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

launching PQ

This commit is contained in:
Alejandro Moreo Fernandez 2025-12-04 18:00:01 +01:00
parent 78fd05ab33
commit 90981088b0
2 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
BayesianKDEy/full_experiments.py
View File

@ -54,12 +54,13 @@ def methods():
yield 'BayesianACC', ACC(LR()), acc_hyper, lambda hyper: BayesianCC(LR(), mcmc_seed=0)
yield 'BootstrapHDy', DMy(LR()), hdy_hyper, lambda hyper: AggregativeBootstrap(DMy(LR(), **hyper), n_test_samples=1000, random_state=0),
# yield 'BayesianHDy', PQ(LR(), stan_seed=0), hdy_hyper
yield 'BayesianHDy', DMy(LR()), hdy_hyper, lambda hyper: PQ(LR(), stan_seed=0, **hyper),
yield 'BootstrapKDEy', KDEyML(LR()), kdey_hyper, lambda hyper: AggregativeBootstrap(KDEyML(LR(), **hyper), n_test_samples=1000, random_state=0, verbose=True),
yield 'BayesianKDEy', KDEyML(LR()), kdey_hyper, lambda hyper: BayesianKDEy(mcmc_seed=0, **hyper),
yield 'BayesianKDEy*', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, **hyper),
yield 'BayKDEy*CLR', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore_CLR=True, step_size=.15, **hyper),
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*CLR2', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore_CLR=True, step_size=.15, **hyper),
def model_selection(train: LabelledCollection, point_quantifier: AggregativeQuantifier, grid: dict):

5
quapy/method/confidence.py
View File

@ -323,13 +323,16 @@ class ConfidenceIntervals(ConfidenceRegionABC):
:param samples: np.ndarray of shape (n_bootstrap_samples, n_classes)
:param confidence_level: float, the confidence level (default 0.95)
"""
def __init__(self, samples, confidence_level=0.95):
def __init__(self, samples, confidence_level=0.95, bonferroni_correction=False):
assert 0 < confidence_level < 1, f'{confidence_level=} must be in range(0,1)'
samples = np.asarray(samples)
self.means_ = samples.mean(axis=0)
alpha = 1-confidence_level
if bonferroni_correction:
n_classes = samples.shape[-1]
alpha = alpha/n_classes
low_perc = (alpha/2.)*100
high_perc = (1-alpha/2.)*100
self.I_low, self.I_high = np.percentile(samples, q=[low_perc, high_perc], axis=0)