search

Waikato / moa

MOA is an open source framework for Big Data stream mining. It includes a collection of machine learning algorithms (classification, regression, clustering, outlier detection, concept drift detection and recommender systems) and tools for evaluation.
http://moa.cms.waikato.ac.nz/
GNU General Public License v3.0
609 stars 353 forks source link

rxjava observable to stream #161

Closed mbehrisch closed 5 years ago

mbehrisch commented 5 years ago

Hi,

I'm a bit stuck.... I have a range of conceptual, implementation and understanding questions.

  1. [EASY] Where can I find the latest Javadoc?
  2. [A bit history] Why do I see the mix between the yahoo/apache samoa, moa classes, and weka (e.g., InstanceHeader)?? 3) [Impl] Little bit of context: I'm receiving data through a socket.io connection and distribute it directly through a Java rxJava Observable implementation == my stream. As long as I define the InstanceHeader for bootstrapping the algorithms e.g., myOutlierDetector.setModelContext(stream.getHeader()); and use (weka) Instances for the algorithm input I should be fine, right?

Thanks

abifet commented 5 years ago
  1. You can find the javadoc inside the last release.
  2. MOA uses samoa instances now, instead of weka instances as before.
  3. In MOA you need to use samoa instances, not weka instances.