #### Example +> +> ```python +> from spacy.training import biluo_to_iob +> +> tags = ["O", "O", "B-LOC", "I-LOC", "L-LOC", "O"] +> iob_tags = biluo_to_iob(tags) +> assert iob_tags == ["O", "O", "B-LOC", "I-LOC", "I-LOC", "O"] +> ``` + +| Name | Description | +| ----------- | --------------------------------------------------------------------------------------- | +| `tags` | A sequence of [BILUO](/usage/linguistic-features#accessing-ner) tags. ~~Iterable[str]~~ | +| **RETURNS** | A list of [IOB](/usage/linguistic-features#accessing-ner) tags. ~~List[str]~~ | + +### training.iob_to_biluo {#iob_to_biluo tag="function"} + +Convert a sequence of [IOB](/usage/linguistic-features#accessing-ner) tags to +[BILUO](/usage/linguistic-features#accessing-ner) tags. This is useful if you +want use the IOB tags with a model that only supports BILUO tags. + + + +This method was previously available as `spacy.gold.iob_to_biluo`. + + + +> #### Example +> +> ```python +> from spacy.training import iob_to_biluo +> +> tags = ["O", "O", "B-LOC", "I-LOC", "O"] +> biluo_tags = iob_to_biluo(tags) +> assert biluo_tags == ["O", "O", "B-LOC", "L-LOC", "O"] +> ``` + +| Name | Description | +| ----------- | ------------------------------------------------------------------------------------- | +| `tags` | A sequence of [IOB](/usage/linguistic-features#accessing-ner) tags. ~~Iterable[str]~~ | +| **RETURNS** | A list of [BILUO](/usage/linguistic-features#accessing-ner) tags. ~~List[str]~~ | + ## Utility functions {#util source="spacy/util.py"} spaCy comes with a small collection of utility functions located in diff --git a/website/docs/api/vocab.md b/website/docs/api/vocab.md index afbd1301d..5e4de219a 100644 --- a/website/docs/api/vocab.md +++ b/website/docs/api/vocab.md @@ -308,14 +308,14 @@ Load state from a binary string. > assert type(PERSON) == int > ``` -| Name | Description | -| ---------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `strings` | A table managing the string-to-int mapping. ~~StringStore~~ | -| `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` | 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]]]]]~~ | +| Name | Description | +| ---------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `strings` | A table managing the string-to-int mapping. ~~StringStore~~ | +| `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` | 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`](/api/doc#noun_chunks). ~~Optional[Callable[[Union[Doc, Span], Iterator[Tuple[int, int, int]]]]]~~ | ## Serialization fields {#serialization-fields} diff --git a/website/docs/usage/v3-4.md b/website/docs/usage/v3-4.md index 597fc3cc8..e10110b71 100644 --- a/website/docs/usage/v3-4.md +++ b/website/docs/usage/v3-4.md @@ -66,8 +66,8 @@ The English CNN pipelines have new word vectors: | Package | Model Version | TAG | Parser LAS | NER F | | ----------------------------------------------- | ------------- | ---: | ---------: | ----: | | [`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_md`](/models/en#en_core_web_md) | v3.4.0 | 97.2 | 90.3 | 85.5 | +| [`en_core_web_lg`](/models/en#en_core_web_lg) | 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/sidebars.json b/website/meta/sidebars.json index 2d8745d77..339e4085b 100644 --- a/website/meta/sidebars.json +++ b/website/meta/sidebars.json @@ -45,7 +45,7 @@ { "text": "v2.x Documentation", "url": "https://v2.spacy.io" }, { "text": "Custom Solutions", - "url": "https://explosion.ai/spacy-tailored-pipelines" + "url": "https://explosion.ai/custom-solutions" } ] } diff --git a/website/meta/site.json b/website/meta/site.json index 360a72178..fa79d3c69 100644 --- a/website/meta/site.json +++ b/website/meta/site.json @@ -51,7 +51,7 @@ { "text": "Online Course", "url": "https://course.spacy.io" }, { "text": "Custom Solutions", - "url": "https://explosion.ai/spacy-tailored-pipelines" + "url": "https://explosion.ai/custom-solutions" } ] }, diff --git a/website/meta/universe.json b/website/meta/universe.json index 97b53e9c5..99d121507 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -1023,25 +1023,6 @@ }, "category": ["pipeline"] }, - { - "id": "spacy-sentence-segmenter", - "title": "Sentence Segmenter", - "slogan": "Custom sentence segmentation for spaCy", - "code_example": [ - "from seg.newline.segmenter import NewLineSegmenter", - "import spacy", - "", - "nlseg = NewLineSegmenter()", - "nlp = spacy.load('en')", - "nlp.add_pipe(nlseg.set_sent_starts, name='sentence_segmenter', before='parser')", - "doc = nlp(my_doc_text)" - ], - "author": "tc64", - "author_links": { - "github": "tc64" - }, - "category": ["pipeline"] - }, { "id": "spacy_cld", "title": "spaCy-CLD", @@ -1468,13 +1449,26 @@ "image": "https://jasonkessler.github.io/2012conventions0.0.2.2.png", "code_example": [ "import spacy", - "import scattertext as st", "", - "nlp = spacy.load('en')", - "corpus = st.CorpusFromPandas(convention_df,", - " category_col='party',", - " text_col='text',", - " nlp=nlp).build()" + "from scattertext import SampleCorpora, produce_scattertext_explorer", + "from scattertext import produce_scattertext_html", + "from scattertext.CorpusFromPandas import CorpusFromPandas", + "", + "nlp = spacy.load('en_core_web_sm')", + "convention_df = SampleCorpora.ConventionData2012.get_data()", + "corpus = CorpusFromPandas(convention_df,", + " category_col='party',", + " text_col='text',", + " nlp=nlp).build()", + "", + "html = produce_scattertext_html(corpus,", + " category='democrat',", + " category_name='Democratic',", + " not_category_name='Republican',", + " minimum_term_frequency=5,", + " width_in_pixels=1000)", + "open('./simple.html', 'wb').write(html.encode('utf-8'))", + "print('Open ./simple.html in Chrome or Firefox.')" ], "author": "Jason Kessler", "author_links": { @@ -4068,6 +4062,33 @@ "author_links": { "github": "yasufumy" } + }, + { + "id": "spacy-pythainlp", + "title": "spaCy-PyThaiNLP", + "slogan": "PyThaiNLP for spaCy", + "description": "This package wraps the PyThaiNLP library to add support for Thai to spaCy.", + "github": "PyThaiNLP/spaCy-PyThaiNLP", + "code_example": [ + "import spacy", + "import spacy_pythainlp.core", + "", + "nlp = spacy.blank('th')", + "nlp.add_pipe('pythainlp')", + "doc = nlp('ผมเป็นคนไทย แต่มะลิอยากไปโรงเรียนส่วนผมจะไปไหน ผมอยากไปเที่ยว')", + "", + "print(list(doc.sents))", + "# output: [ผมเป็นคนไทย แต่มะลิอยากไปโรงเรียนส่วนผมจะไปไหน , ผมอยากไปเที่ยว]" + ], + "code_language": "python", + "author": "Wannaphong Phatthiyaphaibun", + "author_links": { + "twitter": "@wannaphong_p", + "github": "wannaphong", + "website": "https://iam.wannaphong.com/" + }, + "category": ["pipeline", "research"], + "tags": ["Thai"] } ], diff --git a/website/src/widgets/landing.js b/website/src/widgets/landing.js index b7ae35f6e..c3aaa8a22 100644 --- a/website/src/widgets/landing.js +++ b/website/src/widgets/landing.js @@ -105,13 +105,13 @@ const Landing = ({ data }) => { - + spaCy Tailored Pipelines