Opened 12 years ago

Closed 12 years ago

Last modified 10 years ago

#722 closed feature request (done)

IModel should provide a Predict() method to get predicted values for an input vector

Reported by: gkronber Owned by: mkommend
Priority: medium Milestone: HeuristicLab 3.3.0
Component: ZZZ OBSOLETE: Modeling Version: 3.2
Keywords: Cc:

Description

This is necessary for the new model analyzer.

To make this feasible, models generated by GP have to internally keep an ITreeEvaluator.

Change History (16)

comment:1 Changed 12 years ago by gkronber

  • Status changed from new to assigned

comment:2 Changed 12 years ago by gkronber

r2285:

  • renamed HL.Modeling.IModel to HL.Modeling.IAnalyzerModel
  • added interface HL.Modeling.IPredictor and implementations for StructId and SVM
  • these predictors hold all necessary information to predict output values based on inputvalues and are stored into the HL.Modeling database.
  • also: removed parameter PunishmentFactor from GP algorithms (this parameter is internal to TreeEvaluators now).

comment:3 Changed 12 years ago by gkronber

r2290:

  • introduced a variablename to index mapping for SVM models (to make sure we can use the model for prediction in the model analyzer)
  • added support to enable and disable algorithms in the dispatcher and removed DispatcherBase
  • fixed bugs when calculating variable impacts and reading the final model of GP algorithms

comment:4 Changed 12 years ago by gkronber

r2291: deleted DispatcherBase

comment:5 Changed 12 years ago by mkommend

added FunctionTree getter in GP.StructureIdentification.Predictor, which is needed in the ModelAnalyzer r2317

comment:6 follow-up: Changed 12 years ago by gkronber

Applied changes in modeling plugins that are necessary for the new model analyzer with r2327:

  • predictor has properties for the lower and upper limit of the predicted value
  • added views for predictors that show the limits (also added a new view for GeneticProgrammingModel that shows the size and height of the model)
  • Reintroduced TreeEvaluatorInjectors that read a PunishmentFactor and calculate the lower and upper limits for estimated values (limits are set in the tree evaluators)
  • Added operators to create Predictors. Changed modeling algorithms to use the predictors for the calculation of final model qualities and variable impacts (to be compatible with the new model analyzer the predictors use a very large PunishmentFactor)
  • replaced all private implementations of double.IsAlmost and use HL.Commons instead (see #733 r2324)
  • Implemented operator SolutionExtractor and moved BestSolutionStorer from HL.Logging to HL.Modeling (fixes #734)

comment:7 in reply to: ↑ 6 ; follow-ups: Changed 12 years ago by gkronber

Replying to gkronber:

Applied changes in modeling plugins that are necessary for the new model analyzer with r2327:

The full changeset is 2326:2328.

comment:8 in reply to: ↑ 7 Changed 12 years ago by gkronber

The full changeset is r2326:2328.

comment:9 in reply to: ↑ 7 Changed 12 years ago by gkronber

Replying to gkronber: This is a changeset for #728

comment:10 Changed 12 years ago by gkronber

  • Resolution set to fixed
  • Status changed from assigned to closed

comment:11 Changed 12 years ago by mkommend

  • Resolution fixed deleted
  • Status changed from closed to reopened

comment:12 Changed 12 years ago by mkommend

  • Owner changed from gkronber to mkommend
  • Status changed from reopened to new

comment:13 Changed 12 years ago by mkommend

  • Status changed from new to assigned

comment:14 Changed 12 years ago by mkommend

  • Resolution set to fixed
  • Status changed from assigned to closed

added static method in PredictorBuilder to make it useable from the ModelAnalyzer r2332

comment:15 Changed 10 years ago by swagner

  • Milestone changed from Iteration 4 to Current

Milestone Iteration 4 deleted

comment:11 Changed 10 years ago by swagner

  • Milestone changed from Current to HeuristicLab 3.3.0

Milestone Current deleted

Note: See TracTickets for help on using tickets.