bayesianCC with custom prior

BayesianKDEy/_bayeisan_kdey.py

@@ -42,6 +42,8 @@ class BayesianKDEy(AggregativeSoftQuantifier, KDEBase, WithConfidenceABC):
     :param region: string, set to `intervals` for constructing confidence intervals (default), or to
         `ellipse` for constructing an ellipse in the probability simplex, or to `ellipse-clr` for
         constructing an ellipse in the Centered-Log Ratio (CLR) unconstrained space.
+    :param prior: an array-list with the alpha parameters of a Dirichlet prior, or the string 'uniform'
+        for a uniform, uninformative prior (default)
     :param verbose: bool, whether to display progress bar
     """
     def __init__(self,
@@ -249,7 +251,7 @@ class BayesianKDEy(AggregativeSoftQuantifier, KDEBase, WithConfidenceABC):
         test_densities = jnp.array(test_densities)
         n_classes = X_probs.shape[-1]
         if isinstance(self.prior, str) and self.prior == 'uniform':
-            alpha = [1.]*n_classes
+            alpha = [1.] * n_classes
         else:
             alpha = self.prior
 

BayesianKDEy/prior_effect.py

@@ -32,8 +32,8 @@ def methods():
     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.]}
 
-    #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)
-    yield f'BaKDE-Ait', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison',
+    # yield f'BaKDE-Ait', KDEyCLR(LR()), kdey_hyper_clr, lambda hyper: BayesianKDEy(kernel='aitchison',
                                                                                                mcmc_seed=0,
                                                                                                engine='numpyro',
                                                                                                temperature=None,

quapy/method/_bayesian.py

@@ -33,7 +33,7 @@ P_TEST_C: str = "P_test(C)"
 P_C_COND_Y: str = "P(C|Y)"
 
 
-def model_bayesianCC(n_c_unlabeled: np.ndarray, n_y_and_c_labeled: np.ndarray) -> None:
+def model_bayesianCC(n_c_unlabeled: np.ndarray, n_y_and_c_labeled: np.ndarray, alpha: np.ndarray) -> None:
     """
     Defines a probabilistic model in `NumPyro <https://num.pyro.ai/>`_.
 
@@ -47,7 +47,7 @@ def model_bayesianCC(n_c_unlabeled: np.ndarray, n_y_and_c_labeled: np.ndarray) -
     K = len(n_c_unlabeled)
     L = len(n_y_labeled)
 
-    pi_ = numpyro.sample(P_TEST_Y, dist.Dirichlet(jnp.ones(L)))
+    pi_ = numpyro.sample(P_TEST_Y, dist.Dirichlet(jnp.asarray(alpha, dtype=jnp.float32)))
     p_c_cond_y = numpyro.sample(P_C_COND_Y, dist.Dirichlet(jnp.ones(K).repeat(L).reshape(L, K)))
 
     with numpyro.plate('plate', L):
@@ -57,13 +57,13 @@ def model_bayesianCC(n_c_unlabeled: np.ndarray, n_y_and_c_labeled: np.ndarray) -
     numpyro.sample('N_c', dist.Multinomial(jnp.sum(n_c_unlabeled), p_c), obs=n_c_unlabeled)
 
 
-
+def sample_posterior_bayesianCC(
-def sample_posterior(
+        n_c_unlabeled: np.ndarray,
-    n_c_unlabeled: np.ndarray,
+        n_y_and_c_labeled: np.ndarray,
-    n_y_and_c_labeled: np.ndarray,
+        num_warmup: int,
-    num_warmup: int,
+        num_samples: int,
-    num_samples: int,
+        alpha: np.ndarray,
-    seed: int = 0,
+        seed: int = 0,
 ) -> dict:
     """
     Samples from the Bayesian quantification model in NumPyro using the
@@ -75,9 +75,12 @@ def sample_posterior(
         with entry `(y, c)` being the number of instances labeled as class `y` and predicted as class `c`.
     :param num_warmup: the number of warmup steps.
     :param num_samples: the number of samples to draw.
+    :param alpha: a `np.ndarray` of shape `(n_classes,)` with the alpha parameters of the
+        Dirichlet prior
     :seed: the random seed.
     :return: a `dict` with the samples. The keys are the names of the latent variables.
     """
+
     mcmc = numpyro.infer.MCMC(
         numpyro.infer.NUTS(model_bayesianCC),
         num_warmup=num_warmup,
@@ -85,7 +88,7 @@ def sample_posterior(
         progress_bar=False
     )
     rng_key = jax.random.PRNGKey(seed)
-    mcmc.run(rng_key, n_c_unlabeled=n_c_unlabeled, n_y_and_c_labeled=n_y_and_c_labeled)
+    mcmc.run(rng_key, n_c_unlabeled=n_c_unlabeled, n_y_and_c_labeled=n_y_and_c_labeled, alpha=alpha)
     return mcmc.get_samples()
 
 

quapy/method/confidence.py

@@ -1,3 +1,6 @@
+from numbers import Number
+from typing import Iterable
+
 import numpy as np
 from joblib import Parallel, delayed
 from sklearn.base import BaseEstimator
@@ -726,6 +729,8 @@ class BayesianCC(AggregativeCrispQuantifier, WithConfidenceABC):
     :param region: string, set to `intervals` for constructing confidence intervals (default), or to
         `ellipse` for constructing an ellipse in the probability simplex, or to `ellipse-clr` for
         constructing an ellipse in the Centered-Log Ratio (CLR) unconstrained space.
+    :param prior: an array-list with the alpha parameters of a Dirichlet prior, or the string 'uniform'
+        for a uniform, uninformative prior (default)
     """
     def __init__(self,
                  classifier: BaseEstimator=None,
@@ -735,12 +740,16 @@ class BayesianCC(AggregativeCrispQuantifier, WithConfidenceABC):
                  num_samples: int = 1_000,
                  mcmc_seed: int = 0,
                  confidence_level: float = 0.95,
-                 region: str = 'intervals'):
+                 region: str = 'intervals',
+                 prior = 'uniform'):
 
         if num_warmup <= 0:
             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 ((isinstance(prior, str) and prior == 'uniform') or
+                (isinstance(prior, Iterable) and all(isinstance(v, Number) for v in prior))), \
+            f'wrong type for {prior=}; expected "uniform" or an array-like of real values'
 
         if _bayesian.DEPENDENCIES_INSTALLED is False:
             raise ImportError("Auxiliary dependencies are required. "
@@ -752,6 +761,7 @@ class BayesianCC(AggregativeCrispQuantifier, WithConfidenceABC):
         self.mcmc_seed = mcmc_seed
         self.confidence_level = confidence_level
         self.region = region
+        self.prior = prior
 
         # Array of shape (n_classes, n_predicted_classes,) where entry (y, c) is the number of instances
         # labeled as class y and predicted as class c.
@@ -782,11 +792,18 @@ class BayesianCC(AggregativeCrispQuantifier, WithConfidenceABC):
 
         n_c_unlabeled = F.counts_from_labels(classif_predictions, self.classifier.classes_).astype(float)
 
-        self._samples = _bayesian.sample_posterior(
+        n_classes = len(self.classifier.classes_)
+        if isinstance(self.prior, str) and self.prior == 'uniform':
+            alpha = np.asarray([1.] * n_classes)
+        else:
+            alpha = np.asarray(self.prior)
+
+        self._samples = _bayesian.sample_posterior_bayesianCC(
             n_c_unlabeled=n_c_unlabeled,
             n_y_and_c_labeled=self._n_and_c_labeled,
             num_warmup=self.num_warmup,
             num_samples=self.num_samples,
+            alpha=alpha,
             seed=self.mcmc_seed,
         )
         return self._samples