this is the right place to ask, but I'd be more interested to see a scikit-learn-compatible implementation available, perhaps in scikit-learn-contrib more than to see it part of the main package...
On 19 Aug 2017 2:13 am, "Michael Capizzi" <mcapi...@email.arizona.edu> wrote: > Hi all - > > Forgive me if this is the wrong place for posting this question, but I'd > like to inquire about the community's interest in incorporating a new > Transformer into the code base. > > This paper ( https://nlp.stanford.edu/pubs/sidaw12_simple_sentiment.pdf ) > is a "classic" in Natural Language Processing and is often times used as a > very competitive baseline. TL;DR it transforms a traditional count-based > feature space into the conditional probabilities of a `Naive Bayes` > classifier. These transformed features can then be used to train any > linear classifier. The paper focuses on `SVM`. > > The attached notebook has an example of the custom `Transformer` I built > along with a custom `Classifier` to utilize this `Transformer` in a > `multiclass` case (as the feature space transformation differs depending on > the label). > > If there is interest in the community for the inclusion of this > `Transformer` and `Classifier`, I'd happily go through the official process > of a `pull-request`, etc. > > -Michael > > _______________________________________________ > scikit-learn mailing list > scikit-learn@python.org > https://mail.python.org/mailman/listinfo/scikit-learn > >
_______________________________________________ scikit-learn mailing list scikit-learn@python.org https://mail.python.org/mailman/listinfo/scikit-learn