Permalink
Switch branches/tags
Commits on Feb 8, 2018
  1. partial dependence plot fix and test for binary classification (#2153)

    zmjones authored and pat-s committed Feb 8, 2018
    found the issue while updating the tutorial, added two tests that
    would have caught the tutorial bug and another one that could have
    occured
Commits on Jan 30, 2018
  1. bugfix and new tests for generatePartialDependenceData (#2148)

    zmjones authored and larskotthoff committed Jan 30, 2018
    jacobian estimation bug which was hidden in tests because the
    multiclass tests where the jacobian was estimated use the iris data
    where the number of classes matched the n[1] arg
    
    tests are added that would have caught it and n[1] was changed to
    equal 4 as well as the actual bug being fixed
  2. move mmpf to suggests (#2145)

    zmjones authored and larskotthoff committed Jan 30, 2018
Commits on Jan 25, 2018
  1. mmpf integration in generatePartialDependenceData (#2041)

    zmjones authored and larskotthoff committed Jan 25, 2018
    - speed improvements from using mmpf package and rewrite of generate
       function
     - remove centering
     - new functions for derivative estimationa
     - remove functional anova
Commits on Mar 29, 2017
  1. add permutation importance reference (#1747)

    zmjones authored and berndbischl committed Mar 29, 2017
    closes #1712
Commits on Mar 10, 2017
  1. Ensembles parallel (#1116)

    zmjones authored and jakob-r committed Mar 10, 2017
    * parallel ensemble training
    
     - skipped stacking due to incoming refactoring
     - skipped prediction (left in branch) due to proposed
       parallelization of all prediction functions
    
    * add description to variables
    
    * remove unnecessary variables
    
    * cleanup passed variables for MulticlassWrapper
    
    * cleanup passed variables for MultilabelBinaryRelevanceWrapper
    
    * add missing bracket
    
    * this solved the problem; do not really now why it appeared now, but it is solved. :)
    
    * wrongly named variables
    
    * remove unused variables
    
    * models have to be named for multilabelBinaryRelevanceWrapper
    
    * parallelize predictions
    
    * revert parallel predictions
    
    * add parallelization doc
    
    * fix indentations
    
    * skip on viper api down
    
    * fix brackets
    
    * typo
    
    * more typos
    
    * add rd file [ci-skip]
    
    * Update CostSensRegrWrapper.R
    
    * Update parallelization.R
Commits on Mar 6, 2017
  1. regr.randomForest: refactored se-estimation code, improved docs and d…

    zmjones authored and berndbischl committed Mar 6, 2017
    …efault is now se.method = "Jackknife".
Commits on Oct 15, 2016
  1. rewrite of generateFeatureGrid and better tests (#1291)

    zmjones authored and larskotthoff committed Oct 15, 2016
    - better handling of factors and ordered factors
     - test resample = "none" and "subsample" (not bootstrap)
     - test range match (for resample = "none") and factor level preservation
Commits on Sep 14, 2016
  1. fixes for issue #63 in the tutorial (#1243)

    zmjones authored and larskotthoff committed Sep 14, 2016
    - incorrect jacobian function in doPartialDerivativeIteratoin
     - improper fun/fun.wrapper (for weights use)
     - test added based on tutorial fail
     - simplified code a bit
Commits on Sep 12, 2016
  1. remove weight.fun in place of expanded fun in generatePartialDependen…

    zmjones authored and larskotthoff committed Sep 12, 2016
    …ce (#1235)
    
    * remove weight.fun in place of expanded fun in generatePartialDependence
    
     - internal wrapper for fun arg to allow passing of internal
       newdata (prediction grid) and data (training data from input arg)
       which allows computation of weights in fun instead of via an extra
       step using another arg, weight.fun (now removed)
    
    * fix typo
Commits on Aug 30, 2016
Commits on Aug 29, 2016
  1. require weight.fun to be vectorized (#1206)

    zmjones authored and larskotthoff committed Aug 29, 2016
    accept a data.frame for x arg to weight.fun in
    generatePartialDependenceData and generateFunctionalANOVAData which
    allows the use of faster vectorized weighting functions. for
    nonvectorized operations users can write a loop or use apply. also now
    checking that weights are nonnegative.
  2. fix for #55 in tutorial (#1205)

    zmjones authored and berndbischl committed Aug 29, 2016
Commits on Aug 26, 2016
  1. add weight fun arg to generatePartialDependenceData and generateFunct…

    zmjones authored and larskotthoff committed Aug 26, 2016
    …ionalANOVAData (#1194)
    
    for use with methods to detect regions of extrapolation
Commits on Aug 24, 2016
Commits on Aug 23, 2016
Commits on Aug 18, 2016
Commits on Aug 17, 2016
Commits on Aug 16, 2016
  1. fix for #1141 (#1159)

    zmjones authored and larskotthoff committed Aug 16, 2016
    use significant digits for numeric type facet variables in plotPartialDependence
  2. fixes #922 (#1160)

    zmjones authored and larskotthoff committed Aug 16, 2016
    adds support for classification tile plots in plotPartialDependence
  3. adds measures arg to plotThreshVsPerf (#1157)

    zmjones authored and larskotthoff committed Aug 16, 2016
    should fix #1061
Commits on Aug 12, 2016
  1. fix for FeatureImportance print method (#1135)

    zmjones authored and larskotthoff committed Aug 12, 2016
    * fix for FeatureImportance print method
    
     - the get function returns na and breaks the measure field in the print method
    
    * Update generateFeatureImportance.R
    
    * Update generateFeatureImportance.R
  2. move generateFeatureGrid to utils (#1134)

    zmjones authored and larskotthoff committed Aug 12, 2016
    - can be used in places other than generatePartialDependenceData
Commits on Aug 11, 2016
  1. new fun generateFeatureImportanceData (#1112)

    zmjones authored and larskotthoff committed Aug 11, 2016
    - new generic feature importance method not for use as a filter
     - adds local importance computation
     - refactors permutation.importance filter to use this new code
Commits on Aug 10, 2016
  1. move all but paramhelpers to imports (#1096)

    zmjones authored and mllg committed Aug 10, 2016
    - move all imports statements to zzz.R
     - remove stri_paste from glmboost learner notes
Commits on Jul 22, 2016
  1. add functional anova (#917)

    zmjones authored and larskotthoff committed Jul 22, 2016
Commits on Jul 8, 2016
  1. fix for issue #996 (#997)

    zmjones authored and larskotthoff committed Jul 8, 2016
  2. fix for issue #994 (#998)

    zmjones authored and larskotthoff committed Jul 8, 2016
Commits on Jul 6, 2016
Commits on Jun 19, 2016
Commits on Jun 3, 2016
Commits on May 30, 2016