New MultiObjectiveEvolutionarySearch package, courtesy of Carlos Martinez Cortes.CS 795/895 Introduction to Data Science Lecture 10 – Introduction to Weka Dr. New MultiObjectiveEvolutionaryFuzz圜lassifier package, courtesy of Carlos Martinez Cortes. Provides an exemplar-based approach to modeling New AnalogicalModeling package, courtesy of Nathan Glenn. Provides text filters for sentiment analysis of tweets New AffectiveTweets package, courtesy of Felipe Bravom. Provides rank correlation metrics, Kendall tau and Spearman rho, for evaluating regression schemes New RankCorrelation package, courtesy of Quan Sun. Can work with either CPU-based or GPU-based native libraries New wekaDeepLearning4j package - provides a MLP classifier built using the DL4J library. RPlugin package updated to support the latest version of MLR. distributedWekaBase now includes the latest version of Ted Dunning's t-digest quantile estimator, bringing a factor of 4 speedup over the old implementation. New implementations in the ensemblesOfNestedDichotomies package. Multi-class FLDA in the discriminantAnalysis package. GUIs now support copying/pasting of array configurations to/from the clipboard. GUIs with result lists now support multi-entry delete. Knowledge Flow now offers an additional executor service that uses a single worker thread steps can, if necessary, declare programatically that they should run in the single-threaded executor. JRip now prunes redundant numeric attribute-value tests from rules. RandomForest now has an option for computing the mean impurity decrease variable importance scores. new RelationNameModifier, SendToPerspective, WriteWekaLog, Job, StorePropertiesInEnvironment, SetPropertiesFromEnvironment, WriteDataToResult and GetDataFromResult steps in Knowledge Flow. Package manager now employs a new class loading mechanism that attempts to avoid third-party library clashes by isolating the third-party libraries in each package. 
Package manager now handles redirects generated by SourceForge.
0 kommentar(er)
