Making linter happy

Author: Christian Jorgensen

examples/pcovc/PCovC_multioutput.py

@@ -69,7 +69,6 @@
 labels_list = [["Even", "Odd"], [">= 5", "< 5"]]
 
 for i, c, cmap in zip(range(3), [is_even, is_less_than_five, y], [cmap1, cmap2, cmap3]):
-
     scat_pca = axs[0, i].scatter(T_pca[:, 0], T_pca[:, 1], c=c, cmap=cmap)
     axs[1, i].scatter(T_pcovc[:, 0], T_pcovc[:, 1], c=c, cmap=cmap)
 
@@ -114,7 +113,6 @@
 labels_list = [["Even", "Odd"], ["0", "1", "2"]]
 
 for i, c, cmap in zip(range(3), [is_even, num_holes, y], [cmap1, cmap2, cmap3]):
-
     scat_pca = axs[0, i].scatter(T_pca[:, 0], T_pca[:, 1], c=c, cmap=cmap)
     axs[1, i].scatter(T_pcovc[:, 0], T_pcovc[:, 1], c=c, cmap=cmap)
 

src/skmatter/decomposition/_kernel_pcovc.py

@@ -87,9 +87,17 @@ class KernelPCovC(LinearClassifierMixin, _BaseKPCov):
         - ``sklearn.linear_model.RidgeClassifierCV()``
         - ``sklearn.linear_model.Perceptron()``
 
-        If a pre-fitted classifier is provided, it is used to compute :math:`{\mathbf{Z}}`.
-        If None and ``n_outputs_ < 2``, ``sklearn.linear_model.LogisticRegression()`` is used.
-        If None and ``n_outputs_ == 2``, ``sklearn.multioutput.MultiOutputClassifier()`` is used.
+        If a pre-fitted classifier
+        is provided, it is used to compute :math:`{\mathbf{Z}}`.
+        Note that any pre-fitting of the classifier will be lost if `KernelPCovC` is
+        within a composite estimator that enforces cloning, e.g.,
+        `sklearn.pipeline.Pipeline` with model caching.
+        In such cases, the classifier will be re-fitted on the same
+        training data as the composite estimator.
+        If None and ``n_outputs < 2``, ``sklearn.linear_model.LogisticRegression()`` is used.
+        If None and ``n_outputs >= 2``, a ``sklearn.multioutput.MultiOutputClassifier()`` is
+        constructed, with ``sklearn.linear_model.LogisticRegression()`` models used for each
+        label.
 
     kernel : {"linear", "poly", "rbf", "sigmoid", "precomputed"} or callable, default="linear"
         Kernel.
@@ -455,8 +463,8 @@ def decision_function(self, X=None, T=None):
         Z : numpy.ndarray, shape (n_samples,) or (n_samples, n_classes), or a list of \
                 n_outputs_ such arrays if n_outputs_ > 1
             Confidence scores. For binary classification, has shape `(n_samples,)`,
-            for multiclass classification, has shape `(n_samples, n_classes)`. 
-            If n_outputs_ > 1, the list can contain arrays with differing shapes 
+            for multiclass classification, has shape `(n_samples, n_classes)`.
+            If n_outputs_ > 1, the list can contain arrays with differing shapes
             depending on the number of classes in each output of Y.
         """
         check_is_fitted(self, attributes=["pkz_", "ptz_"])
@@ -489,15 +497,14 @@ def decision_function(self, X=None, T=None):
                     est_.decision_function(T) for est_ in self.classifier_.estimators_
                 ]
 
-    def score(self, X, y):
-
+    def score(self, X, y, sample_weight=None):
         # accuracy_score will handle everything but multiclass-multilabel
         if self.n_outputs_ > 1 and len(self.classes_) > 2:
             y_pred = self.predict(X)
             return np.mean(np.all(y == y_pred, axis=1))
 
         else:
-            return super().score(X, y)
+            return super().score(X, y, sample_weight)
 
     # Inherit the docstring from scikit-learn
     score.__doc__ = LinearClassifierMixin.score.__doc__

src/skmatter/decomposition/_pcovc.py

@@ -21,14 +21,6 @@
 from skmatter.utils import check_cl_fit
 
 
-# No inheritance from MultiOutputMixin because decision_function would fail
-# test_check_estimator.py 'check_classifier_multioutput' (line 2479 of estimator_checks.py).
-# This is the only test for multioutput classifiers, so is it OK to exclude this tag?
-
-# did a search of all classifiers that inherit from MultiOutputMixin - none of them implement
-# decision function
-
-
 class PCovC(LinearClassifierMixin, _BasePCov):
     r"""Principal Covariates Classification (PCovC).
 
@@ -133,7 +125,9 @@ class PCovC(LinearClassifierMixin, _BasePCov):
         In such cases, the classifier will be re-fitted on the same
         training data as the composite estimator.
         If None and ``n_outputs < 2``, ``sklearn.linear_model.LogisticRegression()`` is used.
-        If None and ``n_outputs == 2``, ``sklearn.multioutput.MultiOutputClassifier()`` is used.
+        If None and ``n_outputs >= 2``, a ``sklearn.multioutput.MultiOutputClassifier()`` is
+        constructed, with ``sklearn.linear_model.LogisticRegression()`` models used for each
+        label.
 
     iterated_power : int or 'auto', default='auto'
         Number of iterations for the power method computed by
@@ -453,12 +447,13 @@ def decision_function(self, X=None, T=None):
 
         Returns
         -------
-        Z : numpy.ndarray, shape (n_samples,) or (n_samples, n_classes), or a list of \
-                n_outputs such arrays if n_outputs > 1
-            Confidence scores. For binary classification, has shape `(n_samples,)`,
-            for multiclass classification, has shape `(n_samples, n_classes)`. 
-            If n_outputs > 1, the list can contain arrays with differing shapes 
-            depending on the number of classes in each output of Y.
+        Z : numpy.ndarray, shape (n_samples,) or (n_samples, n_classes), or
+            a list of n_outputs such arrays if n_outputs > 1.
+            Confidence scores. For binary classification, has shape
+            `(n_samples,)`, for multiclass classification, has shape
+            `(n_samples, n_classes)`. If n_outputs > 1, the list can
+            contain arrays with differing shapes depending on the number
+            of classes in each output of Y.
         """
         check_is_fitted(self, attributes=["pxz_", "ptz_"])
 
@@ -514,15 +509,14 @@ def transform(self, X=None):
         """
         return super().transform(X)
 
-    def score(self, X, y):
-
+    def score(self, X, y, sample_weight=None):
         # accuracy_score will handle everything but multiclass-multilabel
         if self.n_outputs_ > 1 and len(self.classes_) > 2:
             y_pred = self.predict(X)
             return np.mean(np.all(y == y_pred, axis=1))
 
         else:
-            return super().score(X, y)
+            return super().score(X, y, sample_weight)
 
     # Inherit the docstring from scikit-learn
     score.__doc__ = LinearClassifierMixin.score.__doc__

tests/test_kernel_pcovc.py

@@ -2,7 +2,7 @@
 
 import numpy as np
 from sklearn import exceptions
-from sklearn.calibration import LinearSVC
+from sklearn.svm import LinearSVC
 from sklearn.datasets import load_breast_cancer as get_dataset
 from sklearn.multioutput import MultiOutputClassifier
 from sklearn.naive_bayes import GaussianNB
@@ -31,12 +31,17 @@ def __init__(self, *args, **kwargs):
         scaler = StandardScaler()
         self.X = scaler.fit_transform(self.X)
 
-        self.model = lambda mixing=0.5, classifier=LogisticRegression(), n_components=4, **kwargs: KernelPCovC(
-            mixing=mixing,
-            classifier=classifier,
-            n_components=n_components,
-            svd_solver=kwargs.pop("svd_solver", "full"),
-            **kwargs,
+        self.model = (
+            lambda mixing=0.5,
+            classifier=LogisticRegression(),
+            n_components=4,
+            **kwargs: KernelPCovC(
+                mixing=mixing,
+                classifier=classifier,
+                n_components=n_components,
+                svd_solver=kwargs.pop("svd_solver", "full"),
+                **kwargs,
+            )
         )
 
     def setUp(self):
@@ -484,9 +489,10 @@ def test_bad_n_components(self):
 
 
 class KernelPCovCMultiOutputTest(KernelPCovCBaseTest):
-
     def test_prefit_multioutput(self):
-        """Check that KPCovC works if a prefit classifier is passed when `n_outputs > 1`."""
+        """Check that KPCovC works if a prefit classifier
+        is passed when `n_outputs > 1`.
+        """
         kernel_params = {"kernel": "sigmoid", "gamma": 1, "degree": 3, "coef0": 0}
         K = pairwise_kernels(
             self.X, metric="sigmoid", filter_params=True, **kernel_params
@@ -545,7 +551,9 @@ def test_precomputed_multioutput(self):
         self.assertTrue(np.linalg.norm(t3 - t1) < self.error_tol)
 
     def test_Z_shape_multioutput(self):
-        """Check that KPCovC returns the evidence Z in the desired form when `n_outputs > 1`."""
+        """Check that KPCovC returns the evidence Z in
+        the desired form when `n_outputs > 1`.
+        """
         kpcovc = KernelPCovC(classifier=MultiOutputClassifier(estimator=Perceptron()))
 
         Y_double = np.column_stack((self.Y, self.Y))
@@ -563,7 +571,9 @@ def test_Z_shape_multioutput(self):
                 self.assertEqual(z_slice.ndim, 1)
 
     def test_decision_function_multioutput(self):
-        """Check that KPCovC's decision_function works in edge cases when `n_outputs > 1`."""
+        """Check that KPCovC's decision_function works
+        in edge cases when `n_outputs > 1`.
+        """
         kpcovc = self.model(
             classifier=MultiOutputClassifier(estimator=LinearSVC()), center=True
         )
@@ -580,7 +590,7 @@ def test_decision_function_multioutput(self):
         T = kpcovc.transform(self.X)
         _ = kpcovc.decision_function(T=T)
 
-    #TODO: Add tests for addition of score function to pcovc.py
+    # TODO: Add tests for addition of score function to pcovc.py
 
 
 if __name__ == "__main__":

tests/test_pcovc.py

@@ -3,7 +3,6 @@
 
 import numpy as np
 from sklearn import exceptions
-from sklearn.calibration import LinearSVC
 from sklearn.datasets import load_iris as get_dataset
 from sklearn.decomposition import PCA
 from sklearn.linear_model import LogisticRegression, RidgeClassifier
@@ -580,9 +579,10 @@ def test_incompatible_coef_shape(self):
 
 
 class PCovCMultiOutputTest(PCovCBaseTest):
-
     def test_prefit_multioutput(self):
-        """Check that PCovC works if a prefit classifier is passed when `n_outputs > 1`."""
+        """Check that PCovC works if a prefit classifier
+        is passed when `n_outputs > 1`.
+        """
         classifier = MultiOutputClassifier(estimator=LogisticRegression())
         Y_double = np.column_stack((self.Y, self.Y))
 
@@ -625,7 +625,9 @@ def test_precomputed_multioutput(self):
         self.assertTrue(np.linalg.norm(t3 - t1) < self.error_tol)
 
     def test_Z_shape_multioutput(self):
-        """Check that PCovC returns the evidence Z in the desired form when `n_outputs > 1`."""
+        """Check that PCovC returns the evidence Z in the
+        desired form when `n_outputs > 1`.
+        """
         pcovc = PCovC()
 
         Y_double = np.column_stack((self.Y, self.Y))
@@ -643,7 +645,9 @@ def test_Z_shape_multioutput(self):
                 self.assertEqual(est.coef_.shape[0], z_slice.shape[1])
 
     def test_decision_function_multioutput(self):
-        """Check that PCovC's decision_function works in edge cases when `n_outputs > 1`."""
+        """Check that PCovC's decision_function works in edge
+        cases when `n_outputs_ > 1`.
+        """
         pcovc = self.model(classifier=MultiOutputClassifier(estimator=LinearSVC()))
         pcovc.fit(self.X, np.column_stack((self.Y, self.Y)))
         with self.assertRaises(ValueError) as cm:
@@ -656,6 +660,8 @@ def test_decision_function_multioutput(self):
         T = pcovc.transform(self.X)
         _ = pcovc.decision_function(T=T)
 
-    #TODO: Add tests for addition of score function to pcovc.py
+    # TODO: Add tests for addition of score function to pcovc.py
+
+
 if __name__ == "__main__":
     unittest.main(verbosity=2)