#2652 closed defect (done)

Scaling of variable values is missing for k-nearest neighbors models

Reported by: gkronber Owned by: gkronber
Priority: medium Milestone: HeuristicLab 3.3.15
Component: Algorithms.DataAnalysis Version: 3.3.14
Keywords: Cc:

Description (last modified by gkronber)

Input variables are not scaled and it is not possible to specify different weigths for different features explicitly.

Scaling should be added (same scaling factors for training/test) and an optional parameter for feature weights should be added.

Change History (7)

comment:1 Changed 18 months ago by gkronber

  • Description modified (diff)
  • Summary changed from Scaling of variable values is inconsistent for k-nearest neighbors models to Scaling of variable values is missing for k-nearest neighbors models

comment:2 Changed 18 months ago by gkronber

r14235: added scaling and optional specification of feature-weights for kNN

comment:3 Changed 18 months ago by gkronber

  • Status changed from new to accepted

comment:4 Changed 18 months ago by gkronber

  • Owner changed from gkronber to mkommend
  • Status changed from accepted to reviewing

comment:5 Changed 16 months ago by mkommend

  • Owner changed from mkommend to gkronber
  • Status changed from reviewing to readytorelease

Reviewed and tested r14235 (could not test backwards compatibility). Everything looks good.

comment:6 Changed 16 months ago by gkronber

r14308: merged r14235 from trunk to stable

comment:7 Changed 16 months ago by gkronber

  • Resolution set to done
  • Status changed from readytorelease to closed
Note: See TracTickets for help on using tickets.