Weka

Weka (which stands for Waikato Environment for Knowledge Analysis) is a software package that contains a collection of tools and algorithms for data analysis and predictive modelling.

Introduction

This document aims at introducing the “supervised machine learning” paradigm building on the Weka machine learning framework and some application examples that illustrate its main functionality.

Instalation

In Linux, download the software .zip file and extract it, and then run ./weka.sh in the extracted directory.

Usage

The graphical user interface is divided in different menus:

• Explorer is used to explore datasets, ML algorithms and analyze results
• Experimenter is used to design experiments for performance and comparison evaluations
• KnowledgeFlow is an advanced Explorer application to graphically design ML pipelines
• Workbench conbines the functionality of the explorer and the experimenter into a single GUI
• Simple GUI is a command-line interface to access ML algorithms.