0.9.0

What's Changed

Added

• Class hierarchy for objectives
• AdditiveKernel, LinearKernel, MaternKernel, PeriodicKernel,
  PiecewisePolynomialKernel, PolynomialKernel, ProductKernel, RBFKernel,
  RFFKernel, RQKernel, ScaleKernel classes
• KernelFactory protocol enabling context-dependent construction of kernels
• Preset mechanism for GaussianProcessSurrogate
• hypothesis strategies and roundtrip test for kernels, constraints, objectives,
  priors and acquisition functions
• New acquisition functions: qSR, qNEI, LogEI, qLogEI, qLogNEI
• GammaPrior, HalfCauchyPrior, NormalPrior, HalfNormalPrior, LogNormalPrior
  and SmoothedBoxPrior classes
• Possibility to deserialize classes from optional class name abbreviations
• Basic deserialization tests using different class type specifiers
• Serialization user guide
• Environment variables user guide
• Utility for estimating memory requirements of discrete product search space
• mypy for search space and objectives

Changed

• Reorganized acquisition.py into acquisition subpackage
• Reorganized simulation.py into simulation subpackage
• Reorganized gaussian_process.py into gaussian_process subpackage
• Acquisition functions are now their own objects
• acquisition_function_cls constructor parameter renamed to acquisition_function
• User guide now explains the new objective classes
• Telemetry deactivation warning is only shown to developers
• torch, gpytorch and botorch are lazy-loaded for improved startup time
• If an exception is encountered during simulation, incomplete results are returned
  with a warning instead of passing through the uncaught exception
• Environment variables BAYBE_NUMPY_USE_SINGLE_PRECISION and
  BAYBE_TORCH_USE_SINGLE_PRECISION to enforce single point precision usage

Removed

• model_params attribute from Surrogate base class, GaussianProcessSurrogate and
  CustomONNXSurrogate
• Dependency on requests package

Fixed

• n_task_params now evaluates to 1 if task_idx == 0
• Simulation no longer fails in ignore mode when lookup dataframe contains duplicate
  parameter configurations
• Simulation no longer fails for targets in MATCH mode
• closest_element now works for array-like input of all kinds
• Structuring concrete subclasses no longer requires providing an explicit type field
• _target(s) attributes of Objectives are now de-/serialized without leading
  underscore to support user-friendly serialization strings
• Telemetry does not execute any code if it was disabled
• Running simulations no longer alters the states of the global random number generators

Deprecations

• The former baybe.objective.Objective class has been replaced with
  SingleTargetObjective and DesirabilityObjective
• acquisition_function_cls constructor parameter for BayesianRecommender
• VarUCB and qVarUCB acquisition functions

Expired Deprecations (from 0.6.*)

• BayBE class
• baybe.surrogate module
• baybe.targets.Objective class
• baybe.strategies.Strategy class

Merged Pull Requests

• Emojification by @AdrianSosic in #189
• Lazy load DTypeFloatTorch by @rjavadi in #173
• Fix: n_task_params now evaluates to 1 if task_idx == 0 by @tobiasploetz in #187
• Acquisition package by @AdrianSosic in #190
• Mypy for search spaces by @AdrianSosic in #177
• Lazy load torch in surrogates by @rjavadi in #165
• Objective classes by @AdrianSosic in #188
• Correct simulate_scenarios to simulate_experiment in docs by @brandon-holt in #199
• Acquisition function classes by @AdrianSosic in #191
• Skeleton for kernels by @AVHopp in #196
• Hypothesis for objectives by @AdrianSosic in #197
• Fix lookup bug in simulation by @AdrianSosic in #202
• Hypothesis for constraints by @AdrianSosic in #178
• Drop model_params where unnecessary by @AdrianSosic in #204
• Hotfix for match mode simulation by @AdrianSosic in #208
• Update objective user guide by @AdrianSosic in #201
• Telemetry changes by @Scienfitz in #205
• Use tox-uv by @AdrianSosic in #182
• torch lazy loading by @AdrianSosic in #206
• Create simulation subpackage by @AdrianSosic in #210
• New acquisition functions by @Scienfitz in #203
• Custom kernel priors by @AVHopp in #219
• Serialization user guide by @AdrianSosic in #216
• Refactor surrogates and decorators by @AdrianSosic in #209
• Enable force docs and tag selection by @Scienfitz in #230
• Simplification of doc building script by @AVHopp in #224
• More Priors by @Scienfitz in #225
• Fix telemetry execution by @Scienfitz in #237
• Enable returning incomplete simulation results by @AdrianSosic in #213
• Include custom ScaleKernel by @AVHopp in #221
• Relocate priors by @AdrianSosic in #238
• Enable single point precision via env vars by @Scienfitz in #226
• Refactor GP Surrogates by @AdrianSosic in #235
• Arithmetic kernels by @AdrianSosic in #241
• Ditch requests by @Scienfitz in #240
• Increate hypothesis deadline by @Scienfitz in #245
• Avoid altering RNG states by @AdrianSosic in #239
• User guide for environment variables by @Scienfitz in #227
• Minor README fixes by @AdrianSosic in #242
• Memory estimation utilities by @Scienfitz in #228
• Add more kernels by @Scienfitz in #244
• Release 0.9.0 by @AdrianSosic in #217

New Contributors

• @tobiasploetz made their first contribution in #187
• @brandon-holt made their first contribution in #199

Full Changelog: 0.8.2...0.9.0