heal-research / HeuristicLab

HeuristicLab - An environment for heuristic and evolutionary optimization
https://dev.heuristiclab.com
GNU General Public License v3.0
39 stars 16 forks source link

Implement measures for analyzing algorithm behavior #1886

Closed HeuristicLab-Trac-Bot closed 9 years ago

HeuristicLab-Trac-Bot commented 12 years ago

Issue migrated from trac ticket # 1886

milestone: HeuristicLab 3.3.x Backlog | component: Analysis | priority: medium | resolution: obsolete

2012-06-29 13:15:07: @Shabbafru created the issue

HeuristicLab-Trac-Bot commented 12 years ago

2012-10-04 16:19:43: @Shabbafru commented


r8739 removed static method calls to similarity calculators

HeuristicLab-Trac-Bot commented 12 years ago

2012-10-11 17:17:58: @Shabbafru commented


r8797 added a comparison factor parameter to the crossover analyzer so that it can be defined what a successful crossover is

HeuristicLab-Trac-Bot commented 12 years ago

2012-10-30 20:47:17: @Shabbafru commented


r8864 added more analyzers for crossover performance

HeuristicLab-Trac-Bot commented 12 years ago

2012-10-31 10:12:18: @Shabbafru commented


r8865 fixed crossover performance operator initialization

HeuristicLab-Trac-Bot commented 12 years ago

2012-11-02 16:22:19: @Shabbafru commented


r8866 further improvements for the crossover performance analyzer

HeuristicLab-Trac-Bot commented 12 years ago

2012-11-04 23:11:19: @Shabbafru commented


r8867 improved mutation analyzer

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-10 17:26:34: @Shabbafru commented


r9020 added an analyzer for unwanted mutation for the TSP

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-12 10:07:43: @Shabbafru commented


r9032 added a crossover analyzer for the QAP

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-12 22:10:31: @Shabbafru commented


r9042 added mutation performance analyzer for the QAP

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-12 23:29:01: @Shabbafru commented


r9044

  • improved unwanted mutation analyzer
  • added test functions crossover performance analyzer
HeuristicLab-Trac-Bot commented 11 years ago

2012-12-13 10:32:03: @Shabbafru commented


r9045 added mutation performance analyzer for test functions

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-13 13:41:53: @Shabbafru commented


r9050 added performance analyzers for the VRP

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-13 16:52:53: @Shabbafru commented


r9053 added a dialog for adding operators as successors to other operators

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-14 11:06:38: @Shabbafru commented


r9054 added an analyzer for comparing the current solution to the rest of the population

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-14 15:13:07: @Shabbafru commented


r9058 also track quality of solutions

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-14 16:03:38: @Shabbafru commented


r9059 track min and max quality values for scaling

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-15 00:00:53: @Shabbafru commented


r9060 cleaned up plugin dependencies

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-17 08:34:15: @Shabbafru commented


r9061 added average of first, last, upper and lower 25% to statistical tabular view

HeuristicLab-Trac-Bot commented 11 years ago

2012-12-21 11:00:59: @Shabbafru commented


r9087 added coloring of the rows in the statistical view

HeuristicLab-Trac-Bot commented 11 years ago

2013-01-03 13:23:51: @Shabbafru commented


r9095 added a project for views

HeuristicLab-Trac-Bot commented 11 years ago

2013-01-13 01:08:23: @Shabbafru commented


r9150 fixed successor configuration and added successful mutation chart

HeuristicLab-Trac-Bot commented 11 years ago

2013-01-24 01:06:57: @Shabbafru commented


r9185 fixed scaling of qualities

HeuristicLab-Trac-Bot commented 11 years ago

2013-01-25 15:05:24: @Shabbafru commented


r9189 fixed unwanted mutations analyzer

HeuristicLab-Trac-Bot commented 11 years ago

2013-01-28 15:18:51: @Shabbafru commented


r9192 RunCollectionStatisticalTabularView now respects RunCollectionFilters

HeuristicLab-Trac-Bot commented 11 years ago

2013-01-31 11:03:58: @Shabbafru commented


r9196

  • fixed a cloning bug
  • fixed forgotten event handler deregistration
  • added a run collection view for analyzing parameter influences
HeuristicLab-Trac-Bot commented 11 years ago

2013-01-31 13:13:23: @Shabbafru commented


r9197 don't do testing if there aren't enough groups

HeuristicLab-Trac-Bot commented 11 years ago

2013-01-31 14:39:49: @Shabbafru commented


r9198 added calculation of the overall parameter influence

HeuristicLab-Trac-Bot commented 11 years ago

2013-02-08 14:17:39: @Shabbafru commented


r9210 added view for displaying result correlations

HeuristicLab-Trac-Bot commented 11 years ago

2013-02-27 21:55:33: @Shabbafru commented


r9252 automatically calculate statistical values for each run

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-13 16:22:08: @Shabbafru commented


r9316 implemented Kruskal-Wallis Test

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-14 16:33:04: @Shabbafru commented


r9317 started working on a statistical testing run collection view

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-18 13:40:58: @Shabbafru commented


r9318 added test for normality and pairwise statistical testing

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-18 15:09:13: @Shabbafru commented


r9319 improved view and added documentation

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-18 19:29:18: @Shabbafru commented


r9320 some more improvements for the statistical testing view

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-21 11:56:00: @Shabbafru commented


r9328

  • fixed a bug in the ResultCorrelationView
  • added sample size determination by estimating means, Cohen's D and Hedges' G
HeuristicLab-Trac-Bot commented 11 years ago

2013-03-21 13:26:45: @Shabbafru commented


r9329 calculate Cohen's D and Hedges' G for pairwise comparison and updated documentation

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-21 16:47:50: @Shabbafru commented


r9330 added a view for sample size determination

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-25 10:29:43: @Shabbafru commented


r9331 added analyzer for selection pressure

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-26 12:09:35: @Shabbafru commented


r9333 improved run collection views

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-28 10:08:56: @Shabbafru commented


r9336 added ttest and sample size determination for the ttest

HeuristicLab-Trac-Bot commented 11 years ago

2013-03-28 14:03:54: @Shabbafru commented


r9337 fixed bugs in TTest

HeuristicLab-Trac-Bot commented 11 years ago

2013-04-02 22:39:34: @Shabbafru commented


r9341 some minor AB fixes

HeuristicLab-Trac-Bot commented 11 years ago

2013-04-11 09:35:04: @Shabbafru commented


r9354 removed views that went into the statistical hypothesis testing branch (#2031)

HeuristicLab-Trac-Bot commented 11 years ago

2013-04-16 00:02:24: @Shabbafru commented


r9361 adapted create experiment dialog so that it can generate random configurations

HeuristicLab-Trac-Bot commented 11 years ago

2013-04-16 16:24:42: @Shabbafru commented


r9364 added repetitions for random parameter configurations

HeuristicLab-Trac-Bot commented 11 years ago

2013-04-19 13:47:58: @Shabbafru commented


r9384 added calculation of selection intensity

HeuristicLab-Trac-Bot commented 11 years ago

2013-04-30 20:35:35: @Shabbafru commented


r9412 added GA with evaluated solutions as a stopping criteria

HeuristicLab-Trac-Bot commented 11 years ago

2013-05-01 20:23:52: @gkronber commented


r9412: I'm not sure it is necessary to add a GA variant with evaluated solutions as stopping criterion (this is almost the same as pop-size * generations)

HeuristicLab-Trac-Bot commented 11 years ago

2013-05-02 09:11:48: @Shabbafru commented


Replying to [comment:98 gkronber]:

r9412: I'm not sure it is necessary to add a GA variant with evaluated solutions as stopping criterion (this is almost the same as pop-size * generations) Yes, that's true, but it makes creating experiments simpler as I can fix the evaluated solutions and just vary the population size. Generations are not varied and are then simply a result. Because I want to define ranges for parameters and then draw random samples it would be more complicated to check if a drawn configuration has the correct amount of evaluated solutions (or only calculated configurations where this is the case).

HeuristicLab-Trac-Bot commented 11 years ago

2013-05-02 13:15:19: @Shabbafru commented


r9418

  • changed duplicate solutions analyzer to also track avg. diversity as the standard diversity analyzer needs too much memory
  • fixed project references of eslGA