scikit-learn · xiaowei1234 · Feb 11, 2022 · Feb 14, 2022 · Feb 11, 2022 · Feb 14, 2022
diff --git a/doc/whats_new/_contributors.rst b/doc/whats_new/_contributors.rst
@@ -176,4 +176,6 @@
 
 .. _Nicolas Hug: https://github.com/NicolasHug
 
-.. _Guillaume Lemaitre: https://github.com/glemaitre
+.. _Guillaume Lemaitre: https://github.com/glemaitre
+
+.. _Xiao Wei: https://github.com/xiaowei1234
diff --git a/doc/whats_new/v1.1.rst b/doc/whats_new/v1.1.rst
@@ -537,6 +537,12 @@ Changelog
   `alpha`, `max_iter` and `tol`.
   :pr:`22240` by :user:`Arturo Amor <ArturoAmorQ>`.
 
+- |Enhancement| :class:`linear_model.PoissonRegressor`, `linear_model.GammaRegressor`,
+  and `linear_model.TweedieRegressor` fit methods will now allow penalty term `alpha`
+  to be an iterable of same length as the number of features in X in addition to a
+  scalar value.
+  :pr:`22485` by :user:`Xiao Wei <xiaowei1234>`.
+
 - |Fix| :class:`linear_model.LogisticRegression` and
   :class:`linear_model.LogisticRegressionCV` now set the `n_iter_` attribute
   with a shape that respects the docstring and that is consistent with the shape

diff --git a/sklearn/linear_model/_glm/glm.py b/sklearn/linear_model/_glm/glm.py
@@ -7,6 +7,7 @@
 # License: BSD 3 clause
 
 import numbers
+from collections.abc import Iterable
 
 import numpy as np
 import scipy.optimize
@@ -68,12 +69,16 @@ class GeneralizedLinearRegressor(RegressorMixin, BaseEstimator):
 
     Parameters
     ----------
-    alpha : float, default=1
-        Constant that multiplies the penalty term and thus determines the
+    alpha : {float, array-like}, default=1
+        Constant(s) that multiplies the penalty term and thus determines the
         regularization strength. ``alpha = 0`` is equivalent to unpenalized
         GLMs. In this case, the design matrix `X` must have full column rank
         (no collinearities).
         Values must be in the range `[0.0, inf)`.
+        If alpha is a scalar then the value is applied to all non-intercept terms
+        If alpha is an array-like then each value must be in the range `[0.0, inf)`
+        and the length must equal to n_features.
+        If alpha is greater than 1 dimension it will be converted to 1 dimension.
 
     fit_intercept : bool, default=True
         Specifies if a constant (a.k.a. bias or intercept) should be
@@ -213,14 +218,6 @@ def fit(self, X, y, sample_weight=None):
                     "an element of ['auto', 'identity', 'log']; "
                     "got (link={0})".format(self.link)
                 )
-
-        check_scalar(
-            self.alpha,
-            name="alpha",
-            target_type=numbers.Real,
-            min_val=0.0,
-            include_boundaries="left",
-        )
         if not isinstance(self.fit_intercept, bool):
             raise ValueError(
                 "The argument fit_intercept must be bool; got {0}".format(
@@ -268,7 +265,29 @@ def fit(self, X, y, sample_weight=None):
             y_numeric=True,
             multi_output=False,
         )
-
+        if isinstance(self.alpha, Iterable) and not isinstance(self.alpha, str):
+            for i, val in enumerate(self.alpha):
+                check_scalar(
+                    val,
+                    name=f"alpha at index {i}",
+                    target_type=numbers.Real,
+                    min_val=0.0,
+                    include_boundaries="left",
+                )
+            self.alpha = np.asarray(self.alpha, dtype=np.float64).ravel()
+            if self.alpha.size != X.shape[1]:
+                raise ValueError(
+                    f"X width is {X.shape[1]} while alpha is of length"
+                    f" {self.alpha.size}"
+                )
+        else:
+            check_scalar(
+                self.alpha,
+                name="alpha",
+                target_type=numbers.Real,
+                min_val=0.0,
+                include_boundaries="left",
+            )
         weights = _check_sample_weight(sample_weight, X)
 
         _, n_features = X.shape

diff --git a/sklearn/linear_model/_glm/tests/test_glm.py b/sklearn/linear_model/_glm/tests/test_glm.py
@@ -195,6 +195,60 @@ def test_glm_scalar_argument(Estimator, params, err_type, err_msg):
         glm.fit(X, y)
 
 
+@pytest.mark.parametrize(
+    "Estimator",
+    [GeneralizedLinearRegressor, PoissonRegressor, GammaRegressor, TweedieRegressor],
+)
+@pytest.mark.parametrize(
+    "params, err_type, err_msg",
+    [
+        (
+            {"alpha": [1, "2"]},
+            TypeError,
+            "alpha at index 1 must be an instance of float, not str.",
+        ),
+        (
+            {"alpha": [1, 2, 3], "fit_intercept": True},
+            ValueError,
+            "X width is 2 while alpha is of length 3",
+        ),
+        (
+            {"alpha": [1, 2, 3], "fit_intercept": False},
+            ValueError,
+            "X width is 2 while alpha is of length 3",
+        ),
+        ({"alpha": [-2, 2]}, ValueError, "alpha at index 0 == -2, must be >= 0.0"),
+    ],
+)
+def test_glm_alpha_array(Estimator, params, err_type, err_msg):
+    """Test GLM for invalid alpha input when alpha is an iterable"""
+    X = [[1, 2], [2, 4]]
+    y = [1, 2]
+    glm = Estimator(**params)
+    with pytest.raises(err_type, match=err_msg):
+        glm.fit(X, y)
+
+
+@pytest.mark.parametrize(
+    "Estimator",
+    [GeneralizedLinearRegressor, PoissonRegressor, GammaRegressor, TweedieRegressor],
+)
+def test_glm_alpha_array_reg(Estimator):
+    """Test GLM regression when alpha is an array and 2nd column
+    has different alpha than 1st column
+    """
+    X = np.asarray([[1, 2], [1, 3], [1, 4], [1, 3]])
+    y = np.asarray([2, 2, 3, 2])
+    scalar_coefs = Estimator(alpha=1.0, fit_intercept=False).fit(X, y).coef_
+    X_scaled = X.copy()
+    X_scaled[:, 1] = X_scaled[:, 1] * 2.0
+    array_coefs = (
+        Estimator(alpha=[1.0, 4.0], fit_intercept=False).fit(X_scaled, y).coef_
+    )
+    array_coefs[1] *= 2.0
+    assert_allclose(scalar_coefs, array_coefs, atol=1e-4)
+
+
 @pytest.mark.parametrize("warm_start", ["not bool", 1, 0, [True]])
 def test_glm_warm_start_argument(warm_start):
     """Test GLM for invalid warm_start argument."""