newbie
/
Deeplearning
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
44 Commits 1 Branch 0 Tags 498 KiB
Commit Graph

2 Commits

Author SHA1 Message Date
newbieQQ a7e95141d2 feat: add data visualization script for comprehensive analysis 
- Introduced `visualize.py` to generate various visualizations including:
  - Class distribution bar chart
  - Feature distribution histograms (overlaid by class)
  - Feature box plots (for top N features)
  - PCA reduced scatter plot with confidence ellipses
  - t-SNE reduced scatter plot
  - Heatmaps for class means and standard deviations
  - Global feature correlation heatmap
  - Overview of global feature distributions

- Implemented data loading functions to handle multiple file formats and structures.
- Added command-line interface for flexible usage with options for feature limits and PCA/t-SNE toggles.

Co-authored-by: Copilot <copilot@github.com>
 2026-05-14 10:27:32 +08:00
newbieQQ f6f839ebc0 refactor: unify module structure and suppress training warnings 
- Move canonical implementations to Qfunctions layer (divSet.py, loadData.py, saveToXlsx.py)
- Remove duplicate compatibility shims (loaData.py, saveToxlsx.py)
- Remove redundant Qtorch/Functions/ directory
- Add zero_division=0 to sklearn metrics to suppress UndefinedMetricWarning
- Set matplotlib backend to Agg to eliminate Wayland/Qt warnings
- Update all imports to use canonical module paths
 2026-03-29 12:48:41 +08:00