diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index f226057c9..619570090 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -107,22 +107,22 @@ jobs: - name: Test import run: python -W error -c "import spacy" - - name: "Test download CLI" - run: | - python -m spacy download ca_core_news_sm - python -m spacy download ca_core_news_md - python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')" - if: matrix.python_version == '3.9' - - - name: "Test download_url in info CLI" - run: | - python -W error -m spacy info ca_core_news_sm | grep -q download_url - if: matrix.python_version == '3.9' - - - name: "Test no warnings on load (#11713)" - run: | - python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')" - if: matrix.python_version == '3.9' +# - name: "Test download CLI" +# run: | +# python -m spacy download ca_core_news_sm +# python -m spacy download ca_core_news_md +# python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')" +# if: matrix.python_version == '3.9' +# +# - name: "Test download_url in info CLI" +# run: | +# python -W error -m spacy info ca_core_news_sm | grep -q download_url +# if: matrix.python_version == '3.9' +# +# - name: "Test no warnings on load (#11713)" +# run: | +# python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')" +# if: matrix.python_version == '3.9' - name: "Test convert CLI" run: | @@ -146,17 +146,17 @@ jobs: python -m spacy train ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy --training.max_steps 10 --gpu-id -1 if: matrix.python_version == '3.9' - - name: "Test assemble CLI" - run: | - python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')" - PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir - if: matrix.python_version == '3.9' - - - name: "Test assemble CLI vectors warning" - run: | - python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')" - python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113 - if: matrix.python_version == '3.9' +# - name: "Test assemble CLI" +# run: | +# python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')" +# PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir +# if: matrix.python_version == '3.9' +# +# - name: "Test assemble CLI vectors warning" +# run: | +# python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')" +# python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113 +# if: matrix.python_version == '3.9' - name: "Install test requirements" run: | @@ -165,6 +165,7 @@ jobs: - name: "Run CPU tests" run: | python -m pytest --pyargs spacy -W error + if: "!(startsWith(matrix.os, 'macos') && matrix.python_version == '3.11')" - name: "Run CPU tests with thinc-apple-ops" run: | diff --git a/README.md b/README.md index 36a015caf..59d3ee9ee 100644 --- a/README.md +++ b/README.md @@ -35,19 +35,20 @@ open-source software, released under the [MIT license](https://github.com/explos ## πŸ“– Documentation -| Documentation | | -| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| ⭐️ **[spaCy 101]** | New to spaCy? Here's everything you need to know! | -| πŸ“š **[Usage Guides]** | How to use spaCy and its features. | -| πŸš€ **[New in v3.0]** | New features, backwards incompatibilities and migration guide. | -| πŸͺ **[Project Templates]** | End-to-end workflows you can clone, modify and run. | -| πŸŽ› **[API Reference]** | The detailed reference for spaCy's API. | -| πŸ“¦ **[Models]** | Download trained pipelines for spaCy. | -| 🌌 **[Universe]** | Plugins, extensions, demos and books from the spaCy ecosystem. | -| πŸ‘©β€πŸ« **[Online Course]** | Learn spaCy in this free and interactive online course. | -| πŸ“Ί **[Videos]** | Our YouTube channel with video tutorials, talks and more. | -| πŸ›  **[Changelog]** | Changes and version history. | -| πŸ’ **[Contribute]** | How to contribute to the spaCy project and code base. | +| Documentation | | +| ----------------------------- | ---------------------------------------------------------------------- | +| ⭐️ **[spaCy 101]** | New to spaCy? Here's everything you need to know! | +| πŸ“š **[Usage Guides]** | How to use spaCy and its features. | +| πŸš€ **[New in v3.0]** | New features, backwards incompatibilities and migration guide. | +| πŸͺ **[Project Templates]** | End-to-end workflows you can clone, modify and run. | +| πŸŽ› **[API Reference]** | The detailed reference for spaCy's API. | +| πŸ“¦ **[Models]** | Download trained pipelines for spaCy. | +| 🌌 **[Universe]** | Plugins, extensions, demos and books from the spaCy ecosystem. | +| βš™οΈ **[spaCy VS Code Extension]** | Additional tooling and features for working with spaCy's config files. | +| πŸ‘©β€πŸ« **[Online Course]** | Learn spaCy in this free and interactive online course. | +| πŸ“Ί **[Videos]** | Our YouTube channel with video tutorials, talks and more. | +| πŸ›  **[Changelog]** | Changes and version history. | +| πŸ’ **[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)** | @@ -57,13 +58,13 @@ open-source software, released under the [MIT license](https://github.com/explos [api reference]: https://spacy.io/api/ [models]: https://spacy.io/models [universe]: https://spacy.io/universe +[spaCy VS Code Extension]: https://github.com/explosion/spacy-vscode [videos]: https://www.youtube.com/c/ExplosionAI [online course]: https://course.spacy.io [project templates]: https://github.com/explosion/projects [changelog]: https://spacy.io/usage#changelog [contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md - ## πŸ’¬ Where to ask questions The spaCy project is maintained by the [spaCy team](https://explosion.ai/about). diff --git a/requirements.txt b/requirements.txt index 63e03d558..b979929c5 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,7 +9,7 @@ murmurhash>=0.28.0,<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 +typer>=0.3.0,<0.10.0 pathy>=0.10.0 smart-open>=5.2.1,<7.0.0 # Third party dependencies diff --git a/setup.cfg b/setup.cfg index eea557337..45734888f 100644 --- a/setup.cfg +++ b/setup.cfg @@ -52,7 +52,7 @@ install_requires = srsly>=2.4.3,<3.0.0 catalogue>=2.0.6,<2.1.0 # Third-party dependencies - typer>=0.3.0,<0.8.0 + typer>=0.3.0,<0.10.0 pathy>=0.10.0 smart-open>=5.2.1,<7.0.0 tqdm>=4.38.0,<5.0.0 diff --git a/spacy/about.py b/spacy/about.py index 640e9e93b..c6b09039e 100644 --- a/spacy/about.py +++ b/spacy/about.py @@ -1,6 +1,6 @@ # fmt: off __title__ = "spacy" -__version__ = "3.5.0" +__version__ = "3.6.0.dev0" __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/download.py b/spacy/cli/download.py index 0c9a32b93..df4bca53d 100644 --- a/spacy/cli/download.py +++ b/spacy/cli/download.py @@ -81,11 +81,8 @@ def download( def get_model_filename(model_name: str, version: str, sdist: bool = False) -> str: dl_tpl = "{m}-{v}/{m}-{v}{s}" - egg_tpl = "#egg={m}=={v}" suffix = SDIST_SUFFIX if sdist else WHEEL_SUFFIX filename = dl_tpl.format(m=model_name, v=version, s=suffix) - if sdist: - filename += egg_tpl.format(m=model_name, v=version) return filename diff --git a/spacy/cli/evaluate.py b/spacy/cli/evaluate.py index 8f3d6b859..9fcdd18be 100644 --- a/spacy/cli/evaluate.py +++ b/spacy/cli/evaluate.py @@ -27,6 +27,7 @@ def evaluate_cli( gold_preproc: bool = Opt(False, "--gold-preproc", "-G", help="Use gold preprocessing"), displacy_path: Optional[Path] = Opt(None, "--displacy-path", "-dp", help="Directory to output rendered parses as HTML", exists=True, file_okay=False), displacy_limit: int = Opt(25, "--displacy-limit", "-dl", help="Limit of parses to render as HTML"), + per_component: bool = Opt(False, "--per-component", "-P", help="Return scores per component, only applicable when an output JSON file is specified."), # fmt: on ): """ @@ -50,6 +51,7 @@ def evaluate_cli( gold_preproc=gold_preproc, displacy_path=displacy_path, displacy_limit=displacy_limit, + per_component=per_component, silent=False, ) @@ -64,6 +66,7 @@ def evaluate( displacy_limit: int = 25, silent: bool = True, spans_key: str = "sc", + per_component: bool = False, ) -> Dict[str, Any]: msg = Printer(no_print=silent, pretty=not silent) fix_random_seed() @@ -78,50 +81,61 @@ def evaluate( corpus = Corpus(data_path, gold_preproc=gold_preproc) nlp = util.load_model(model) dev_dataset = list(corpus(nlp)) - scores = nlp.evaluate(dev_dataset) - metrics = { - "TOK": "token_acc", - "TAG": "tag_acc", - "POS": "pos_acc", - "MORPH": "morph_acc", - "LEMMA": "lemma_acc", - "UAS": "dep_uas", - "LAS": "dep_las", - "NER P": "ents_p", - "NER R": "ents_r", - "NER F": "ents_f", - "TEXTCAT": "cats_score", - "SENT P": "sents_p", - "SENT R": "sents_r", - "SENT F": "sents_f", - "SPAN P": f"spans_{spans_key}_p", - "SPAN R": f"spans_{spans_key}_r", - "SPAN F": f"spans_{spans_key}_f", - "SPEED": "speed", - } - results = {} - data = {} - for metric, key in metrics.items(): - if key in scores: - if key == "cats_score": - metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")" - if isinstance(scores[key], (int, float)): - if key == "speed": - results[metric] = f"{scores[key]:.0f}" + scores = nlp.evaluate(dev_dataset, per_component=per_component) + if per_component: + data = scores + if output is None: + msg.warn( + "The per-component option is enabled but there is no output JSON file provided to save the scores to." + ) + else: + msg.info("Per-component scores will be saved to output JSON file.") + else: + metrics = { + "TOK": "token_acc", + "TAG": "tag_acc", + "POS": "pos_acc", + "MORPH": "morph_acc", + "LEMMA": "lemma_acc", + "UAS": "dep_uas", + "LAS": "dep_las", + "NER P": "ents_p", + "NER R": "ents_r", + "NER F": "ents_f", + "TEXTCAT": "cats_score", + "SENT P": "sents_p", + "SENT R": "sents_r", + "SENT F": "sents_f", + "SPAN P": f"spans_{spans_key}_p", + "SPAN R": f"spans_{spans_key}_r", + "SPAN F": f"spans_{spans_key}_f", + "SPEED": "speed", + } + results = {} + data = {} + for metric, key in metrics.items(): + if key in scores: + if key == "cats_score": + metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")" + if isinstance(scores[key], (int, float)): + if key == "speed": + results[metric] = f"{scores[key]:.0f}" + else: + results[metric] = f"{scores[key]*100:.2f}" else: - results[metric] = f"{scores[key]*100:.2f}" - else: - results[metric] = "-" - data[re.sub(r"[\s/]", "_", key.lower())] = scores[key] + results[metric] = "-" + data[re.sub(r"[\s/]", "_", key.lower())] = scores[key] - msg.table(results, title="Results") - data = handle_scores_per_type(scores, data, spans_key=spans_key, silent=silent) + msg.table(results, title="Results") + data = handle_scores_per_type(scores, data, spans_key=spans_key, silent=silent) if displacy_path: factory_names = [nlp.get_pipe_meta(pipe).factory for pipe in nlp.pipe_names] docs = list(nlp.pipe(ex.reference.text for ex in dev_dataset[:displacy_limit])) render_deps = "parser" in factory_names render_ents = "ner" in factory_names + render_spans = "spancat" in factory_names + render_parses( docs, displacy_path, @@ -129,6 +143,7 @@ def evaluate( limit=displacy_limit, deps=render_deps, ents=render_ents, + spans=render_spans, ) msg.good(f"Generated {displacy_limit} parses as HTML", displacy_path) @@ -182,6 +197,7 @@ def render_parses( limit: int = 250, deps: bool = True, ents: bool = True, + spans: bool = True, ): docs[0].user_data["title"] = model_name if ents: @@ -195,6 +211,11 @@ def render_parses( with (output_path / "parses.html").open("w", encoding="utf8") as file_: file_.write(html) + if spans: + html = displacy.render(docs[:limit], style="span", page=True) + with (output_path / "spans.html").open("w", encoding="utf8") as file_: + file_.write(html) + def print_prf_per_type( msg: Printer, scores: Dict[str, Dict[str, float]], name: str, type: str diff --git a/spacy/errors.py b/spacy/errors.py index f90ad9c39..928c3be90 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -970,9 +970,12 @@ class Errors(metaclass=ErrorsWithCodes): E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port=port)` " "or use `auto_select_port=True` to pick an available port automatically.") E1051 = ("'allow_overlap' can only be False when max_positive is 1, but found 'max_positive': {max_positive}.") - E1052 = ("Both 'min_length' and 'max_length' should be larger than 0, but found" + E1052 = ("Unable to copy spans: the character offsets for the span at " + "index {i} in the span group do not align with the tokenization " + "in the target doc.") + E1053 = ("Both 'min_length' and 'max_length' should be larger than 0, but found" " 'min_length': {min_length}, 'max_length': {max_length}") - E1053 = ("The text, including whitespace, must match between reference and " + E1054 = ("The text, including whitespace, must match between reference and " "predicted docs when training {component}.") diff --git a/spacy/lang/ms/__init__.py b/spacy/lang/ms/__init__.py new file mode 100644 index 000000000..31a58a7e6 --- /dev/null +++ b/spacy/lang/ms/__init__.py @@ -0,0 +1,24 @@ +from .stop_words import STOP_WORDS +from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES, TOKENIZER_INFIXES +from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS +from .lex_attrs import LEX_ATTRS +from .syntax_iterators import SYNTAX_ITERATORS +from ...language import Language, BaseDefaults + + +class MalayDefaults(BaseDefaults): + tokenizer_exceptions = TOKENIZER_EXCEPTIONS + prefixes = TOKENIZER_PREFIXES + suffixes = TOKENIZER_SUFFIXES + infixes = TOKENIZER_INFIXES + syntax_iterators = SYNTAX_ITERATORS + lex_attr_getters = LEX_ATTRS + stop_words = STOP_WORDS + + +class Malay(Language): + lang = "ms" + Defaults = MalayDefaults + + +__all__ = ["Malay"] diff --git a/spacy/lang/ms/_tokenizer_exceptions_list.py b/spacy/lang/ms/_tokenizer_exceptions_list.py new file mode 100644 index 000000000..fba1dd70f --- /dev/null +++ b/spacy/lang/ms/_tokenizer_exceptions_list.py @@ -0,0 +1,1943 @@ +# from https://prpm.dbp.gov.my/cari1?keyword= +# dbp https://en.wikipedia.org/wiki/Dewan_Bahasa_dan_Pustaka +MS_BASE_EXCEPTIONS = set( + """ +aba-aba +abah-abah +abar-abar +abrit-abritan +abu-abu +abuk-abuk +abun-abun +acak-acak +acak-acakan +acang-acang +aci-aci +aci-acian +aci-acinya +adang-adang +adap-adapan +adik-beradik +aduk-adukan +agak-agak +agar-agar +agut-agut +air-cooled +ajar-ajar +aji-aji +akal-akal +akhir-akhir +aki-aki +alah-mengalahi +alan-alan +alang-alang +alang-alangan +alap-alap +ali-ali +alih-alih +aling-aling +aling-alingan +alip-alipan +alon-alon +alu-alu +alu-aluan +alun-alun +alur-alur +ambah-ambah +ambai-ambai +ambil-mengambil +ambring-ambringan +ambu-ambu +ambung-ambung +amin-amin +ampai-ampai +amung-amung +anai-anai +anak-anak +anak-anakan +anak-beranak +ancak-ancak +ancang-ancang +andang-andang +angan-angan +anggar-anggar +angin-angin +angin-anginan +angkul-angkul +angkup-angkup +angkut-angkut +ani-ani +aning-aning +anjang-anjang +anjing-anjing +anjung-anjung +anjung-anjungan +antar-antar +ante-mortem +anting-anting +antung-antung +anyam-menganyam +apa-apa +api-api +apit-apit +aprit-apritan +arah-arah +arak-arakan +aram-aram +ari-ari +aru-aru +asa-asaan +asam-asaman +asuh-asuh +atas-mengatasi +ati-ati +audio-visual +avant-garde +awang-awang +awang-gemawang +ayak-ayak +ayam-ayam +ayam-ayaman +ayang-ayang +ayeng-ayengan +ayun-temayun +back-up +bahu-membahu +baik-baik +bajang-bajang +baji-baji +balai-balai +balam-balam +balas-membalas +baling-baling +balut-balut +bangun-bangun +bantal-bantal +barat-barat +barau-barau +bari-bari +barung-barung +basa-basi +bata-bata +batir-batir +bau-bauan +bayang-bayang +bedil-bedal +begana-begini +bekal-bekalan +belat-belit +belu-belai +benggal-benggil +bengkal-bengkil +bengkang-bengkok +bengkang-bengkong +berabad-abad +berabun-rabun +berada-ada +beragah-agah +beragak-agak +beragam-ragam +beraja-raja +berakit-rakit +beraku-akuan +beralun-alun +beramah-ramahan +beramah-tamah +beramai-ramai +berambai-ambai +berambal-ambalan +beramuk-amukan +berandai-andai +berandai-randai +berang-berang +berangan-angan +beranggap-anggapan +berangguk-angguk +berangin-angin +berangka-angka +berangka-angkaan +berangkai-rangkai +beranja-anja +berantai-rantai +berapi-api +berapung-apung +berarak-arakan +beras-beras +berasing-asingan +beratus-ratus +berawas-awas +berayal-ayalan +berayun-ayun +berbagai-bagai +berbahas-bahasan +berbalas-balasan +berbalik-balik +berbanjar-banjar +berbantah-bantah +berbanyak-banyak +berbarik-barik +berbasah-basah +berbatu-batu +berbayang-bayang +berbecak-becak +berbedil-bedilan +berbeka-beka +berbelakang-belakangan +berbelang-belang +berbeli-belian +berbelit-belit +berbelok-belok +berbenar-benar +berbencah-bencah +berbesar-besar +berbidai-bidai +berbiku-biku +berbilik-bilik +berbinar-binar +berbincang-bincang +berbingkah-bingkah +berbintang-bintang +berbintik-bintik +berbintil-bintil +berbisik-bisik +berbolak-balik +berbolong-bolong +berbondong-bondong +berbongkah-bongkah +berbuai-buai +berbual-bual +berbukit-bukit +berbulan-bulan +berbunga-bunga +berbuntut-buntut +berbunuh-bunuhan +berburu-buru +berburuk-buruk +berbutir-butir +bercabang-cabang +bercaci-cacian +bercakap-cakap +bercakar-cakaran +bercantik-cantik +bercari-cari +bercari-carian +bercarik-carik +bercepat-cepat +bercerai-berai +bercerai-cerai +bercetai-cetai +bercikun-cikun +bercinta-cintaan +bercita-cita +berciut-ciut +berconteng-conteng +bercoreng-coreng +bercoreng-moreng +bercuit-cuit +bercumbu-cumbu +bercumbu-cumbuan +bercura-bura +bercura-cura +berdada-dadaan +berdahulu-dahuluan +berdalam-dalam +berdebar-debar +berdecap-decap +berdedai-dedai +berdegap-degap +berdegar-degar +berdeham-deham +berdekah-dekah +berdekat-dekat +berdelat-delat +berdembun-dembun +berdempang-dempang +berdendam-dendaman +berdengkang-dengkang +berdentang-dentang +berdentum-dentum +berdentung-dentung +berdepak-depak +berdepan-depan +berderai-derai +berderak-derak +berderau-derau +berdering-dering +berderung-derung +berdesak-desakan +berdesing-desing +berdesus-desus +berdikit-dikit +berdingkit-dingkit +berdua-dua +berduri-duri +berduru-duru +berduyun-duyun +berebut-rebut +berebut-rebutan +beregang-regang +berek-berek +berembut-rembut +berempat-empat +berenak-enak +berenteng-renteng +beresah-resah +berfoya-foya +bergagah-gagahan +bergagap-gagap +bergalur-galur +berganda-ganda +berganti-ganti +bergarah-garah +bergaruk-garuk +bergegas-gegas +bergelang-gelang +bergelap-gelap +bergelas-gelasan +bergeleng-geleng +bergemal-gemal +bergembut-gembut +bergerek-gerek +bergesa-gesa +bergilir-gilir +bergolek-golek +bergores-gores +bergotong-royong +bergugus-gugus +bergulung-gulung +bergulut-gulut +bergumpal-gumpal +bergunung-gunung +berhadap-hadapan +berhamun-hamun +berhandai-handai +berhanyut-hanyut +berhari-hari +berhati-hati +berhilau-hilau +berhujan-hujan +beria-ia +beria-ria +beriak-riak +beribu-ribu +berigi-rigi +bering-bering +beringat-ingat +beringgit-ringgit +berintik-rintik +beriring-iring +beriring-iringan +berjabir-jabir +berjaga-jaga +berjagung-jagung +berjalan-jalan +berjalar-jalar +berjalin-jalin +berjalur-jalur +berjam-jam +berjauh-jauhan +berjejal-jejal +berjela-jela +berjenis-jenis +berjenjang-jenjang +berjilid-jilid +berjinak-jinak +berjingkat-jingkat +berjingkrak-jingkrak +berjongkok-jongkok +berjubel-jubel +berjujut-jujutan +berjulai-julai +berjumbai-jumbai +berjurai-jurai +berjurus-jurus +berjuta-juta +berkaca-kaca +berkait-kaitan +berkala-kala +berkali-kali +berkanjar-kanjar +berkaok-kaok +berkarung-karung +berkasih-kasihan +berkata-kata +berkatak-katak +berkecai-kecai +berkecek-kecek +berkecil-kecil +berkecil-kecilan +berkedip-kedip +berkejang-kejang +berkejap-kejap +berkejar-kejaran +berkelar-kelar +berkelip-kelip +berkelit-kelit +berkelok-kelok +berkelompok-kelompok +berkelun-kelun +berkembur-kembur +berkempul-kempul +berkena-kenaan +berkenal-kenalan +berkendur-kendur +berkeok-keok +berkepak-kepak +berkepal-kepal +berkeping-keping +berkepul-kepul +berkeras-kerasan +berkeritik-keritik +berkeruit-keruit +berkerut-kerut +berketak-ketak +berketak-ketik +berketi-keti +berketil-ketil +berketuk-ketak +berketul-ketul +berkial-kial +berkian-kian +berkias-kiasan +berkibar-kibar +berkilah-kilah +berkilat-kilat +berkilau-kilauan +berkilo-kilo +berkinja-kinja +berkipas-kipas +berkira-kira +berkirim-kiriman +berkobar-kobar +berkobok-kobok +berkocak-kocak +berkodi-kodi +berkolek-kolek +berkopah-kopah +berkotak-kotak +berkuat-kuatan +berkunang-kunang +berkurun-kurun +berkusau-kusau +berkusu-kusu +berkusut-kusut +berkuting-kuting +berkutu-kutuan +berlabun-labun +berlain-lainan +berlalai-lalai +berlama-lama +berlambai-lambai +berlambak-lambak +berlampang-lampang +berlapang-lapang +berlapis-lapis +berlapuk-lapuk +berlarah-larah +berlarat-larat +berlari-larian +berlarik-larik +berlarut-larut +berlawak-lawak +berlayap-layapan +berlebih-lebih +berlebih-lebihan +berlekas-lekas +berlena-lena +berlengah-lengah +berlenggek-lenggek +berlenggok-lenggok +berleret-leret +berliang-liuk +berliku-liku +berlimpah-limpah +berlimpap-limpap +berlimpit-limpit +berlinang-linang +berlindak-lindak +berlipat-lipat +berlompok-lompok +berloncat-loncatan +berlopak-lopak +berlubang-lubang +bermaaf-maafan +bermacam-macam +bermain-main +bermalas-malas +bermanik-manik +bermanis-manis +bermanja-manja +bermasak-masak +bermati-mati +bermegah-megah +bermemek-memek +bermesra-mesraan +bermewah-mewah +berminggu-minggu +berminta-minta +bermuda-muda +bermudah-mudah +bermuka-muka +bermula-mula +bermulut-mulut +bernafsi-nafsi +bernaka-naka +berniat-niat +berogak-ogak +beroleng-oleng +berolok-olok +beromong-omong +beronggok-onggok +berorang-orang +beroyal-royal +berpada-pada +berpahit-pahit +berpair-pair +berpal-pal +berpalu-palu +berpalu-paluan +berpalun-palun +berpandai-pandai +berpandang-pandangan +berpangkat-pangkat +berpanjang-panjang +berpasang-pasang +berpasang-pasangan +berpayah-payah +berpeluh-peluh +berpeluk-pelukan +berpenat-penat +berpencar-pencar +berpendar-pendar +berpenggal-penggal +berperai-perai +berpesai-pesai +berpesta-pesta +berpesuk-pesuk +berpetak-petak +berpeti-peti +berpihak-pihak +berpijar-pijar +berpikul-pikul +berpilih-pilih +berpilin-pilin +berpindah-pindah +berpintal-pintal +berpirau-pirau +berpisah-pisah +berpolah-polah +berpongah-pongah +berpontang-panting +berporah-porah +berpotong-potong +berpuak-puak +berpual-pual +berpugak-pugak +berpuluh-puluh +berpulun-pulun +berpuntal-puntal +berpura-pura +berpusar-pusar +berpusing-pusing +berpusu-pusu +berputar-putar +bersaf-saf +bersahut-sahutan +bersakit-sakit +bersalah-salahan +bersalam-salaman +bersalin-salin +bersama-sama +bersambut-sambutan +bersampan-sampan +bersantai-santai +bersapa-sapaan +bersarang-sarang +bersedan-sedan +bersedia-sedia +bersedu-sedu +bersekat-sekat +berselang-selang +berselang-seli +bersembur-semburan +bersempit-sempit +bersenang-senang +bersenang-senangkan +bersenda-senda +bersendi-sendi +bersepah-sepah +bersepi-sepi +berserak-serak +berseri-seri +bersesak-sesak +bersetai-setai +bersia-sia +bersiap-siap +bersiar-siar +bersilir-silir +bersimbur-simburan +bersinau-sinau +bersorak-sorai +bersuap-suapan +bersudah-sudah +bersuka-suka +bersuka-sukaan +bersuku-suku +bersumpah-sumpahan +bersungguh-sungguh +bersungut-sungut +bersunyi-sunyi +bersusah-susah +bersusuk-susuk +bersusuk-susukan +bersutan-sutan +bertabur-tabur +bertahu-tahu +bertahun-tahun +bertajuk-tajuk +bertakik-takik +bertala-tala +bertali-tali +bertalu-talu +bertambah-tambah +bertanda-tandaan +bertangis-tangisan +bertangkil-tangkil +bertanya-tanya +bertarik-tarikan +bertatai-tatai +bertatih-tatih +bertawan-tawan +bertawar-tawaran +bertebu-tebu +bertebu-tebukan +berteguh-teguh +berteguh-teguhan +berteka-teki +bertelau-telau +bertele-tele +bertempat-tempat +bertempuh-tempuh +bertenang-tenang +bertenggang-tenggangan +bertentu-tentu +bertepek-tepek +berterang-terang +berterang-terangan +bertikam-tikaman +bertimbal-timbalan +bertimbun-timbun +bertimpa-timpa +bertimpas-timpas +bertingkah-tingkah +bertingkat-tingkat +bertinjau-tinjauan +bertiras-tiras +bertitar-titar +bertoboh-toboh +bertolak-tolak +bertolak-tolakan +bertolong-tolongan +bertonjol-tonjol +bertua-tua +bertua-tuaan +bertual-tual +bertubi-tubi +bertukar-tukar +bertukar-tukaran +bertukas-tukas +bertumpak-tumpak +bertunda-tunda +bertunjuk-tunjukan +bertura-tura +berturut-turut +bertutur-tutur +beruas-ruas +berubah-ubah +berulang-alik +berulang-ulang +berumbai-rumbai +berundung-undung +berunggas-runggas +berungkur-ungkuran +beruntai-untai +beruntun-runtun +berunyai-unyai +berupa-rupa +berura-ura +beruris-uris +berurut-urutan +berwarna-warna +berwarna-warni +berwindu-windu +berwiru-wiru +beryang-yang +besar-besaran +betak-betak +beti-beti +betul-betul +biang-biang +biar-biar +biji-bijian +bila-bila +bilang-bilang +bincang-bincut +bini-binian +biri-biri +biru-biru +bisik-bisik +biti-biti +bolak-balik +bolang-baling +bongkar-bangkir +buah-buahan +buat-buatan +buaya-buaya +bubun-bubun +bugi-bugi +built-in +bukan-bukan +bulan-bulan +bulan-bulanan +bulang-bulang +bulat-bulat +buli-buli +bulu-bulu +buluh-buluh +bulus-bulus +bunga-bungaan +bunuh-membunuh +bunyi-bunyian +buru-buru +burung-burungan +bye-bye +cabik-cabik +caing-caing +calar-balar +cara-cara +carut-marut +cawi-cawi +cebar-cebur +celam-celum +celangak-celinguk +celas-celus +celedang-celedok +celengkak-celengkok +cemas-cemas +centang-perenang +cepat-cepat +cerai-berai +ceruk-menceruk +ceruk-meruk +check-up +chit-chat +cirit-birit +cita-cita +close-up +closed-circuit +cobak-cabik +cobar-cabir +cola-cala +compang-camping +congak-cangit +congkah-cangkih +congkah-mangkih +copak-capik +corak-carik +corat-coret +coreng-moreng +cuang-caing +cubung-cubung +culik-culik +cuma-cuma +cumi-cumi +cungap-cangip +cupu-cupu +dahulu-mendahului +dali-dali +dapur-dapur +dari-dari +daru-daru +datang-datang +datang-mendatangi +daun-daunan +dawai-dawai +dayang-dayang +degap-degap +dekak-dekak +dekat-dekat +dengar-dengaran +desas-desus +diam-diam +do-it-yourself +dokok-dokok +dolak-dalik +dorong-mendorong +drive-in +dua-dua +dua-duanya +duduk-duduk +dulang-dulang +ecek-ecek +embuh-embuhan +empek-empek +empok-empok +encal-encal +endap-endap +endut-endutan +engah-engah +enggan-enggan +engkah-engkah +entah-berentah +erang-erot +erong-erong +fast-food +fifty-fifty +flip-flop +follow-up +foya-foya +gaba-gaba +gabai-gabai +gada-gada +gading-gading +gado-gado +gajah-gajahan +gala-gala +gali-galian +galing-galing +galu-galu +gamit-gamitan +gampang-gampangan +ganal-ganal +ganda-berganda +gapah-gopoh +gara-gara +garah-garah +gatal-gatal +gawar-gawar +gaya-gayanya +gedebak-gedebuk +gelang-gelang +gelembung-gelembungan +geli-geli +geliang-geliut +geliat-geliut +gempul-gempul +gendang-gendang +genjang-genjot +gerabak-gerubuk +gerak-gerik +gerbas-gerbus +gerit-gerit +geruh-gerah +getak-getuk +geti-geti +gila-gila +gila-gilaan +gilang-gemilang +gilap-gemilap +gili-gili +giling-giling +ginang-ginang +girik-girik +giring-giring +go-kart +golak-galik +gonta-ganti +gotong-royong +gual-gail +gudu-gudu +gula-gula +gulang-gulang +guna-guna +guntang-guntang +gunung-ganang +gunung-gemunung +gunung-gunungan +habis-habis +habis-habisan +halai-balai +half-time +hampir-hampir +harap-harapan +harum-haruman +hati-hati +heavy-duty +hebat-hebatan +hidup-hidup +hiru-biru +hiruk-pikuk +hubaya-hubaya +hula-hula +huru-hara +ibar-ibar +icak-icak +igau-igauan +ikut-ikut +ikut-ikutan +ilam-ilam +imbang-imbangan +inang-inang +inca-binca +incang-incut +ingat-ingat +ingat-ingatan +ingau-ingauan +inggang-inggung +injak-injak +iras-iras +iring-iringan +iseng-iseng +jadi-jadian +jala-jala +jamah-jamahan +jambu-jambu +jangan-jangan +jarang-jarang +jari-jari +jaring-jaring +jarum-jarum +jauh-jauh +jawi-jawi +jebat-jebatan +jelur-jelir +jendal-jendul +jenggar-jenggur +jentik-jentik +jerah-jerih +jolong-jolong +jongkar-jangkir +juak-juak +juang-juang +julung-julung +jurai-jurai +kabu-kabu +kacang-kacang +kacang-kacangan +kacau-balau +kadang-kadang +kail-kail +kait-kait +kakek-kakek +kalau-kalau +kaleng-kalengan +kalut-malut +kambing-kambing +kanak-kanak +kapa-kapa +kapan-kapan +kapu-kapu +karang-karangan +karang-mengarang +kareseh-peseh +karut-marut +katang-katang +kawa-kawa +kayu-kayuan +keabu-abuan +keasyik-asyikan +kebarat-baratan +kebasah-basahan +kebat-kebit +kebata-bataan +kebelanda-belandaan +kebiru-biruan +kebudak-budakan +kecil-kecilan +kecil-mengecil +kecuh-kecah +kedek-kedek +kegadis-gadisan +kegelap-gelapan +kegila-gilaan +kegirang-girangan +kehijau-hijauan +kehitam-hitaman +kejaga-jagaan +kejingga-jinggaan +kekabur-kaburan +kekanak-kanakan +kekoboi-koboian +kekuning-kuningan +kelak-kelik +kelak-keluk +kelaki-lakian +kelang-kelok +kelap-kelip +kelek-kelek +kelek-kelekan +kelik-kelik +kelip-kelip +kelusuh-kelasah +kelut-melut +kemak-kemik +kemalu-maluan +kemanja-manjaan +kemarah-marahan +kemasam-masaman +kemati-matian +kemerah-merahan +kempang-kempis +kempas-kempis +kemuda-mudaan +kena-mengena +kenal-mengenal +kenang-kenangan +kencang-kencung +kendang-kendang +kendang-kendangan +kentung-kentung +kenyat-kenyit +kepandir-pandiran +kepang-kepot +keperak-perakan +kepilu-piluan +kepura-puraan +keputih-putihan +kerah-kerahan +kerancak-rancakan +kerang-kerangan +kerang-keroh +kerang-kerung +kerap-kerap +keras-mengerasi +kercap-kercip +kercap-kercup +keriang-keriut +kernyat-kernyut +kerong-kerong +keropas-kerapis +kertak-kertuk +keruntang-pungkang +kesap-kesip +kesenak-senakan +kesewenang-wenangan +kesia-siaan +kesik-kesik +kesipu-sipuan +kesu-kesi +kesuh-kesih +kesuk-kesik +ketergesa-gesaan +keti-keti +ketidur-tiduran +ketiga-tiganya +ketua-tuaan +ketuan-tuanan +keungu-unguan +kia-kia +kiak-kiak +kial-kial +kiang-kiut +kibang-kibut +kicang-kecoh +kicang-kicu +kida-kida +kilau-mengilau +kili-kili +kira-kira +kira-kiraan +kisi-kisi +kocah-kacih +kodok-kodok +kolang-kaling +koleh-koleh +kolong-kolong +koma-koma +komat-kamit +kontal-kantil +kontang-kanting +kosak-kasik +kotak-katik +kotak-kotak +kuat-kuat +kucar-kacir +kucing-kucing +kucing-kucingan +kuda-kuda +kuda-kudaan +kudap-kudap +kulah-kulah +kulak-kulak +kulik-kulik +kulum-kulum +kumat-kamit +kunang-kunang +kupat-kapit +kupu-kupu +kura-kura +kurang-kurang +kusat-mesat +kutat-kutet +kuti-kuti +labi-labi +labu-labu +lagi-lagi +laguh-lagah +laki-laki +lalu-lalang +lama-kelamaan +lama-lama +lamat-lamat +lambat-lambat +lancar-lancar +langak-longok +langit-langit +lanja-lanjaan +lapat-lapat +large-scale +lari-lari +lauk-pauk +lawah-lawah +lawak-lawak +lawi-lawi +layang-layang +layu-layuan +lebih-lebih +legak-legok +lekak-lekuk +lekap-lekup +lekas-lekas +lekuh-lekih +lekup-lekap +lenggak-lenggok +lenggok-lenggok +lengket-lengket +lentam-lentum +lentang-lentok +lentang-lentung +lepa-lepa +lerang-lerang +lereng-lereng +letah-letai +letup-letup +liang-liuk +lidah-lidah +line-up +liuk-liuk +liung-liung +lobi-lobi +lock-up +lopak-lapik +lopak-lopak +lumba-lumba +lumi-lumi +luntang-lantung +lupa-lupa +lupa-lupaan +main-mainan +makan-makanan +make-up +malai-malai +malam-malam +malar-malar +mali-mali +malu-malu +mana-mana +manik-manik +manis-manisan +mark-up +masing-masing +mata-mata +mati-matian +maya-maya +megap-megap +megrek-megrek +melak-melak +melambai-lambai +melambai-lambaikan +melambat-lambatkan +melaun-laun +melawak-lawak +melayap-layap +melayap-layapkan +melebih-lebihi +melebih-lebihkan +melejang-lejangkan +melengah-lengah +melihat-lihat +melimpah-limpah +melincah-lincah +meloncat-loncat +melonco-lonco +melonjak-lonjak +memacak-macak +memaki-maki +memaksa-maksa +memandai-mandai +memanggil-manggil +memanis-manis +memanjut-manjut +memasak-masak +memata-matai +mematah-matah +mematut-matut +memayah-mayahkan +membagi-bagikan +membalik-balik +membangkit-bangkit +membayang-bayangi +membayang-bayangkan +membelai-belai +membenar-benar +membenar-benari +memberai-beraikan +membesar-besarkan +membolak-balikkan +membuang-buang +membuat-buat +membunga-bungai +memburu-buru +memburu-burukan +memburuk-burukkan +memencak-mencak +memencar-mencar +memetak-metak +memetang-metangkan +memetir-metir +memikir-mikirkan +memilih-milih +meminang-minang +meminta-minta +memisah-misahkan +memontang-mantingkan +memperamat-amat +memperamat-amatkan +memperbagai-bagaikan +memperganda-gandakan +memperganduh-ganduhkan +mempermacam-macamkan +memperolok-olokkan +mempersama-samakan +mempertubi-tubi +mempertubi-tubikan +memperturut-turutkan +memuja-muja +memukang-mukang +memulun-mulun +memundi-mundi +memundi-mundikan +memuyu-muyu +menagak-nagak +menakut-nakuti +menanjur-nanjur +menanti-nanti +menari-nari +mencabik-cabik +mencabik-cabikkan +mencaing-caing +mencak-mencak +mencakup-cakup +mencapak-capak +mencari-cari +mencarik-carik +mencarut-carut +mencengis-cengis +mencepak-cepak +mencepuk-cepuk +mencerai-beraikan +mencetai-cetai +menciap-ciap +menciar-ciar +mencita-citakan +menciut-ciut +mencoang-coang +mencubit-cubit +mencuri-curi +mendecap-decap +mendengking-dengking +menderak-derakkan +menderau-derau +menderu-deru +mendesas-desuskan +mendesus-desus +mendewa-dewakan +mendudu-dudu +menebu-nebu +menegur-neguri +mengabung-ngabung +mengaci-acikan +mengada-ada +mengaduk-aduk +mengagak-agak +mengagak-agihkan +mengagut-agut +mengais-ngais +mengali-ali +mengalur-alur +mengamang-amang +mengamat-amati +mengambai-ambaikan +mengambang-ambang +mengancak-ancak +mengangan-angankan +mengangguk-angguk +mengangin-anginkan +mengangkat-angkat +mengap-mengap +mengapa-apai +mengapi-apikan +mengarah-arahi +mengata-ngatai +mengaum-aumkan +mengejan-ejan +mengelai-ngelai +mengelepik-ngelepik +mengelus-elus +mengembut-embut +mengenap-enapkan +mengenjak-enjak +mengepak-ngepak +mengepak-ngepakkan +menggaba-gabai +menggalur-galur +menggamak-gamak +menggapai-gapai +menggapai-gapaikan +menggelepar-gelepar +menggelepar-geleparkan +menggemak-gemak +menggerecak-gerecak +menggesa-gesakan +menggili-gili +menggorek-gorek +menggosok-gosok +mengguit-guit +menghalai-balaikan +menghinap-hinap +mengiang-ngiang +mengibas-ngibas +mengidam-idamkan +mengilah-ngilahkan +mengilai-ilai +mengilat-ngilatkan +mengilik-ngilik +mengimak-imak +mengiming-iming +menginjak-injak +mengipas-ngipas +mengira-ngira +mengira-ngirakan +mengiras-iras +mengiras-irasi +mengitar-ngitar +mengitik-ngitik +mengogok-ogok +mengolak-alikkan +mengoleng-oleng +mengongkang-ongkang +mengongkok-ongkok +mengonyah-anyih +mengotak-ngatikkan +mengoyak-ngoyakkan +mengoyak-oyak +menguar-nguarkan +menguar-uarkan +menguber-uber +mengubit-ubit +mengubrak-abrik +mengucar-ngacirkan +mengucek-ngucek +menguik-uik +menguis-uis +mengulit-ulit +menguman-uman +mengumbang-ambingkan +mengumpak-umpak +mengungkat-ungkat +mengungkit-ungkit +mengurik-urik +mengutak-ngatikkan +mengutik-ngutik +menimang-nimang +meningkat-ningkat +meniru-niru +meniup-niup +menjadi-jadi +menjengek-jengek +menjengit-jengit +menjilat-jilat +mentah-mentah +mentang-mentang +menunda-nunda +menusuk-nusuk +menyama-nyama +menyambar-nyambar +menyanjung-nyanjung +menyapu-nyapu +menyarat-nyarat +menyendi-nyendi +menyeret-nyeret +menyeru-nyerukan +menyia-nyiakan +menyungguh-nyungguhi +meraba-raba +merangkak-rangkak +merasa-rasai +meraung-raung +meraung-raungkan +merayau-rayau +merayu-rayu +mereka-reka +merelap-relap +meremah-remah +meremeh-temehkan +merempah-rempahi +merengek-rengek +merenik-renik +merenta-renta +merenyai-renyai +merintang-rintang +merintik-rintik +merobek-robek +meronta-ronta +merungus-rungus +merungut-rungut +mewarna-warnikan +meyakin-yakini +miju-miju +minta-minta +moga-moga +morat-marit +muda-mudi +mudah-mudahan +muka-muka +mula-mula +muluk-muluk +naga-naga +nanti-nantian +nasi-nasi +nasib-nasiban +nenek-nenek +nyolong-nyolong +ogah-ogahan +ogak-ogak +olak-alik +olak-olak +olang-aling +olang-alingan +oleh-oleh +olok-olok +olok-olokan +olong-olong +on-screen +onde-onde +one-to-one +oneng-oneng +ongkang-ongkang +ongol-ongol +onyah-anyih +orak-arik +orang-aring +orang-orangan +orok-orok +orong-orong +otak-otak +otak-otakan +padi-padian +pagi-pagi +palas-palas +paling-paling +palu-memalu +panas-panas +pandang-memandang +panji-panji +para-para +paru-paru +pasang-memasang +pasu-pasu +paya-paya +pecah-pecah +pelan-pelan +pengundang-undang +perang-perangan +perintang-rintang +perlahan-lahan +perlip-perlipan +pertama-tama +perundang-undangan +pesan-pesan +piat-piut +pick-up +pijak-pijak +pijar-pijar +pijat-pijat +pina-pina +pisang-pisang +play-off +pohon-pohonan +pokrol-pokrolan +polang-paling +poma-poma +pontang-panting +porak-parik +porak-peranda +potong-memotong +puji-pujian +pukang-pukang +pukul-memukul +pulang-pergi +pulut-pulut +pundi-pundi +punggung-memunggung +pura-pura +pusar-pusar +push-up +pusing-pusing +putus-putus +rada-rada +radio-frequency +ragu-ragu +rama-rama +rambu-rambu +rango-rango +rasa-rasanya +rata-rata +real-time +rebah-rebah +rebah-rebahan +redam-redam +reka-reka +reka-rekaan +remah-remah +remang-remang +rembah-rembih +remeh-temeh +rempah-rempah +repuh-repuh +riang-riang +ribu-ribu +rigi-rigi +robak-rabik +robat-rabit +role-play +roll-on +rombang-rambing +ruak-ruak +ruku-ruku +rumah-rumah +rumah-rumahan +rumput-rumputan +runding-merunding +runggu-rangga +runner-up +rupa-rupa +rupa-rupanya +saban-saban +sabung-menyabung +saing-menyaing +salah-salah +sama-sama +samar-samar +sambar-menyambar +sambung-bersambung +sambung-menyambung +sambut-menyambut +sampai-sampai +sandar-menyandar +sangat-sangat +sangkut-menyangkut +sapa-menyapa +sapu-sapu +sarit-sarit +satu-satu +satu-satunya +sayup-menyayup +sayup-sayup +sayur-mayur +sayur-sayuran +sci-fi +seakal-akal +seakan-akan +sealak-alak +sebaik-baiknya +sebelah-menyebelah +sebentar-sebentar +seberang-menyeberang +seboleh-bolehnya +sedalam-dalamnya +sedang-menyedang +sedap-sedapan +sedapat-dapatnya +sedikit-dikitnya +sedikit-sedikit +sedikit-sedikitnya +seelok-eloknya +segala-galanya +segan-menyegan +segan-menyegani +segan-segan +sehari-hari +sehari-harian +sejadi-jadinya +sekali-kali +sekali-sekali +sekira-kira +sekonyong-konyong +sekuasa-kuasanya +sekurang-kurangnya +sela-menyela +sela-sela +selama-lamanya +selambat-lambatnya +selang-seli +selang-seling +selar-belar +selat-latnya +selekas-lekasnya +selepas-lepas +self-esteem +self-help +sema-sema +semah-semah +semak-semak +semalam-malaman +semasa-masa +semata-mata +sembunyi-sembunyi +sembunyi-sembunyian +semena-mena +semenda-menyemenda +semengga-mengga +sementang-mentang +semu-semu +semut-semutan +sengal-sengal +sengau-sengauan +seolah-olah +sepala-pala +sepandai-pandai +sepetang-petangan +sepoi-sepoi +sepuas-puasnya +serang-menyerang +seraya-menyeraya +serba-serbi +serbah-serbih +serembah-serembih +sering-sering +serta-menyertai +serta-serta +sesal-menyesali +sesudah-sudah +sesudah-sudahnya +sesuka-suka +setempat-setempat +setengah-setengah +setidak-tidaknya +seupaya-upaya +seupaya-upayanya +sewaktu-waktu +sewenang-wenang +short-term +sia-sia +siang-siang +siapa-siapa +sibar-sibar +sibur-sibur +sida-sida +siku-siku +silah-silah +silang-menyilang +silir-semilir +sinar-seminar +sindir-menyindir +singgah-menyinggah +sorak-sorai +stand-by +stand-up +sudu-sudu +sudung-sudung +suka-suka +sulang-menyulang +sulur-suluran +sumpah-sumpah +sumpit-sumpit +sungguh-sungguh +sungut-sungut +suram-suram +surat-menyurat +suruh-suruhan +tabar-tabar +tabir-mabir +tabrak-tubruk +tabuh-tabuhan +tahu-menahu +tahu-tahu +takang-takik +take-off +takut-takut +takut-takutan +tali-bertali +tali-tali +tampak-tampak +tanam-menanam +tanam-tanaman +tanda-tanda +tangan-menangan +tangan-tangan +tanggung-menanggung +tapa-tapa +tapak-tapak +tari-menari +tari-tarian +tarik-menarik +tatah-tatah +tawak-tawak +tawang-tawang +tawar-menawar +tawar-tawar +tayum-temayum +tebu-tebu +tegak-tegak +teka-teki +temas-temas +tembak-menembak +temut-temut +tenggang-menenggang +teraba-raba +terambang-ambang +terang-terang +terang-terangan +teranggar-anggar +terangguk-angguk +teranggul-anggul +terangin-angin +terangkup-angkup +teranja-anja +terapung-apung +terayan-rayan +terayap-rayap +terbada-bada +terbahak-bahak +terbata-bata +terbatuk-batuk +terbayang-bayang +terbengkil-bengkil +terbirit-birit +terbuai-buai +terbuang-buang +terburu-buru +tercangak-cangak +tercengang-cengang +tercilap-cilap +tercongget-congget +tercungap-cungap +terdangka-dangka +terdengih-dengih +terekeh-ekeh +terembut-embut +terembut-rembut +terengah-engah +teresak-esak +tergagap-gagap +tergagau-gagau +tergaguk-gaguk +tergapai-gapai +tergegap-gegap +tergegas-gegas +tergelung-gelung +tergerenyeng-gerenyeng +tergesa-gesa +tergila-gila +tergontai-gontai +tergudik-gudik +terguling-guling +tergulut-gulut +terharak-harak +terharap-harap +terhengit-hengit +terhinggut-hinggut +terigau-igau +terincut-incut +teringa-inga +teringat-ingat +terinjak-injak +terjembak-jembak +terjerit-jerit +terkadang-kadang +terkakah-kakah +terkakak-kakak +terkanjar-kanjar +terkapah-kapah +terkapai-kapai +terkapung-kapung +terkatah-katah +terkatung-katung +terkecap-kecap +terkedek-kedek +terkedip-kedip +terkejar-kejar +terkekau-kekau +terkekeh-kekeh +terkekek-kekek +terkelinjat-kelinjat +terkelip-kelip +terkempul-kempul +terkemut-kemut +terkencar-kencar +terkepak-kepak +terkesot-kesot +terkesut-kesut +terkial-kial +terkincak-kincak +terkindap-kindap +terkinja-kinja +terkirai-kirai +terkitar-kitar +terkocoh-kocoh +terkokol-kokol +terkosel-kosel +terkoteng-koteng +terkumpal-kumpal +terlara-lara +terlayang-layang +terlebih-lebih +terlincah-lincah +terliuk-liuk +terlolong-lolong +terlongong-longong +termangu-mangu +termanja-manja +termata-mata +termengah-mengah +termimpi-mimpi +ternanti-nanti +terngiang-ngiang +teroleng-oleng +terpandang-pandang +terpecah-pecah +terpekik-pekik +terpereh-pereh +terpikau-pikau +terpinga-pinga +terpingkal-pingkal +terpontang-panting +terpusing-pusing +terputus-putus +tersanga-sanga +tersaruk-saruk +tersedan-sedan +tersedih-sedih +tersedu-sedu +tersendat-sendat +tersendeng-sendeng +tersengal-sengal +tersengguk-sengguk +tersengut-sengut +tersera-sera +terserak-serak +tersetai-setai +tersia-sia +tersipu-sipu +tersoja-soja +tersungkuk-sungkuk +tertagak-tagak +tertahan-tahan +tertatih-tatih +tertegun-tegun +tertekan-tekan +terteleng-teleng +terumbang-ambing +terumbang-umbang +terungkap-ungkap +terus-menerus +terus-terusan +think-tank +tiap-tiap +tiba-tiba +tidak-tidak +tidur-tidur +tie-dye +tiga-tiganya +tikam-menikam +tilik-menilik +timah-timah +timang-timangan +timbang-menimbang +timu-timu +tindih-bertindih +tinjau-meninjau +tip-off +tiru-tiruan +tiup-tiup +tokak-takik +tokok-menokok +tolak-menolak +tolong-menolong +top-level +trade-in +tua-tua +tuan-tuan +tuang-tuang +tuban-tuban +tukang-menukang +tukar-menukar +tulang-tulangan +tuli-tuli +tulis-menulis +tumbuh-tumbuhan +tune-up +tunggang-tunggit +tupai-tupai +turun-temurun +turut-menurut +turut-turutan +two-tone +uar-uar +ubel-ubel +ubun-ubun +ubur-ubur +uci-uci +udap-udapan +ugal-ugalan +uir-uir +ujar-ujar +ukir-mengukir +ula-ula +ulak-ulak +ulang-alik +ulang-aling +ulang-ulang +ulap-ulap +ular-ular +ular-ularan +ulung-ulung +umang-umang +umbang-ambing +umbi-umbian +umbul-umbul +umbut-umbut +uncang-uncit +undak-undakan +undang-undang +unduk-unduk +undung-undung +undur-undur +unggat-unggit +ungkit-ungkit +unting-unting +untung-untung +untung-untungan +upside-down +ura-ura +uran-uran +urat-urat +uring-uringan +urup-urup +urup-urupan +urus-urus +user-user +user-useran +utar-utar +voice-over +walk-out +wangi-wangian +wanti-wanti +wara-wara +warna-warni +water-cooled +world-class +yang-yang +""".split() +) diff --git a/spacy/lang/ms/examples.py b/spacy/lang/ms/examples.py new file mode 100644 index 000000000..97ab19b6e --- /dev/null +++ b/spacy/lang/ms/examples.py @@ -0,0 +1,17 @@ +""" +Example sentences to test spaCy and its language models. + +>>> from spacy.lang.ms.examples import sentences +>>> docs = nlp.pipe(sentences) +""" + + +sentences = [ + "Malaysia ialah sebuah negara yang terletak di Asia Tenggara.", + "Berapa banyak pelajar yang akan menghadiri majlis perpisahan sekolah?", + "Pengeluaran makanan berasal dari beberapa lokasi termasuk Cameron Highlands, Johor Bahru, dan Kuching.", + "Syarikat XYZ telah menghasilkan 20,000 unit produk baharu dalam setahun terakhir", + "Kuala Lumpur merupakan ibu negara Malaysia." "Kau berada di mana semalam?", + "Siapa yang akan memimpin projek itu?", + "Siapa perdana menteri Malaysia sekarang?", +] diff --git a/spacy/lang/ms/lex_attrs.py b/spacy/lang/ms/lex_attrs.py new file mode 100644 index 000000000..42759fa4f --- /dev/null +++ b/spacy/lang/ms/lex_attrs.py @@ -0,0 +1,66 @@ +import unicodedata + +from .punctuation import LIST_CURRENCY +from ...attrs import IS_CURRENCY, LIKE_NUM + + +_num_words = [ + "kosong", + "satu", + "dua", + "tiga", + "empat", + "lima", + "enam", + "tujuh", + "lapan", + "sembilan", + "sepuluh", + "sebelas", + "belas", + "puluh", + "ratus", + "ribu", + "juta", + "billion", + "trillion", + "kuadrilion", + "kuintilion", + "sekstilion", + "septilion", + "oktilion", + "nonilion", + "desilion", +] + + +def like_num(text): + if text.startswith(("+", "-", "Β±", "~")): + 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 + if text.lower() in _num_words: + return True + if text.count("-") == 1: + _, num = text.split("-") + if num.isdigit() or num in _num_words: + return True + return False + + +def is_currency(text): + if text in LIST_CURRENCY: + return True + + for char in text: + if unicodedata.category(char) != "Sc": + return False + return True + + +LEX_ATTRS = {IS_CURRENCY: is_currency, LIKE_NUM: like_num} diff --git a/spacy/lang/ms/punctuation.py b/spacy/lang/ms/punctuation.py new file mode 100644 index 000000000..9fff72576 --- /dev/null +++ b/spacy/lang/ms/punctuation.py @@ -0,0 +1,61 @@ +from ..punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES +from ..char_classes import ALPHA, merge_chars, split_chars, _currency, _units + + +_units = ( + _units + "s bit Gbps Mbps mbps Kbps kbps Ζ’ ppi px " + "Hz kHz MHz GHz mAh " + "ratus rb ribu ribuan " + "juta jt jutaan mill?iar million bil[l]?iun bilyun billion " +) +_currency = _currency + r" USD RM MYR Rp IDR RMB SGD S\$" +_months = ( + "Januari Februari Mac April Mei Jun Julai Ogos September " + "Oktober November Disember Januari Februari Mac Mei Jun " + "Julai Ogos Oktober Disember Jan Feb Mac Jun Julai Ogos Sept " + "Okt Nov Dis" +) + + +UNITS = merge_chars(_units) +CURRENCY = merge_chars(_currency) +HTML_PREFIX = r"<(b|strong|i|em|p|span|div|br)\s?/>|]+)>" +HTML_SUFFIX = r"" +MONTHS = merge_chars(_months) +LIST_CURRENCY = split_chars(_currency) + +_prefixes = list(TOKENIZER_PREFIXES) +_prefixes.remove("#") # hashtag +_prefixes = _prefixes + LIST_CURRENCY + [HTML_PREFIX] + ["/", "β€”"] + +_suffixes = ( + TOKENIZER_SUFFIXES + + [r"\-[Nn]ya", "-[KkMm]u", "[β€”-]"] + + [ + # disabled: variable width currency variable + # r"(?<={c})(?:[0-9]+)".format(c=CURRENCY), + r"(?<=[0-9])(?:{u})".format(u=UNITS), + r"(?<=[0-9])%", + # disabled: variable width HTML_SUFFIX variable + # r"(?<=[0-9{a}]{h})(?:[\.,:-])".format(a=ALPHA, h=HTML_SUFFIX), + r"(?<=[0-9{a}])(?:{h})".format(a=ALPHA, h=HTML_SUFFIX), + ] +) + +_infixes = TOKENIZER_INFIXES + [ + r"(?<=[0-9])[\\/](?=[0-9%-])", + r"(?<=[0-9])%(?=[{a}0-9/])".format(a=ALPHA), + # disabled: variable width units variable + # r"(?<={u})[\/-](?=[0-9])".format(u=UNITS), + # disabled: variable width months variable + # r"(?<={m})[\/-](?=[0-9])".format(m=MONTHS), + r'(?<=[0-9)][.,])"(?=[0-9])', + r'(?<=[{a})][.,\'])["β€”](?=[{a}])'.format(a=ALPHA), + r"(?<=[{a}])-(?=[0-9])".format(a=ALPHA), + r"(?<=[0-9])-(?=[{a}])".format(a=ALPHA), + r"(?<=[{a}])[\/-](?={c}|[{a}])".format(a=ALPHA, c=CURRENCY), +] + +TOKENIZER_PREFIXES = _prefixes +TOKENIZER_SUFFIXES = _suffixes +TOKENIZER_INFIXES = _infixes diff --git a/spacy/lang/ms/stop_words.py b/spacy/lang/ms/stop_words.py new file mode 100644 index 000000000..b1bfaea79 --- /dev/null +++ b/spacy/lang/ms/stop_words.py @@ -0,0 +1,118 @@ +STOP_WORDS = set( + """ +ada adalah adanya adapun agak agaknya agar akan akankah akhir akhiri akhirnya +aku akulah amat amatlah anda andalah antar antara antaranya apa apaan apabila +apakah apalagi apatah artinya asal asalkan atas atau ataukah ataupun awal +awalnya + +bagai bagaikan bagaimana bagaimanakah bagaimanapun bagi bagian bahkan bahwa +bahwasanya baik bakal bakalan balik banyak bapak baru bawah beberapa begini +beginian beginikah beginilah begitu begitukah begitulah begitupun bekerja +belakang belakangan belum belumlah benar benarkah benarlah berada berakhir +berakhirlah berakhirnya berapa berapakah berapalah berapapun berarti berawal +berbagai berdatangan beri berikan berikut berikutnya berjumlah berkali-kali +berkata berkehendak berkeinginan berkenaan berlainan berlalu berlangsung +berlebihan bermacam bermacam-macam bermaksud bermula bersama bersama-sama +bersiap bersiap-siap bertanya bertanya-tanya berturut berturut-turut bertutur +berujar berupa besar betul betulkah biasa biasanya bila bilakah bisa bisakah +boleh bolehkah bolehlah buat bukan bukankah bukanlah bukannya bulan bung + +cara caranya cukup cukupkah cukuplah cuma + +dahulu dalam dan dapat dari daripada datang dekat demi demikian demikianlah +dengan depan di dia diakhiri diakhirinya dialah diantara diantaranya diberi +diberikan diberikannya dibuat dibuatnya didapat didatangkan digunakan +diibaratkan diibaratkannya diingat diingatkan diinginkan dijawab dijelaskan +dijelaskannya dikarenakan dikatakan dikatakannya dikerjakan diketahui +diketahuinya dikira dilakukan dilalui dilihat dimaksud dimaksudkan +dimaksudkannya dimaksudnya diminta dimintai dimisalkan dimulai dimulailah +dimulainya dimungkinkan dini dipastikan diperbuat diperbuatnya dipergunakan +diperkirakan diperlihatkan diperlukan diperlukannya dipersoalkan dipertanyakan +dipunyai diri dirinya disampaikan disebut disebutkan disebutkannya disini +disinilah ditambahkan ditandaskan ditanya ditanyai ditanyakan ditegaskan +ditujukan ditunjuk ditunjuki ditunjukkan ditunjukkannya ditunjuknya dituturkan +dituturkannya diucapkan diucapkannya diungkapkan dong dua dulu + +empat enggak enggaknya entah entahlah + +guna gunakan + +hal hampir hanya hanyalah hari harus haruslah harusnya hendak hendaklah +hendaknya hingga + +ia ialah ibarat ibaratkan ibaratnya ibu ikut ingat ingat-ingat ingin inginkah +inginkan ini inikah inilah itu itukah itulah + +jadi jadilah jadinya jangan jangankan janganlah jauh jawab jawaban jawabnya +jelas jelaskan jelaslah jelasnya jika jikalau juga jumlah jumlahnya justru + +kala kalau kalaulah kalaupun kalian kami kamilah kamu kamulah kan kapan +kapankah kapanpun karena karenanya kasus kata katakan katakanlah katanya ke +keadaan kebetulan kecil kedua keduanya keinginan kelamaan kelihatan +kelihatannya kelima keluar kembali kemudian kemungkinan kemungkinannya kenapa +kepada kepadanya kesampaian keseluruhan keseluruhannya keterlaluan ketika +khususnya kini kinilah kira kira-kira kiranya kita kitalah kok kurang + +lagi lagian lah lain lainnya lalu lama lamanya lanjut lanjutnya lebih lewat +lima luar + +macam maka makanya makin malah malahan mampu mampukah mana manakala manalagi +masa masalah masalahnya masih masihkah masing masing-masing mau maupun +melainkan melakukan melalui melihat melihatnya memang memastikan memberi +memberikan membuat memerlukan memihak meminta memintakan memisalkan memperbuat +mempergunakan memperkirakan memperlihatkan mempersiapkan mempersoalkan +mempertanyakan mempunyai memulai memungkinkan menaiki menambahkan menandaskan +menanti menanti-nanti menantikan menanya menanyai menanyakan mendapat +mendapatkan mendatang mendatangi mendatangkan menegaskan mengakhiri mengapa +mengatakan mengatakannya mengenai mengerjakan mengetahui menggunakan +menghendaki mengibaratkan mengibaratkannya mengingat mengingatkan menginginkan +mengira mengucapkan mengucapkannya mengungkapkan menjadi menjawab menjelaskan +menuju menunjuk menunjuki menunjukkan menunjuknya menurut menuturkan +menyampaikan menyangkut menyatakan menyebutkan menyeluruh menyiapkan merasa +mereka merekalah merupakan meski meskipun meyakini meyakinkan minta mirip +misal misalkan misalnya mula mulai mulailah mulanya mungkin mungkinkah + +nah naik namun nanti nantinya nyaris nyatanya + +oleh olehnya + +pada padahal padanya pak paling panjang pantas para pasti pastilah penting +pentingnya per percuma perlu perlukah perlunya pernah persoalan pertama +pertama-tama pertanyaan pertanyakan pihak pihaknya pukul pula pun punya + +rasa rasanya rata rupanya + +saat saatnya saja sajalah saling sama sama-sama sambil sampai sampai-sampai +sampaikan sana sangat sangatlah satu saya sayalah se sebab sebabnya sebagai +sebagaimana sebagainya sebagian sebaik sebaik-baiknya sebaiknya sebaliknya +sebanyak sebegini sebegitu sebelum sebelumnya sebenarnya seberapa sebesar +sebetulnya sebisanya sebuah sebut sebutlah sebutnya secara secukupnya sedang +sedangkan sedemikian sedikit sedikitnya seenaknya segala segalanya segera +seharusnya sehingga seingat sejak sejauh sejenak sejumlah sekadar sekadarnya +sekali sekali-kali sekalian sekaligus sekalipun sekarang sekarang sekecil +seketika sekiranya sekitar sekitarnya sekurang-kurangnya sekurangnya sela +selain selaku selalu selama selama-lamanya selamanya selanjutnya seluruh +seluruhnya semacam semakin semampu semampunya semasa semasih semata semata-mata +semaunya sementara semisal semisalnya sempat semua semuanya semula sendiri +sendirian sendirinya seolah seolah-olah seorang sepanjang sepantasnya +sepantasnyalah seperlunya seperti sepertinya sepihak sering seringnya serta +serupa sesaat sesama sesampai sesegera sesekali seseorang sesuatu sesuatunya +sesudah sesudahnya setelah setempat setengah seterusnya setiap setiba setibanya +setidak-tidaknya setidaknya setinggi seusai sewaktu siap siapa siapakah +siapapun sini sinilah soal soalnya suatu sudah sudahkah sudahlah supaya + +tadi tadinya tahu tahun tak tambah tambahnya tampak tampaknya tandas tandasnya +tanpa tanya tanyakan tanyanya tapi tegas tegasnya telah tempat tengah tentang +tentu tentulah tentunya tepat terakhir terasa terbanyak terdahulu terdapat +terdiri terhadap terhadapnya teringat teringat-ingat terjadi terjadilah +terjadinya terkira terlalu terlebih terlihat termasuk ternyata tersampaikan +tersebut tersebutlah tertentu tertuju terus terutama tetap tetapi tiap tiba +tiba-tiba tidak tidakkah tidaklah tiga tinggi toh tunjuk turut tutur tuturnya + +ucap ucapnya ujar ujarnya umum umumnya ungkap ungkapnya untuk usah usai + +waduh wah wahai waktu waktunya walau walaupun wong + +yaitu yakin yakni yang +""".split() +) diff --git a/spacy/lang/ms/syntax_iterators.py b/spacy/lang/ms/syntax_iterators.py new file mode 100644 index 000000000..fa984d411 --- /dev/null +++ b/spacy/lang/ms/syntax_iterators.py @@ -0,0 +1,41 @@ +from typing import Union, Iterator, Tuple + +from ...symbols import NOUN, PROPN, PRON +from ...errors import Errors +from ...tokens import Doc, Span + + +def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Tuple[int, int, int]]: + """ + Detect base noun phrases from a dependency parse. Works on both Doc and Span. + """ + # fmt: off + labels = ["nsubj", "nsubj:pass", "obj", "iobj", "ROOT", "appos", "nmod", "nmod:poss"] + # fmt: on + doc = doclike.doc # Ensure works on both Doc and Span. + if not doc.has_annotation("DEP"): + raise ValueError(Errors.E029) + np_deps = [doc.vocab.strings[label] for label in labels] + conj = doc.vocab.strings.add("conj") + np_label = doc.vocab.strings.add("NP") + prev_end = -1 + for i, word in enumerate(doclike): + if word.pos not in (NOUN, PROPN, PRON): + continue + # Prevent nested chunks from being produced + if word.left_edge.i <= prev_end: + continue + if word.dep in np_deps: + prev_end = word.right_edge.i + yield word.left_edge.i, word.right_edge.i + 1, np_label + elif word.dep == conj: + head = word.head + while head.dep == conj and head.head.i < head.i: + head = head.head + # If the head is an NP, and we're coordinated to it, we're an NP + if head.dep in np_deps: + prev_end = word.right_edge.i + yield word.left_edge.i, word.right_edge.i + 1, np_label + + +SYNTAX_ITERATORS = {"noun_chunks": noun_chunks} diff --git a/spacy/lang/ms/tokenizer_exceptions.py b/spacy/lang/ms/tokenizer_exceptions.py new file mode 100644 index 000000000..6b6cf3b15 --- /dev/null +++ b/spacy/lang/ms/tokenizer_exceptions.py @@ -0,0 +1,1533 @@ +from ..tokenizer_exceptions import BASE_EXCEPTIONS +from ._tokenizer_exceptions_list import MS_BASE_EXCEPTIONS +from ...symbols import ORTH, NORM +from ...util import update_exc + + +# Daftar singkatan dan Akronim dari: +# https://ms.wiktionary.org/wiki/Wiktionary:Senarai_akronim_dan_singkatan + +_exc = {} + +for orth in MS_BASE_EXCEPTIONS: + _exc[orth] = [{ORTH: orth}] + orth_title = orth.title() + _exc[orth_title] = [{ORTH: orth_title}] + orth_caps = orth.upper() + _exc[orth_caps] = [{ORTH: orth_caps}] + orth_lower = orth.lower() + _exc[orth_lower] = [{ORTH: orth_lower}] + orth_first_upper = orth[0].upper() + orth[1:] + _exc[orth_first_upper] = [{ORTH: orth_first_upper}] + if "-" in orth: + orth_title = "-".join([part.title() for part in orth.split("-")]) + _exc[orth_title] = [{ORTH: orth_title}] + orth_caps = "-".join([part.upper() for part in orth.split("-")]) + _exc[orth_caps] = [{ORTH: orth_caps}] + +for exc_data in [ + {ORTH: "Jan.", NORM: "Januari"}, + {ORTH: "Feb.", NORM: "Februari"}, + {ORTH: "Mac.", NORM: "Mac"}, + {ORTH: "Apr.", NORM: "April"}, + {ORTH: "Jun.", NORM: "Jun"}, + {ORTH: "Jul.", NORM: "Julai"}, + {ORTH: "Ogos.", NORM: "Ogos"}, + {ORTH: "Sep.", NORM: "September"}, + {ORTH: "Okt.", NORM: "Oktober"}, + {ORTH: "Nov.", NORM: "November"}, + {ORTH: "Dis.", NORM: "Disember"}, +]: + _exc[exc_data[ORTH]] = [exc_data] + +_other_exc = { + "do'a": [{ORTH: "do'a", NORM: "doa"}], + "jum'at": [{ORTH: "jum'at", NORM: "Jumat"}], + "Jum'at": [{ORTH: "Jum'at", NORM: "Jumat"}], + "la'nat": [{ORTH: "la'nat", NORM: "laknat"}], + "ma'af": [{ORTH: "ma'af", NORM: "maaf"}], + "mu'jizat": [{ORTH: "mu'jizat", NORM: "mukjizat"}], + "Mu'jizat": [{ORTH: "Mu'jizat", NORM: "mukjizat"}], + "ni'mat": [{ORTH: "ni'mat", NORM: "nikmat"}], + "raka'at": [{ORTH: "raka'at", NORM: "rakaat"}], + "ta'at": [{ORTH: "ta'at", NORM: "taat"}], +} + +_exc.update(_other_exc) + +for orth in [ + "1 Kor.", + "1 Ptr.", + "1 Raj.", + "1 Sam.", + "1 Taw.", + "1 Tes.", + "1 Tim.", + "1 Yoh.", + "1Ch.", + "1Co.", + "1Jo.", + "1Ki.", + "1Pe.", + "1Sa.", + "1Th.", + "1Ti.", + "2 Kor.", + "2 Ptr.", + "2 Raj.", + "2 Sam.", + "2 Taw.", + "2 Tes.", + "2 Tim.", + "2 Yoh.", + "2Ch.", + "2Co.", + "2Jo.", + "2Ki.", + "2Pe.", + "2Sa.", + "2Th.", + "2Ti.", + "3 Yoh.", + "3D", + "3F", + "3Jo.", + "3M", + "8MP", + "AA", + "AAAAAA", + "AB", + "Abd.", + "ABC", + "ABIM", + "ABM", + "ABMI", + "ABS", + "AC", + "Ac", + "ACAPLPL", + "Act.", + "AD", + "AD LIB", + "ADAM", + "ADB", + "ADD", + "ADIL", + "ADN", + "ADR", + "ADRI", + "ADSL", + "ADUN", + "AFAS", + "AFTA", + "Ag", + "AGMARIS", + "AH", + "AI", + "AIA", + "AIDS", + "AIJV", + "AIM", + "a/k", + "ak", + "AKN", + "Al", + "a/l", + "AM", + "Am", + "Am.", + "AMN", + "Amo.", + "AMPS", + "Ams.", + "AMWA", + "AN", + "a.n.", + "ANGKASA", + "ANM", + "ANSI", + "Ant.", + "AOL", + "AP", + "a/p", + "APD", + "APEC", + "API", + "APIK", + "APM", + "APN", + "APP", + "Apr.", + "APRI", + "Ar", + "Ar.", + "ark.", + "A.S.", + "As", + "a.s.", + "ASA", + "ASAS 50", + "ASB", + "ASCII", + "ASEAN", + "ASEAN+3", + "ASEM", + "a.s.f.", + "ASN", + "a.s.o.", + "ASP", + "Ast.", + "A.T.", + "At", + "ATM", + "a.t.r.", + "ATUR", + "Au", + "AURI", + "Aug.", + "AWOL", + "Ayb.", + "B", + "BA", + "Ba", + "BAC", + "BAFIA", + "BAM", + "BANANA", + "BAPP", + "BASF", + "BATA", + "BB", + "BBC", + "BBE", + "BBS", + "BC", + "BCG", + "BCIC", + "b.d.", + "BDSSHAM", + "Be", + "BEER", + "BERNAMA", + "Bh", + "b.h.", + "Bhd.", + "Bi", + "BIDS", + "Bil.", + "bil.", + "BIMP-EAGA", + "Bio.", + "BIOS", + "BITMB", + "BJ", + "Bk", + "b.k.", + "BKAL", + "bkn.", + "BKP", + "BL", + "BLR", + "BM", + "BMI", + "BMW", + "BN", + "BNM", + "BO", + "BOJ", + "BOO", + "BOP", + "BOT", + "BP", + "b.p.", + "BPA", + "BPAs", + "bpd.", + "BPIMB", + "BPM", + "BPO", + "BPPH", + "Br", + "Br.", + "BSA", + "B.Sc.", + "B.Sh.", + "b.s.j.", + "BSN", + "Bt.", + "bt.", + "BWT", + "BYOB", + "C", + "C.", + "C/E", + "Ca", + "CAAM", + "CAD", + "CAM", + "CATV", + "CBS", + "CBT", + "CC", + "CCD", + "CCM", + "CCR", + "cct-km", + "CCTV", + "CCU", + "CD", + "Cd", + "CD-ROM", + "CD-RW", + "CDRC", + "Ce", + "CEO", + "CEPT", + "Cetak", + "Cf", + "CFO", + "CFTC", + "CGC", + "CGI", + "CH", + "CIA", + "CIAST", + "CID", + "CIDB", + "CIQ", + "CKD", + "CL", + "Cl", + "c.l.", + "CLI", + "CLOB", + "CM", + "Cm", + "cm.", + "CMAG", + "CMI", + "CMP", + "CNN", + "Co", + "COD", + "Col.", + "COLA", + "COMDEX", + "CP", + "CPI", + "CPO", + "CPR", + "CPU", + "Cr", + "CRDF", + "Cs", + "CST", + "CT", + "CTIP", + "CTRM", + "Cu", + "CUEPACS", + "D-8", + "d/a", + "DAGS", + "Dan.", + "DANCED", + "DAP", + "DARA", + "Db", + "DBKL", + "DBP", + "DBR", + "DC", + "DDA", + "DDT", + "DEB", + "Dec.", + "Deu.", + "DFIs", + "dgn.", + "DHL", + "DIBML", + "DIN", + "Dis.", + "DJ", + "d.l.l.", + "dlm.", + "dng.", + "DNS", + "DO", + "DOA", + "DOE", + "DOF", + "DOSH", + "doz.", + "DPPS", + "Dr.", + "dr.", + "drp.", + "drpd.", + "Ds", + "d.sb.", + "d.st.", + "DSTN2", + "Dt.", + "DTAs", + "DTMF", + "DTP", + "DTV", + "DUBES", + "DUNHILL", + "DV8", + "DVD", + "DVE", + "DVS", + "dw.t.", + "Dy", + "DYMM", + "E", + "E-Commerce", + "E-Dagang", + "E&E", + "E-Faraid", + "E-Government", + "E-Kerajaan", + "E-Mail", + "E-Services", + "E-Village", + "E-Zine", + "EALAF", + "EBI", + "EBP", + "EC", + "ECAFE", + "Ecc.", + "ECI", + "ECM", + "ECOSOC", + "ECP", + "ECR", + "EDI", + "EE", + "EEC", + "Ef.", + "EG", + "Eko.", + "EKS", + "ELWS", + "ELX", + "EMI", + "EMUs", + "En.", + "EP", + "EPF", + "Eph.", + "EPP", + "EPS", + "EPU", + "ER", + "Er", + "ERL", + "ERT", + "Es", + "ESCAP", + "ESOS", + "ESP", + "EST", + "Est.", + "ET", + "ETA", + "ETACS", + "ETC", + "ETD", + "EU", + "Eu", + "EVIAN", + "Exim Bank", + "Exo.", + "Eze.", + "Ezr.", + "F", + "FAM", + "FAMA", + "FAO", + "FAQ", + "FAX", + "FBI", + "FC", + "FCA", + "FCC", + "FDI", + "FE", + "Fe", + "f.e.", + "Feb.", + "FELCRA", + "FELDA", + "FI", + "FIA 1993", + "FIAT", + "FIC", + "FIDA", + "FIFA", + "FIMA", + "Fiz.", + "Flm.", + "Flp.", + "FM", + "Fm", + "FMUTM", + "FO", + "FOA", + "FOB", + "FOC", + "FOMCA", + "FORD", + "Fr", + "FRIM", + "FRTI", + "FSMP", + "FTA", + "FTE", + "FTP", + "G", + "g.", + "G15", + "G77", + "Ga", + "GAC", + "GACM", + "Gal.", + "GAPENA", + "GATS", + "GATT", + "GB", + "Gbps.", + "Gd", + "GDP", + "Ge", + "GEC", + "Gen.", + "Geo.", + "Geog.", + "Gerakan", + "GH", + "GIF", + "GII", + "GIS", + "GITIC", + "GITN", + "GJ", + "GLCs", + "GM", + "GMBH", + "GMI", + "GMT", + "GNP", + "GNS", + "GOLD", + "GP", + "GPC", + "GPIM", + "GPMS", + "GPO", + "GPP", + "GPS", + "GRO", + "GRS", + "GSMC", + "GST", + "GTZ", + "GUI", + "GWh.", + "H", + "Ha", + "Hab.", + "Hag.", + "Hak.", + "ham", + "hb.", + "HCI", + "HDTV", + "He", + "Heb.", + "Hf", + "Hg", + "HI-FI", + "HIS", + "HIV", + "Hj.", + "HMS", + "Ho", + "Hos.", + "HP", + "HRDC", + "HRDF", + "HRMIS", + "Hs", + "Hut.", + "I", + "I/O", + "IA", + "IAA", + "IADPs", + "IB", + "i.b.", + "IBA", + "IBFIM", + "IBG", + "Ibr.", + "IBRD", + "IBS", + "IC", + "ICA", + "ICBM", + "ICFM", + "ICI", + "ICM", + "ICOR", + "ICP", + "ICT", + "ICU", + "ID", + "Id.", + "IDB", + "IDFR", + "IE", + "i.e.", + "IFSB", + "IGAs", + "IGS", + "IHP", + "IHPG", + "IIM", + "IINA", + "IKKL", + "IKP", + "IKPH", + "IKS", + "Im.", + "IMD", + "IMF", + "IMP2", + "IMR", + "IMS-GT", + "IMT-GT", + "In", + "in.", + "INFRA", + "INSEP", + "INSPEN", + "INTAN", + "IOFC", + "IOU", + "IP", + "IPA", + "IPBA", + "IPCs", + "IPEBP", + "IPI", + "IPKIM", + "IPKPM", + "IPO", + "IPP", + "IPPM", + "IPPPM", + "i.pt.", + "IPTAR", + "IPTNM", + "IQR", + "Ir", + "IRA", + "IRPA", + "IRS", + "i.s.", + "ISA", + "Isa.", + "ISDN", + "ISMM", + "ISO", + "ISP", + "ist.", + "IT", + "i.t.", + "ITA", + "ITAF", + "ITEX", + "ITK", + "ITM", + "ITO", + "ITRCo", + "ITTA", + "ITU", + "JAK", + "JAKIM", + "Jam.", + "Jan.", + "Jb.", + "JBIC", + "JD", + "JDA", + "Jdg.", + "Jer.", + "Jh.", + "JICA", + "JJ", + "Jk.", + "JKKK", + "jkps.", + "JKR", + "JMTI", + "JOA", + "Joe.", + "Joh.", + "Jon.", + "Jos.", + "JP", + "JPA", + "JPEG", + "JPH", + "JPJ", + "JPSHK", + "JPS", + "JPT", + "JRDA", + "JSM", + "JT", + "Jud.", + "Jul.", + "Jun.", + "JVC", + "Jw.", + "K", + "K-Economy", + "KADA", + "KBE", + "KBIA", + "KBPA", + "KBSM", + "KD", + "Kd.", + "KDI", + "KDN", + "KDNK", + "KE", + "KEAP", + "Kej.", + "Kel.", + "KEM", + "KEMLU", + "kep.", + "Kg.", + "kg.", + "KGB", + "KGK", + "KH", + "ki.", + "Kid.", + "KIK", + "KIKMTT", + "KIM", + "Kim.", + "Kis.", + "KIX", + "KKGSK", + "KKK", + "KKPPA", + "KL", + "Kl.", + "KLCI", + "KLIA", + "KLIBOR", + "KLIM", + "KLM", + "KLSE", + "KM", + "KMM", + "KNK", + "KO", + "Kol.", + "Kom.", + "Komp.", + "KOMSAS", + "KPAI", + "KPB", + "KPBA", + "KPC", + "kpd.", + "KPE", + "KPIs", + "KPPL", + "KPPMS", + "KPWM", + "Kr", + "KRM", + "KSTI", + "KT", + "KTA", + "KTABKL", + "KTM", + "KTMB", + "kV", + "kW", + "kWh", + "kWj", + "KWSP", + "LA", + "La", + "LABOR", + "Lam.", + "LAN", + "LAPD", + "LASER", + "LAX", + "lb.", + "LC", + "LCD", + "LCHRF", + "LCLY", + "LED", + "Lev.", + "LFPR", + "LFS", + "LFX", + "LGM", + "Li", + "LID", + "Lin.", + "LKN", + "LKPM", + "LKPP", + "LKTP", + "LKWJ", + "LLB", + "LLC", + "LLN", + "LLS", + "LMSM", + "LNG", + "LOA", + "LOBATA", + "LOFSA", + "LPG", + "LPIP", + "LPKI", + "LPKLPL", + "LPKN", + "LPN", + "LPP", + "LPPK", + "LPPM", + "LPPP", + "LPPTP", + "Lr", + "LRs", + "LRT", + "LS", + "LTAKL", + "LTD", + "LTK", + "Lu", + "LUAS", + "Luk.", + "lw.", + "lwn.", + "M\n", + "m", + "M&A", + "MAB", + "MACRES", + "MAD", + "MADA", + "MAGERAN", + "MAHA", + "MAHSURI", + "Mal.", + "MALINDO", + "MAMPU", + "Mar.", + "MARA", + "MARC", + "MARDI", + "MARLBORO", + "MAS", + "MASSA", + "MASSCORP", + "Mat.", + "MATRADE", + "MAVCAP", + "MB", + "MBA", + "MBBS", + "MBM", + "MBO", + "MBS", + "MBTU", + "MC", + "MCA", + "MCB", + "MCSL", + "MCSv5", + "MD", + "Md", + "MDB", + "MDC", + "MDG", + "MDV", + "MEASAT", + "MEATJ", + "MECIB", + "MEMO", + "MENLU", + "MEPS", + "MES", + "MESDAQ", + "METEOR", + "MFI", + "MFIs", + "MG", + "Mg", + "MGM", + "MGR", + "MGS", + "MHA", + "Mi.", + "MIA", + "MIB", + "MIC", + "Mic.", + "MICE", + "MIDA", + "MIDF", + "MIDI", + "MIG", + "MIGHT", + "MII", + "MIMOS", + "MINDEF", + "MINT", + "mis.", + "MIT", + "MITC", + "MITI", + "Ml.", + "MLNG", + "mlpd.", + "MM", + "mm", + "MMN", + "mmscfd.", + "MMU", + "MMX", + "Mn", + "Mn.", + "MNA", + "MNCs", + "MO", + "Mo", + "MOA", + "MOD", + "MODEM", + "MOE", + "MOH", + "MOSTE", + "MOSTI", + "MOU", + "MP", + "MPB", + "MPEG", + "MPOB", + "MPP", + "mppa.", + "MPPJ", + "MPS", + "MPTM", + "MR", + "m.r.", + "MRB", + "MRELB", + "Mrk.", + "MRRDB", + "MS", + "MS-DOS", + "MSC", + "MSG", + "MSM", + "Mt", + "MTC", + "MTCP", + "MTD", + "MTDC", + "MTPB", + "MTV", + "Muz.", + "MV", + "MW", + "MY", + "MyKe", + "Mzm.", + "N", + "N/A", + "Na", + "NAB", + "NACIWID", + "Nah.", + "NAP", + "NASA", + "NATO", + "NAV", + "NB", + "Nb", + "NBA", + "NBC", + "NCR", + "Nd", + "NDP", + "Ne", + "NEAC", + "NEC", + "NEF", + "Neh.", + "NEP", + "NEqO", + "NERP", + "NF", + "NFPEs", + "NG", + "NGOs", + "NGV", + "NHEF", + "NHHES", + "NHK", + "Ni", + "NIDC", + "NIH", + "NIP", + "NIPA", + "NIS", + "NISIR", + "NITA", + "NITC", + "NITP", + "NIV", + "NLAC", + "NMPBSP", + "NMU", + "No", + "No.", + "no.", + "NOSS", + "Nov.", + "Np", + "NPC", + "NPCS", + "NPL", + "NRCC", + "NRW", + "NS", + "Ns", + "NSB", + "NTA", + "NTHRDC", + "NTMP", + "NTSC", + "Num.", + "NUTF", + "NVP", + "NVTC", + "NWRC", + "O", + "Ob.", + "Oba.", + "OC", + "OCPD", + "Oct.", + "OD", + "ODA", + "OECD", + "OEM", + "Ogo.", + "OHQs", + "OIC", + "Okt.", + "OPEC", + "OPP", + "OPP3", + "OPR", + "OS", + "Os", + "OSA", + "OT", + "OUG", + "oz.", + "P", + "P&P", + "PA", + "Pa", + "PABK", + "PABX", + "PAK", + "PAKSI", + "PAL", + "PALL MALL", + "PAS", + "PATA", + "PAWS", + "Pb", + "PBA", + "PBB", + "PBM", + "PBP", + "PBSM", + "PBT", + "PC", + "PC(s)", + "PCB", + "PCIRITA", + "PCM", + "PCMCIA", + "PCN", + "PD", + "Pd", + "pd.", + "PDS", + "PE", + "PEKEMAS", + "PEMADAM", + "PENA", + "PENIS", + "PERDANA", + "PERKESO", + "PERKIM", + "PERNAS", + "PERTAMA", + "PERTIWI", + "PESAKA", + "PETA", + "PETRONAS", + "PGU", + "Ph.", + "PHD", + "Phi.", + "Phm.", + "PIK", + "PIKOM", + "PIN", + "PINTAS", + "PIPM", + "PISK", + "PITA", + "PIXEL", + "PJ", + "PJK", + "PJKB", + "PJP", + "PKBM", + "PKBTA", + "PKEN", + "Pkh.", + "PKKM", + "PKLPA", + "PKM", + "PKNS", + "PKPIM", + "PKPM", + "PKR", + "PKS", + "Pl.", + "p.l.", + "PLA", + "PLC", + "PLCHP", + "PLCs", + "PLI", + "PLT", + "PLUS", + "PLWS", + "PM", + "Pm", + "PMM", + "PMP", + "PMR", + "PMS", + "Pn.", + "PNAT", + "PNS", + "PO", + "Po", + "POCPA", + "POKEMON", + "Pol.", + "POP", + "PORIM", + "PORLA", + "PORTAFOAM", + "PP", + "PPA", + "PPBE", + "PPBK", + "ppd.", + "PPGM", + "PPI", + "PPK", + "PPL", + "PPM", + "PPP", + "PPPB", + "PPPLM", + "PPPM", + "PPR", + "PPRT", + "PPS", + "PPTM", + "PPU", + "PR", + "Pr", + "Pr.", + "prb.", + "PRI", + "PRO", + "Pro.", + "Prof.", + "PROSPER", + "PROSTAR", + "PROTON", + "PS", + "PSA", + "Psa.", + "PSCs", + "PSDC", + "PSDH", + "Psi.", + "PSKE", + "PSRM", + "PST", + "PT", + "Pt", + "PTD", + "PTP", + "Pu", + "PUNB", + "QA", + "QC", + "QCC", + "R&D", + "RA", + "Ra", + "RAM", + "RAPP", + "Rat.", + "Rb", + "RCA", + "RDA", + "RDAs", + "RDCs", + "RE", + "Re", + "REHDA", + "Rev.", + "Rf", + "Rg", + "RGB", + "Rh", + "RI", + "RIDA", + "RIP", + "RISDA", + "r.l.", + "RM", + "Rm.", + "RMKe-8", + "Rn", + "ROC", + "ROM", + "Rom.", + "RPG", + "RPS", + "RRI", + "RRIM", + "RRJP", + "RRP", + "RSGC", + "RSS", + "RSVP", + "Rt.", + "RTA", + "RTM", + "Ru", + "Rut.", + "RWCR", + "RX", + "S", + "S/N", + "S&T", + "S-VHS", + "SA", + "SAC", + "SADCs", + "SAGA", + "SALCRA", + "SALM", + "SALT", + "SAM", + "SAP", + "SARS", + "Sas.", + "s.a.w.", + "SB", + "Sb", + "Sb.", + "SBA", + "SBB", + "sbg.", + "SBK", + "SC", + "Sc", + "SCA", + "SCADA", + "SCANS", + "SCSI", + "SCuM", + "SDCs", + "Sdn. Bhd.", + "sdr.", + "SDRC", + "Se", + "SEATO", + "SEB", + "SECAM", + "SEDCs", + "SEFF", + "Sej.", + "SEMS", + "Sep.", + "Sept.", + "SESB", + "SESCo", + "s.f.", + "Sg", + "SGPCA", + "SGPPI", + "SGPPKRM", + "SGX", + "Si", + "Si.", + "SIA 1983", + "SIC", + "SIM", + "SING", + "SIRIM", + "SITTDEC", + "sj.", + "SKDTP", + "SKM", + "SKSM", + "SL", + "Sl.", + "sl.", + "SLMCH", + "SLR", + "SM", + "Sm", + "SMART", + "SMEs", + "SMEt", + "SMIs", + "SMIDEC", + "SMIDP", + "SMJK", + "SMR", + "SMS", + "SMT", + "SMTP", + "SN", + "Sn", + "SOB", + "SOCSO", + "SOHO", + "Son.", + "SOS", + "Sos.", + "SP", + "SPA", + "SPAM", + "SPCA", + "SPKR", + "SPLAM", + "SPM", + "SPNB", + "SPSP", + "t.", + "Ta", + "Tadb.", + "TAF", + "TAF-W", + "Tani", + "TAP", + "TAR", + "TARBI", + "TB", + "Tb", + "TBA", + "TBTP", + "Tc", + "TCPD", + "TDCs", + "Te", + "TEKUN", + "TELCO", + "TELEX", + "TEUs", + "TFP", + "TGV", + "TH", + "Th", + "THIS", + "Ti", + "TICAD", + "Tit.", + "TKA", + "Tks.", + "Tl", + "TLDM", + "TM", + "Tm", + "TMB", + "TMK", + "TNB", + "TNSB", + "TNT", + "TOEFL", + "TP", + "TPIM", + "TPK", + "TPPP", + "TPPT", + "TPSM", + "TPUB", + "TQM", + "Tr.", + "TRIPs", + "tsb.", + "tscf.", + "t.sh.", + "t.s.t.", + "TT", + "t.t.", + "TUDM", + "TV", + "TVSMR", + "TWAIN", + "TX", + "TYPHIrapid", + "U", + "Ubat", + "UDA", + "Udg.", + "UFO", + "UH", + "UIA", + "UiTM", + "UK", + "UKM", + "UL", + "Ul.", + "ULC", + "UM", + "UMNO", + "UMS", + "UN", + "UN/OSCAL", + "UNCLE", + "UNCTAD", + "UNDP", + "UNESCO", + "UNFCCC", + "UNFPA", + "UNHCR", + "UNICEF", + "UNIMAS", + "UNTAET", + "UPE", + "UPM", + "UPS", + "UPSR", + "URL", + "US", + "USAINS", + "USD", + "USM", + "USNO", + "USS", + "USSR", + "UTC", + "UTF", + "utk.", + "UTM", + "V", + "VAT", + "VCC", + "VCD", + "VCR", + "VD", + "VDSC", + "VGA", + "VHF", + "VHS", + "VIP", + "VMS", + "VO", + "VOA", + "VoIP", + "VR", + "VSOP", + "VW", + "W", + "W/O", + "WAP", + "WAY", + "WC", + "WDDM", + "WDM", + "WHO", + "Why.", + "WIM", + "WPG", + "WTO", + "WWF", + "WWW", + "WYSIWYG", + "Xe", + "XO", + "XXL", + "Y", + "Y2K", + "YAB", + "Yak.", + "YAM", + "YAS", + "YB", + "Yb", + "Yeh.", + "Yer.", + "Yes.", + "yg.", + "Yl.", + "YM", + "YMCA", + "Yoh.", + "Yos.", + "Y.Th.", + "YTM", + "Yud.", + "Yun.", + "Za.", + "Zec.", + "Zef.", + "Zep.", + "ZIP", + "Zn", + "Zr", +]: + _exc[orth] = [{ORTH: orth}] + +TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc) diff --git a/spacy/language.py b/spacy/language.py index 9fdcf6328..0e9ff6893 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -1,6 +1,6 @@ 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 +from typing import NoReturn, TypeVar, cast, overload from dataclasses import dataclass import random @@ -1269,7 +1269,10 @@ class Language: "No 'get_examples' callback provided to 'Language.initialize', creating dummy examples" ) doc = Doc(self.vocab, words=["x", "y", "z"]) - get_examples = lambda: [Example.from_dict(doc, {})] + + def get_examples(): + return [Example.from_dict(doc, {})] + if not hasattr(get_examples, "__call__"): err = Errors.E930.format( method="Language.initialize", obj=type(get_examples) @@ -1372,6 +1375,7 @@ class Language: scorer: Optional[Scorer] = None, component_cfg: Optional[Dict[str, Dict[str, Any]]] = None, scorer_cfg: Optional[Dict[str, Any]] = None, + per_component: bool = False, ) -> Dict[str, Any]: """Evaluate a model's pipeline components. @@ -1383,6 +1387,8 @@ class Language: arguments for specific components. scorer_cfg (dict): An optional dictionary with extra keyword arguments for the scorer. + per_component (bool): Whether to return the scores keyed by component + name. Defaults to False. RETURNS (Scorer): The scorer containing the evaluation results. @@ -1415,7 +1421,7 @@ class Language: for eg, doc in zip(examples, docs): eg.predicted = doc end_time = timer() - results = scorer.score(examples) + results = scorer.score(examples, per_component=per_component) n_words = sum(len(eg.predicted) for eg in examples) results["speed"] = n_words / (end_time - start_time) return results diff --git a/spacy/ml/extract_spans.py b/spacy/ml/extract_spans.py index d5e9bc07c..af6be78db 100644 --- a/spacy/ml/extract_spans.py +++ b/spacy/ml/extract_spans.py @@ -1,4 +1,4 @@ -from typing import Tuple, Callable +from typing import List, Tuple, Callable from thinc.api import Model, to_numpy from thinc.types import Ragged, Ints1d @@ -52,14 +52,14 @@ def _get_span_indices(ops, spans: Ragged, lengths: Ints1d) -> Ints1d: indices will be [5, 6, 7, 8, 8, 9]. """ spans, lengths = _ensure_cpu(spans, lengths) - indices = [] + indices: List[int] = [] offset = 0 for i, length in enumerate(lengths): spans_i = spans[i].dataXd + offset for j in range(spans_i.shape[0]): - indices.append(ops.xp.arange(spans_i[j, 0], spans_i[j, 1])) # type: ignore[call-overload, index] + indices.extend(range(spans_i[j, 0], spans_i[j, 1])) # type: ignore[arg-type, call-overload] offset += length - return ops.flatten(indices, dtype="i", ndim_if_empty=1) + return ops.asarray1i(indices) def _ensure_cpu(spans: Ragged, lengths: Ints1d) -> Tuple[Ragged, Ints1d]: diff --git a/spacy/pipeline/span_finder.py b/spacy/pipeline/span_finder.py index f11bcf793..d767c6e18 100644 --- a/spacy/pipeline/span_finder.py +++ b/spacy/pipeline/span_finder.py @@ -173,7 +173,7 @@ class SpanFinder(TrainablePipe): min_length = 1 if max_length < 1 or min_length < 1: raise ValueError( - Errors.E1052.format(min_length=min_length, max_length=max_length) + Errors.E1053.format(min_length=min_length, max_length=max_length) ) self.min_length = min_length self.max_length = max_length @@ -267,7 +267,7 @@ class SpanFinder(TrainablePipe): masks = [] for eg in examples: if eg.x.text != eg.y.text: - raise ValueError(Errors.E1053.format(component="span_finder")) + raise ValueError(Errors.E1054.format(component="span_finder")) n_tokens = len(eg.predicted) truth = ops.xp.zeros((n_tokens, 2), dtype="float32") mask = ops.xp.ones((n_tokens, 2), dtype="float32") diff --git a/spacy/scorer.py b/spacy/scorer.py index de4f52be6..86cd00a50 100644 --- a/spacy/scorer.py +++ b/spacy/scorer.py @@ -121,20 +121,30 @@ class Scorer: nlp.add_pipe(pipe) self.nlp = nlp - def score(self, examples: Iterable[Example]) -> Dict[str, Any]: + def score( + self, examples: Iterable[Example], *, per_component: bool = False + ) -> Dict[str, Any]: """Evaluate a list of Examples. examples (Iterable[Example]): The predicted annotations + correct annotations. + per_component (bool): Whether to return the scores keyed by component + name. Defaults to False. RETURNS (Dict): A dictionary of scores. DOCS: https://spacy.io/api/scorer#score """ scores = {} if hasattr(self.nlp.tokenizer, "score"): - scores.update(self.nlp.tokenizer.score(examples, **self.cfg)) # type: ignore + if per_component: + scores["tokenizer"] = self.nlp.tokenizer.score(examples, **self.cfg) + else: + scores.update(self.nlp.tokenizer.score(examples, **self.cfg)) # type: ignore for name, component in self.nlp.pipeline: if hasattr(component, "score"): - scores.update(component.score(examples, **self.cfg)) + if per_component: + scores[name] = component.score(examples, **self.cfg) + else: + scores.update(component.score(examples, **self.cfg)) return scores @staticmethod diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py index 3a5c8e451..00b8f5f1c 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -291,6 +291,11 @@ def ml_tokenizer(): return get_lang_class("ml")().tokenizer +@pytest.fixture(scope="session") +def ms_tokenizer(): + return get_lang_class("ms")().tokenizer + + @pytest.fixture(scope="session") def nb_tokenizer(): return get_lang_class("nb")().tokenizer diff --git a/spacy/tests/doc/test_span_group.py b/spacy/tests/doc/test_span_group.py index 818569c64..cea2c42ee 100644 --- a/spacy/tests/doc/test_span_group.py +++ b/spacy/tests/doc/test_span_group.py @@ -93,6 +93,21 @@ def test_span_group_copy(doc): assert span_group.attrs["key"] == "value" assert list(span_group) != list(clone) + # can't copy if the character offsets don't align to tokens + doc2 = Doc(doc.vocab, words=[t.text + "x" for t in doc]) + with pytest.raises(ValueError): + span_group.copy(doc=doc2) + + # can copy with valid character offsets despite different tokenization + doc3 = doc.copy() + with doc3.retokenize() as retokenizer: + retokenizer.merge(doc3[0:2]) + retokenizer.merge(doc3[3:6]) + span_group = SpanGroup(doc, spans=[doc[0:6], doc[3:6]]) + for span1, span2 in zip(span_group, span_group.copy(doc=doc3)): + assert span1.start_char == span2.start_char + assert span1.end_char == span2.end_char + def test_span_group_set_item(doc, other_doc): span_group = doc.spans["SPANS"] @@ -253,3 +268,12 @@ def test_span_group_typing(doc: Doc): for i, span in enumerate(span_group): assert span == span_group[i] == spans[i] filter_spans(span_group) + + +def test_span_group_init_doc(en_tokenizer): + """Test that all spans must come from the specified doc.""" + doc1 = en_tokenizer("a b c") + doc2 = en_tokenizer("a b c") + span_group = SpanGroup(doc1, spans=[doc1[0:1], doc1[1:2]]) + with pytest.raises(ValueError): + span_group = SpanGroup(doc1, spans=[doc1[0:1], doc2[1:2]]) diff --git a/spacy/tests/lang/ms/__init__.py b/spacy/tests/lang/ms/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/spacy/tests/lang/ms/test_noun_chunks.py b/spacy/tests/lang/ms/test_noun_chunks.py new file mode 100644 index 000000000..859307d00 --- /dev/null +++ b/spacy/tests/lang/ms/test_noun_chunks.py @@ -0,0 +1,8 @@ +import pytest + + +def test_noun_chunks_is_parsed_ms(ms_tokenizer): + """Test that noun_chunks raises Value Error for 'ms' language if Doc is not parsed.""" + doc = ms_tokenizer("sebelas") + with pytest.raises(ValueError): + list(doc.noun_chunks) diff --git a/spacy/tests/lang/ms/test_prefix_suffix_infix.py b/spacy/tests/lang/ms/test_prefix_suffix_infix.py new file mode 100644 index 000000000..0d2b2c507 --- /dev/null +++ b/spacy/tests/lang/ms/test_prefix_suffix_infix.py @@ -0,0 +1,112 @@ +import pytest + + +@pytest.mark.parametrize("text", ["(Ma'arif)"]) +def test_ms_tokenizer_splits_no_special(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 3 + + +@pytest.mark.parametrize("text", ["Ma'arif"]) +def test_ms_tokenizer_splits_no_punct(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 1 + + +@pytest.mark.parametrize("text", ["(Ma'arif"]) +def test_ms_tokenizer_splits_prefix_punct(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 2 + + +@pytest.mark.parametrize("text", ["Ma'arif)"]) +def test_ms_tokenizer_splits_suffix_punct(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 2 + + +@pytest.mark.parametrize("text", ["(Ma'arif)"]) +def test_ms_tokenizer_splits_even_wrap(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 3 + + +@pytest.mark.parametrize("text", ["(Ma'arif?)"]) +def test_tokenizer_splits_uneven_wrap(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 4 + + +@pytest.mark.parametrize("text,length", [("S.Kom.", 1), ("SKom.", 2), ("(S.Kom.", 2)]) +def test_ms_tokenizer_splits_prefix_interact(id_tokenizer, text, length): + tokens = id_tokenizer(text) + assert len(tokens) == length + + +@pytest.mark.parametrize("text", ["S.Kom.)"]) +def test_ms_tokenizer_splits_suffix_interact(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 2 + + +@pytest.mark.parametrize("text", ["(S.Kom.)"]) +def test_ms_tokenizer_splits_even_wrap_interact(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 3 + + +@pytest.mark.parametrize("text", ["(S.Kom.?)"]) +def test_ms_tokenizer_splits_uneven_wrap_interact(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 4 + + +@pytest.mark.parametrize( + "text,length", + [("kerana", 1), ("Mahathir-Anwar", 3), ("Tun Dr. Ismail-Abdul Rahman", 6)], +) +def test_my_tokenizer_splits_hyphens(ms_tokenizer, text, length): + tokens = ms_tokenizer(text) + assert len(tokens) == length + + +@pytest.mark.parametrize("text", ["0.1-13.5", "0.0-0.1", "103.27-300"]) +def test_ms_tokenizer_splits_numeric_range(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 3 + + +@pytest.mark.parametrize("text", ["ini.Sani", "Halo.Malaysia"]) +def test_ms_tokenizer_splits_period_infix(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 3 + + +@pytest.mark.parametrize("text", ["Halo,Malaysia", "satu,dua"]) +def test_ms_tokenizer_splits_comma_infix(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 3 + assert tokens[0].text == text.split(",")[0] + assert tokens[1].text == "," + assert tokens[2].text == text.split(",")[1] + + +@pytest.mark.parametrize("text", ["halo...Malaysia", "dia...pergi"]) +def test_ms_tokenizer_splits_ellipsis_infix(id_tokenizer, text): + tokens = id_tokenizer(text) + assert len(tokens) == 3 + + +def test_ms_tokenizer_splits_double_hyphen_infix(id_tokenizer): + tokens = id_tokenizer("Arsene Wenger--pengurus Arsenal--mengadakan sidang media.") + assert len(tokens) == 10 + assert tokens[0].text == "Arsene" + assert tokens[1].text == "Wenger" + assert tokens[2].text == "--" + assert tokens[3].text == "pengurus" + assert tokens[4].text == "Arsenal" + assert tokens[5].text == "--" + assert tokens[6].text == "mengadakan" + assert tokens[7].text == "sidang" + assert tokens[8].text == "media" + assert tokens[9].text == "." diff --git a/spacy/tests/lang/ms/test_text.py b/spacy/tests/lang/ms/test_text.py new file mode 100644 index 000000000..d6cd169ce --- /dev/null +++ b/spacy/tests/lang/ms/test_text.py @@ -0,0 +1,8 @@ +import pytest +from spacy.lang.ms.lex_attrs import like_num + + +@pytest.mark.parametrize("word", ["sebelas"]) +def test_ms_lex_attrs_capitals(word): + assert like_num(word) + assert like_num(word.upper()) diff --git a/spacy/tests/parser/test_ner.py b/spacy/tests/parser/test_ner.py index 030182a63..7198859b3 100644 --- a/spacy/tests/parser/test_ner.py +++ b/spacy/tests/parser/test_ner.py @@ -728,9 +728,9 @@ def test_neg_annotation(neg_key): ner.add_label("ORG") example = Example.from_dict(neg_doc, {"entities": [(7, 17, "PERSON")]}) example.reference.spans[neg_key] = [ - Span(neg_doc, 2, 4, "ORG"), - Span(neg_doc, 2, 3, "PERSON"), - Span(neg_doc, 1, 4, "PERSON"), + Span(example.reference, 2, 4, "ORG"), + Span(example.reference, 2, 3, "PERSON"), + Span(example.reference, 1, 4, "PERSON"), ] optimizer = nlp.initialize() @@ -755,7 +755,7 @@ def test_neg_annotation_conflict(neg_key): ner.add_label("PERSON") ner.add_label("LOC") example = Example.from_dict(neg_doc, {"entities": [(7, 17, "PERSON")]}) - example.reference.spans[neg_key] = [Span(neg_doc, 2, 4, "PERSON")] + example.reference.spans[neg_key] = [Span(example.reference, 2, 4, "PERSON")] assert len(example.reference.ents) == 1 assert example.reference.ents[0].text == "Shaka Khan" assert example.reference.ents[0].label_ == "PERSON" @@ -788,7 +788,7 @@ def test_beam_valid_parse(neg_key): doc = Doc(nlp.vocab, words=tokens) example = Example.from_dict(doc, {"ner": iob}) - neg_span = Span(doc, 50, 53, "ORG") + neg_span = Span(example.reference, 50, 53, "ORG") example.reference.spans[neg_key] = [neg_span] optimizer = nlp.initialize() diff --git a/spacy/tests/serialize/test_resource_warning.py b/spacy/tests/serialize/test_resource_warning.py index 38701c6d9..befd05635 100644 --- a/spacy/tests/serialize/test_resource_warning.py +++ b/spacy/tests/serialize/test_resource_warning.py @@ -72,7 +72,7 @@ def entity_linker(): def create_kb(vocab): kb = InMemoryLookupKB(vocab, entity_vector_length=1) - kb.add_entity("test", 0.0, zeros((1, 1), dtype="f")) + kb.add_entity("test", 0.0, zeros((1,), dtype="f")) return kb entity_linker = nlp.add_pipe("entity_linker") diff --git a/spacy/tests/test_cli.py b/spacy/tests/test_cli.py index 1fdf059b3..351e6bf11 100644 --- a/spacy/tests/test_cli.py +++ b/spacy/tests/test_cli.py @@ -12,6 +12,7 @@ import srsly from click import NoSuchOption from packaging.specifiers import SpecifierSet from thinc.api import Config, ConfigValidationError +from spacy.tokens import DocBin from spacy import about from spacy.cli import info @@ -27,6 +28,7 @@ from spacy.cli.debug_data import _get_span_characteristics from spacy.cli.debug_data import _print_span_characteristics from spacy.cli.debug_data import _get_spans_length_freq_dist from spacy.cli.download import get_compatibility, get_version +from spacy.cli.evaluate import render_parses from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config from spacy.cli.init_pipeline import _init_labels from spacy.cli.package import get_third_party_dependencies @@ -144,6 +146,70 @@ def test_issue11235(): assert cfg["commands"][0]["script"][0] == f"hello {lang_var}" +@pytest.mark.issue(12566) +@pytest.mark.parametrize( + "factory,output_file", + [("deps", "parses.html"), ("ents", "entities.html"), ("spans", "spans.html")], +) +def test_issue12566(factory: str, output_file: str): + """ + Test if all displaCy types (ents, dep, spans) produce an HTML file + """ + with make_tempdir() as tmp_dir: + # Create sample spaCy file + doc_json = { + "ents": [ + {"end": 54, "label": "nam_adj_country", "start": 44}, + {"end": 83, "label": "nam_liv_person", "start": 69}, + {"end": 100, "label": "nam_pro_title_book", "start": 86}, + ], + "spans": { + "sc": [ + {"end": 54, "kb_id": "", "label": "nam_adj_country", "start": 44}, + {"end": 83, "kb_id": "", "label": "nam_liv_person", "start": 69}, + { + "end": 100, + "kb_id": "", + "label": "nam_pro_title_book", + "start": 86, + }, + ] + }, + "text": "Niedawno czytaΕ‚ em nowΔ… ksiΔ…ΕΌkΔ™ znakomitego szkockiego medioznawcy , " + "Briana McNaira - Cultural Chaos .", + "tokens": [ + # fmt: off + {"id": 0, "start": 0, "end": 8, "tag": "ADV", "pos": "ADV", "morph": "Degree=Pos", "lemma": "niedawno", "dep": "advmod", "head": 1, }, + {"id": 1, "start": 9, "end": 15, "tag": "PRAET", "pos": "VERB", "morph": "Animacy=Hum|Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act", "lemma": "czytaΔ‡", "dep": "ROOT", "head": 1, }, + {"id": 2, "start": 16, "end": 18, "tag": "AGLT", "pos": "NOUN", "morph": "Animacy=Inan|Case=Ins|Gender=Masc|Number=Sing", "lemma": "em", "dep": "iobj", "head": 1, }, + {"id": 3, "start": 19, "end": 23, "tag": "ADJ", "pos": "ADJ", "morph": "Case=Acc|Degree=Pos|Gender=Fem|Number=Sing", "lemma": "nowy", "dep": "amod", "head": 4, }, + {"id": 4, "start": 24, "end": 31, "tag": "SUBST", "pos": "NOUN", "morph": "Case=Acc|Gender=Fem|Number=Sing", "lemma": "ksiΔ…ΕΌka", "dep": "obj", "head": 1, }, + {"id": 5, "start": 32, "end": 43, "tag": "ADJ", "pos": "ADJ", "morph": "Animacy=Nhum|Case=Gen|Degree=Pos|Gender=Masc|Number=Sing", "lemma": "znakomit", "dep": "acl", "head": 4, }, + {"id": 6, "start": 44, "end": 54, "tag": "ADJ", "pos": "ADJ", "morph": "Animacy=Hum|Case=Gen|Degree=Pos|Gender=Masc|Number=Sing", "lemma": "szkockiy", "dep": "amod", "head": 7, }, + {"id": 7, "start": 55, "end": 66, "tag": "SUBST", "pos": "NOUN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "medioznawca", "dep": "iobj", "head": 5, }, + {"id": 8, "start": 67, "end": 68, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Comm", "lemma": ",", "dep": "punct", "head": 9, }, + {"id": 9, "start": 69, "end": 75, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "Brian", "dep": "nmod", "head": 4, }, + {"id": 10, "start": 76, "end": 83, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "McNair", "dep": "flat", "head": 9, }, + {"id": 11, "start": 84, "end": 85, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Dash", "lemma": "-", "dep": "punct", "head": 12, }, + {"id": 12, "start": 86, "end": 94, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Inan|Case=Nom|Gender=Masc|Number=Sing", "lemma": "Cultural", "dep": "conj", "head": 4, }, + {"id": 13, "start": 95, "end": 100, "tag": "SUBST", "pos": "NOUN", "morph": "Animacy=Inan|Case=Nom|Gender=Masc|Number=Sing", "lemma": "Chaos", "dep": "flat", "head": 12, }, + {"id": 14, "start": 101, "end": 102, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Peri", "lemma": ".", "dep": "punct", "head": 1, }, + # fmt: on + ], + } + + # Create a .spacy file + nlp = spacy.blank("pl") + doc = Doc(nlp.vocab).from_json(doc_json) + + # Run the evaluate command and check if the html files exist + render_parses( + docs=[doc], output_path=tmp_dir, model_name="", limit=1, **{factory: True} + ) + + assert (tmp_dir / output_file).is_file() + + def test_cli_info(): nlp = Dutch() nlp.add_pipe("textcat") diff --git a/spacy/tests/test_scorer.py b/spacy/tests/test_scorer.py index dbb47b423..f95c44149 100644 --- a/spacy/tests/test_scorer.py +++ b/spacy/tests/test_scorer.py @@ -115,6 +115,14 @@ def test_tokenization(sented_doc): assert scores["token_r"] == approx(0.33333333) assert scores["token_f"] == 0.4 + # per-component scoring + scorer = Scorer() + scores = scorer.score([example], per_component=True) + assert scores["tokenizer"]["token_acc"] == 0.5 + assert scores["tokenizer"]["token_p"] == 0.5 + assert scores["tokenizer"]["token_r"] == approx(0.33333333) + assert scores["tokenizer"]["token_f"] == 0.4 + def test_sents(sented_doc): scorer = Scorer() @@ -278,6 +286,13 @@ def test_tag_score(tagged_doc): assert results["morph_per_feat"]["Poss"]["f"] == 0.0 assert results["morph_per_feat"]["Number"]["f"] == approx(0.72727272) + # per-component scoring + scorer = Scorer() + results = scorer.score([example], per_component=True) + assert results["tagger"]["tag_acc"] == 0.9 + assert results["morphologizer"]["pos_acc"] == 0.9 + assert results["morphologizer"]["morph_acc"] == approx(0.8) + def test_partial_annotation(en_tokenizer): pred_doc = en_tokenizer("a b c d e") @@ -423,14 +438,14 @@ def test_score_spans(): return doc.spans[span_key] # Predict exactly the same, but overlapping spans will be discarded - pred.spans[key] = spans + pred.spans[key] = gold.spans[key].copy(doc=pred) eg = Example(pred, gold) scores = Scorer.score_spans([eg], attr=key, getter=span_getter) assert scores[f"{key}_p"] == 1.0 assert scores[f"{key}_r"] < 1.0 # Allow overlapping, now both precision and recall should be 100% - pred.spans[key] = spans + pred.spans[key] = gold.spans[key].copy(doc=pred) eg = Example(pred, gold) scores = Scorer.score_spans([eg], attr=key, getter=span_getter, allow_overlap=True) assert scores[f"{key}_p"] == 1.0 diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx index a54b4ad3c..6c196ad78 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -1264,12 +1264,14 @@ cdef class Doc: other.user_span_hooks = dict(self.user_span_hooks) other.length = self.length other.max_length = self.max_length - other.spans = self.spans.copy(doc=other) buff_size = other.max_length + (PADDING*2) assert buff_size > 0 tokens = other.mem.alloc(buff_size, sizeof(TokenC)) memcpy(tokens, self.c - PADDING, buff_size * sizeof(TokenC)) other.c = &tokens[PADDING] + # copy spans after setting tokens so that SpanGroup.copy can verify + # that the start/end offsets are valid + other.spans = self.spans.copy(doc=other) return other def to_disk(self, path, *, exclude=tuple()): diff --git a/spacy/tokens/span.pyi b/spacy/tokens/span.pyi index a92f19e20..b982eb810 100644 --- a/spacy/tokens/span.pyi +++ b/spacy/tokens/span.pyi @@ -1,10 +1,12 @@ -from typing import Callable, Protocol, Iterator, Optional, Union, Tuple, Any, overload -from thinc.types import Floats1d, Ints2d, FloatsXd +from typing import Any, Callable, Iterator, Optional, Protocol, Tuple, Union, overload + +from thinc.types import Floats1d, FloatsXd, Ints2d + +from ..lexeme import Lexeme +from ..vocab import Vocab from .doc import Doc from .token import Token from .underscore import Underscore -from ..lexeme import Lexeme -from ..vocab import Vocab class SpanMethod(Protocol): def __call__(self: Span, *args: Any, **kwargs: Any) -> Any: ... # type: ignore[misc] @@ -51,7 +53,12 @@ class Span: kb_id: Union[str, int] = ..., span_id: Union[str, int] = ..., ) -> None: ... - def __richcmp__(self, other: Span, op: int) -> bool: ... + def __lt__(self, other: Any) -> bool: ... + def __le__(self, other: Any) -> bool: ... + def __eq__(self, other: Any) -> bool: ... + def __ne__(self, other: Any) -> bool: ... + def __gt__(self, other: Any) -> bool: ... + def __ge__(self, other: Any) -> bool: ... def __hash__(self) -> int: ... def __len__(self) -> int: ... def __repr__(self) -> str: ... diff --git a/spacy/tokens/span_group.pyi b/spacy/tokens/span_group.pyi index 0b4aa83aa..d063bb595 100644 --- a/spacy/tokens/span_group.pyi +++ b/spacy/tokens/span_group.pyi @@ -1,4 +1,5 @@ -from typing import Any, Dict, Iterable, Optional +from typing import Any, Dict, Iterable, Iterator, Optional + from .doc import Doc from .span import Span @@ -18,7 +19,7 @@ class SpanGroup: def doc(self) -> Doc: ... @property def has_overlap(self) -> bool: ... - def __iter__(self): ... + def __iter__(self) -> Iterator[Span]: ... 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 608dda283..c748fa256 100644 --- a/spacy/tokens/span_group.pyx +++ b/spacy/tokens/span_group.pyx @@ -52,6 +52,8 @@ cdef class SpanGroup: if len(spans) : self.c.reserve(len(spans)) for span in spans: + if doc is not span.doc: + raise ValueError(Errors.E855.format(obj="span")) self.push_back(span.c) def __repr__(self): @@ -261,11 +263,22 @@ cdef class SpanGroup: """ if doc is None: doc = self.doc + if doc is self.doc: + spans = list(self) + else: + spans = [doc.char_span(span.start_char, span.end_char, label=span.label_, kb_id=span.kb_id, span_id=span.id) for span in self] + for i, span in enumerate(spans): + if span is None: + raise ValueError(Errors.E1052.format(i=i)) + if span.kb_id in self.doc.vocab.strings: + doc.vocab.strings.add(span.kb_id_) + if span.id in span.doc.vocab.strings: + doc.vocab.strings.add(span.id_) return SpanGroup( doc, name=self.name, attrs=deepcopy(self.attrs), - spans=list(self), + spans=spans, ) def _concat( diff --git a/spacy/training/initialize.py b/spacy/training/initialize.py index e90617852..9cf759c55 100644 --- a/spacy/training/initialize.py +++ b/spacy/training/initialize.py @@ -133,10 +133,11 @@ def init_vocab( logger.info("Added vectors: %s", vectors) # warn if source model vectors are not identical sourced_vectors_hashes = nlp.meta.pop("_sourced_vectors_hashes", {}) - vectors_hash = hash(nlp.vocab.vectors.to_bytes(exclude=["strings"])) - for sourced_component, sourced_vectors_hash in sourced_vectors_hashes.items(): - if vectors_hash != sourced_vectors_hash: - warnings.warn(Warnings.W113.format(name=sourced_component)) + if len(sourced_vectors_hashes) > 0: + vectors_hash = hash(nlp.vocab.vectors.to_bytes(exclude=["strings"])) + for sourced_component, sourced_vectors_hash in sourced_vectors_hashes.items(): + if vectors_hash != sourced_vectors_hash: + warnings.warn(Warnings.W113.format(name=sourced_component)) logger.info("Finished initializing nlp object") diff --git a/spacy/ty.py b/spacy/ty.py index 8f2903d78..7e79a3d4d 100644 --- a/spacy/ty.py +++ b/spacy/ty.py @@ -1,11 +1,13 @@ from typing import TYPE_CHECKING from typing import Optional, Any, Iterable, Dict, Callable, Sequence, List + from .compat import Protocol, runtime_checkable from thinc.api import Optimizer, Model if TYPE_CHECKING: from .training import Example + from .language import Language @runtime_checkable @@ -32,7 +34,7 @@ class InitializableComponent(Protocol): def initialize( self, get_examples: Callable[[], Iterable["Example"]], - nlp: Iterable["Example"], + nlp: "Language", **kwargs: Any ): ... diff --git a/website/docs/api/cli.mdx b/website/docs/api/cli.mdx index 323ea2a92..5b4bca1ce 100644 --- a/website/docs/api/cli.mdx +++ b/website/docs/api/cli.mdx @@ -1163,18 +1163,19 @@ skew. To render a sample of dependency parses in a HTML file using the $ python -m spacy benchmark accuracy [model] [data_path] [--output] [--code] [--gold-preproc] [--gpu-id] [--displacy-path] [--displacy-limit] ``` -| Name | Description | -| ----------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| `model` | Pipeline to evaluate. Can be a package or a path to a data directory. ~~str (positional)~~ | -| `data_path` | Location of evaluation data in spaCy's [binary format](/api/data-formats#training). ~~Path (positional)~~ | -| `--output`, `-o` | Output JSON file for metrics. If not set, no metrics will be exported. ~~Optional[Path] \(option)~~ | -| `--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)~~ | -| `--gold-preproc`, `-G` | Use gold preprocessing. ~~bool (flag)~~ | -| `--gpu-id`, `-g` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~ | -| `--displacy-path`, `-dp` | Directory to output rendered parses as HTML. If not set, no visualizations will be generated. ~~Optional[Path] \(option)~~ | -| `--displacy-limit`, `-dl` | Number of parses to generate per file. Defaults to `25`. Keep in mind that a significantly higher number might cause the `.html` files to render slowly. ~~int (option)~~ | -| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | -| **CREATES** | Training results and optional metrics and visualizations. | +| Name | Description | +| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| `model` | Pipeline to evaluate. Can be a package or a path to a data directory. ~~str (positional)~~ | +| `data_path` | Location of evaluation data in spaCy's [binary format](/api/data-formats#training). ~~Path (positional)~~ | +| `--output`, `-o` | Output JSON file for metrics. If not set, no metrics will be exported. ~~Optional[Path] \(option)~~ | +| `--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)~~ | +| `--gold-preproc`, `-G` | Use gold preprocessing. ~~bool (flag)~~ | +| `--gpu-id`, `-g` | GPU to use, if any. Defaults to `-1` for CPU. ~~int (option)~~ | +| `--displacy-path`, `-dp` | Directory to output rendered parses as HTML. If not set, no visualizations will be generated. ~~Optional[Path] \(option)~~ | +| `--displacy-limit`, `-dl` | Number of parses to generate per file. Defaults to `25`. Keep in mind that a significantly higher number might cause the `.html` files to render slowly. ~~int (option)~~ | +| `--per-component`, `-P` 3.6 | Whether to return the scores keyed by component name. Defaults to `False`. ~~bool (flag)~~ | +| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ | +| **CREATES** | Training results and optional metrics and visualizations. | ### speed {id="benchmark-speed", version="3.5", tag="command"} @@ -1220,7 +1221,7 @@ $ python -m spacy apply [model] [data-path] [output-file] [--code] [--text-key] | ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `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)~~ | +| `output-file` | Output `DocBin` path. ~~str (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)~~ | | `--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)~~ | @@ -1640,7 +1641,7 @@ with [`spacy package`](/api/cli#package) and `--build wheel`. For more details, see the spaCy project [integration](/usage/projects#huggingface_hub). ```bash -$ python -m spacy huggingface-hub push [whl_path] [--org] [--msg] [--local-repo] [--verbose] +$ python -m spacy huggingface-hub push [whl_path] [--org] [--msg] [--verbose] ``` > #### Example @@ -1654,6 +1655,5 @@ $ python -m spacy huggingface-hub push [whl_path] [--org] [--msg] [--local-repo] | `whl_path` | The path to the `.whl` file packaged with [`spacy package`](https://spacy.io/api/cli#package). ~~Path(positional)~~ | | `--org`, `-o` | Optional name of organization to which the pipeline should be uploaded. ~~str (option)~~ | | `--msg`, `-m` | Commit message to use for update. Defaults to `"Update spaCy pipeline"`. ~~str (option)~~ | -| `--local-repo`, `-l` | Local path to the model repository (will be created if it doesn't exist). Defaults to `hub` in the current working directory. ~~Path (option)~~ | | `--verbose`, `-V` | Output additional info for debugging, e.g. the full generated hub metadata. ~~bool (flag)~~ | | **UPLOADS** | The pipeline to the hub. | diff --git a/website/docs/api/entitylinker.mdx b/website/docs/api/entitylinker.mdx index d84dd3ca9..21d2e9015 100644 --- a/website/docs/api/entitylinker.mdx +++ b/website/docs/api/entitylinker.mdx @@ -64,7 +64,7 @@ architectures and their arguments and hyperparameters. | `use_gold_ents` | Whether to copy entities from the gold docs or not. Defaults to `True`. If `False`, entities must be set in the training data or by an annotating component in the pipeline. ~~int~~ | | `get_candidates` | Function that generates plausible candidates for a given `Span` object. Defaults to [CandidateGenerator](/api/architectures#CandidateGenerator), a function looking up exact, case-dependent aliases in the KB. ~~Callable[[KnowledgeBase, Span], Iterable[Candidate]]~~ | | `get_candidates_batch` 3.5 | Function that generates plausible candidates for a given batch of `Span` objects. Defaults to [CandidateBatchGenerator](/api/architectures#CandidateBatchGenerator), a function looking up exact, case-dependent aliases in the KB. ~~Callable[[KnowledgeBase, Iterable[Span]], Iterable[Iterable[Candidate]]]~~ | -| `generate_empty_kb` 3.6 | Function that generates an empty `KnowledgeBase` object. Defaults to [`spacy.EmptyKB.v2`](/api/architectures#EmptyKB), which generates an empty [`InMemoryLookupKB`](/api/inmemorylookupkb). ~~Callable[[Vocab, int], KnowledgeBase]~~ | +| `generate_empty_kb` 3.5.1 | Function that generates an empty `KnowledgeBase` object. Defaults to [`spacy.EmptyKB.v2`](/api/architectures#EmptyKB), which generates an empty [`InMemoryLookupKB`](/api/inmemorylookupkb). ~~Callable[[Vocab, int], KnowledgeBase]~~ | | `overwrite` 3.2 | Whether existing annotation is overwritten. Defaults to `True`. ~~bool~~ | | `scorer` 3.2 | The scoring method. Defaults to [`Scorer.score_links`](/api/scorer#score_links). ~~Optional[Callable]~~ | | `threshold` 3.4 | Confidence threshold for entity predictions. The default of `None` implies that all predictions are accepted, otherwise those with a score beneath the treshold are discarded. If there are no predictions with scores above the threshold, the linked entity is `NIL`. ~~Optional[float]~~ | diff --git a/website/docs/api/inmemorylookupkb.mdx b/website/docs/api/inmemorylookupkb.mdx index c24fe78d6..15b1d3bf2 100644 --- a/website/docs/api/inmemorylookupkb.mdx +++ b/website/docs/api/inmemorylookupkb.mdx @@ -292,7 +292,7 @@ Restore the state of the knowledge base from a given directory. Note that the > ```python > from spacy.vocab import Vocab > vocab = Vocab().from_disk("/path/to/vocab") -> kb = FullyImplementedKB(vocab=vocab, entity_vector_length=64) +> kb = InMemoryLookupKB(vocab=vocab, entity_vector_length=64) > kb.from_disk("/path/to/kb") > ``` diff --git a/website/docs/api/language.mdx b/website/docs/api/language.mdx index 93ddd79a2..de23156b9 100644 --- a/website/docs/api/language.mdx +++ b/website/docs/api/language.mdx @@ -382,15 +382,16 @@ objects instead of tuples of `Doc` and `GoldParse` objects. > print(scores) > ``` -| Name | Description | -| --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | -| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ | -| _keyword-only_ | | -| `batch_size` | The batch size to use. ~~Optional[int]~~ | -| `scorer` | Optional [`Scorer`](/api/scorer) to use. If not passed in, a new one will be created. ~~Optional[Scorer]~~ | -| `component_cfg` | Optional dictionary of keyword arguments for components, keyed by component names. Defaults to `None`. ~~Optional[Dict[str, Dict[str, Any]]]~~ | -| `scorer_cfg` | Optional dictionary of keyword arguments for the `Scorer`. Defaults to `None`. ~~Optional[Dict[str, Any]]~~ | -| **RETURNS** | A dictionary of evaluation scores. ~~Dict[str, Union[float, Dict[str, float]]]~~ | +| Name | Description | +| -------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | +| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ | +| _keyword-only_ | | +| `batch_size` | The batch size to use. ~~Optional[int]~~ | +| `scorer` | Optional [`Scorer`](/api/scorer) to use. If not passed in, a new one will be created. ~~Optional[Scorer]~~ | +| `component_cfg` | Optional dictionary of keyword arguments for components, keyed by component names. Defaults to `None`. ~~Optional[Dict[str, Dict[str, Any]]]~~ | +| `scorer_cfg` | Optional dictionary of keyword arguments for the `Scorer`. Defaults to `None`. ~~Optional[Dict[str, Any]]~~ | +| `per_component` 3.6 | Whether to return the scores keyed by component name. Defaults to `False`. ~~bool~~ | +| **RETURNS** | A dictionary of evaluation scores. ~~Dict[str, Union[float, Dict[str, float]]]~~ | ## Language.use_params {id="use_params",tag="contextmanager, method"} diff --git a/website/docs/api/morphology.mdx b/website/docs/api/morphology.mdx index 5d4affafe..018ce2524 100644 --- a/website/docs/api/morphology.mdx +++ b/website/docs/api/morphology.mdx @@ -213,11 +213,11 @@ Retrieve values for a feature by field. > assert morph.get("Feat1") == ["Val1", "Val2"] > ``` -| Name | Description | -| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ | -| `field` | The field to retrieve. ~~str~~ | -| `default` 3.6 | The value to return if the field is not present. If unset or `None`, the default return value is `[]`. ~~Optional[List[str]]~~ | -| **RETURNS** | A list of the individual features. ~~List[str]~~ | +| Name | Description | +| ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ | +| `field` | The field to retrieve. ~~str~~ | +| `default` 3.5.3 | The value to return if the field is not present. If unset or `None`, the default return value is `[]`. ~~Optional[List[str]]~~ | +| **RETURNS** | A list of the individual features. ~~List[str]~~ | ### MorphAnalysis.to_dict {id="morphanalysis-to_dict",tag="method"} diff --git a/website/docs/api/scorer.mdx b/website/docs/api/scorer.mdx index 6f0c95f6f..9bdd0a8f4 100644 --- a/website/docs/api/scorer.mdx +++ b/website/docs/api/scorer.mdx @@ -33,7 +33,7 @@ Create a new `Scorer`. | `default_lang` | The language to use for a default pipeline if `nlp` is not provided. Defaults to `xx`. ~~str~~ | | `default_pipeline` | The pipeline components to use for a default pipeline if `nlp` is not provided. Defaults to `("senter", "tagger", "morphologizer", "parser", "ner", "textcat")`. ~~Iterable[string]~~ | | _keyword-only_ | | -| `\*\*kwargs` | Any additional settings to pass on to the individual scoring methods. ~~Any~~ | +| `**kwargs` | Any additional settings to pass on to the individual scoring methods. ~~Any~~ | ## Scorer.score {id="score",tag="method"} @@ -67,10 +67,12 @@ core pipeline components, the individual score names start with the `Token` or > scores = scorer.score(examples) > ``` -| Name | Description | -| ----------- | ------------------------------------------------------------------------------------------------------------------- | -| `examples` | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ | -| **RETURNS** | A dictionary of scores. ~~Dict[str, Union[float, Dict[str, float]]]~~ | +| Name | Description | +| -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- | +| `examples` | The `Example` objects holding both the predictions and the correct gold-standard annotations. ~~Iterable[Example]~~ | +| _keyword-only_ | | +| `per_component` 3.6 | Whether to return the scores keyed by component name. Defaults to `False`. ~~bool~~ | +| **RETURNS** | A dictionary of scores. ~~Dict[str, Union[float, Dict[str, float]]]~~ | ## Scorer.score_tokenization {id="score_tokenization",tag="staticmethod",version="3"} diff --git a/website/docs/api/top-level.mdx b/website/docs/api/top-level.mdx index 6de1acdf0..64ec342cd 100644 --- a/website/docs/api/top-level.mdx +++ b/website/docs/api/top-level.mdx @@ -469,7 +469,7 @@ factories. | `optimizers` | Registry for functions that create [optimizers](https://thinc.ai/docs/api-optimizers). | | `readers` | Registry for file and data readers, including training and evaluation data readers like [`Corpus`](/api/corpus). | | `schedules` | Registry for functions that create [schedules](https://thinc.ai/docs/api-schedules). | -| `scorers` | Registry for functions that create scoring methods for user with the [`Scorer`](/api/scorer). Scoring methods are called with `Iterable[Example]` and arbitrary `\*\*kwargs` and return scores as `Dict[str, Any]`. | +| `scorers` | Registry for functions that create scoring methods for user with the [`Scorer`](/api/scorer). Scoring methods are called with `Iterable[Example]` and arbitrary `**kwargs` and return scores as `Dict[str, Any]`. | | `tokenizers` | Registry for tokenizer factories. Registered functions should return a callback that receives the `nlp` object and returns a [`Tokenizer`](/api/tokenizer) or a custom callable. | ### spacy-transformers registry {id="registry-transformers"} diff --git a/website/docs/usage/index.mdx b/website/docs/usage/index.mdx index a5b7990d6..4b06178d5 100644 --- a/website/docs/usage/index.mdx +++ b/website/docs/usage/index.mdx @@ -259,6 +259,26 @@ source code and recompiling frequently. $ python setup.py develop ``` +#### Visual Studio Code extension + +![spaCy extension demo](/images/spacy-extension-demo.gif) + +The [spaCy VSCode Extension](https://github.com/explosion/spacy-vscode) provides +additional tooling and features for working with spaCy's config files. Version +1.0.0 includes hover descriptions for registry functions, variables, and section +names within the config as an installable extension. + +1. Install a supported version of Python on your system (`>=3.7`) +2. Install the + [Python Extension for Visual Studio Code](https://code.visualstudio.com/docs/python/python-tutorial) +3. Create a + [virtual python environment](https://docs.python.org/3/library/venv.html) +4. Install all python requirements (`spaCy >= 3.4.0` & `pygls >= 1.0.0`) +5. Install + [spaCy extension for Visual Studio Code](https://marketplace.visualstudio.com/items?itemName=Explosion.spacy-extension) +6. Select your python environment +7. You are ready to work with `.cfg` files in spaCy! + ### Building an executable {id="executable"} The spaCy repository includes a [`Makefile`](%%GITHUB_SPACY/Makefile) that diff --git a/website/docs/usage/visualizers.mdx b/website/docs/usage/visualizers.mdx index c372744de..1ac931753 100644 --- a/website/docs/usage/visualizers.mdx +++ b/website/docs/usage/visualizers.mdx @@ -56,14 +56,19 @@ wrap. So if you come across this problem, especially when using custom labels, you'll have to increase the `distance` setting in the `options` to allow longer arcs. +Moreover, you might need to modify the `offset_x` argument depending on the shape +of your document. Otherwise, the left part of the document may overflow beyond the +container's border. + -| Argument | Description | -| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `compact` | "Compact mode" with square arrows that takes up less space. Defaults to `False`. ~~bool~~ | -| `color` | Text color. Can be provided in any CSS legal format as a string e.g.: `"#00ff00"`, `"rgb(0, 255, 0)"`, `"hsl(120, 100%, 50%)"` and `"green"` all correspond to the color green (without transparency). Defaults to `"#000000"`. ~~str~~ | -| `bg` | Background color. Can be provided in any CSS legal format as a string e.g.: `"#00ff00"`, `"rgb(0, 255, 0)"`, `"hsl(120, 100%, 50%)"` and `"green"` all correspond to the color green (without transparency). Defaults to `"#ffffff"`. ~~str~~ | -| `font` | Font name or font family for all text. Defaults to `"Arial"`. ~~str~~ | +| Argument | Description | +| ---------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `compact` | "Compact mode" with square arrows that takes up less space. Defaults to `False`. ~~bool~~ | +| `color` | Text color. Can be provided in any CSS legal format as a string e.g.: `"#00ff00"`, `"rgb(0, 255, 0)"`, `"hsl(120, 100%, 50%)"` and `"green"` all correspond to the color green (without transparency). Defaults to `"#000000"`. ~~str~~ | +| `bg` | Background color. Can be provided in any CSS legal format as a string e.g.: `"#00ff00"`, `"rgb(0, 255, 0)"`, `"hsl(120, 100%, 50%)"` and `"green"` all correspond to the color green (without transparency). 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. You might need to tweak this setting for long texts. Defaults to `50`. ~~int~~ | For a list of all available options, see the [`displacy` API documentation](/api/top-level#displacy_options). diff --git a/website/meta/languages.json b/website/meta/languages.json index 46c0d3adb..f88d2b7bf 100644 --- a/website/meta/languages.json +++ b/website/meta/languages.json @@ -264,6 +264,11 @@ "code": "mr", "name": "Marathi" }, + { + "code": "ms", + "name": "Malay", + "has_examples": true + }, { "code": "nb", "name": "Norwegian BokmΓ₯l", diff --git a/website/meta/universe.json b/website/meta/universe.json index 4067c4d1e..c2047c97d 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -1,5 +1,72 @@ { "resources": [ + { + "id": "spacy-vscode", + "title": "spaCy Visual Studio Code Extension", + "thumb": "https://raw.githubusercontent.com/explosion/spacy-vscode/main/icon.png", + "slogan": "Work with spaCy's config files in VS Code", + "description": "The spaCy VS Code Extension provides additional tooling and features for working with spaCy's config files. Version 1.0.0 includes hover descriptions for registry functions, variables, and section names within the config as an installable extension.", + "url": "https://marketplace.visualstudio.com/items?itemName=Explosion.spacy-extension", + "github": "explosion/spacy-vscode", + "code_language": "python", + "author": "Explosion", + "author_links": { + "twitter": "@explosion_ai", + "github": "explosion" + }, + "category": ["extension"], + "tags": [] + }, + { + "id": "parsigs", + "title": "parsigs", + "slogan": "Structuring prescriptions text made simple using spaCy", + "description": "Parsigs is an open-source project that aims to extract the relevant dosage information from prescriptions text without compromising the patient's privacy.\n\nNotice you also need to install the model in order to use the package: `pip install https://huggingface.co/royashcenazi/en_parsigs/resolve/main/en_parsigs-any-py3-none-any.whl`", + "github": "royashcenazi/parsigs", + "pip": "parsigs", + "code_language": "python", + "author": "Roy Ashcenazi", + "code_example": [ + "# You'll need to install the trained model, see instructions in the description section", + "from parsigs.parse_sig_api import StructuredSig, SigParser", + "sig_parser = SigParser()", + "", + "sig = 'Take 1 tablet of ibuprofen 200mg 3 times every day for 3 weeks'", + "parsed_sig = sig_parser.parse(sig)" + ], + "author_links": { + "github": "royashcenazi" + }, + "category": ["model", "research", "biomedical"], + "tags": ["sigs", "prescription","pharma"] + }, + { + "id": "latincy", + "title": "LatinCy", + "thumb": "https://raw.githubusercontent.com/diyclassics/la_core_web_lg/main/latincy-logo.png", + "slogan": "Synthetic trained spaCy pipelines for Latin NLP", + "description": "Set of trained general purpose Latin-language 'core' pipelines for use with spaCy. The models are trained on a large amount of available Latin data, including all five of the Latin Universal Dependency treebanks, which have been preprocessed to be compatible with each other.", + "url": "https://huggingface.co/latincy", + "code_example": [ + "# pip install https://huggingface.co/latincy/la_core_web_lg/resolve/main/la_core_web_lg-any-py3-none-any.whl", + "import spacy", + "nlp = spacy.load('la_core_web_lg')", + "doc = nlp('Haec narrantur a poetis de Perseo')", + "", + "print(f'{doc[0].text}, {doc[0].norm_}, {doc[0].lemma_}, {doc[0].pos_}')", + "", + "# > Haec, haec, hic, DET" + ], + "code_language": "python", + "author": "Patrick J. Burns", + "author_links": { + "twitter": "@diyclassics", + "github": "diyclassics", + "website": "https://diyclassics.github.io/" + }, + "category": ["pipeline", "research"], + "tags": ["latin"] + }, { "id": "spacy-wasm", "title": "spacy-wasm", @@ -334,7 +401,7 @@ }, { "id": "spacypdfreader", - "title": "spadypdfreader", + "title": "spacypdfreader", "category": ["pipeline"], "tags": ["PDF"], "slogan": "Easy PDF to text to spaCy text extraction in Python.", @@ -351,7 +418,7 @@ }, "code_example": [ "import spacy", - "from spacypdfreader import pdf_reader", + "from spacypdfreader.spacypdfreader import pdf_reader", "", "nlp = spacy.load('en_core_web_sm')", "doc = pdf_reader('tests/data/test_pdf_01.pdf', nlp)", @@ -2810,6 +2877,58 @@ "tags": ["coreference", "multi-lingual", "cross-lingual", "allennlp"], "spacy_version": 3 }, + { + "id": "adeptaugmentations", + "title": "Adept Augmentations", + "slogan": " A Python library aimed at dissecting and augmenting NER training data for a few-shot scenario.", + "description": "EntitySwapAugmenter takes either a `datasets.Dataset` or a `spacy.tokens.DocBin`. Additionally, it is optional to provide a set of labels. It initially creates a knowledge base of entities belonging to a certain label. When running `augmenter.augment()` for N runs, it then creates N new sentences with random swaps of the original entities with an entity of the same corresponding label from the knowledge base.\n\nFor example, assuming that we have knowledge base for `PERSONS`, `LOCATIONS` and `PRODUCTS`. We can then create additional data for the sentence \"Momofuko Ando created instant noodles in Osaka.\" using `augmenter.augment(N=2)`, resulting in \"David created instant noodles in Madrid.\" or \"Tom created Adept Augmentations in the Netherlands\".", + "github": "argilla-io/adept-augmentations", + "pip": "adept-augmentations", + "thumb": "https://raw.githubusercontent.com/argilla-io/adept-augmentations/main/logo.png", + "code_example": [ + "from adept_augmentations import EntitySwapAugmenter", + "import spacy", + "from spacy.tokens import Doc, DocBin", + "nlp = spacy.blank(\"en\")", + "", + "# Create some example golden data", + "example_data = [", + " (\"Apple is looking at buying U.K. startup for $1 billion\", [(0, 5, \"ORG\"), (27, 31, \"LOC\"), (44, 54, \"MONEY\")]),", + " (\"Microsoft acquires GitHub for $7.5 billion\", [(0, 9, \"ORG\"), (19, 25, \"ORG\"), (30, 42, \"MONEY\")]),", + "]", + "", + "# Create a new DocBin", + "nlp = spacy.blank(\"en\")", + "docs = []", + "for entry in example_data:", + " doc = Doc(nlp.vocab, words=entry[0].split())", + " doc.ents = [doc.char_span(ent[0], ent[1], label=ent[2]) for ent in entry[1]]", + " docs.append(doc)", + "golden_dataset = DocBin(docs=docs)", + "", + "# Augment Data", + "augmented_dataset = EntitySwapAugmenter(golden_dataset).augment(4)", + "for doc in augmented_dataset.get_docs(nlp.vocab):", + " print(doc.text)", + "", + "# GitHub is looking at buying U.K. startup for $ 7.5 billion", + "# Microsoft is looking at buying U.K. startup for $ 1 billion", + "# Microsoft is looking at buying U.K. startup for $ 7.5 billion", + "# GitHub is looking at buying U.K. startup for $ 1 billion", + "# Microsoft acquires Apple for $ 7.5 billion", + "# Apple acquires Microsoft for $ 1 billion", + "# Microsoft acquires Microsoft for $ 7.5 billion", + "# GitHub acquires GitHub for $ 1 billion" + ], + "author": "David Berenstein", + "author_links": { + "github": "davidberenstein1957", + "website": "https://www.linkedin.com/in/david-berenstein-1bab11105/" + }, + "category": ["standalone"], + "tags": ["ner", "few-shot", "augmentation", "datasets", "training"], + "spacy_version": 3 + }, { "id": "blackstone", "title": "Blackstone", @@ -4162,6 +4281,37 @@ }, "category": ["pipeline", "research"], "tags": ["Thai"] + }, + { + "id": "vetiver", + "title": "Vetiver", + "slogan": "Version, share, deploy, and monitor models.", + "description": "The goal of vetiver is to provide fluent tooling to version, deploy, and monitor a trained model. Functions handle creating model objects, versioning models, predicting from a remote API endpoint, deploying Dockerfiles, and more.", + "github": "rstudio/vetiver-python", + "pip": "vetiver", + "code_example": [ + "import spacy", + "from vetiver import VetiverModel, VetiverAPI", + "", + "# If you use this model, you'll need to download it first:", + "# python -m spacy download en_core_web_md", + "nlp = spacy.load('en_core_web_md')", + "# Create deployable model object with your nlp Language object", + "v = VetiverModel(nlp, model_name = 'my_model')", + "# Try out your API endpoint locally", + "VetiverAPI(v).run()" + ], + "code_language": "python", + "url": "https://vetiver.rstudio.com/", + "thumb": "https://raw.githubusercontent.com/rstudio/vetiver-python/main/docs/figures/square-logo.svg", + "author": "Posit, PBC", + "author_links": { + "twitter": "posit_pbc", + "github": "rstudio", + "website": "https://posit.co/" + }, + "category": ["apis", "standalone"], + "tags": ["apis", "deployment"] } ], diff --git a/website/public/images/spacy-extension-demo.gif b/website/public/images/spacy-extension-demo.gif new file mode 100644 index 000000000..a857bbe2d Binary files /dev/null and b/website/public/images/spacy-extension-demo.gif differ