Opened 8 years ago
Closed 8 years ago
#2778 closed defect (done)
Shuffling manipulation in the DataPreprocessing does not work as expected
| Reported by: | mkommend | Owned by: | mkommend |
|---|---|---|---|
| Priority: | high | Milestone: | HeuristicLab 3.3.15 |
| Component: | DataPreprocessing | Version: | 3.3.14 |
| Keywords: | Cc: |
Description (last modified by gkronber)
- Although the option to treat the training / test partition individually is deactivated, rows in none of those partitions are not shuffled, which is rather unexpected.
- Shuffling is implemented by swapping indices from the start until the end that introduces a bias.
For curious readers more information on shuffling can be found on Wikipedia.
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
- Owner changed from mkommend to gkronber
- Status changed from accepted to reviewing
comment:3 Changed 8 years ago by gkronber
r14947: fixed off-by-one error
comment:4 Changed 8 years ago by gkronber
- Owner changed from gkronber to mkommend
- Status changed from reviewing to readytorelease
Reviewed r14886, please release.
comment:5 Changed 8 years ago by gkronber
- Description modified (diff)
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.
r14886: Refactored and corrected shuffling in DataPreprocessing.