[ENH] Add UnconditionalDistfitRegressor and DeterministicReductionRegressor

docs/source/api_reference/regression.rst

@@ -196,6 +196,21 @@ This section lists simple regressors which can be used as baselines.
     DeltaPointRegressor
     DummyProbaRegressor
 
+.. currentmodule:: skpro.regression.unconditional_distfit
+
+.. autosummary::
+    :toctree: auto_generated/
+    :template: class.rst
+
+    UnconditionalDistfitRegressor
+
+.. currentmodule:: skpro.regression.deterministic_reduction
+
+.. autosummary::
+    :toctree: auto_generated/
+    :template: class.rst
+
+    DeterministicReductionRegressor
 
 Linear regression
 -----------------

examples/baseline_regressors_demo.py

@@ -0,0 +1,27 @@
+"""Example usage for baseline probabilistic regressors."""
+import logging
+
+import numpy as np
+from sklearn.linear_model import LinearRegression
+
+from skpro.regression.deterministic_reduction import DeterministicReductionRegressor
+from skpro.regression.unconditional_distfit import UnconditionalDistfitRegressor
+
+# Generate synthetic data
+X = np.random.randn(100, 3)
+y = 2 * X[:, 0] + np.random.randn(100)
+
+# 1. Unconditional density baseline (featureless)
+reg1 = UnconditionalDistfitRegressor()
+reg1.fit(X, y)
+dist1 = reg1.predict_proba(X)
+logging.info("UnconditionalDistfitRegressor mean: %s", dist1.mean())
+logging.info("Sample from unconditional: %s", dist1.sample(5))
+
+# 2. Deterministic-style baseline (mean from regressor, constant variance)
+reg2 = DeterministicReductionRegressor(LinearRegression(), distr_type="gaussian")
+reg2.fit(X, y)
+dist2 = reg2.predict_proba(X)
+logging.info("DeterministicReductionRegressor mean: %s", dist2.mean)
+logging.info("DeterministicReductionRegressor sigma: %s", dist2.sigma)
+logging.info("Sample from deterministic baseline: %s", dist2.sample(5))

examples/baseline_regressors_kde_hist.py

@@ -0,0 +1,21 @@
+"""Example: unconditional norm and laplace baselines with distfit."""
+import logging
+
+import numpy as np
+
+from skpro.regression.unconditional_distfit import UnconditionalDistfitRegressor
+
+X = np.random.randn(80, 2)
+y = np.random.randn(80)
+
+# Distfit norm baseline
+reg_norm = UnconditionalDistfitRegressor(distr_type="norm")
+reg_norm.fit(X, y)
+dist_norm = reg_norm.predict_proba(X)
+logging.info("Norm baseline mean: %s", dist_norm.mean())
+
+# Distfit laplace baseline
+reg_laplace = UnconditionalDistfitRegressor(distr_type="laplace")
+reg_laplace.fit(X, y)
+dist_laplace = reg_laplace.predict_proba(X)
+logging.info("Laplace baseline mean: %s", dist_laplace.mean())

examples/benchmark_baseline_regressors.py

@@ -0,0 +1,40 @@
+"""Benchmark script for baseline probabilistic regressors."""
+import logging
+
+import numpy as np
+from sklearn.linear_model import LinearRegression
+
+from skpro.metrics import PinballLoss
+from skpro.regression.deterministic_reduction import DeterministicReductionRegressor
+from skpro.regression.unconditional_distfit import UnconditionalDistfitRegressor
+
+# Generate synthetic data
+X = np.random.randn(200, 5)
+y = 3 * X[:, 0] - 2 * X[:, 1] + np.random.randn(200)
+
+# Split
+X_train, X_test = X[:150], X[150:]
+y_train, y_test = y[:150], y[150:]
+
+# Baseline 1: Unconditional
+reg1 = UnconditionalDistfitRegressor()
+reg1.fit(X_train, y_train)
+dist1 = reg1.predict_proba(X_test)
+
+# Baseline 2: Deterministic reduction
+reg2 = DeterministicReductionRegressor(LinearRegression(), distr_type="gaussian")
+reg2.fit(X_train, y_train)
+dist2 = reg2.predict_proba(X_test)
+
+# Evaluate pinball loss at alpha=0.1, 0.5, 0.9
+alphas = [0.1, 0.5, 0.9]
+for alpha in alphas:
+    loss1 = PinballLoss(alpha=alpha)(y_test, dist1)
+    loss2 = PinballLoss(alpha=alpha)(y_test, dist2)
+    logging.info(
+        "Alpha=%s: UnconditionalDistfitRegressor pinball loss=%.4f, "
+        "DeterministicReductionRegressor pinball loss=%.4f",
+        alpha,
+        loss1,
+        loss2,
+    )

skpro/distributions/tests/test_proba_basic.py

@@ -112,6 +112,9 @@ def test_proba_index_coercion():
 @pytest.mark.parametrize("fun", ["pdf", "ppf", "cdf"])
 def test_proba_plotting(fun):
     """Test that plotting functions do not crash and return ax as expected."""
+    import matplotlib
+
+    matplotlib.use("Agg", force=True)
     from matplotlib.axes import Axes
     from matplotlib.figure import Figure
 

skpro/regression/__init__.py

@@ -5,13 +5,17 @@
     MapieCrossConformalRegressor,
     MapieSplitConformalRegressor,
 )
+from skpro.regression.deterministic_reduction import DeterministicReductionRegressor
 from skpro.regression.jackknife import MapieJackknifeAfterBootstrapRegressor
 from skpro.regression.nonparametric import NadarayaWatsonCDE
+from skpro.regression.unconditional_distfit import UnconditionalDistfitRegressor
 
 __all__ = [
+    "DeterministicReductionRegressor",
     "MapieSplitConformalRegressor",
     "MapieCrossConformalRegressor",
     "MapieConformalizedQuantileRegressor",
     "MapieJackknifeAfterBootstrapRegressor",
     "NadarayaWatsonCDE",
+    "UnconditionalDistfitRegressor",
 ]

skpro/regression/deterministic_reduction.py

@@ -0,0 +1,150 @@
+"""Deterministic regression reduction baseline.
+
+Outputs Gaussian (or Laplace) with mean=prediction, var=training sample var.
+"""
+
+import numpy as np
+
+from skpro.distributions.laplace import Laplace
+from skpro.distributions.normal import Normal
+from skpro.regression.base import BaseProbaRegressor
+
+
+class DeterministicReductionRegressor(BaseProbaRegressor):
+    """
+    Wraps a deterministic regressor to output a Gaussian or Laplace.
+
+    The output has mean=prediction, var=training sample var.
+    Multi-output y is not supported (raises NotImplementedError).
+
+    Examples
+    --------
+    >>> from sklearn.linear_model import LinearRegression
+    >>> from skpro.regression.deterministic_reduction import (
+    ...     DeterministicReductionRegressor
+    ... )
+    >>> import pandas as pd
+    >>> X = pd.DataFrame({"a": [1, 2, 3]})
+    >>> y = pd.DataFrame([1, 2, 3])
+    >>> reg = DeterministicReductionRegressor(
+    ...     LinearRegression(),
+    ...     distr_type="gaussian"
+    ... )
+    >>> reg.fit(X, y)  # doctest: +ELLIPSIS
+    DeterministicReductionRegressor(...)
+    >>> dist = reg.predict_proba(X)
+    >>> dist.mean()  # doctest: +NORMALIZE_WHITESPACE
+        0
+    0  1.0
+    1  2.0
+    2  3.0
+
+    References
+    ----------
+    - Gaussian Processes for State Space Models and Change Point Detection
+      (Turner, 2011 thesis). https://mlg.eng.cam.ac.uk/pub/pdf/Tur11.pdf
+    - A Probabilistic View of Linear Regression
+      (Bishop, PRML; Keng, 2016; various tutorials).
+    - mlr3proba and related probabilistic ML frameworks.
+    - Efficient and Distance-Aware Deep Regressor for Uncertainty Quantification
+      (Bui et al., 2024).
+      https://proceedings.mlr.press/v238/manh-bui24a/manh-bui24a.pdf
+    """
+
+    _tags = {
+        "authors": ["arnavk23"],
+        "estimator_type": "regressor_proba",
+        # estimator tags
+        # --------------
+        "capability:multioutput": False,
+        "capability:missing": True,
+        "X_inner_mtype": "pd_DataFrame_Table",
+        "y_inner_mtype": "pd_DataFrame_Table",
+    }
+
+    def __init__(self, regressor, distr_type="gaussian"):
+        allowed_types = ["gaussian", "laplace"]
+        if distr_type not in allowed_types:
+            raise ValueError(
+                f"distr_type must be one of {allowed_types}, got {distr_type}"
+            )
+        self.regressor = regressor
+        self.distr_type = distr_type
+        super().__init__()
+
+    def _fit(self, X, y, C=None):
+        # Ensure X and y are DataFrames with string column names
+        import pandas as pd
+        from sklearn.base import clone
+
+        if not isinstance(X, pd.DataFrame):
+            X = pd.DataFrame(X)
+        X = X.copy()
+        X.columns = [str(col) for col in X.columns]
+        if not isinstance(y, pd.DataFrame):
+            y = pd.DataFrame(y)
+        y = y.copy()
+        y.columns = [str(col) for col in y.columns]
+        if y.shape[1] > 1:
+            raise NotImplementedError(
+                "DeterministicReductionRegressor only supports univariate y. "
+                f"Got shape: {y.shape}"
+            )
+        self._X_cols = X.columns
+        self._y_cols = y.columns
+        self._X_index = X.index
+        self._y_index = y.index
+        # Clone the regressor to avoid mutating the parameter
+        self.regressor_ = clone(self.regressor)
+        self.regressor_ = self.regressor_.fit(
+            X, y.values.ravel() if y.shape[1] == 1 else y
+        )
+        y_arr = y.values.flatten()
+        self.train_mean_ = np.mean(y_arr)
+        self.train_var_ = np.var(y_arr)
+        return self
+
+    def _predict_proba(self, X):
+        import pandas as pd
+
+        # Ensure X is a DataFrame with string column names
+        if not isinstance(X, pd.DataFrame):
+            X = pd.DataFrame(X, columns=self._X_cols)
+        X = X.copy()
+        X.columns = [str(col) for col in X.columns]
+        mean_pred = self.regressor_.predict(X)
+        # Ensure output shape matches y
+        if mean_pred.ndim == 1:
+            mean_pred = mean_pred.reshape(-1, 1)
+        # Return distribution with correct index/columns
+        if self.distr_type == "gaussian":
+            return Normal(
+                mu=mean_pred,
+                sigma=np.sqrt(self.train_var_),
+                index=X.index,
+                columns=self._y_cols,
+            )
+        if self.distr_type == "laplace":
+            # Laplace scale = sqrt(var/2)
+            return Laplace(
+                mu=mean_pred,
+                scale=np.sqrt(self.train_var_ / 2),
+                index=X.index,
+                columns=self._y_cols,
+            )
+        raise ValueError(f"Unknown distr_type: {self.distr_type}")
+
+    def get_params(self, deep=True):
+        """Get parameters for this estimator."""
+        # Only return true hyperparameters, not fitted attributes
+        return {"regressor": self.regressor, "distr_type": self.distr_type}
+
+    @classmethod
+    def get_test_params(cls, parameter_set="default"):
+        """Return testing parameter sets for automated tests."""
+        from sklearn.linear_model import LinearRegression
+
+        return [
+            {"regressor": LinearRegression(), "distr_type": "gaussian"},
+            {"regressor": LinearRegression(), "distr_type": "laplace"},
+        ]