Skip to content

Latest commit

 

History

History

README.md

Classifier reference

Feature reference for the classifier gem. Every example here runs against the version in this repository.

The README gives the short tour. These pages give the detail.

Command line

Page Contents
classifier Train, classify, and manage models from the shell
keywords TF-IDF keyword extraction and term scores

Classifiers

Page Use it for
Bayes Fast probabilistic classification. The default choice
Logistic Regression Linear classification with calibrated probabilities
LSI Semantic similarity, search, related documents, and summaries
k-Nearest Neighbors Classification with the nearest examples and their votes

Vectorization

Page Contents
TF-IDF Term weights, n-grams, document frequency filters

Shared behavior

Page Contents
Persistence Save, load, storage backends, and custom backends
Streaming Training on data larger than memory
Configuration Global settings and the native extension

Which classifier

Start with Bayes. It trains in one pass, needs no fit step, and handles most text classification tasks.

  • Choose Logistic Regression when you need a probability per category, and you accept a fit step after training.
  • Choose LSI when you need similarity, search, or related documents, and not only a label.
  • Choose k-Nearest Neighbors when you want to see which examples drove the answer.
  • Choose TF-IDF when you want term weights rather than a category.