/trained-models

The classifiers used by TopicAxis

Primary LanguagePythonMIT LicenseMIT

This repository contains the trained scikit-learn models that are used by TopicAxis to perform web page content classification.

class description
CategoryClassifier the classifier that is used by TopicAxis API to classify the contents of a page into the 5 supported categories programming, technology, business, science and politics
KeywordSelectionClassifier the classifier that is used by the newsmanager service to select which extracted keywords are usable and which are just noise