Integrate composable methods from qunfold

.github/workflows/ci.yml

@@ -28,6 +28,6 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip setuptools wheel
-        python -m pip install -e .[bayes,tests]
+        python -m pip install -e .[bayes,composable,tests]
     - name: Test with unittest
       run: python -m unittest

docs/source/quapy.method.rst

@@ -52,6 +52,14 @@ quapy.method.non\_aggregative module
    :undoc-members:
    :show-inheritance:
 
+quapy.method.composable module
+------------------------
+
+.. automodule:: quapy.method.composable
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 Module contents
 ---------------
 

quapy/method/composable.py

@@ -0,0 +1,90 @@
+"""This module allows the composition of quantification methods from loss functions and feature transformations. This functionality is realized through an integration of the qunfold package: https://github.com/mirkobunse/qunfold."""
+
+import qunfold
+from qunfold.quapy import QuaPyWrapper
+from qunfold.sklearn import CVClassifier
+from qunfold import (
+    LeastSquaresLoss, # losses
+    BlobelLoss,
+    EnergyLoss,
+    HellingerSurrogateLoss,
+    CombinedLoss,
+    TikhonovRegularization,
+    TikhonovRegularized,
+    ClassTransformer, # transformers
+    HistogramTransformer,
+    DistanceTransformer,
+    KernelTransformer,
+    EnergyKernelTransformer,
+    LaplacianKernelTransformer,
+    GaussianKernelTransformer,
+    GaussianRFFKernelTransformer,
+)
+
+__all__ = [ # control public members, e.g., for auto-documentation in sphinx; omit QuaPyWrapper
+    "ComposableQuantifier",
+    "CVClassifier",
+    "LeastSquaresLoss",
+    "BlobelLoss",
+    "EnergyLoss",
+    "HellingerSurrogateLoss",
+    "CombinedLoss",
+    "TikhonovRegularization",
+    "TikhonovRegularized",
+    "ClassTransformer",
+    "HistogramTransformer",
+    "DistanceTransformer",
+    "KernelTransformer",
+    "EnergyKernelTransformer",
+    "LaplacianKernelTransformer",
+    "GaussianKernelTransformer",
+    "GaussianRFFKernelTransformer",
+]
+
+def ComposableQuantifier(loss, transformer, **kwargs):
+    """A generic quantification / unfolding method that solves a linear system of equations.
+
+    This class represents any quantifier that can be described in terms of a loss function, a feature transformation, and a regularization term. In this implementation, the loss is minimized through unconstrained second-order minimization. Valid probability estimates are ensured through a soft-max trick by Bunse (2022).
+
+    Args:
+        loss: An instance of a loss class from `quapy.methods.composable`.
+        transformer: An instance of a transformer class from `quapy.methods.composable`.
+        solver (optional): The `method` argument in `scipy.optimize.minimize`. Defaults to `"trust-ncg"`.
+        solver_options (optional): The `options` argument in `scipy.optimize.minimize`. Defaults to `{"gtol": 1e-8, "maxiter": 1000}`.
+        seed (optional): A random number generator seed from which a numpy RandomState is created. Defaults to `None`.
+
+    Examples:
+        Here, we create the ordinal variant of ACC (Bunse et al., 2023). This variant consists of the original feature transformation of ACC and of the original loss of ACC, the latter of which is regularized towards smooth solutions.
+
+            >>> from qunfold.method.composable import (
+            >>>     ComposableQuantifier,
+            >>>     TikhonovRegularized,
+            >>>     LeastSquaresLoss,
+            >>>     ClassTransformer,
+            >>> )
+            >>> from sklearn.ensemble import RandomForestClassifier
+            >>> o_acc = ComposableQuantifier(
+            >>>     TikhonovRegularized(LeastSquaresLoss(), 0.01),
+            >>>     ClassTransformer(RandomForestClassifier(oob_score=True))
+            >>> )
+
+        Here, we perform hyper-parameter optimization with the ordinal ACC.
+
+            >>> quapy.model_selection.GridSearchQ(
+            >>>     model = o_acc,
+            >>>     param_grid = { # try both splitting criteria
+            >>>         "transformer__classifier__estimator__criterion": ["gini", "entropy"],
+            >>>     },
+            >>>     # ...
+            >>> )
+
+        To use a classifier that does not provide the `oob_score` argument, such as logistic regression, you have to configure a cross validation of this classifier. Here, we employ 10 cross validation folds. 5 folds are the default.
+
+            >>> from qunfold.method.composable import CVClassifier
+            >>> from sklearn.linear_model import LogisticRegression
+            >>> acc_lr = ComposableQuantifier(
+            >>>     LeastSquaresLoss(),
+            >>>     ClassTransformer(CVClassifier(LogisticRegression(), 10))
+            >>> )
+        """
+    return QuaPyWrapper(qunfold.GenericMethod(loss, transformer, **kwargs))

quapy/tests/test_methods.py

@@ -9,6 +9,29 @@
 from quapy.method import AGGREGATIVE_METHODS, BINARY_METHODS, NON_AGGREGATIVE_METHODS
 from quapy.functional import check_prevalence_vector
 
+# a random selection of composed methods to test the qunfold integration
+from quapy.method.composable import (
+    ComposableQuantifier,
+    LeastSquaresLoss,
+    HellingerSurrogateLoss,
+    ClassTransformer,
+    HistogramTransformer,
+    CVClassifier,
+)
+COMPOSABLE_METHODS = [
+    ComposableQuantifier( # ACC
+        LeastSquaresLoss(),
+        ClassTransformer(CVClassifier(LogisticRegression()))
+    ),
+    ComposableQuantifier( # HDy
+        HellingerSurrogateLoss(),
+        HistogramTransformer(
+            3, # 3 bins per class
+            preprocessor = ClassTransformer(CVClassifier(LogisticRegression()))
+        )
+    ),
+]
+
 class TestMethods(unittest.TestCase):
 
     tiny_dataset_multiclass = qp.datasets.fetch_UCIMulticlassDataset('academic-success').reduce(n_test=10)
@@ -87,6 +110,14 @@ def test_quanet(self):
         estim_prevalences = model.quantify(dataset.test.instances)
         self.assertTrue(check_prevalence_vector(estim_prevalences))
 
+    def test_composable(self):
+        for dataset in TestMethods.datasets:
+            for q in COMPOSABLE_METHODS:
+                print('testing', q)
+                q.fit(dataset.training)
+                estim_prevalences = q.quantify(dataset.test.X)
+                self.assertTrue(check_prevalence_vector(estim_prevalences))
+
 
 if __name__ == '__main__':
     unittest.main()

setup.py

@@ -125,7 +125,9 @@ def get_version(rel_path):
     # projects.
     extras_require={  # Optional
        'bayes': ['jax', 'jaxlib', 'numpyro'],
+       'composable': ['qunfold @ git+https://github.com/mirkobunse/[email protected]'],
        'tests': ['certifi'],
+       'docs' : ['sphinx-rtd-theme'],
     },
 
     # If there are data files included in your packages that need to be