-
-
Notifications
You must be signed in to change notification settings - Fork 93
Weka
Joaquin Vanschoren edited this page Aug 14, 2017
·
4 revisions
OpenML is integrated in the Weka (Waikato Environment for Knowledge Analysis) Experimenter and the Command Line Interface.
OpenML is available as a weka extension in the package manager:
- Download the latest version (3.7.13 or higher).
- Launch Weka, or start from commandline:
java -jar weka.jar
- If you need more memory (e.g. 1GB), start as follows:
java -Xmx1G -jar weka.jar
- Open the package manager (Under 'Tools')
- Select package OpenmlWeka and click install. Afterwards, restart WEKA.
- From the Tools menu, open the 'OpenML Experimenter'.
You can solve OpenML Tasks in the Weka Experimenter, and automatically upload your experiments to OpenML (or store them locally).
-
From the Tools menu, open the 'OpenML Experimenter'.
- Enter your API key in the top field (log in first). You can also store this in a config file (see below).
- In the 'Tasks' panel, click the 'Add New' button to add new tasks. Insert the task id's as comma-separated values (e.g., '1,2,3,4,5'). Use search to find interesting tasks and click the icon to list the ID's. In the future this search will also be integrated in WEKA.
- Add algorithms in the "Algorithm" panel.
- Go to the "Run" tab, and click on the "Start" button.
- The experiment will be executed and sent to OpenML.org.
- The runs will now appear on OpenML.org. You can follow their progress and check for errors on your profile page under 'Runs'.
<h2 id="weka-start-cli">Quick Start CommandLine Interface</h2>
The Command Line interface is useful for running experiments automatically on a server, without using a GUI.
<ol>
<li>Create a config file called <code>openml.conf</code> in a new directory called <code>.openml</code> in your home dir. It should contain the following line:
<pre>api_key = YOUR_KEY</pre>
</li>
<li>Execute the following command: <pre>java -cp weka.jar openml.experiment.TaskBasedExperiment -T <task_id> -C <classifier_classpath> -- <parameter_settings></pre></li>
<li>For example, the following command will run Weka's J48 algorithm on Task 1: <pre>java -cp OpenWeka.beta.jar openml.experiment.TaskBasedExperiment -T 1 -C weka.classifiers.trees.J48</pre> </li>
<li>The following suffix will set some parameters of this classifier: <pre>-- -C 0.25 -M 2</pre></li>
</ol>
Please report any bugs that you may encounter to <a href="mailto:[email protected]">[email protected]</a>.
Drafts:
Proposals:
Other: