v5.0.2

What's Changed

• [DOC] minor improvements to README: white background for logo, link table formatting by @fkiraly in #186
• add optuna optional import by @SimonBlanke in #187
• [BUG] fix TSCOptCV integration for metric function input by @fkiraly in #190

Full Changelog: v5.0.1...v5.0.2

v5.0.0

What's Changed

• Bump pytest from 7.4.4 to 8.3.2 by @dependabot[bot] in #84
• add prototype for sklearn integration by @SimonBlanke in #87
• Feature/fix sklearn best params scores by @SimonBlanke in #89
• Bump pytest from 8.3.2 to 8.3.3 by @dependabot[bot] in #91
• [BUG] fix non-use of params in sklearn adapter objective function by @fkiraly in #97
• Bump pytest from 8.3.3 to 8.3.4 by @dependabot[bot] in #98
• Bump scikit-learn from 1.5.2 to 1.6.0 by @dependabot[bot] in #99
• Bump scikit-learn from 1.6.0 to 1.6.1 by @dependabot[bot] in #100
• Bump pytest from 8.3.4 to 8.3.5 by @dependabot[bot] in #104
• Update README.md by @MekongDelta-mind in #109
• ⚡️ Speed up function run_search by 8% by @misrasaurabh1 in #106
• [MNT] max concurrency for CI jobs by @fkiraly in #111
• [MNT] simplify CI specs by @fkiraly in #114
• [DOC] complete docstring for Hyperactive.search_data by @fkiraly in #118
• Skip multiprocessing by @SimonBlanke in #119
• [MNT] skip multiprocessing tests that hang on windows by @fkiraly in #116
• V5 API rework - unified API for optimizers and experiments by @fkiraly in #110
• [DOC] add r prefix in docstirngs with TeX backslashes by @fkiraly in #124
• ⚡️ Speed up function gfo2hyper by 15% by @misrasaurabh1 in #105
• [ENH] prototype gfo adapter, more hill climbing classes by @fkiraly in #121
• [MNT] bound scikit-learn < 1.7.0 by @fkiraly in #133
• [MNT] testing with no extras by @fkiraly in #132
• [ENH] quick testing utility check_estimator by @fkiraly in #130
• Bump pytest from 8.3.5 to 8.4.0 by @dependabot[bot] in #129
• [DOC] fix broken shields in README by @fkiraly in #120
• Add optimization algorithms from GFO by @SimonBlanke in #127
• Bump pytest from 8.4.0 to 8.4.1 by @dependabot[bot] in #137
• Feature/random search sk by @SimonBlanke in #139
• Feature/sklearn v1.7 by @SimonBlanke in #138
• [ENH] sign handling in experiments and optimization by @fkiraly in #142
• [MNT] raise scikit-learn bound to scikit-learn<1.8 by @fkiraly in #145
• [MNT] raise scikit-learn bound to scikit-learn<1.8 by @fkiraly in #149
• [ENH] minor improvements to CI by @fkiraly in #144
• [MNT] code quality job by @fkiraly in #151
• [MNT] lint entire repository using pre-commit by @SimonBlanke in #156
• [ENH] sktime integration - forecasters by @fkiraly in #157
• [ENH] optuna optimizer interface by @SimonBlanke in #155
• [DOC] fix docstring example in ForecastingOptCV by @fkiraly in #160
• [ENH] change BaseOptimizer.run method to BaseOptimizer.solve by @fkiraly in #159
• [ENH] parallelization backends for grid and random search by @fkiraly in #150
• [ENH] parallelization backends for grid and random search by @SimonBlanke in #162
• [MNT] Rename 'toy'-module to 'bench' by @SimonBlanke in #164
• [MNT] Cleanup v4 by @SimonBlanke in #165
• [MNT] change master to main by @fkiraly in #166
• [MNT] restore sklearn integration tests in sklearn integration test job by @fkiraly in #167
• [MNT] Change examples to v5 + small fixes by @SimonBlanke in #168
• [ENH] in test_parallelize_simple_loop, use name of backend as fixture name by @fkiraly in #170
• [BUG] fix docstrings of benchmark toy experiments by @fkiraly in #171
• [BUG] fix params ignored in SktimeForecastingExperiment by @fkiraly in #175
• [DOC] improved docstrings for estimator tuners in integrations module by @fkiraly in #172
• [ENH] experiments: uniform call signature and terminology by @fkiraly in #178
• [ENH] sktime integration - time series classification by @fkiraly in #173
• [ENH] allowing old function API to be passed as experiment by @fkiraly in #152
• Small fixes by @SimonBlanke in #179
• Bump pytest from 8.4.1 to 8.4.2 by @dependabot[bot] in #181
• Fix selection direction, scorer handling, and fit kwargs; resolve sktime doctest by @SimonBlanke in #182
• V5 by @SimonBlanke in #185

New Contributors

• @dependabot[bot] made their first contribution in #84
• @MekongDelta-mind made their first contribution in #109
• @misrasaurabh1 made their first contribution in #106

Full Changelog: v4.8.0...v5.0.0

v4.8.0

• add support for numpy v2
• add support for pandas v2
• add support for python 3.12
• transfer setup.py to pyproject.toml
• change project structure to src-layout

v4.7.0

• add Genetic algorithm optimizer
• add Differential evolution optimizer

v4.6.0

add support for constrained optimization

v4.5.0

• add early stopping feature to custom optimization strategies
• display additional outputs from objective-function in results in command-line
• add type hints to hyperactive-api
• add tests for new features
• add test for verbosity=False

v4.4.0

• add new feature: "optimization strategies"
• redesign progress-bar

v4.3.0

• add new features from GFO
  • add Spiral Optimization
  • add Lipschitz Optimizer
  • add DIRECT Optimizer
  • print the random seed for reproducibility

v4.0.0

v4.0.0

v3.2.4

Changes from v3.0.0 -> v3.2.4:

• Decouple number of runs from active processes (Thanks to PartiallyTyped). This reduces memory load if number of jobs is huge
• New feature: The progress board enables the user to monitor the optimization progress during the run.
  • Display trend of best score
  • Plot parameters and score in parallel coordinates
  • Generate filter file to define an upper and/or lower bound for all parameters and the score in the parallel coordinate plot
  • List parameters of 5 best scores
• add Python 3.8 to tests
• add warnings of search space values does not contain lists
• improve stability of result-methods
• add tests for hyperactive-memory + search spaces