HomeSearchSitemapLegalContact Us
 
News

Rapid-I optimizes the constomer support for mobilkom austria: incoming mails are automatically categorized and forwarded.

Read more...
 

New release: Rapid-I released a new version of the leading open-source data mining solution RapidMiner 4.2

Read more...
 

Second year in row, readers of KDnuggets News have picked RapidMiner as the open-source solution they use most.

Read more...
 
Hosted by
SourceForge.net Logo
RapidMiner 4.0 (YALE) Released

New release: on Tuesday, July 31st, 2007, Rapid-I released a new version of the open-source data mining software RapidMiner 4.0 (formerly: YALE).

 

Image

 

Because of legal issues, Rapid-I decided to change the name of YALE. The name RapidMiner was chosen for its fit to the company name Rapid-I and to the naming scheme of the line of products planned by Rapid-I for the future. Only the name changes. Everything else stays the same. RapidMiner / YALE will remain open-source software under GNU GPL and available to end-users free of charge and is also available under a commercial OEM license.

Changes from RapidMiner 4.0beta2 to RapidMiner 4.0

General Improvements:

  • RapidMiner now supports workspaces for different projects. The default workspace must be set during the first start of RapidMiner.
  • Training and test data do no longer need to have exactly the same structure. Changing the order of nominal values often caused problems for past versions.
  • The operator PerformanceEvaluator is now divided into smaller task dependent operators allowing for additional checks.
  • New compatibility checks for prediction models between training and application data.
  • A filter for the New Operator tab is added.
  • Added learning for numerical attributes for rule learners.
  • Improved the visualization for almost all performance criteria.
  • Added 3D visualization of confusion matrix
  • Added automatical (averaged) ROC curve visualization for AUC criterion.
  • New plotter: Deviation.
  • amongst others

Screenshots

New Operators:

  • Performance
  • ClassificationPerformance
  • BinominalClassificationPerformance
  • RegressionPerformance
  • UserBasedPerformance
  • SingleRuleWeighting
  • MPCKMeans

Bugfixes:

This release contains many bugfixes including the removal of unnecessary parameters from RandomForest, name mixing bug for attribute names with different cases, a bug in the Anova and t-test calculation operators, a bug preventing the visualization of cluster model graphs, a bug for discretization operators inside of looping chains, a bug in rule learners preventing greater equal conditions, a bug during the saving of neural network models amongst others.

Links

 
< Prev   Next >