Learn R Programming

exreport (version 0.4.1)

wekaExperiment: Problem: Comparison between several Machine Learning algorithms from the Weka library

Description

A problem containing experimental data obtaining by comparing several instances of Machine Algorithms from the Weka library. The variables are as follows:

Usage

data(wekaExperiment)

Arguments

Format

A data frame with

Details

  • method. Classification algorithms used in the experimen (NaiveBayes, J48, IBk)
  • problem. Problems used as benchmark in the comparison, up to 12.
  • featureSelection. Boolean parameter indicating if the data was preprocessed
  • fold. For each configuration a 10-fold cross validation was performed. This variable is a numeric value ranging from 1 to 10.
  • accuracy. This is a measure of the performance of each algorithm. Representing the percentage of correctly classified instances.
  • trainingTime. A second measure of performance. This one indicates the time in seconds that took the algorithm to build the model.