Google Git
Sign in
apache / predictionio-template-text-classifier / b24325a39b396d73c4b99aa300ec49848df4d33e
commitb24325a39b396d73c4b99aa300ec49848df4d33e[log] [tgz]
authorDonald Szeto <donald@apache.org>Thu May 04 11:24:55 2017 -0700
committerDonald Szeto <donald@apache.org>Thu May 04 11:24:55 2017 -0700
tree6a290cb21d8bd2c78d89b19f02ed174b1109d46e
parent6b89e6e5eeabde5916b5a1d29e70aa27a498fefe [diff]
6.0 release
10 files changed
tree: 6a290cb21d8bd2c78d89b19f02ed174b1109d46e
  1. data/
  2. project/
  3. src/
  4. .gitignore
  5. build.sbt
  6. engine.json
  7. README.md
  8. template.json
README.md

Text Classification Engine

Look at the following tutorial for a Quick Start guide and implementation details.

Release Information

Version 6.0

  • Use Apache Lucene as tokenizer
  • Add stopwords filter
  • Rename Scala package name
  • Update SBT version

Version 5.0 First Apache Version

  • Major changes to namespace to reflect donation to the Apache Software Foundation.
  • Build changes to support modified Apache build mechanism

Version 4.0

Re-structure and design preparator and algo. less memory usage and run time is faster. Move BIDMach, VW & SPPMI algo changes to bidmach branch temporarily.

Version 3.1

Fix DataSource to read “content”, “e-mail”, and use label “spam” for tutorial data. Fix engine.json for default algorithm setting.

Version 2.2

Modified PreparedData to use MLLib hashing and tf-idf implementations.

Version 2.1

Fixed dot product implementation in the predict methods to work with batch predict method for evaluation.

Version 2.0

Included three different data sets: e-mail spam, 20 newsgroups, and the rotten tomatoes semantic analysis set. Includes Multinomial Logistic Regression algorithm for text classification.

Version 1.2

Fixed import script bug occuring with Python 2.

Version 1.1 Changes

Changed data import Python script to pull straight from the 20 newsgroups page.