The Experimenter allows users to set up machine learning experiments, run them across multiple machines, and analyze the results. It automates the experimental process, stores performance statistics in ARFF format, and distributes computing loads. As a demonstration, it compares the J48 decision tree method against the OneR baseline on selected datasets. Users first set up the experiment, run it by clicking Start, and then analyze the results on the Analyze tab, which indicates statistically better or worse performers compared to the baseline.

1. The Experimenter

2. Introduction The Experimenter enables you to set up large-scale experiments, start them running, leave them, and come back when they have finished and analyze the performance statistics that have been collected They automate the experimental process The statistics can be stored in ARFF format It allows users to distribute the computing load across multiple machines using Java RMI

3. Introduction

4. Demonstration We will compare the J48 decision tree method with the baseline methods OneR Steps: First click New to start a new experiment Then, on the line below, select the destination for the results Underneath, select the datasets To the right of the datasets, select the algorithms to be tested. Click Add new to get a standard Weka object editor from which you can choose and configure a classifier. Repeat this operation to add the two classifiers

5. Demonstration To run the experiment click on the Run tab and then click on the Start button. The result will be stored on the output file To analyze the two selected classifiers , go to the Analyse tab and click on Experiment The symbol placed beside a result indicates that it is statistically better (v) or worse (*) than the baseline scheme At the bottom of column 2 are counts (x/y/z) of the number of times the scheme was better than (x), the same as (y), or worse than (z) the baseline scheme on the datasets used in the experiment

6. Demonstration

7. Visit more self help tutorials Pick a tutorial of your choice and browse through it at your own pace. The tutorials section is free, self-guiding and will not involve any additional support. Visit us at www.dataminingtools.net