134 lines
4.4 KiB
Python
134 lines
4.4 KiB
Python
import pickle
|
|
import os
|
|
from time import time
|
|
from collections import defaultdict
|
|
from tqdm import tqdm
|
|
import numpy as np
|
|
from sklearn.linear_model import LogisticRegression
|
|
|
|
import quapy as qp
|
|
from KDEy.kdey_devel import KDEyMLauto, optim_minimize
|
|
from method._kdey import KDEBase
|
|
from quapy.method.aggregative import PACC, EMQ, KDEyML
|
|
from quapy.model_selection import GridSearchQ
|
|
from quapy.protocol import UPP
|
|
from pathlib import Path
|
|
from quapy import functional as F
|
|
|
|
SEED = 1
|
|
|
|
|
|
def newLR():
|
|
return LogisticRegression(max_iter=1000)#, C=1, class_weight='balanced')
|
|
|
|
SAMPLE_SIZE=150
|
|
qp.environ['SAMPLE_SIZE'] = SAMPLE_SIZE
|
|
|
|
epsilon = 1e-10
|
|
# n_bags_test = 2
|
|
# DATASETS = [qp.datasets.UCI_MULTICLASS_DATASETS[21]]
|
|
DATASETS = qp.datasets.UCI_MULTICLASS_DATASETS
|
|
for i, dataset in enumerate(DATASETS):
|
|
data = qp.datasets.fetch_UCIMulticlassDataset(dataset)
|
|
n_classes = data.n_classes
|
|
print(f'{i=}')
|
|
print(f'{dataset=}')
|
|
print(f'{n_classes=}')
|
|
print(len(data.training))
|
|
print(len(data.test))
|
|
|
|
train, test = data.train_test
|
|
train_prev = train.prevalence()
|
|
test_prev = test.prevalence()
|
|
|
|
print(f'train-prev = {F.strprev(train_prev)}')
|
|
print(f'test-prev = {F.strprev(test_prev)}')
|
|
|
|
# protocol = UPP(test, repeats=n_bags_test)
|
|
#
|
|
# for sample, prev in protocol():
|
|
# print(f'sample-prev = {F.strprev(prev)}')
|
|
|
|
# prev = np.asarray([0.2, 0.3, 0.5])
|
|
# prev = np.asarray([0.33, 0.33, 0.34])
|
|
# prev = train_prev
|
|
|
|
# sample = test.sampling(SAMPLE_SIZE, *prev, random_state=1)
|
|
# print(f'sample-prev = {F.strprev(prev)}')
|
|
|
|
repeats = 10
|
|
prot = UPP(test, sample_size=SAMPLE_SIZE, repeats=repeats)
|
|
kde = KDEyMLauto(newLR())
|
|
kde.fit(train)
|
|
tr_posteriors, tr_y = kde.classif_predictions.Xy
|
|
for it, (sample, prev) in tqdm(enumerate(prot()), total=repeats):
|
|
te_posteriors = kde.classifier.predict_proba(sample)
|
|
classes = train.classes_
|
|
|
|
xaxis = []
|
|
ae_error = []
|
|
rae_error = []
|
|
mse_error = []
|
|
kld_error = []
|
|
likelihood_val = []
|
|
|
|
# for bandwidth in np.linspace(0.01, 0.2, 50):
|
|
for bandwidth in np.logspace(-3, 0.5, 50):
|
|
mix_densities = kde.get_mixture_components(tr_posteriors, tr_y, classes, bandwidth)
|
|
test_densities = [kde.pdf(kde_i, te_posteriors) for kde_i in mix_densities]
|
|
|
|
def neg_loglikelihood_prev(prev):
|
|
test_mixture_likelihood = sum(prev_i * dens_i for prev_i, dens_i in zip(prev, test_densities))
|
|
test_loglikelihood = np.log(test_mixture_likelihood + epsilon)
|
|
return -np.sum(test_loglikelihood)
|
|
|
|
init_prev = np.full(fill_value=1 / n_classes, shape=(n_classes,))
|
|
pred_prev, likelihood = optim_minimize(neg_loglikelihood_prev, init_prev, return_loss=True)
|
|
|
|
xaxis.append(bandwidth)
|
|
ae_error.append(qp.error.ae(prev, pred_prev))
|
|
rae_error.append(qp.error.rae(prev, pred_prev))
|
|
mse_error.append(qp.error.mse(prev, pred_prev))
|
|
kld_error.append(qp.error.kld(prev, pred_prev))
|
|
likelihood_val.append(likelihood)
|
|
|
|
import matplotlib.pyplot as plt
|
|
|
|
# Crear la figura
|
|
fig, ax1 = plt.subplots(figsize=(8, 6))
|
|
|
|
# Pintar las series ae_error, rae_error, y kld_error en el primer eje Y
|
|
ax1.plot(xaxis, ae_error, label='AE Error', marker='o', color='b')
|
|
# ax1.plot(xaxis, rae_error, label='RAE Error', marker='s', color='g')
|
|
# ax1.plot(xaxis, kld_error, label='KLD Error', marker='^', color='r')
|
|
ax1.plot(xaxis, mse_error, label='MSE Error', marker='^', color='c')
|
|
ax1.set_xscale('log')
|
|
|
|
# Configurar etiquetas para el primer eje Y
|
|
ax1.set_xlabel('Bandwidth')
|
|
ax1.set_ylabel('Error Value')
|
|
ax1.grid(True)
|
|
ax1.legend(loc='upper left')
|
|
|
|
# Crear un segundo eje Y que comparte el eje X
|
|
ax2 = ax1.twinx()
|
|
|
|
# Pintar likelihood_val en el segundo eje Y
|
|
ax2.plot(xaxis, likelihood_val, label='(neg)Likelihood', marker='x', color='purple')
|
|
|
|
# Configurar etiquetas para el segundo eje Y
|
|
ax2.set_ylabel('Likelihood Value')
|
|
ax2.legend(loc='upper right')
|
|
|
|
# Mostrar el gráfico
|
|
plt.title('Error Metrics vs Bandwidth')
|
|
# plt.show()
|
|
os.makedirs('./plots/likelihood/', exist_ok=True)
|
|
plt.savefig(f'./plots/likelihood/{dataset}-fig{it}.png')
|
|
plt.close()
|
|
|
|
|
|
|
|
|
|
|