What is malibu?

 

malibu is an open source, portable machine learning workbench written in C++. This collection of learning algorithms focuses on supervised learning problems. It includes both third-party and native implementations covering a number of classification algorithms and wrapper methods. malibu also encompasses the most complete set of validation algorithms, metrics, tests and graphs. The sum total is tied together with an experimental hypertext graphical user interface (hGUI).

 

Features

  • hypertext (HTML) graphical user interface
  • Validation algorithms (Cross-, Holdout-, progressive-validation, ...)
  • Evaluation methods (metrics, plots)
  • Dataset Input/Output (many formats including arff, csv)
  • Dataset Manipulation (normalization, discreetization)
  • Standard Classifiers (SVM, C4.5, KNN, AdaBoost)
  • Wrappers (Extending Classification to other Problems)

Hypertext Interface

 

This hypertext (HTML) graphical user interface integrates learning algorithm controls with complete user documentation. The user controls comprise a configuration editor with extensive documenation on each algorithm and the corresponding set of parameters.