spark-RELIEFFC-fselection (homepage)

Distributed version of RELIEF-F algorithm for Apache Spark.

@sramirez / (0)

The present algorithm (called BELIEF) implements Feature Weighting (FW) on Spark for its application on Big Data problems. This repository contains an improved implementation of RELIEF-F algorithm [1], which has been extended with a cheap but effective feature redundancy elimination technique. BELIEF leverages distance computations computed in prior steps to estimate inter-feature redundancy relationships at virtually no cost. BELIEF is also highly scalable to different sample sizes, from hundreds of samples to thousands.

Tags (No tags yet, login to add one. )

How to

Include this package in your Spark Applications using:

spark-shell, pyspark, or spark-submit

> $SPARK_HOME/bin/spark-shell --packages sramirez:spark-RELIEFFC-fselection:0.5.0


If you use the sbt-spark-package plugin, in your sbt build file, add:

spDependencies += "sramirez/spark-RELIEFFC-fselection:0.5.0"


resolvers += "Spark Packages Repo" at ""

libraryDependencies += "sramirez" % "spark-RELIEFFC-fselection" % "0.5.0"


In your pom.xml, add:
  <!-- list of dependencies -->
  <!-- list of other repositories -->


Version: 0.5.0 ( 01a74b | zip | jar ) / Date: 2018-04-09 / License: Apache-2.0 / Scala version: 2.11