Timeline
08/12/16:
- 14:20 Changeset [14254] by
-
removed logging
- 13:30 Changeset [14253] by
-
bugfixing (memory leaks)
- 09:15 Changeset [14252] by
-
#2615:
added IDisposable to classes with Dispose()-Method
08/10/16:
- 20:10 Changeset [14251] by
-
- extended non-linear regression to work with factors
- fixed bugs in constants optimizer and tree interpreter
- improved simplification of factor variables
- added support for factors to ERC view
- added support for factors to solution comparison view
- activated view for all factors
- 12:37 Ticket #2657 (Possibility to do multiple random restarts for non-linear regression ...) created by
- 11:43 Ticket #2656 (Terms should be ordered by impact after simplification of symbolic ...) created by
- 07:18 Documentation/DevelopmentCenter/IntegrateHeuristicLab edited by
- (diff)
08/09/16:
- 16:26 Changeset [14250] by
-
#2651: removed workaround, added application base directory
- 15:34 Changeset [14249] by
-
#2650 added new symbol FactorVariable (renamed previous symbol to BinaryFactorVariable)
Work in progress.
- 15:18 Changeset [14248] by
-
#2650: added support for factor variables to target variation view together with Philipp
- 13:49 Changeset [14247] by
-
- partially reverted builder testsettings
- added example on how to use native callbacks (depth-first-search and bfs)
- 10:47 Changeset [14246] by
-
#2651: updated test settings (deployment items)
08/08/16:
- 23:36 Changeset [14245] by
-
#2651: worked on igraph integration
- 20:48 Changeset [14244] by
-
#2651: worked on igraph integration, additional layout algorithms, density, page rank
- added unit tests
- 13:00 Changeset [14243] by
-
#2650: renamed FactorVariable -> BinaryFactorVariable
- 11:39 Changeset [14242] by
-
#2650: added support for factor variables to OneR algorithm
- 10:22 Changeset [14241] by
-
#2650: added support for factor variables in specific solution comparison view for symbolic classification solutions
08/05/16:
- 18:44 Changeset [14240] by
-
#2650: added support for categorical variables to LDA and MNL (TODO: OneR )
- 17:40 Changeset [14239] by
-
#2650: merged r14234:14236 from trunk to branch
- 17:34 Changeset [14238] by
-
- added weight for FactorVariable (necessary for LR)
- introduced VariableBase and VariableTreeNodeBase and IVariableSymbol
- support for factors in LR
- extended variable impacts in solution view
- fixed ERC view for regression
- support for FactorVariable in simplifier
- improved support for FactorVariable in constants optimizer
- multiple related changes and small fixes
- 14:25 Changeset [14237] by
-
#2650: work in progress..
- 13:42 Ticket #2655 (Symbolic regression variable coefficients are never mutated using an ...) created by
- Bug in the code: […]
- 11:58 Changeset [14236] by
-
#2653: added synchronization in NearestNeighbourModel and made some related changes to GradientBoostedTreesModelSurrogate
- 11:45 Ticket #2654 (Neural network model does not scale input variables) created by
- Also neural network ensemble model
08/04/16:
- 17:09 Changeset [14235] by
-
#2652: added scaling and optional specification of feature-weights for kNN
- 16:42 Changeset [14234] by
-
#2651: initial commit of igraph in ExtLibs
- 16:04 Ticket #2653 (GetEstimatedValues is not thread-safe for k-nearest neighbours model) created by
- 14:28 Ticket #2652 (Scaling of variable values is missing for k-nearest neighbors models) created by
- Input variables are not scaled and it is not possible to specify …
- 11:18 Ticket #2651 (Integrate igraph in HeuristicLab) created by
- "igraph is a collection of network analysis tools with the emphasis on …
08/03/16:
- 18:59 Changeset [14233] by
-
#2650 added to files missed in the last commit
- 18:54 Changeset [14232] by
-
created a feature branch for #2650 (support for categorical variables in symb reg) with a first set of changes
work in progress...
- 18:26 Changeset [14231] by
-
#2635: Add evaluator option to aggregate statistics during evaluation (slower). Improve analyzer.
- 18:10 Ticket #2650 (Support for categorical variables (R factors) for symbolic regression ...) created by
- We frequently encounter regression / classification problems where the …
- 08:55 Changeset [14230] by
-
#2631: minor change
- 08:33 Changeset [14229] by
-
#2371: removed usage of C# 6.0 readonly properties
08/02/16:
- 18:09 Changeset [14228] by
-
#2371: added constructors to allow specification of random seeds for randomly generated regression problem instances (primarily for unit tests)
- 16:21 Changeset [14227] by
-
#2640: moved NSGA-II to category: 'population-based algorithms' and moved random search to category: 'single-solution algorithms'
- 16:16 Changeset [14226] by
-
#2649 adapted OnlineSharpeRatioCalculator and OnlineNormalizedMeanSquaredErrorCalculator to use PopulationVariance instead of Variance (minor difference for vectors with only a few elements)
- 16:05 Ticket #2649 (OnlineNMSECalculator should use population variance instead of sample ...) created by
- Also see #745 and #2628
- 16:03 Changeset [14225] by
-
#745: used NMSE instead of squared Pearson's correlation coeff as results.
08/01/16:
- 15:20 Changeset [14224] by
-
#2647: Removed obsolete comment.
- 11:49 Changeset [14223] by
-
#2647: Fix logical mistake.
- 09:40 Changeset [14222] by
-
#2648: corrected output path
- 09:39 Ticket #2648 (Correct outputpath of sim# 3.0.9) created by
07/29/16:
- 11:10 Changeset [14221] by
-
#2647: Addressed the issue described above by adding the [Storable] attribute to the node parent member, and cloning the swapped subtree during crossover.
