Add Tokenwiser to Projects (#7541)

* Add tokenwiser

* Update universe.json
This commit is contained in:
vincent d warmerdam 2021-04-01 14:39:36 +02:00 committed by GitHub
parent 59c2069eb1
commit 8b3eec6e62
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -231,6 +231,49 @@
"website": "https://koaning.io" "website": "https://koaning.io"
} }
}, },
{
"id": "tokenwiser",
"title": "tokenwiser",
"slogan": "Connect vowpal-wabbit & scikit-learn models to spaCy to run simple classification benchmarks. Comes with many utility functions for spaCy pipelines.",
"github": "koaning/tokenwiser",
"pip": "tokenwiser",
"thumb": "https://koaning.github.io/tokenwiser/token.png",
"image": "https://koaning.github.io/tokenwiser/logo-tokw.png",
"code_example": [
"import spacy",
"",
"from sklearn.pipeline import make_pipeline",
"from sklearn.feature_extraction.text import CountVectorizer",
"from sklearn.linear_model import LogisticRegression",
"",
"from tokenwiser.component import attach_sklearn_categoriser",
"",
"X = [",
" 'i really like this post',",
" 'thanks for that comment',",
" 'i enjoy this friendly forum',",
" 'this is a bad post',",
" 'i dislike this article',",
" 'this is not well written'",
"]",
"",
"y = ['pos', 'pos', 'pos', 'neg', 'neg', 'neg']",
"",
"# Note that we're training a pipeline here via a single-batch `.fit()` method",
"pipe = make_pipeline(CountVectorizer(), LogisticRegression()).fit(X, y)",
"",
"nlp = spacy.load('en_core_web_sm')",
"# This is where we attach our pre-trained model as a pipeline step.",
"attach_sklearn_categoriser(nlp, pipe_name='silly_sentiment', estimator=pipe)"
],
"category": ["pipeline", "training"],
"author": "Vincent D. Warmerdam",
"author_links": {
"twitter": "fishnets88",
"github": "koaning",
"website": "https://koaning.io"
}
},
{ {
"id": "spacy-stanza", "id": "spacy-stanza",
"title": "spacy-stanza", "title": "spacy-stanza",