Opened 8 years ago
Closed 8 years ago
#2601 closed defect (done)
ClassificationPerformanceMeasures are not recalculated when the data changes
| Reported by: | mkommend | Owned by: | mkommend |
|---|---|---|---|
| Priority: | medium | Milestone: | HeuristicLab 3.3.14 |
| Component: | Problems.DataAnalysis | Version: | 3.3.13 |
| Keywords: | Cc: |
Description
After the data of a classification solution is changed all classification results have to be recalculated. This is the case for the standard performance measures (accuracy, ...), but the classification performance measures depending on the positive class are only updated when there was no error during their calculation.
When new data is loaded all available samples belong to the test partition, hence the performance measures for the training partition cannot be calculated and are not reset, displaying the old, out-dated values.
Change History (6)
comment:1 Changed 8 years ago by mkommend
- Status changed from new to accepted
comment:2 Changed 8 years ago by mkommend
comment:3 Changed 8 years ago by mkommend
- Owner changed from mkommend to gkronber
- Status changed from accepted to reviewing
comment:4 Changed 8 years ago by gkronber
Reviewed r13801. Thanks
comment:5 Changed 8 years ago by gkronber
- Owner changed from gkronber to mkommend
- Status changed from reviewing to readytorelease
comment:6 Changed 8 years ago by mkommend
- Resolution set to done
- Status changed from readytorelease to closed
Note: See
TracTickets for help on using
tickets.
r13801: Reset classification performance measures to double.NaN before calculating the new ones.