Tags

Tags give the ability to mark specific points in history as being important
  • 1.15.1

    3082c088 · Edit .gitlab-ci.yml ·
    Release: New PP overhaul
    # Changes and Fixes for Better Postprocessing Functionalities
    
    Fixes and changes for new postprocessing (PP) including the following:
    
    * cosmetic changes (legends, coloring, ...)
    * implementation of true function evaluation at global minima (keyword `pp_truef_at_glmins`)
    * implementation of local minima search (keyword `pp_local_minima`)
    * implementation of collecting acquisition points in `acquisitions.dat` file
    * fixing determination of grid size used for plotting the true function (keyword `pp_truef_npts`)
    * avoiding double evaluations for dumping & plotting in PP
    * acquisition function now plotting with default slice at next acquisition point
    * bug fix in plotting of only 0 or 1 iterations
    * enabling more flexible setting of user function for PP
    * corrections of std (vs var) in plotting of model minima predictions
    * added custom scatter functionality for advanced PP with updated tutorial
    * changed CI/CD pipy token tied to yuhzuu (Yuhao Zhang)
  • 1.14.1

    Release: Tutorials updated
    Updated website docs to include new pp tutorials
  • 1.14.0

    Release: New PP overhaul
    # Postprocessing Architecture Refactor
    
    This merge request introduces a comprehensive refactor of BOSS's postprocessing functionality, introducing modular classes that lets our users create custom visualizations while maintaining backward compatibility with the old `PPMain`-based workflow.
    
    ## Changes Overview
    
    ### New Modular Architecture
    
    The postprocessing system has been restructured into three distinct layers:
    
    1. **`PPMain` (High-level orchestrator)** - `boss/pp/pp_main.py`
       * Maintains the user-facing API for automated postprocessing workflows
       * Delegates plot creation to the new `Plotter` class
       * Delegates data dumps to the new `Dumper` class
       * Coordinates generation of all diagnostic outputs and data dumps
       * **No breaking changes to existing user code**
    2. **`Plotter` (Mid-level plotting interface)** - `boss/pp/plotter.py`
       * New high-level plotting interface for interactive and custom visualizations
       * Can be used independently of `PPMain` for greater control
       * Provides convenient methods for common plots: `plot_model()`, `plot_acq_func()`, `plot_acquisitions()`, `plot_convergence()`, `plot_hyperparameters()`, etc.
       * Supports both automated workflows and manual customization
    3. **Graphics primitives (Low-level building blocks)** - `boss/pp/graphics.py` and `boss/pp/elements.py`
       * **Graphics objects** (`Curve`, `Contour`, `Surface`): Create mesh-based visualizations of functions over input spaces
       * **Element objects** (`Acquisitions`, `Minimum`, `NextAcquisition`): Composable overlays that can be added to graphics using the `+=` operator
       * Maximum flexibility for advanced users who need fine-grained control
       * Some groundwork for supporting multi-objective BO has also been done in these classes
    4. `Dumper` - `boss/pp/dumper.py`
       * Handles all writing of results to file.
    
    ### Key Benefits
    
    * **Separation of concerns**: Plotting logic is now cleanly separated from orchestration and data dumping
    * **Reusability**: Graphics and elements can be composed and reused in custom visualizations
    * **Flexibility**: Users can choose the appropriate level of abstraction for their needs:
      * Use `PPMain` for automated, comprehensive postprocessing
      * Use `Plotter` for interactive exploration and standard plots with some customization
      * Use `Graphics` and `Elements` directly for maximum control over visualizations
    * **Backward compatibility**: Existing code using `PPMain` continues to work unchanged
    
    ## Documentation
    
    Comprehensive tutorials demonstrating the new functionality have been added:
    
    * **`doc/tutorials/notebooks/advanced_plotting_part1.ipynb`**: Introduction to the `Plotter` class, covering all plotting methods and common use cases
    * **`doc/tutorials/notebooks/advanced_plotting_part2.ipynb`**: Deep dive into `Graphics` and `Elements` objects for advanced customization
  • 1.13.2

    Release: Multiplicative Cost Function
    # Release notes
    
    ## New features
    * New added multiplicative cost function
    
    ## Bug fixes
    * Updated BOSS documentation for restarts to reflect RST files generation discrepancy when restarting from file vs rst object
  • 1.13.1

    Release: Documentation update
    # Release notes
    
    ## New features
    * RST file now logs multiple acquisition entries per iteration for BOSS runs
    
    ## Bug fixes
    * Updated BOSS documentation. BOSS installation tutorial updated to recommend venv installation and without --user flag. File restart tutorials now correctly describe how the interpts keyword are handled during restarts, i.e all existing datapoints from the restarted .RST file are treated as initpts for the resumes/restarted run.
  • 1.13.0

    d3352f97 · bump version -> 1.13.0 ·
    Release: BOSS 1.13.0
  • 1.11.0

    0278068f · bump version -> 1.11.0 ·
    Release: 1.11.0
  • 1.10.1

    2b3eeb94 · bump version -> 1.10.1 ·
    Release: 1.10.1
  • 1.10.0

    a7dd8c3b · bump version -> 1.10.0 ·
    Release: 1.10.0
  • 1.9.2

    eae23c82 · bump version -> 1.9.2 ·
    Release: 1.9.2
  • 1.8.0

    0c60a1b8 · bump version -> 1.8.0 ·
    Release: 1.8.0
  • 1.7.0

    Release: 1.7.0
    Release 1.7.0
  • 1.6.2

    a812207d · bump version -> 1.6.2 ·
    Release: 1.6.2
    Release 1.6.2
  • 1.6.1

    Release: 1.6.1
    Release 1.6.1
  • 1.6

    03fbe9da · version -> 1.6 ·
    Release: 1.6
    Release 1.6