Maintenance Release: Different Behavior of Enum Serialization

What's Changed

• sketch of how default kernel will change by @R-M-Lee in #435
• Fix enum serialization problems by @jduerholt in #458
• [Lint] apply ruff format as all safe fixes by @CompRhys in #456

Full Changelog: v0.0.14...v0.0.15

Dataframe serialization, Transfer learning, Active Learning and Maintenance

What's Changed

• Make link to logo an url by @bertiqwerty in #416
• Readme example by @bertiqwerty in #419
• Remove polyfill.io (#417) by @DavidWalz in #420
• Add detergent to api by @bertiqwerty in #421
• remove try-catch from scipy import by @bertiqwerty in #418
• Types for bounds by @jduerholt in #423
• BNH and TNK by @jduerholt in #424
• Add arXiv reference to README by @TobyBoyne in #425
• Interpoint constraints for botorch strategies by @jduerholt in #426
• Feature Scaling in DoE by @jduerholt in #358
• Update CONTRIBUTING.md by @R-M-Lee in #432
• Make feature validation part of the constraints. by @jduerholt in #427
• new benchmark with sum of mvnorm pdfs by @R-M-Lee in #434
• Add default generators by @jduerholt in #431
• Update information on GAUCHE by @jduerholt in #437
• EqalityConstraint --> EqualityConstraint by @jduerholt in #440
• Use weights_only for load by @kit1980 in #429
• Tutorial on Transfer Learning Bayesian Optimisation by @jpfolch in #439
• Active Learning by @jdridder in #361
• Move variance of fixed features check to predictive strategy by @bertiqwerty in #441
• Moving Output Objective by @jduerholt in #442
• Applying linting to notebooks by @CompRhys in #445
• [QOL] Use LogEI by default in the Tutorials and unrelated tests. by @CompRhys in #449
• Linear Interpolation by @jduerholt in #443
• Serialization for Candidates and Experiments Data Frames by @jduerholt in #452

New Contributors

• @kit1980 made their first contribution in #429
• @CompRhys made their first contribution in #445

Full Changelog: v0.0.13...v0.0.14

BNN Surrogates, High dim BO, Logo, fixes

What's Changed

• Remove math.inf from ContinuousInput data model by @jduerholt in #387
• Add generic typing to Constraints by @TobyBoyne in #386
• Initial attempt to incorporate MultiTask GPs by @jpfolch in #353
• fixed wrong link in docu by @niklaswulkow in #391
• add to_candidates for stepwise strategy by @jkleinekorte in #392
• Remove get_features, get_feature_keys, and get_feature from Domain by @jduerholt in #393
• Make surrogates available in the Stepwise Strategy by @jduerholt in #394
• name construction in a method by @bertiqwerty in #395
• Feature type hints by @bertiqwerty in #396
• FractionalFactorialStrategy by @jduerholt in #397
• Fix bug in get_scaler by @jduerholt in #400
• ZDT1 Benchmark Tutorial by @jduerholt in #401
• Implement Priors from "Vanilla Bayesian Optimization Performs Great in High Dimensions" by @jduerholt in #402
• Refactor the fractional factorial strategy by @jduerholt in #403
• duplicates plot by @jduerholt in #404
• FIx warning in Iterative Trimming Module by @jduerholt in #406
• Compatibility fix for latest scipy by @jduerholt in #411
• Code example in README by @TobyBoyne in #410
• Infinite Width BNN Kernel and Surrogate by @jduerholt in #405
• Finally a Logo by @jduerholt in #412
• add icon by @jduerholt in #415
• Logo in docs intro by @R-M-Lee in #413
• add bofire logo to docs by @bertiqwerty in #414

New Contributors

• @jpfolch made their first contribution in #353

Full Changelog: v0.0.12...v0.0.13

Classification surrogates, Entmoot and LinearDeterministicSurrogate

What's Changed

• Classification surrogates by @gmancino in #297
• Automatic Hyperparameter Optimization for Mixed GPs by @jduerholt in #357
• Add Task Feature by @jduerholt in #360
• Refactoring of stepwise strategies and introduction of transforms by @bertiqwerty in #355, #365 and #363
• User guide for surrogates by @niklaswulkow in #370 and #371
• Implement ENTMOOT in Bofire by @TobyBoyne in #278
• Make batch_limit and maxiter configurable by @jduerholt in #380
• LinearDeterministicSurrogate by @jduerholt in #385

New Contributors

• @niklaswulkow made their first contribution in #370
• @TobyBoyne made their first contribution in #278

Full Changelog: v0.0.11...v.0.0.12

LSR-BO and Multiplicative Constraints

What's Changed

• LSR-BO by @jduerholt in #338
• Add mixed tanimoto gp surrogate by @xxEthene in #318
• Refactor random strategy by @jduerholt in #347
• Multilinear constraint by @jduerholt in #348

New Contributors

• @xxEthene made their first contribution in #318

Full Changelog: v0.0.10...v0.0.11

Pydantic 2

What's Changed

• experiments and candidates can be None by @bertiqwerty in #311
• Interpoint Constraints by @jduerholt in #313
• gp output scaler by @simonsung06 in #309
• Botorch 0.9.5 by @jduerholt in #317
• DoE: Fix bug if fixed_experiments contain columns that are not in domain by @dlinzner-bcs in #321
• Seed handling for Sampling by @jduerholt in #323
• batch constraints for DoE and call for interpointEqualityConstraint by @Osburg in #322
• Refactor test suite for data models by @jduerholt in #327
• Tests for base.py by @jduerholt in #329
• Add noise prior by @jkeupp in #326
• Tests for CategoricalInput by @jduerholt in #330
• Compatibility PR for Formulaic 1.0.1 by @jduerholt in #332
• Universal constraint sampler by @Osburg in #328
• pydantic 2 - migration by @bertiqwerty in #279

Full Changelog: v0.0.8...v0.0.10

BoFire for BoTorch 0.9.5

What's Changed

• Interpoint constraints available both as data model and implemented in the PolytopeSampler by @jduerholt in #313
• Configurable output scalers for all surrogates by @simonsung06 in #309

Full Changelog: v0.0.8...v0.0.9

BoFire for BoTorch 0.9.4

What's Changed

• Fix number of experiments condition for zero experiments by @jduerholt in #266
• Smaller model dumps by @jduerholt in #267
• Added outlier detection tutorial by @swagataroy123 in #262
• Add generic benchmark module by @jduerholt in #269
• Add log single-objective ACQFs by @jduerholt in #271
• Bayesian optimization over molecules by @swagataroy123 in #268
• Change random seed behavior by @jduerholt in #276
• Sync the output of surrogate.predict and strategy.predict by @jduerholt in #282
• Fix infeasible cost calculation for categorical inputs by @jduerholt in #281
• Refactor get acquisition in SOBO strategies and adapt to new way of handling constraints by @gmancino in #275
• Feature/experiment validation by @jduerholt in #289
• Implement possibility to run hyperparameter opts in the strategy by @jduerholt in #287
• Refactor the candidates/experiments validators. by @jduerholt in #291
• Add possibility to compute feature importance over the lengthscales in a SingleTaskGPSurrogate by @jduerholt in #293
• Fix for categorical features that are fixed in fully categorical BO by @simonsung06 in #295
• Mapping happens outside of runner by @bertiqwerty in #296
• Add polynomial kernel by @dlinzner-bcs in #298
• 286 add surrogate models that can extrapolate by @dlinzner-bcs in #299
• Iterative branch and bound by @dlinzner-bcs in #302
• Updated rdkit fragment/descriptor list by @simonsung06 in #306
• Allow for max_active=#(variables in constraint) in n_choose_k_constraints_as_bounds() by @Osburg in #304
• Add output_scaler to mlp by @simonsung06 in #305
• Add multi-objective log ACQFs by @jduerholt in #308

New Contributors

• @gmancino made their first contribution in #275

Full Changelog: v0.0.7...v0.0.8

BoFire for BoTorch 0.9.2

This release includes a BoFire version which requires BoTorch 0.9.2. In addition the following things are new:

What's Changed

• relaxing error to a warning by @ufukguenes in #257
• Outlier detection in predictive strategies by @swagataroy123 in #235
• added calibration metric by @swagataroy123 in #253
• CategoricalMolecularFeature by @jduerholt in #260
• Fix for to and from categorical variable encoding by @simonsung06 in #261
• DoE for categorical features by @ufukguenes in #259
• stratified kfold for cv by @simonsung06 in #263
• Make compatible with latest botorch release and main branch by @jduerholt in #265

New Contributors

• @ufukguenes made their first contribution in #257

Full Changelog: v0.0.6...v0.0.7

BoFire for BoTorch 0.9.1

This release includes a BoFire version which is compatible with BoTorch 0.9.1 and therefore requires at least Python 3.9.