set alpha=0 as default

Author: MatthiasSchmidtblaicherQC

src/glum/_glm.py

@@ -940,7 +940,7 @@ def _set_up_for_fit(self, y: np.ndarray) -> None:
             elif (self.lower_bounds is None) and (self.upper_bounds is None):
                 if np.all(np.asarray(self.l1_ratio) == 0):
                     self._solver = "irls-ls"
-                elif getattr(self, "alpha", 1) == 0 and not self.alpha_search:
+                elif getattr(self, "alpha", 0) == 0 and not self.alpha_search:
                     self._solver = "irls-ls"
                 else:
                     self._solver = "irls-cd"
@@ -2304,8 +2304,7 @@ def covariance_matrix(
             _expected_information = expected_information
 
         if (
-            (hasattr(self, "alpha") and self.alpha is None)
-            or (
+            (
                 hasattr(self, "alpha")
                 and isinstance(self.alpha, (int, float))
                 and self.alpha > 0
@@ -2914,11 +2913,11 @@ class GeneralizedLinearRegressor(GeneralizedLinearRegressorBase):
     alpha : {float, array-like}, optional (default=None)
         Constant that multiplies the penalty terms and thus determines the
         regularization strength. If ``alpha_search`` is ``False`` (the default),
-        then ``alpha`` must be a scalar or None (equivalent to ``alpha=1.0``).
+        then ``alpha`` must be a scalar or None (equivalent to ``alpha=0``).
         If ``alpha_search`` is ``True``, then ``alpha`` must be an iterable or
         ``None``. See ``alpha_search`` to find how the regularization path is
         set if ``alpha`` is ``None``. See the notes for the exact mathematical
-        meaning of this parameter. ``alpha = 0`` is equivalent to unpenalized
+        meaning of this parameter. ``alpha=0`` is equivalent to unpenalized
         GLMs. In this case, the design matrix ``X`` must have full column rank
         (no collinearities).
 
@@ -3146,10 +3145,11 @@ class GeneralizedLinearRegressor(GeneralizedLinearRegressorBase):
 
     drop_first : bool, optional (default = False)
         If ``True``, drop the first column when encoding categorical variables.
-        Set this to True when alpha=0 and solver='auto' to prevent an error due to a
-        singular feature matrix. In the case of using a formula with interactions,
-        setting this argument to ``True`` ensures structural full-rankness (it is
-        equivalent to ``ensure_full_rank`` in formulaic and tabmat).
+        Set this to True when ``alpha=0`` and ``solver='auto'`` to prevent an error
+        due to a singular feature matrix. In the case of using a formula with 
+        interactions, setting this argument to ``True`` ensures structural 
+        full-rankness (it is equivalent to ``ensure_full_rank`` in formulaic and 
+        tabmat).
 
     robust : bool, optional (default = False)
         If true, then robust standard errors are computed by default.
@@ -3573,7 +3573,7 @@ def fit(
                 self.coef_ = self.coef_path_[-1]
         else:
             if self.alpha is None:
-                _alpha = 1.0
+                _alpha = 0.0
             else:
                 _alpha = self.alpha
             if _alpha > 0 and self.l1_ratio > 0 and self._solver != "irls-cd":

tests/glm/test_distribution.py

@@ -296,7 +296,6 @@ def test_poisson_deviance_dispersion_loglihood(weighted):
     # logLik(glm_model)  # -7.390977 (df=1)
 
     regressor = GeneralizedLinearRegressor(
-        alpha=0,
         family="poisson",
         fit_intercept=False,
         gradient_tol=1e-8,
@@ -345,7 +344,6 @@ def test_gamma_deviance_dispersion_loglihood(weighted):
     # logLik(glm_model)  # -7.057068 (df=2)
 
     regressor = GeneralizedLinearRegressor(
-        alpha=0,
         family="gamma",
         fit_intercept=False,
         gradient_tol=1e-8,
@@ -393,7 +391,6 @@ def test_gaussian_deviance_dispersion_loglihood(family, weighted):
     # logLik(glm_model)  # -7.863404 (df=2)
 
     regressor = GeneralizedLinearRegressor(
-        alpha=0,
         family=family,
         fit_intercept=False,
         gradient_tol=1e-8,
@@ -441,7 +438,6 @@ def test_tweedie_deviance_dispersion_loglihood(weighted):
     # logLiktweedie(glm_model)  # -8.35485
 
     regressor = GeneralizedLinearRegressor(
-        alpha=0,
         family=TweedieDistribution(1.5),
         fit_intercept=False,
         gradient_tol=1e-8,
@@ -490,7 +486,6 @@ def test_binomial_deviance_dispersion_loglihood(weighted):
     # logLik(glm_model)  # -3.365058 (df=1)
 
     regressor = GeneralizedLinearRegressor(
-        alpha=0,
         family="binomial",
         fit_intercept=False,
         gradient_tol=1e-8,
@@ -535,7 +530,6 @@ def test_negative_binomial_deviance_dispersion_loglihood(weighted):
     # logLik(glm_model)  # -4.187887 (df=1)
 
     regressor = GeneralizedLinearRegressor(
-        alpha=0,
         family="negative.binomial",
         fit_intercept=False,
         gradient_tol=1e-8,