Update mirror for nightlies (#718)

.github/workflows/daily.yml

@@ -2,6 +2,7 @@ name: Daily runs
 on:
   schedule:
     - cron: '0 5 * * *'
+  workflow_dispatch:
   push:
     paths:
     - '.github/workflows/daily.yml'
@@ -34,17 +35,20 @@ jobs:
         run: |
           # needed for tabmat
           echo "Install compilation dependencies"
-          micromamba install -y c-compiler cxx-compiler cython jemalloc-local libgomp mako xsimd
+          micromamba install -y c-compiler cxx-compiler 'cython!=3.0.4' jemalloc-local libgomp mako xsimd
 
-          PRE_WHEELS="https://pypi.anaconda.org/scipy-wheels-nightly/simple"
+          PRE_WHEELS="https://pypi.anaconda.org/scientific-python-nightly-wheels/simple/"
           for pkg in numpy pandas scikit-learn scipy; do
             echo "Installing $pkg nightly"
             micromamba remove -y --force $pkg
             pip install --pre --no-deps --only-binary :all: --upgrade --timeout=60 -i $PRE_WHEELS $pkg
           done
+          echo Install pyarrow nightly
+          micromamba remove -y --force pyarrow
+          pip install --extra-index-url https://pypi.fury.io/arrow-nightlies/ --prefer-binary --pre --no-deps pyarrow
           echo Install tabmat nightly
           micromamba remove -y --force tabmat
-          pip install git+https://github.com/Quantco/tabmat
+          pip install --no-use-pep517 --no-deps git+https://github.com/Quantco/tabmat
       - name: Install repository
         shell: bash -el {0}
         run: pip install --no-use-pep517 --no-deps --disable-pip-version-check -e .

src/glum/_distribution.py

@@ -616,7 +616,7 @@ class TweedieDistribution(ExponentialDispersionModel):
         :math:`0 < \mathrm{power} < 1`, no distribution exists.
     """
 
-    upper_bound = np.Inf
+    upper_bound = np.inf
     include_upper_bound = False
 
     def __init__(self, power=0):
@@ -630,7 +630,7 @@ def __eq__(self, other):  # noqa D
     def lower_bound(self) -> float:
         """Return the lowest value of ``y`` allowed."""
         if self.power <= 0:
-            return -np.Inf
+            return -np.inf
         if self.power >= 1:
             return 0
         raise ValueError
@@ -904,8 +904,8 @@ class GeneralizedHyperbolicSecant(ExponentialDispersionModel):
     The GHS distribution is for targets ``y`` in ``(-∞, +∞)``.
     """
 
-    lower_bound = -np.Inf
-    upper_bound = np.Inf
+    lower_bound = -np.inf
+    upper_bound = np.inf
     include_lower_bound = False
     include_upper_bound = False
 
@@ -1133,7 +1133,7 @@ class NegativeBinomialDistribution(ExponentialDispersionModel):
     """
 
     lower_bound = 0
-    upper_bound = np.Inf
+    upper_bound = np.inf
     include_lower_bound = True
     include_upper_bound = False
 

src/glum/_glm.py

@@ -929,7 +929,11 @@ def _make_grid(max_alpha: float) -> np.ndarray:
                     warnings.warn("`min_alpha` is set. Ignoring `min_alpha_ratio`.")
                 min_alpha = self.min_alpha
             return np.logspace(
-                np.log(max_alpha), np.log(min_alpha), self.n_alphas, base=np.e
+                np.log(max_alpha),
+                np.log(min_alpha),
+                self.n_alphas,
+                base=np.e,
+                dtype=X.dtype,
             )
 
         if np.all(P1_no_alpha == 0):
@@ -1631,7 +1635,7 @@ def _wald_test_matrix(
         # We want to calculate Rb_r^T (RVR)^{-1} Rb_r.
         # We can do it in a more numerically stable way by using `scipy.linalg.solve`:
         try:
-            test_stat = float(Rb_r.T @ linalg.solve(RVR, Rb_r))
+            test_stat = (Rb_r.T @ linalg.solve(RVR, Rb_r))[0]
         except linalg.LinAlgError as err:
             raise linalg.LinAlgError("The restriction matrix is not full rank") from err
         p_value = 1 - stats.chi2.cdf(test_stat, Q)
@@ -2286,7 +2290,7 @@ def _expand_categorical_penalties(penalty, X, drop_first):
                             list(
                                 chain.from_iterable(
                                     [elmt for _ in dtype.categories[int(drop_first) :]]
-                                    if pd.api.types.is_categorical_dtype(dtype)
+                                    if isinstance(dtype, pd.CategoricalDtype)
                                     else [elmt]
                                     for elmt, dtype in zip(penalty, X.dtypes)
                                 )

src/glum/_glm_cv.py

@@ -454,7 +454,10 @@ def fit(
         if self.alphas is None:
             alphas = [self._get_alpha_path(l1, X, y, sample_weight) for l1 in l1_ratio]
         else:
-            alphas = np.tile(np.sort(self.alphas)[::-1], (len(l1_ratio), 1))
+            alphas = np.tile(
+                np.sort(np.asarray(self.alphas, dtype=X.dtype))[::-1],
+                (len(l1_ratio), 1),
+            )
 
         if len(l1_ratio) == 1:
             self.alphas_ = alphas[0]

src/glum/_solvers.py

@@ -916,7 +916,7 @@ def _trust_constr_solver(
         # we express constraints in the form A theta <= b
         constraints = LinearConstraint(
             A=A_ineq_,
-            lb=-np.Inf,
+            lb=-np.inf,
             ub=b_ineq,
         )
     else:

src/glum/_util.py

@@ -34,11 +34,11 @@ def _align_df_categories(df, dtypes) -> pd.DataFrame:
     categorical_dtypes = [
         column
         for column, dtype in dtypes.items()
-        if pd.api.types.is_categorical_dtype(dtype) and (column in df)
+        if isinstance(dtype, pd.CategoricalDtype) and (column in df)
     ]
 
     for column in categorical_dtypes:
-        if not pd.api.types.is_categorical_dtype(df[column]):
+        if not isinstance(df[column].dtype, pd.CategoricalDtype):
             _logger.info(f"Casting {column} to categorical.")
             changed_dtypes[column] = df[column].astype(dtypes[column])
         elif list(df[column].cat.categories) != list(dtypes[column].categories):

src/glum_benchmarks/orig_sklearn_fork/_glm.py

@@ -757,15 +757,15 @@ def power(self, power):
         if not isinstance(power, numbers.Real):
             raise TypeError("power must be a real number, input was {}".format(power))
 
-        self._upper_bound = np.Inf
+        self._upper_bound = np.inf
         self._include_upper_bound = False
         if power < 0:
             # Extreme Stable
-            self._lower_bound = -np.Inf
+            self._lower_bound = -np.inf
             self._include_lower_bound = False
         elif power == 0:
             # NormalDistribution
-            self._lower_bound = -np.Inf
+            self._lower_bound = -np.inf
             self._include_lower_bound = False
         elif (power > 0) and (power < 1):
             raise ValueError("For 0<power<1, no distribution exists.")
@@ -877,8 +877,8 @@ class GeneralizedHyperbolicSecant(ExponentialDispersionModel):
     """
 
     def __init__(self):
-        self._lower_bound = -np.Inf
-        self._upper_bound = np.Inf
+        self._lower_bound = -np.inf
+        self._upper_bound = np.inf
         self._include_lower_bound = False
         self._include_upper_bound = False
 

tests/glm/test_glm.py

@@ -844,12 +844,12 @@ def test_poisson_ridge(solver, tol, scale_predictors, use_sparse):
     # true_beta = model["beta"][:, 0]
     # print(true_intercept, true_beta)
 
-    X_dense = np.array([[-2, -1, 1, 2], [0, 0, 1, 1]], dtype=np.float_).T
+    X_dense = np.array([[-2, -1, 1, 2], [0, 0, 1, 1]], dtype=np.float64).T
     if use_sparse:
         X = sparse.csc_matrix(X_dense)
     else:
         X = X_dense
-    y = np.array([0, 1, 1, 2], dtype=np.float_)
+    y = np.array([0, 1, 1, 2], dtype=np.float64)
     model_args = dict(
         alpha=1,
         l1_ratio=0,
@@ -891,8 +891,8 @@ def check(G):
 
 @pytest.mark.parametrize("scale_predictors", [True, False])
 def test_poisson_ridge_bounded(scale_predictors):
-    X = np.array([[-1, 1, 1, 2], [0, 0, 1, 1]], dtype=np.float_).T
-    y = np.array([0, 1, 1, 2], dtype=np.float_)
+    X = np.array([[-1, 1, 1, 2], [0, 0, 1, 1]], dtype=np.float64).T
+    y = np.array([0, 1, 1, 2], dtype=np.float64)
     lb = np.array([-0.1, -0.1])
     ub = np.array([0.1, 0.1])
 
@@ -930,8 +930,8 @@ def test_poisson_ridge_bounded(scale_predictors):
 
 @pytest.mark.parametrize("scale_predictors", [True, False])
 def test_poisson_ridge_ineq_constrained(scale_predictors):
-    X = np.array([[-1, 1, 1, 2], [0, 0, 1, 1]], dtype=np.float_).T
-    y = np.array([0, 1, 1, 2], dtype=np.float_)
+    X = np.array([[-1, 1, 1, 2], [0, 0, 1, 1]], dtype=np.float64).T
+    y = np.array([0, 1, 1, 2], dtype=np.float64)
     A_ineq = np.array([[1, 0], [0, 1], [-1, 0], [0, -1]])
     b_ineq = 0.1 * np.ones(shape=(4))
 
@@ -1472,7 +1472,7 @@ def test_clonable(estimator):
 def test_get_best_intercept(
     link: Link, distribution: ExponentialDispersionModel, tol: float, offset
 ):
-    y = np.array([1, 1, 1, 2], dtype=np.float_)
+    y = np.array([1, 1, 1, 2], dtype=np.float64)
     if isinstance(distribution, BinomialDistribution):
         y -= 1
 
@@ -2077,7 +2077,7 @@ def test_wald_test_matrix(regression_data, family, fit_intercept, R, r):
     )
 
     np.testing.assert_allclose(
-        our_results.test_statistic, sm_results.statistic, rtol=1e-3
+        our_results.test_statistic, sm_results.statistic[0], rtol=1e-3
     )
     np.testing.assert_allclose(our_results.p_value, sm_results.pvalue, atol=1e-3)
     assert our_results.df == sm_results.df_denom
@@ -2090,7 +2090,7 @@ def test_wald_test_matrix(regression_data, family, fit_intercept, R, r):
     )
 
     np.testing.assert_allclose(
-        our_results.test_statistic, sm_results.statistic, rtol=1e-3
+        our_results.test_statistic, sm_results.statistic[0], rtol=1e-3
     )
     np.testing.assert_allclose(our_results.p_value, sm_results.pvalue, atol=1e-3)
     assert our_results.df == sm_results.df_denom
@@ -2103,7 +2103,7 @@ def test_wald_test_matrix(regression_data, family, fit_intercept, R, r):
     sm_results = sm_fit.wald_test((R, r), scalar=False)
 
     np.testing.assert_allclose(
-        our_results.test_statistic, sm_results.statistic, rtol=1e-3
+        our_results.test_statistic, sm_results.statistic[0], rtol=1e-3
     )
     np.testing.assert_allclose(our_results.p_value, sm_results.pvalue, atol=1e-3)
     assert our_results.df == sm_results.df_denom
@@ -2161,7 +2161,7 @@ def test_wald_test_matrix_fixed_cov(regression_data, R, r):
     sm_results = fit_sm.wald_test((R, r), cov_p=mdl.covariance_matrix(), scalar=False)
 
     np.testing.assert_allclose(
-        our_results.test_statistic, sm_results.statistic, rtol=1e-8
+        our_results.test_statistic, sm_results.statistic[0], rtol=1e-8
     )
     np.testing.assert_allclose(our_results.p_value, sm_results.pvalue, atol=1e-8)
     assert our_results.df == sm_results.df_denom