moreo
/
QuaPy
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

adding new config for bayesian

This commit is contained in:
Alejandro Moreo Fernandez 2025-12-04 18:27:15 +01:00
parent 90981088b0
commit d87625bd09
1 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
BayesianKDEy/full_experiments.py
View File

@ -49,18 +49,20 @@ def methods():
hdy_hyper = {'nbins': [3,4,5,8,16,32]} hdy_hyper = {'nbins': [3,4,5,8,16,32]}
kdey_hyper = {'bandwidth': [0.001, 0.005, 0.01, 0.05, 0.1, 0.2]} kdey_hyper = {'bandwidth': [0.001, 0.005, 0.01, 0.05, 0.1, 0.2]}
kdey_hyper_clr = {'bandwidth': [0.05, 0.1, 0.5, 1., 2., 5.]} kdey_hyper_clr = {'bandwidth': [0.05, 0.1, 0.5, 1., 2., 5.]}
only_binary = True
multiclass_method = False
yield 'BootstrapACC', ACC(LR()), acc_hyper, lambda hyper: AggregativeBootstrap(ACC(LR()), n_test_samples=1000, random_state=0), yield 'BootstrapACC', ACC(LR()), acc_hyper, lambda hyper: AggregativeBootstrap(ACC(LR()), n_test_samples=1000, random_state=0), multiclass_method
yield 'BayesianACC', ACC(LR()), acc_hyper, lambda hyper: BayesianCC(LR(), mcmc_seed=0) yield 'BayesianACC', ACC(LR()), acc_hyper, lambda hyper: BayesianCC(LR(), mcmc_seed=0), multiclass_method
yield 'BootstrapHDy', DMy(LR()), hdy_hyper, lambda hyper: AggregativeBootstrap(DMy(LR(), **hyper), n_test_samples=1000, random_state=0), yield 'BootstrapHDy', DMy(LR()), hdy_hyper, lambda hyper: AggregativeBootstrap(DMy(LR(), **hyper), n_test_samples=1000, random_state=0), multiclass_method
yield 'BayesianHDy', DMy(LR()), hdy_hyper, lambda hyper: PQ(LR(), stan_seed=0, **hyper), yield 'BayesianHDy', DMy(LR()), hdy_hyper, lambda hyper: PQ(LR(), stan_seed=0, **hyper), only_binary
yield 'BootstrapKDEy', KDEyML(LR()), kdey_hyper, lambda hyper: AggregativeBootstrap(KDEyML(LR(), **hyper), n_test_samples=1000, random_state=0, verbose=True), yield 'BootstrapKDEy', KDEyML(LR()), kdey_hyper, lambda hyper: AggregativeBootstrap(KDEyML(LR(), **hyper), n_test_samples=1000, random_state=0, verbose=True), multiclass_method
yield 'BayesianKDEy', KDEyML(LR()), kdey_hyper, lambda hyper: BayesianKDEy(mcmc_seed=0, **hyper), yield 'BayesianKDEy', KDEyML(LR()), kdey_hyper, lambda hyper: BayesianKDEy(mcmc_seed=0, **hyper), multiclass_method
yield 'BayesianKDEy*', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, **hyper), yield 'BayesianKDEy*', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, **hyper), multiclass_method
yield 'BayKDEy*CLR', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore_CLR=True, step_size=.1, **hyper), yield 'BayKDEy*CLR', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore_CLR=True, step_size=.15, **hyper), multiclass_method
# yield 'BayKDEy*CLR2', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore_CLR=True, step_size=.15, **hyper), yield 'BayKDEy*CLR2', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore_CLR=True, step_size=.05, **hyper), multiclass_method
def model_selection(train: LabelledCollection, point_quantifier: AggregativeQuantifier, grid: dict): def model_selection(train: LabelledCollection, point_quantifier: AggregativeQuantifier, grid: dict):
@ -158,8 +160,8 @@ if __name__ == '__main__':
is_binary = data.n_classes==2 is_binary = data.n_classes==2
result_subdir = result_dir / ('binary' if is_binary else 'multiclass') result_subdir = result_dir / ('binary' if is_binary else 'multiclass')
hyper_subdir = result_dir / 'hyperparams' / ('binary' if is_binary else 'multiclass') hyper_subdir = result_dir / 'hyperparams' / ('binary' if is_binary else 'multiclass')
for method_name, method, hyper_params, withconf_constructor in methods(): for method_name, method, hyper_params, withconf_constructor, only_binary in methods():
if isinstance(method, BinaryQuantifier) and not is_binary: if only_binary and not is_binary:
continue continue
result_path = experiment_path(result_subdir, data_name, method_name) result_path = experiment_path(result_subdir, data_name, method_name)
hyper_path = experiment_path(hyper_subdir, data_name, method.__class__.__name__) hyper_path = experiment_path(hyper_subdir, data_name, method.__class__.__name__)