From a3ab23bd8d26f5a7c90c651ba30fd394d3247eff Mon Sep 17 00:00:00 2001
From: cajchristian <114787994+cajchristian@users.noreply.github.com>
Date: Thu, 6 Feb 2025 14:35:17 -0600
Subject: [PATCH 01/13] Fixed `_ndim_coords_from_arrays` import

---
 src/skmatter/sample_selection/_base.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/skmatter/sample_selection/_base.py b/src/skmatter/sample_selection/_base.py
index f5531d897..67d5f0472 100644
--- a/src/skmatter/sample_selection/_base.py
+++ b/src/skmatter/sample_selection/_base.py
@@ -4,7 +4,7 @@
 
 import numpy as np
 from scipy.interpolate import LinearNDInterpolator, interp1d
-from scipy.interpolate.interpnd import _ndim_coords_from_arrays
+from scipy.interpolate._interpnd import _ndim_coords_from_arrays
 from scipy.spatial import ConvexHull
 from sklearn.utils.validation import check_array, check_is_fitted, check_X_y
 

From 941a77f0d32eaaa917c5499ab1155f377b50e7ce Mon Sep 17 00:00:00 2001
From: cajchristian <114787994+cajchristian@users.noreply.github.com>
Date: Fri, 7 Feb 2025 14:50:20 -0600
Subject: [PATCH 02/13] Adding `validate_data` calls and tags for CUR, FPS,
 PCovCUR, and PCovFPS

---
 src/skmatter/_selection.py | 62 +++++++++++++++++++++++++++++---------
 1 file changed, 47 insertions(+), 15 deletions(-)

diff --git a/src/skmatter/_selection.py b/src/skmatter/_selection.py
index 6869a2235..c0fa189d9 100644
--- a/src/skmatter/_selection.py
+++ b/src/skmatter/_selection.py
@@ -83,8 +83,13 @@
 from scipy.sparse.linalg import eigsh
 from sklearn.base import BaseEstimator, MetaEstimatorMixin
 from sklearn.feature_selection._base import SelectorMixin
-from sklearn.utils import check_array, check_random_state, check_X_y, safe_mask
-from sklearn.utils.validation import FLOAT_DTYPES, as_float_array, check_is_fitted
+from sklearn.utils import check_random_state, safe_mask
+from sklearn.utils.validation import (
+    FLOAT_DTYPES,
+    as_float_array,
+    check_is_fitted,
+    validate_data,
+)
 
 from .utils import (
     X_orthogonalizer,
@@ -157,11 +162,6 @@ def __init__(
         self.n_to_select = n_to_select
         self.score_threshold = score_threshold
         self.score_threshold_type = score_threshold_type
-        if self.score_threshold_type not in ["relative", "absolute"]:
-            raise ValueError(
-                "invalid score_threshold_type, expected one of 'relative' or 'absolute'"
-            )
-
         self.full = full
         self.progress_bar = progress_bar
         self.random_state = random_state
@@ -184,6 +184,11 @@ def fit(self, X, y=None, warm_start=False):
         -------
         self : object
         """
+        if self.score_threshold_type not in ["relative", "absolute"]:
+            raise ValueError(
+                "invalid score_threshold_type, expected one of 'relative' or 'absolute'"
+            )
+
         if self.selection_type == "feature":
             self._axis = 1
         elif self.selection_type == "sample":
@@ -205,7 +210,7 @@ def fit(self, X, y=None, warm_start=False):
 
         if hasattr(self, "mixing") or y is not None:
             X, y = self._validate_data(X, y, **params)
-            X, y = check_X_y(X, y, multi_output=True)
+            X, y = validate_data(self, X, y, multi_output=True)
 
             if len(y.shape) == 1:
                 # force y to have multi_output 2D format even when it's 1D, since
@@ -214,7 +219,7 @@ def fit(self, X, y=None, warm_start=False):
                 y = y.reshape((len(y), 1))
 
         else:
-            X = check_array(X, **params)
+            X = validate_data(self, X, **params)
 
         if self.full and self.score_threshold is not None:
             raise ValueError(
@@ -308,7 +313,7 @@ def transform(self, X, y=None):
 
         mask = self.get_support()
 
-        X = check_array(X)
+        X = validate_data(self, X, reset=False)
 
         if len(X.shape) == 1:
             if self._axis == 0:
@@ -486,6 +491,11 @@ def _more_tags(self):
             "requires_y": False,
         }
 
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.target_tags.required = False
+        return tags
+
 
 class _CUR(GreedySelector):
     """Transformer that performs Greedy Selection by choosing features
@@ -560,6 +570,9 @@ def score(self, X, y=None):
         score : numpy.ndarray of (n_to_select_from_)
             :math:`\pi` importance for the given samples or features
         """
+
+        X, y = validate_data(self, X, y, reset=False)
+
         return self.pi_
 
     def _init_greedy_search(self, X, y, n_to_select):
@@ -734,6 +747,9 @@ def score(self, X, y=None):
         score : numpy.ndarray of (n_to_select_from_)
             :math:`\pi` importance for the given samples or features
         """
+
+        X, y = validate_data(self, X, y, reset=False)
+
         return self.pi_
 
     def _init_greedy_search(self, X, y, n_to_select):
@@ -927,6 +943,9 @@ def score(self, X, y=None):
         -------
         hausdorff : Hausdorff distances
         """
+
+        X, y = validate_data(self, X, y, reset=False)
+
         return self.hausdorff_
 
     def get_distance(self):
@@ -1048,11 +1067,6 @@ def __init__(
         full=False,
         random_state=0,
     ):
-        if mixing == 1.0:
-            raise ValueError(
-                "Mixing = 1.0 corresponds to traditional FPS."
-                "Please use the FPS class."
-            )
 
         self.mixing = mixing
         self.initialize = initialize
@@ -1067,6 +1081,16 @@ def __init__(
             random_state=random_state,
         )
 
+    def fit(self, X, y=None, warm_start=False):
+
+        if self.mixing == 1.0:
+            raise ValueError(
+                "Mixing = 1.0 corresponds to traditional FPS."
+                "Please use the FPS class."
+            )
+
+        return super().fit(X, y)
+
     def score(self, X, y=None):
         """Returns the Hausdorff distances of all samples to previous selections.
 
@@ -1083,6 +1107,9 @@ def score(self, X, y=None):
         -------
         hausdorff : Hausdorff distances
         """
+
+        X, y = validate_data(self, X, y, reset=False)
+
         return self.hausdorff_
 
     def get_distance(self):
@@ -1159,3 +1186,8 @@ def _more_tags(self):
         return {
             "requires_y": True,
         }
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.target_tags.required = True
+        return tags

From 42d11fb6810d7a506610cd59281368842eb72808 Mon Sep 17 00:00:00 2001
From: cajchristian <114787994+cajchristian@users.noreply.github.com>
Date: Fri, 7 Feb 2025 15:07:42 -0600
Subject: [PATCH 03/13] Adding `validate_data` calls and updated tags to
 Ridge2FoldCV

---
 src/skmatter/linear_model/_ridge.py | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/src/skmatter/linear_model/_ridge.py b/src/skmatter/linear_model/_ridge.py
index 6e4fcf1f3..57e5a21a8 100644
--- a/src/skmatter/linear_model/_ridge.py
+++ b/src/skmatter/linear_model/_ridge.py
@@ -1,13 +1,12 @@
 import numpy as np
 from joblib import Parallel, delayed
-from sklearn.base import BaseEstimator, MultiOutputMixin, RegressorMixin
+from sklearn.base import RegressorMixin, MultiOutputMixin, BaseEstimator
 from sklearn.metrics import check_scoring
 from sklearn.model_selection import KFold, check_cv
-from sklearn.utils import check_array
-from sklearn.utils.validation import check_is_fitted
+from sklearn.utils.validation import check_is_fitted, validate_data
 
 
-class Ridge2FoldCV(BaseEstimator, MultiOutputMixin, RegressorMixin):
+class Ridge2FoldCV(RegressorMixin, MultiOutputMixin, BaseEstimator):
     r"""Ridge regression with an efficient 2-fold cross-validation method using the SVD
     solver.
 
@@ -20,7 +19,7 @@ class Ridge2FoldCV(BaseEstimator, MultiOutputMixin, RegressorMixin):
     while the alpha value is determined with a 2-fold cross-validation from a list of
     alpha values. It is more efficient version than doing 2-fold cross-validation
     naively The algorithmic trick is to reuse the matrices obtained by SVD for each
-    regularization paramater :param alpha: The 2-fold CV can be broken donw to
+    regularization paramater :param alpha: The 2-fold CV can be broken down to
 
     .. math::
 
@@ -136,6 +135,11 @@ def __init__(
         self.shuffle = shuffle
         self.n_jobs = n_jobs
 
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.target_tags.single_output = False
+        return tags
+
     def _more_tags(self):
         return {"multioutput_only": True}
 
@@ -195,7 +199,7 @@ def predict(self, X):
             Training data, where n_samples is the number of samples
             and n_features is the number of features.
         """
-        X = check_array(X)
+        X = validate_data(self, X, reset=False)
 
         check_is_fitted(self, ["coef_"])
 

From 29c5a9dc33154dce962e8432c9e6d1eea826f586 Mon Sep 17 00:00:00 2001
From: cajchristian <114787994+cajchristian@users.noreply.github.com>
Date: Fri, 7 Feb 2025 15:59:08 -0600
Subject: [PATCH 04/13] Added `validate_data` calls to PCovR

---
 src/skmatter/decomposition/_pcovr.py | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/src/skmatter/decomposition/_pcovr.py b/src/skmatter/decomposition/_pcovr.py
index ddaf3bebd..5adfa3f3a 100644
--- a/src/skmatter/decomposition/_pcovr.py
+++ b/src/skmatter/decomposition/_pcovr.py
@@ -10,10 +10,10 @@
 from sklearn.decomposition._pca import _infer_dimension
 from sklearn.linear_model import LinearRegression, Ridge, RidgeCV
 from sklearn.linear_model._base import LinearModel
-from sklearn.utils import check_array, check_random_state
+from sklearn.utils import check_random_state
 from sklearn.utils._arpack import _init_arpack_v0
 from sklearn.utils.extmath import randomized_svd, stable_cumsum, svd_flip
-from sklearn.utils.validation import check_is_fitted, check_X_y
+from sklearn.utils.validation import check_is_fitted, validate_data
 
 from ..utils import check_lr_fit, pcovr_covariance, pcovr_kernel
 
@@ -221,7 +221,8 @@ def fit(self, X, Y, W=None):
             Regression weights, optional when regressor=`precomputed`. If not
             passed, it is assumed that `W = np.linalg.lstsq(X, Y, self.tol)[0]`
         """
-        X, Y = check_X_y(X, Y, y_numeric=True, multi_output=True)
+
+        X, Y = validate_data(self, X, Y, y_numeric=True, multi_output=True)
 
         # saved for inverse transformations from the latent space,
         # should be zero in the case that the features have been properly centered
@@ -582,10 +583,10 @@ def predict(self, X=None, T=None):
             raise ValueError("Either X or T must be supplied.")
 
         if X is not None:
-            X = check_array(X)
+            X = validate_data(self, X, reset=False)
             return X @ self.pxy_
         else:
-            T = check_array(T)
+            T = validate_data(self, T, reset=False)
             return T @ self.pty_
 
     def transform(self, X=None):
@@ -604,7 +605,7 @@ def transform(self, X=None):
 
         return super().transform(X)
 
-    def score(self, X, Y, T=None):
+    def score(self, X, y, T=None):
         r"""Return the (negative) total reconstruction error for X and Y,
         defined as:
 
@@ -635,13 +636,16 @@ def score(self, X, Y, T=None):
             Negative sum of the loss in reconstructing X from the latent-space
             projection T and the loss in predicting Y from the latent-space projection T
         """
+
+        X, y = validate_data(self, X, y, reset=False)
+
         if T is None:
             T = self.transform(X)
 
-        x = self.inverse_transform(T)
-        y = self.predict(T=T)
+        Xrec = self.inverse_transform(T)
+        ypred = self.predict(T=T)
 
         return -(
-            np.linalg.norm(X - x) ** 2.0 / np.linalg.norm(X) ** 2.0
-            + np.linalg.norm(Y - y) ** 2.0 / np.linalg.norm(Y) ** 2.0
+            np.linalg.norm(X - Xrec) ** 2.0 / np.linalg.norm(X) ** 2.0
+            + np.linalg.norm(y - ypred) ** 2.0 / np.linalg.norm(y) ** 2.0
         )

From d38d375c0c42f45750caeeae2518a1a1e2f56996 Mon Sep 17 00:00:00 2001
From: cajchristian <114787994+cajchristian@users.noreply.github.com>
Date: Fri, 7 Feb 2025 16:16:06 -0600
Subject: [PATCH 05/13] Added `validate_data` calls to KPCovR

---
 src/skmatter/decomposition/_kernel_pcovr.py | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/src/skmatter/decomposition/_kernel_pcovr.py b/src/skmatter/decomposition/_kernel_pcovr.py
index 84a9439e1..65fe39a3e 100644
--- a/src/skmatter/decomposition/_kernel_pcovr.py
+++ b/src/skmatter/decomposition/_kernel_pcovr.py
@@ -9,10 +9,10 @@
 from sklearn.kernel_ridge import KernelRidge
 from sklearn.linear_model._base import LinearModel
 from sklearn.metrics.pairwise import pairwise_kernels
-from sklearn.utils import check_array, check_random_state
+from sklearn.utils import check_random_state
 from sklearn.utils._arpack import _init_arpack_v0
 from sklearn.utils.extmath import randomized_svd, stable_cumsum, svd_flip
-from sklearn.utils.validation import check_is_fitted, check_X_y
+from sklearn.utils.validation import check_is_fitted, validate_data
 
 from ..preprocessing import KernelNormalizer
 from ..utils import check_krr_fit, pcovr_kernel
@@ -270,7 +270,7 @@ def fit(self, X, Y, W=None):
         ):
             raise ValueError("Regressor must be an instance of `KernelRidge`")
 
-        X, Y = check_X_y(X, Y, y_numeric=True, multi_output=True)
+        X, Y = validate_data(self, X, Y, y_numeric=True, multi_output=True)
         self.X_fit_ = X.copy()
 
         if self.n_components is None:
@@ -387,7 +387,7 @@ def predict(self, X=None):
         """Predicts the property values"""
         check_is_fitted(self, ["pky_", "pty_"])
 
-        X = check_array(X)
+        X = validate_data(self, X, reset=False)
         K = self._get_kernel(X, self.X_fit_)
         if self.center:
             K = self.centerer_.transform(K)
@@ -408,7 +408,7 @@ def transform(self, X):
         """
         check_is_fitted(self, ["pkt_", "X_fit_"])
 
-        X = check_array(X)
+        X = validate_data(self, X, reset=False)
         K = self._get_kernel(X, self.X_fit_)
 
         if self.center:
@@ -440,7 +440,7 @@ def inverse_transform(self, T):
         """
         return T @ self.ptx_
 
-    def score(self, X, Y):
+    def score(self, X, y):
         r"""Computes the (negative) loss values for KernelPCovR on the given predictor
         and response variables. The loss in :math:`\mathbf{K}`, as explained in
         [Helfrecht2020]_ does not correspond to a traditional Gram loss
@@ -474,7 +474,7 @@ def score(self, X, Y):
         """
         check_is_fitted(self, ["pkt_", "X_fit_"])
 
-        X = check_array(X)
+        X, y = validate_data(self, X, y, reset=False)
 
         K_NN = self._get_kernel(self.X_fit_, self.X_fit_)
         K_VN = self._get_kernel(X, self.X_fit_)
@@ -485,8 +485,8 @@ def score(self, X, Y):
             K_VN = self.centerer_.transform(K_VN)
             K_VV = self.centerer_.transform(K_VV)
 
-        y = K_VN @ self.pky_
-        Lkrr = np.linalg.norm(Y - y) ** 2 / np.linalg.norm(Y) ** 2
+        ypred = K_VN @ self.pky_
+        Lkrr = np.linalg.norm(y - ypred) ** 2 / np.linalg.norm(y) ** 2
 
         t_n = K_NN @ self.pkt_
         t_v = K_VN @ self.pkt_

From 9ae1cc501b998ad1a6cf1d3d5b4167b583326a04 Mon Sep 17 00:00:00 2001
From: cajchristian <114787994+cajchristian@users.noreply.github.com>
Date: Fri, 7 Feb 2025 16:32:08 -0600
Subject: [PATCH 06/13] Fixing linting

---
 src/skmatter/_selection.py           | 4 ----
 src/skmatter/decomposition/_pcovr.py | 2 --
 src/skmatter/linear_model/_ridge.py  | 2 +-
 3 files changed, 1 insertion(+), 7 deletions(-)

diff --git a/src/skmatter/_selection.py b/src/skmatter/_selection.py
index c0fa189d9..50e55cff3 100644
--- a/src/skmatter/_selection.py
+++ b/src/skmatter/_selection.py
@@ -570,7 +570,6 @@ def score(self, X, y=None):
         score : numpy.ndarray of (n_to_select_from_)
             :math:`\pi` importance for the given samples or features
         """
-
         X, y = validate_data(self, X, y, reset=False)
 
         return self.pi_
@@ -747,7 +746,6 @@ def score(self, X, y=None):
         score : numpy.ndarray of (n_to_select_from_)
             :math:`\pi` importance for the given samples or features
         """
-
         X, y = validate_data(self, X, y, reset=False)
 
         return self.pi_
@@ -943,7 +941,6 @@ def score(self, X, y=None):
         -------
         hausdorff : Hausdorff distances
         """
-
         X, y = validate_data(self, X, y, reset=False)
 
         return self.hausdorff_
@@ -1107,7 +1104,6 @@ def score(self, X, y=None):
         -------
         hausdorff : Hausdorff distances
         """
-
         X, y = validate_data(self, X, y, reset=False)
 
         return self.hausdorff_
diff --git a/src/skmatter/decomposition/_pcovr.py b/src/skmatter/decomposition/_pcovr.py
index 5adfa3f3a..8cdd24680 100644
--- a/src/skmatter/decomposition/_pcovr.py
+++ b/src/skmatter/decomposition/_pcovr.py
@@ -221,7 +221,6 @@ def fit(self, X, Y, W=None):
             Regression weights, optional when regressor=`precomputed`. If not
             passed, it is assumed that `W = np.linalg.lstsq(X, Y, self.tol)[0]`
         """
-
         X, Y = validate_data(self, X, Y, y_numeric=True, multi_output=True)
 
         # saved for inverse transformations from the latent space,
@@ -636,7 +635,6 @@ def score(self, X, y, T=None):
             Negative sum of the loss in reconstructing X from the latent-space
             projection T and the loss in predicting Y from the latent-space projection T
         """
-
         X, y = validate_data(self, X, y, reset=False)
 
         if T is None:
diff --git a/src/skmatter/linear_model/_ridge.py b/src/skmatter/linear_model/_ridge.py
index 57e5a21a8..9dd5e1678 100644
--- a/src/skmatter/linear_model/_ridge.py
+++ b/src/skmatter/linear_model/_ridge.py
@@ -1,6 +1,6 @@
 import numpy as np
 from joblib import Parallel, delayed
-from sklearn.base import RegressorMixin, MultiOutputMixin, BaseEstimator
+from sklearn.base import BaseEstimator, MultiOutputMixin, RegressorMixin
 from sklearn.metrics import check_scoring
 from sklearn.model_selection import KFold, check_cv
 from sklearn.utils.validation import check_is_fitted, validate_data

From ad9e59c916136a0f6f8a7a4a872db2ea4cc1c500 Mon Sep 17 00:00:00 2001
From: Philip Loche <ploche@physik.fu-berlin.de>
Date: Tue, 28 Jan 2025 16:52:28 +0100
Subject: [PATCH 07/13] Fix rendering issues and depencies

---
 CHANGELOG      | 1 +
 pyproject.toml | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG b/CHANGELOG
index 46008bb47..7d9c0e581 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -13,6 +13,7 @@ The rules for CHANGELOG file:
 
 0.3.0 (XXXX/XX/XX)
 ------------------
+- Fixed moved function import from scipy and bump scipy dependency to 1.15.0 (#236)
 - Fix rendering issues for `SparseKDE` and `QuickShift` (#236)
 - Updating ``FPS`` to allow a numpy array of ints as an initialize parameter (#145)
 - Supported Python versions are now ranging from 3.9 - 3.12.
diff --git a/pyproject.toml b/pyproject.toml
index e05c76026..4c31a977e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -38,8 +38,8 @@ classifiers = [
     "Topic :: Scientific/Engineering",
 ]
 dependencies = [
-    "scikit-learn < 1.6.0",
-    "scipy < 1.15.0",
+    "scikit-learn >= 1.1.0",
+    "scipy >= 1.15.0",  # explicit here since need a newer version as scikit-learn
 ]
 dynamic = ["version"]
 

From 7f80d783108c7b6af036660dfa6f6a249bd190d5 Mon Sep 17 00:00:00 2001
From: Philip Loche <ploche@physik.fu-berlin.de>
Date: Thu, 13 Feb 2025 12:06:13 +0100
Subject: [PATCH 08/13] update pyproject.toml

---
 pyproject.toml                         | 2 +-
 src/skmatter/sample_selection/_base.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 4c31a977e..db7056b63 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -38,7 +38,7 @@ classifiers = [
     "Topic :: Scientific/Engineering",
 ]
 dependencies = [
-    "scikit-learn >= 1.1.0",
+    "scikit-learn >= 1.6.0",
     "scipy >= 1.15.0",  # explicit here since need a newer version as scikit-learn
 ]
 dynamic = ["version"]
diff --git a/src/skmatter/sample_selection/_base.py b/src/skmatter/sample_selection/_base.py
index 67d5f0472..0abdca1fa 100644
--- a/src/skmatter/sample_selection/_base.py
+++ b/src/skmatter/sample_selection/_base.py
@@ -509,7 +509,7 @@ class DirectionalConvexHull:
     selected_idx_ : numpy.ndarray
                     Indices of datapoints that form the vertices of the
                     convex hull
-    interpolator_high_dim_  : scipy.interpolate.interpnd.LinearNDInterpolator
+    interpolator_high_dim_  : scipy.interpolate._interpnd.LinearNDInterpolator
                     Interpolator for the features in the high-
                     dimensional space
 

From feb10b0bf25ae8586c3b08f862131fdc8c936c19 Mon Sep 17 00:00:00 2001
From: Philip Loche <ploche@physik.fu-berlin.de>
Date: Thu, 13 Feb 2025 14:05:20 +0100
Subject: [PATCH 09/13] fix some tests

---
 .github/workflows/build.yml                   |   2 +-
 .github/workflows/docs.yml                    |   2 +-
 .github/workflows/lint.yml                    |   2 +-
 .github/workflows/tests.yml                   |   2 +-
 .gitignore                                    |   1 +
 .readthedocs.yaml                             |   2 +-
 pyproject.toml                                |   5 +-
 src/skmatter/_selection.py                    |  22 ++--
 src/skmatter/decomposition/_kernel_pcovr.py   |   2 +-
 src/skmatter/decomposition/_pcovr.py          |   4 +-
 src/skmatter/utils/_pcovr_utils.py            | 109 +++++++++++-------
 ...e.tsf-492-wpa-0-247.epfl.ch.11311.XpjwIfdx | Bin 53248 -> 0 bytes
 tests/test_feature_pcov_fps.py                |   5 +-
 tests/test_greedy_selector.py                 |   8 +-
 tests/test_kernel_pcovr.py                    |   4 +-
 tests/test_pcovr.py                           |   9 +-
 tests/test_sample_pcov_fps.py                 |   5 +-
 17 files changed, 105 insertions(+), 79 deletions(-)
 delete mode 100644 tests/.coverage.tsf-492-wpa-0-247.epfl.ch.11311.XpjwIfdx

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 058303f65..61e753ea9 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -15,7 +15,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: "3.12"
+        python-version: "3.13"
 
     - name: install tests dependencies
       run: python -m pip install tox
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
index 75b82499a..1fa0d4420 100644
--- a/.github/workflows/docs.yml
+++ b/.github/workflows/docs.yml
@@ -16,7 +16,7 @@ jobs:
       - name: setup Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: "3.13"
 
       - name: install tests dependencies
         run: python -m pip install tox
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
index 1108289fd..5ae3af316 100644
--- a/.github/workflows/lint.yml
+++ b/.github/workflows/lint.yml
@@ -14,7 +14,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: "3.12"
+        python-version: "3.13"
 
     - name: install tests dependencies
       run: python -m pip install tox
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index d9ebe3475..fe3609798 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -12,7 +12,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-22.04, macos-14, windows-2022]
-        python-version: ["3.9", "3.12"]
+        python-version: ["3.0", "3.13"]
 
     steps:
     - uses: actions/checkout@v4
diff --git a/.gitignore b/.gitignore
index 226933088..1f74b6f04 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,4 @@
+*.coverage*
 *.pyc
 *.ipynb_checkpoints*
 __pycache__
diff --git a/.readthedocs.yaml b/.readthedocs.yaml
index 71882236f..b4c827c42 100644
--- a/.readthedocs.yaml
+++ b/.readthedocs.yaml
@@ -9,7 +9,7 @@ version: 2
 build:
   os: ubuntu-22.04
   tools:
-    python: "3.12"
+    python: "3.13"
   
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
diff --git a/pyproject.toml b/pyproject.toml
index db7056b63..374d06293 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -19,7 +19,7 @@ authors = [
     {name = "Michele Ceriotti"}
 ]
 readme = "README.rst"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 license = {text = "BSD-3-Clause"}
 classifiers = [
     "Development Status :: 4 - Beta",
@@ -75,9 +75,6 @@ include = [
 [tool.coverage.xml]
 output = 'tests/coverage.xml'
 
-[tool.pytest.ini_options]
-testpaths = "tests"
-
 [tool.isort]
 skip = "__init__.py"
 profile = "black"
diff --git a/src/skmatter/_selection.py b/src/skmatter/_selection.py
index 50e55cff3..224c020a7 100644
--- a/src/skmatter/_selection.py
+++ b/src/skmatter/_selection.py
@@ -561,8 +561,7 @@ def score(self, X, y=None):
 
         Parameters
         ----------
-        X : numpy.ndarray of shape [n_samples, n_features]
-            The input samples.
+        X : ignored
         y : ignored
 
         Returns
@@ -570,8 +569,7 @@ def score(self, X, y=None):
         score : numpy.ndarray of (n_to_select_from_)
             :math:`\pi` importance for the given samples or features
         """
-        X, y = validate_data(self, X, y, reset=False)
-
+        validate_data(self, X, y, reset=False)  # present for API consistency
         return self.pi_
 
     def _init_greedy_search(self, X, y, n_to_select):
@@ -746,8 +744,7 @@ def score(self, X, y=None):
         score : numpy.ndarray of (n_to_select_from_)
             :math:`\pi` importance for the given samples or features
         """
-        X, y = validate_data(self, X, y, reset=False)
-
+        validate_data(self, X, y, reset=False)  # present for API consistency
         return self.pi_
 
     def _init_greedy_search(self, X, y, n_to_select):
@@ -941,8 +938,7 @@ def score(self, X, y=None):
         -------
         hausdorff : Hausdorff distances
         """
-        X, y = validate_data(self, X, y, reset=False)
-
+        validate_data(self, X, y, reset=False)
         return self.hausdorff_
 
     def get_distance(self):
@@ -1079,15 +1075,16 @@ def __init__(
         )
 
     def fit(self, X, y=None, warm_start=False):
-
         if self.mixing == 1.0:
             raise ValueError(
-                "Mixing = 1.0 corresponds to traditional FPS."
-                "Please use the FPS class."
+                "Mixing = 1.0 corresponds to traditional FPS. Please use the FPS class."
             )
 
         return super().fit(X, y)
 
+    # docstring is inherited and set from the base class
+    fit.__doc__ = GreedySelector.fit.__doc__
+
     def score(self, X, y=None):
         """Returns the Hausdorff distances of all samples to previous selections.
 
@@ -1104,8 +1101,7 @@ def score(self, X, y=None):
         -------
         hausdorff : Hausdorff distances
         """
-        X, y = validate_data(self, X, y, reset=False)
-
+        validate_data(self, X, y, reset=False)
         return self.hausdorff_
 
     def get_distance(self):
diff --git a/src/skmatter/decomposition/_kernel_pcovr.py b/src/skmatter/decomposition/_kernel_pcovr.py
index 65fe39a3e..825a0cf92 100644
--- a/src/skmatter/decomposition/_kernel_pcovr.py
+++ b/src/skmatter/decomposition/_kernel_pcovr.py
@@ -474,7 +474,7 @@ def score(self, X, y):
         """
         check_is_fitted(self, ["pkt_", "X_fit_"])
 
-        X, y = validate_data(self, X, y, reset=False)
+        X = validate_data(self, X, reset=False)
 
         K_NN = self._get_kernel(self.X_fit_, self.X_fit_)
         K_VN = self._get_kernel(X, self.X_fit_)
diff --git a/src/skmatter/decomposition/_pcovr.py b/src/skmatter/decomposition/_pcovr.py
index 8cdd24680..bc094a720 100644
--- a/src/skmatter/decomposition/_pcovr.py
+++ b/src/skmatter/decomposition/_pcovr.py
@@ -10,7 +10,7 @@
 from sklearn.decomposition._pca import _infer_dimension
 from sklearn.linear_model import LinearRegression, Ridge, RidgeCV
 from sklearn.linear_model._base import LinearModel
-from sklearn.utils import check_random_state
+from sklearn.utils import check_array, check_random_state
 from sklearn.utils._arpack import _init_arpack_v0
 from sklearn.utils.extmath import randomized_svd, stable_cumsum, svd_flip
 from sklearn.utils.validation import check_is_fitted, validate_data
@@ -585,7 +585,7 @@ def predict(self, X=None, T=None):
             X = validate_data(self, X, reset=False)
             return X @ self.pxy_
         else:
-            T = validate_data(self, T, reset=False)
+            T = check_array(T)
             return T @ self.pty_
 
     def transform(self, X=None):
diff --git a/src/skmatter/utils/_pcovr_utils.py b/src/skmatter/utils/_pcovr_utils.py
index 15286e341..8852a6386 100644
--- a/src/skmatter/utils/_pcovr_utils.py
+++ b/src/skmatter/utils/_pcovr_utils.py
@@ -9,18 +9,30 @@
 
 
 def check_lr_fit(regressor, X, y):
-    r"""
+    """
     Checks that a (linear) regressor is fitted, and if not,
-    fits it with the provided data
-
-    :param regressor: sklearn-style regressor
-    :type regressor: object
-    :param X: feature matrix with which to fit the regressor
-        if it is not already fitted
-    :type X: array
-    :param y: target values with which to fit the regressor
-        if it is not already fitted
-    :type y: array
+    fits it with the provided data.
+
+    Parameters
+    ----------
+    regressor : object
+        sklearn-style regressor
+    X : array-like
+        Feature matrix with which to fit the regressor if it is not already fitted
+    y : array-like
+        Target values with which to fit the regressor if it is not already fitted
+
+    Returns
+    -------
+    fitted_regressor : object
+        The fitted regressor. If input regressor was already fitted and compatible with
+        the data, returns a deep copy. Otherwise returns a newly fitted regressor.
+
+    Raises
+    ------
+    ValueError
+        If the fitted regressor's coefficients dimensions are incompatible with the
+        target space.
     """
     try:
         check_is_fitted(regressor)
@@ -32,18 +44,18 @@ def check_lr_fit(regressor, X, y):
         # Check compatibility with y
         if fitted_regressor.coef_.ndim != y.ndim:
             raise ValueError(
-                "The regressor coefficients have a dimension incompatible "
-                "with the supplied target space. "
-                "The coefficients have dimension %d and the targets "
-                "have dimension %d" % (fitted_regressor.coef_.ndim, y.ndim)
+                "The regressor coefficients have a dimension incompatible with the "
+                "supplied target space. The coefficients have dimension "
+                f"{fitted_regressor.coef_.ndim} and the targets have dimension "
+                f"{y.ndim}"
             )
         elif y.ndim == 2:
             if fitted_regressor.coef_.shape[0] != y.shape[1]:
                 raise ValueError(
-                    "The regressor coefficients have a shape incompatible "
-                    "with the supplied target space. "
-                    "The coefficients have shape %r and the targets "
-                    "have shape %r" % (fitted_regressor.coef_.shape, y.shape)
+                    "The regressor coefficients have a shape incompatible with the "
+                    "supplied target space. The coefficients have shape "
+                    f"{fitted_regressor.coef_.shape} and the targets have shape "
+                    f"{y.shape}"
                 )
 
     except NotFittedError:
@@ -54,20 +66,37 @@ def check_lr_fit(regressor, X, y):
 
 
 def check_krr_fit(regressor, K, X, y):
-    r"""
+    """
     Checks that a (kernel ridge) regressor is fitted, and if not,
-    fits it with the provided data
-
-    :param regressor: sklearn-style regressor
-    :type regressor: object
-    :param K: kernel matrix with which to fit the regressor
-        if it is not already fitted
-    :type K: array
-    :param X: feature matrix with which to check the regressor
-    :type X: array
-    :param y: target values with which to fit the regressor
-        if it is not already fitted
-    :type y: array
+    fits it with the provided data.
+
+    Parameters
+    ----------
+    regressor : object
+        sklearn-style regressor
+    K : array-like
+        Kernel matrix with which to fit the regressor if it is not already fitted
+    X : array-like
+        Feature matrix with which to check the regressor
+    y : array-like
+        Target values with which to fit the regressor if it is not already fitted
+
+    Returns
+    -------
+    fitted_regressor : object
+        The fitted regressor. If input regressor was already fitted and compatible with
+        the data, returns a deep copy. Otherwise returns a newly fitted regressor.
+
+    Raises
+    ------
+    ValueError
+        If the fitted regressor's coefficients dimensions are incompatible with the
+        target space.
+
+    Notes
+    -----
+    For unfitted regressors, sets the kernel to "precomputed" before fitting with the
+    provided kernel matrix K to avoid recomputation.
     """
     try:
         check_is_fitted(regressor)
@@ -79,18 +108,18 @@ def check_krr_fit(regressor, K, X, y):
         # Check compatibility with y
         if fitted_regressor.dual_coef_.ndim != y.ndim:
             raise ValueError(
-                "The regressor coefficients have a dimension incompatible "
-                "with the supplied target space. "
-                "The coefficients have dimension %d and the targets "
-                "have dimension %d" % (fitted_regressor.dual_coef_.ndim, y.ndim)
+                "The regressor coefficients have a dimension incompatible with the "
+                "supplied target space. The coefficients have dimension "
+                f"{fitted_regressor.dual_coef_.ndim} and the targets have dimension "
+                f"{y.ndim}"
             )
         elif y.ndim == 2:
             if fitted_regressor.dual_coef_.shape[1] != y.shape[1]:
                 raise ValueError(
-                    "The regressor coefficients have a shape incompatible "
-                    "with the supplied target space. "
-                    "The coefficients have shape %r and the targets "
-                    "have shape %r" % (fitted_regressor.dual_coef_.shape, y.shape)
+                    "The regressor coefficients have a shape incompatible with the "
+                    "supplied target space. The coefficients have shape "
+                    f"{fitted_regressor.dual_coef_.shape} and the targets have shape "
+                    f"{y.shape}"
                 )
 
     except NotFittedError:
diff --git a/tests/.coverage.tsf-492-wpa-0-247.epfl.ch.11311.XpjwIfdx b/tests/.coverage.tsf-492-wpa-0-247.epfl.ch.11311.XpjwIfdx
deleted file mode 100644
index 5d637632bf921d7fd0c0dfe157ca23af76774c48..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 53248
zcmeI)O>Y}T7zglOyY<G7BL_v16-8C%0*+P3t%U>v4m3ax6_rXM;(~-bUXPOn@2<1E
z&dUKIr$~{I_y&mY#5dsB6E{v=c%GddubsqIZ&l5I6+8PfGduH}XJ(vi+Hamc@e(Bl
zVdTq1yl<^rwrxEU!m_L~z1HYuHivfZm;?H5&+ISSEnDr&M{Bijt!n8vtM>ic)7oD3
z_qF#{|E&7uUswNdWZ9()*dPD_2teTfEiidjb?RGN_T^8B><v{CNmoVseeLtF5B3ia
z#NqyDPY#4WCw41>w!J;EFQV{Fj8r5B-cSiI=zFeAyx>SA$I7H0$Ewc@9i5}4juW=i
z{Jhuo`jjhCM^wZp@_ZRxh#%EOD@~ByEm7x*K0$>j?<n9DVmHg)6p<RJNCmEnbuD(i
zezVei@pHwgZ*16CDs7XDT>4s_YYm;qoAP)-1-W6==i2uo8MwzPZV5SUp&L>?&lBC+
zDD)pBp%{8W+RPyK5-$vdI#=#EQT<yR*kUxZ5#DTTsI2GQpyxVgcCQ(oJo7C%v*cOk
z0aY#t4Qrl}Z%vugItOFFN8~?@{SkK#<<K`y!bLe3<xRq@v9H}XxAbM+-ns5H<lLh=
z*EsM_#%kL6Es^JJrOgP!mf%KE1iZUis(-X$TNIV*JU$uH=dG?BCt-TrrOxkm=&kz8
zJ1b6oXUD!eNdtv>x;-z6r#t1jpqZXt5ITH)aoq4InGX^kMZ=*82kDUE+(LH_Mf2>K
zd0;SP!~;!)SwgDm8;v%uEY(5uhGB0$*3yWH6%7!Y3rw=XIB<EW#M}lqJXMiAQtj-j
zo)+G8AW`Ua%BA|j&Z5wnhCsJ7-K|WvN=|)y+rBKPVU+b&_RX0KA=8t$Orz$KuVg%q
z%tZ34Nz&xVXGt?gvMbb_J*QOP-(J+5EM2#g?W|0kJ5GIb)1K%N!SfQo?#?xW&*Vek
z+CuR9)gQ^^Slp~TpQeg8?w0DGY%Z!eSE1YC_tJ~+3Tc(Ewo-kcCVhSt=c>$S@+yC+
zF7{64kY<yS^dcIvGzaSyKybpoq{Olpj*~Qg`7jMnUVHNT>H_j(V^67?X>uCgUxjh(
z(Xz_RR{XI!D;mc#=2<9ih+Y^Dl??RSKsg@AbWbl9X&r8^N}uLs#1~w~(P<;ClUZDN
znm?pLXT}%p_`VGK*?Psxur8J6ejc2BA3cdsM$w=_8PgEGR;DR5yUH_`DZf1;6E4-4
zeLdW{Q)Ws$J61P})2q=JGEs@=E5S+9%A|pHCS&17iZ0Sx+H4eG6$ac}-44I=PsuC%
zQEswhJN5hb?a4SBjC!8w#<ZyW(o{P;EX)PTwTpSYJf#VjKJCoL3ERzZ@S(l~Pj0#g
zds@My%0BB<n*0O4UHjLfFKiHi00bZa0SG_<0uX=z1Rwwb2rQpK(Jt5y|NLL5{bkku
zrZ;R5fB*y_009U<00Izz00bZa0SLU60@XtCUd{Z4$HR5IxV@GA4Zw%(589oF6>3$X
z_R^}oto`#=HV~DD00bZa0SG_<0uX=z1Rwwb2tZ&eP%YlG&94CpmEv|e`z=8F5B%4s
z$*=<f2tWV=5P$##AOHafKmY;|fWQ(8@biEAPyet%00Izz00bZa0SG_<0uX=z1R$`)
z0(kzv#GQ+#K>z{}fB*y_009U<00Izz00c4tJpV^1KmY;|fB*y_009U<00Izz00fp_
z0MGxIzmL&E2tWV=5P$##AOHafKmY;|fB>HVBL*M<0SG_<0uX=z1Rwwb2tWV=%P)ZE
z|I6RUXdwh3009U<00Izz00bZa0SG_<&;Jnv5P$##AOHafKmY;|fB*y_0D<Kf!1Mp*
a?_;zO0uX=z1Rwwb2tWV=5P$##An+e!TOC>e

diff --git a/tests/test_feature_pcov_fps.py b/tests/test_feature_pcov_fps.py
index 321cc78ee..e6910f9a1 100644
--- a/tests/test_feature_pcov_fps.py
+++ b/tests/test_feature_pcov_fps.py
@@ -24,11 +24,12 @@ def test_restart(self):
 
     def test_no_mixing_1(self):
         """Check that the model throws an error when mixing = 1.0."""
+        selector = PCovFPS(n_to_select=1, mixing=1.0)
         with self.assertRaises(ValueError) as cm:
-            _ = PCovFPS(n_to_select=1, mixing=1.0)
+            selector.fit(self.X, y=self.y)
         self.assertEqual(
             str(cm.exception),
-            "Mixing = 1.0 corresponds to traditional FPS." "Please use the FPS class.",
+            "Mixing = 1.0 corresponds to traditional FPS. Please use the FPS class.",
         )
 
 
diff --git a/tests/test_greedy_selector.py b/tests/test_greedy_selector.py
index 0bfe6de99..f85dbeb34 100644
--- a/tests/test_greedy_selector.py
+++ b/tests/test_greedy_selector.py
@@ -73,7 +73,7 @@ def test_bad_transform(self):
             _ = selector.transform(self.X[:, :3])
         self.assertEqual(
             str(cm.exception),
-            "X has a different shape than during fitting. Reshape your data.",
+            "X has 3 features, but GreedyTester is expecting 10 features as input.",
         )
 
     def test_no_nfeatures(self):
@@ -124,8 +124,8 @@ def test_size_input(self):
             selector_feature.fit(X)
         self.assertEqual(
             str(cm.exception),
-            f"Found array with 1 feature(s) (shape={X.shape})"
-            " while a minimum of 2 is required.",
+            f"Found array with 1 feature(s) (shape={X.shape}) while a minimum of 2 is "
+            "required by GreedyTester.",
         )
 
         X = X.reshape(1, -1)
@@ -135,7 +135,7 @@ def test_size_input(self):
         self.assertEqual(
             str(cm.exception),
             f"Found array with 1 sample(s) (shape={X.shape}) while a minimum of 2 is "
-            "required.",
+            "required by GreedyTester.",
         )
 
 
diff --git a/tests/test_kernel_pcovr.py b/tests/test_kernel_pcovr.py
index e4bbda52e..80adf584e 100644
--- a/tests/test_kernel_pcovr.py
+++ b/tests/test_kernel_pcovr.py
@@ -182,6 +182,8 @@ def test_centerer(self):
         self.assertTrue(hasattr(kpcovr, "centerer_"))
         _ = kpcovr.predict(self.X)
         _ = kpcovr.transform(self.X)
+
+        print(self.Y.shape)
         _ = kpcovr.score(self.X, self.Y)
 
     def test_prefit_regressor(self):
@@ -255,7 +257,7 @@ def test_incompatible_coef_shape(self):
 
         # Dimension mismatch
         with self.assertRaises(ValueError) as cm:
-            kpcovr.fit(self.X, self.Y[:, 0])
+            kpcovr.fit(self.X, np.zeros(self.Y.shape + (2,)))
         self.assertTrue(
             str(cm.exception),
             "The regressor coefficients have a dimension incompatible "
diff --git a/tests/test_pcovr.py b/tests/test_pcovr.py
index e589978d2..2059eed44 100644
--- a/tests/test_pcovr.py
+++ b/tests/test_pcovr.py
@@ -491,13 +491,12 @@ def test_incompatible_coef_shape(self):
 
         # Dimension mismatch
         with self.assertRaises(ValueError) as cm:
-            pcovr.fit(self.X, self.Y.squeeze())
+            pcovr.fit(self.X, np.zeros((self.Y.shape[0], 2)))
         self.assertEqual(
             str(cm.exception),
-            "The regressor coefficients have a dimension incompatible "
-            "with the supplied target space. "
-            "The coefficients have dimension %d and the targets "
-            "have dimension %d" % (regressor.coef_.ndim, self.Y.squeeze().ndim),
+            "The regressor coefficients have a dimension incompatible with the "
+            "supplied target space. The coefficients have dimension 1 and the targets "
+            "have dimension 2",
         )
 
         # Shape mismatch (number of targets)
diff --git a/tests/test_sample_pcov_fps.py b/tests/test_sample_pcov_fps.py
index 7679abb0a..b6ed08662 100644
--- a/tests/test_sample_pcov_fps.py
+++ b/tests/test_sample_pcov_fps.py
@@ -24,11 +24,12 @@ def test_restart(self):
 
     def test_no_mixing_1(self):
         """Check that the model throws an error when mixing = 1.0."""
+        selector = PCovFPS(n_to_select=1, mixing=1.0)
         with self.assertRaises(ValueError) as cm:
-            _ = PCovFPS(n_to_select=1, mixing=1.0)
+            selector.fit(self.X, y=self.y)
         self.assertEqual(
             str(cm.exception),
-            "Mixing = 1.0 corresponds to traditional FPS." "Please use the FPS class.",
+            "Mixing = 1.0 corresponds to traditional FPS. Please use the FPS class.",
         )
 
 

From 790eee3680717eb1032f6af5473ac36875431157 Mon Sep 17 00:00:00 2001
From: Philip Loche <ploche@physik.fu-berlin.de>
Date: Thu, 13 Feb 2025 15:24:44 +0100
Subject: [PATCH 10/13] update runners

---
 .github/workflows/tests.yml | 4 ++--
 .readthedocs.yaml           | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index fe3609798..f8f716183 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -11,8 +11,8 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-22.04, macos-14, windows-2022]
-        python-version: ["3.0", "3.13"]
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.10", "3.13"]
 
     steps:
     - uses: actions/checkout@v4
diff --git a/.readthedocs.yaml b/.readthedocs.yaml
index b4c827c42..bee4dd725 100644
--- a/.readthedocs.yaml
+++ b/.readthedocs.yaml
@@ -7,7 +7,7 @@ version: 2
 
 # Set the version of Python and other tools we need
 build:
-  os: ubuntu-22.04
+  os: ubuntu-lts-latest
   tools:
     python: "3.13"
   

From 53ad7b8307945fe5edd3c68cef4303129eb2ac0f Mon Sep 17 00:00:00 2001
From: Philip Loche <ploche@physik.fu-berlin.de>
Date: Thu, 13 Feb 2025 16:33:16 +0100
Subject: [PATCH 11/13] fix docs

---
 examples/pcovr/PCovR-WHODataset.py | 6 ++++--
 examples/pcovr/PCovR_Regressors.py | 3 +--
 examples/pcovr/PCovR_Scaling.py    | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/examples/pcovr/PCovR-WHODataset.py b/examples/pcovr/PCovR-WHODataset.py
index 4a1ecf865..a86482fa1 100644
--- a/examples/pcovr/PCovR-WHODataset.py
+++ b/examples/pcovr/PCovR-WHODataset.py
@@ -109,7 +109,7 @@
 r_pcovr = Ridge(alpha=1e-4, fit_intercept=False, random_state=0).fit(
     T_train_pcovr, y_train
 )
-yp_pcovr = r_pcovr.predict(T_test_pcovr)
+yp_pcovr = r_pcovr.predict(T_test_pcovr).reshape(-1,1)
 
 plt.scatter(y_scaler.inverse_transform(y_test), y_scaler.inverse_transform(yp_pcovr))
 r_pcovr.score(T_test_pcovr, y_test)
@@ -128,7 +128,7 @@
 T_pca = pca.transform(X)
 
 r_pca = Ridge(alpha=1e-4, fit_intercept=False, random_state=0).fit(T_train_pca, y_train)
-yp_pca = r_pca.predict(T_test_pca)
+yp_pca = r_pca.predict(T_test_pca).reshape(-1,1)
 
 plt.scatter(y_scaler.inverse_transform(y_test), y_scaler.inverse_transform(yp_pca))
 r_pca.score(T_test_pca, y_test)
@@ -312,3 +312,5 @@ def add_subplot(ax, axy, T, yp, let=""):
     "Linear and Kernel PCovR for Predicting Life Expectancy", y=0.925, fontsize=10
 )
 plt.show()
+
+# %%
diff --git a/examples/pcovr/PCovR_Regressors.py b/examples/pcovr/PCovR_Regressors.py
index 777009d56..72a122e61 100644
--- a/examples/pcovr/PCovR_Regressors.py
+++ b/examples/pcovr/PCovR_Regressors.py
@@ -24,13 +24,12 @@
 mixing = 0.5
 
 X, y = load_diabetes(return_X_y=True)
-y = y.reshape(X.shape[0], -1)
 
 X_scaler = StandardScaler()
 X_scaled = X_scaler.fit_transform(X)
 
 y_scaler = StandardScaler()
-y_scaled = y_scaler.fit_transform(y)
+y_scaled = y_scaler.fit_transform(y.reshape(-1, 1)).ravel()
 
 
 # %%
diff --git a/examples/pcovr/PCovR_Scaling.py b/examples/pcovr/PCovR_Scaling.py
index 11858ead8..8eb75471e 100644
--- a/examples/pcovr/PCovR_Scaling.py
+++ b/examples/pcovr/PCovR_Scaling.py
@@ -78,7 +78,7 @@
 ax1_Y.set_title("Regression\nWithout Scaling")
 
 ax2_Y.scatter(
-    Yp_scaled, y, c=np.abs(y.flatten() - Yp_scaled.flatten()), cmap="bone_r", ec="k"
+    Yp_scaled, y, c=np.abs(y.ravel() - Yp_scaled.ravel()), cmap="bone_r", ec="k"
 )
 ax2_Y.plot(ax2_Y.get_xlim(), ax2_Y.get_xlim(), "r--")
 ax2_Y.set_xlabel("True Y, unscaled")

From 5101e66c5aa9c960edba42a625f35dc1979f1689 Mon Sep 17 00:00:00 2001
From: Philip Loche <ploche@physik.fu-berlin.de>
Date: Thu, 13 Feb 2025 16:37:36 +0100
Subject: [PATCH 12/13] lint plus warnings as errors

---
 examples/pcovr/PCovR-WHODataset.py | 4 ++--
 pyproject.toml                     | 5 +++++
 tox.ini                            | 2 +-
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/examples/pcovr/PCovR-WHODataset.py b/examples/pcovr/PCovR-WHODataset.py
index a86482fa1..39146f2a8 100644
--- a/examples/pcovr/PCovR-WHODataset.py
+++ b/examples/pcovr/PCovR-WHODataset.py
@@ -109,7 +109,7 @@
 r_pcovr = Ridge(alpha=1e-4, fit_intercept=False, random_state=0).fit(
     T_train_pcovr, y_train
 )
-yp_pcovr = r_pcovr.predict(T_test_pcovr).reshape(-1,1)
+yp_pcovr = r_pcovr.predict(T_test_pcovr).reshape(-1, 1)
 
 plt.scatter(y_scaler.inverse_transform(y_test), y_scaler.inverse_transform(yp_pcovr))
 r_pcovr.score(T_test_pcovr, y_test)
@@ -128,7 +128,7 @@
 T_pca = pca.transform(X)
 
 r_pca = Ridge(alpha=1e-4, fit_intercept=False, random_state=0).fit(T_train_pca, y_train)
-yp_pca = r_pca.predict(T_test_pca).reshape(-1,1)
+yp_pca = r_pca.predict(T_test_pca).reshape(-1, 1)
 
 plt.scatter(y_scaler.inverse_transform(y_test), y_scaler.inverse_transform(yp_pca))
 r_pca.score(T_test_pca, y_test)
diff --git a/pyproject.toml b/pyproject.toml
index 374d06293..eec3f58c2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -84,6 +84,11 @@ include_trailing_comma = true
 lines_after_imports = 2
 known_first_party = "skmatter"
 
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = ["--cov"]
+filterwarnings = ["error"]
+
 [tool.ruff]
 exclude = ["docs/src/examples/"]
 lint.ignore = [
diff --git a/tox.ini b/tox.ini
index 2c5c64764..d1eda0fa1 100644
--- a/tox.ini
+++ b/tox.ini
@@ -42,7 +42,7 @@ deps =
 
 commands =
     # Run unit tests
-    pytest --cov {posargs}
+    pytest {posargs}
 
     # Run documentation tests
     pytest --doctest-modules --pyargs skmatter {posargs}

From f8c2cc8e3e0a2bca72cb51b9808fa674d61e27f3 Mon Sep 17 00:00:00 2001
From: Philip Loche <ploche@physik.fu-berlin.de>
Date: Thu, 13 Feb 2025 16:39:53 +0100
Subject: [PATCH 13/13] update infra

---
 tox.ini | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tox.ini b/tox.ini
index d1eda0fa1..c1bcac3a6 100644
--- a/tox.ini
+++ b/tox.ini
@@ -96,5 +96,4 @@ deps =
 # The documentation runs "examples" to produce outputs via sphinx-gallery.
 extras = examples
 commands =
-    sphinx-build {posargs:-E} -W -b doctest docs/src docs/build/doctest
     sphinx-build {posargs:-E} -W -b html docs/src docs/build/html