Adding spacy-cleaner to the spaCy universe (#11674)

* added spacy-cleaner to the spaCy universe

* Move data to righ section of universe.json

* Cleanup

- fix typo ("replacers")
- spaCy doesn't need to be marked as code
- lemma of "Hello" is lower case

Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com>
This commit is contained in:
Cellan Hall 2022-10-20 12:38:29 +01:00 committed by GitHub
parent bf83f6872a
commit b69d249a22
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -1,5 +1,46 @@
{
"resources": [
{
"id": "spacy-cleaner",
"title": "spacy-cleaner",
"slogan": "Easily clean text with spaCy!",
"description": "**spacy-cleaner** utilises spaCy `Language` models to replace, remove, and \n mutate spaCy tokens. Cleaning actions available are:\n\n* Remove/replace stopwords.\n* Remove/replace punctuation.\n* Remove/replace numbers.\n* Remove/replace emails.\n* Remove/replace URLs.\n* Perform lemmatisation.\n\nSee our [docs](https://ce11an.github.io/spacy-cleaner/) for more information.",
"github": "Ce11an/spacy-cleaner",
"pip": "spacy-cleaner",
"code_example": [
"import spacy",
"import spacy_cleaner",
"from spacy_cleaner.processing import removers, replacers, mutators",
"",
"model = spacy.load(\"en_core_web_sm\")",
"pipeline = spacy_cleaner.Pipeline(",
" model,",
" removers.remove_stopword_token,",
" replacers.replace_punctuation_token,",
" mutators.mutate_lemma_token,",
")",
"",
"texts = [\"Hello, my name is Cellan! I love to swim!\"]",
"",
"pipeline.clean(texts)",
"# ['hello _IS_PUNCT_ Cellan _IS_PUNCT_ love swim _IS_PUNCT_']"
],
"code_language": "python",
"url": "https://ce11an.github.io/spacy-cleaner/",
"image": "https://raw.githubusercontent.com/Ce11an/spacy-cleaner/main/docs/assets/images/spacemen.png",
"author": "Cellan Hall",
"author_links": {
"twitter": "Ce11an",
"github": "Ce11an",
"website": "https://www.linkedin.com/in/cellan-hall/"
},
"category": [
"extension"
],
"tags": [
"text-processing"
]
},
{
"id": "Zshot",
"title": "Zshot",