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

adding experiment with ILR

This commit is contained in:
Alejandro Moreo Fernandez 2025-12-04 20:02:26 +01:00
parent b180aae16c
commit e8d175106f
4 changed files with 21 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
BayesianKDEy/_bayeisan_kdey.py
View File

@ -1,7 +1,7 @@
from sklearn.base import BaseEstimator
import numpy as np
from quapy.method._kdey import KDEBase
from quapy.method.confidence import WithConfidenceABC, ConfidenceRegionABC, CLRtransformation
from quapy.method.confidence import WithConfidenceABC, ConfidenceRegionABC, CLRtransformation, ILRtransformation
from quapy.method.aggregative import AggregativeSoftQuantifier
from tqdm import tqdm
import quapy.functional as F
@ -40,7 +40,7 @@ class BayesianKDEy(AggregativeSoftQuantifier, KDEBase, WithConfidenceABC):
mcmc_seed: int = 0,
confidence_level: float = 0.95,
region: str = 'intervals',
explore_CLR=False,
explore='simplex',
step_size=0.05,
verbose: bool = False):
@ -48,6 +48,8 @@ class BayesianKDEy(AggregativeSoftQuantifier, KDEBase, WithConfidenceABC):
raise ValueError(f'parameter {num_warmup=} must be a positive integer')
if num_samples <= 0:
raise ValueError(f'parameter {num_samples=} must be a positive integer')
assert explore in ['simplex', 'clr', 'ilr'], \
f'unexpected value for param {explore=}; valid ones are "simplex", "clr", and "ilr"'
super().__init__(classifier, fit_classifier, val_split)
self.bandwidth = KDEBase._check_bandwidth(bandwidth, kernel)
@ -57,7 +59,7 @@ class BayesianKDEy(AggregativeSoftQuantifier, KDEBase, WithConfidenceABC):
self.mcmc_seed = mcmc_seed
self.confidence_level = confidence_level
self.region = region
self.explore_CLR = explore_CLR
self.explore = explore
self.step_size = step_size
self.verbose = verbose
@ -112,16 +114,24 @@ class BayesianKDEy(AggregativeSoftQuantifier, KDEBase, WithConfidenceABC):
def sample_neighbour(prev, step_size):
# random-walk Metropolis-Hastings
d = len(prev)
if not self.explore_CLR:
neighbour = None
if self.explore=='simplex':
dir_noise = rng.normal(scale=step_size/np.sqrt(d), size=d)
neighbour = F.normalize_prevalence(prev + dir_noise, method='mapsimplex')
else:
elif self.explore=='clr':
clr = CLRtransformation()
clr_point = clr(prev)
dir_noise = rng.normal(scale=step_size, size=d)
clr_neighbour = clr_point+dir_noise
neighbour = clr.inverse(clr_neighbour)
assert in_simplex(neighbour), 'wrong CLR transformation'
elif self.explore=='ilr':
ilr = ILRtransformation()
ilr_point = ilr(prev)
dir_noise = rng.normal(scale=step_size, size=d)
ilr_neighbour = ilr_point + dir_noise
neighbour = ilr.inverse(ilr_neighbour)
assert in_simplex(neighbour), 'wrong ILR transformation'
return neighbour
n_classes = X_probs.shape[1]

5
BayesianKDEy/full_experiments.py
View File

@ -61,8 +61,9 @@ def methods():
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), multiclass_method
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=.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=.05, **hyper), multiclass_method
yield 'BayKDEy*CLR', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore='clr', step_size=.15, **hyper), multiclass_method
# yield 'BayKDEy*CLR2', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore='clr', step_size=.05, **hyper), multiclass_method
yield 'BayKDEy*ILR', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0, explore='ilr', step_size=.15, **hyper), multiclass_method
def model_selection(train: LabelledCollection, point_quantifier: AggregativeQuantifier, grid: dict):

2
BayesianKDEy/generate_results.py
View File

@ -105,6 +105,8 @@ for setup in ['binary', 'multiclass']:
df = df[df["dataset"] != data_name]
for region in ['CI', 'CE', 'CLR', 'ILR']:
if setup == 'binary' and region=='ILR':
continue
pv = pd.pivot_table(
df, index='dataset', columns='method', values=['ae', f'c-{region}', f'a-{region}'], margins=True
)

2
BayesianKDEy/single_experiment_debug.py
View File

@ -48,7 +48,7 @@ def method():
# 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),
return 'BayKDE*CLR', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison', mcmc_seed=0,
explore_CLR=True,
explore=True,
step_size=.15,
# num_warmup = 5000,
# num_samples = 10_000,