Skip to content

brothertook/vowpal-wabbit-data

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Simple utility class for parsing and vectorizing vowpal wabbit data in python.

Vowpal wabbit format has a few very nice properties:
  * handles text and non-text very naturally
  * groups features by namespace
  * stores meta data, like importance weight and tags

This class tries to maintain fidelity for these properties and in addition:
  * allows for easy slicing and dicing of the data by leveraging pandas
  * supports direct extraction of large, sparse feature matrices grouped by namespace 
  * support simple feature pruning
  * pass-through processing of text using scipy text analyzers

To see it in action, type "python example.py".



About

Python code for working with vowpal wabbit data

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%