Merge remote-tracking branch 'origin/main' into multioutput-pcovc

Author: Christian Jorgensen

.github/workflows/build.yml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
 
     - name: Set up Python
       uses: actions/setup-python@v5

.github/workflows/docs.yml

@@ -11,7 +11,7 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: setup Python
         uses: actions/setup-python@v5

.github/workflows/lint.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
 
     - name: Set up Python
       uses: actions/setup-python@v5

.github/workflows/release.yml

@@ -16,7 +16,7 @@ jobs:
       contents: write
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
       with:
         fetch-depth: 0
     - name: setup Python

.github/workflows/tests-dev.yml

@@ -10,10 +10,12 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.13"]
+        python-version: 
+          - "3.10"
+          - "3.13"
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5

.github/workflows/tests.yml

@@ -11,11 +11,16 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ["3.10", "3.13"]
+        os: 
+          - ubuntu-latest
+          - macos-latest
+          - windows-latest
+        python-version: 
+          - "3.10"
+          - "3.13"
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
 
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v5

examples/pcovc/KPCovC_Comparison.py

@@ -33,6 +33,7 @@
 
 random_state = 0
 n_components = 2
+scale_z = True
 
 # %%
 #
@@ -85,7 +86,7 @@
 # Both PCA and PCovC fail to produce linearly separable latent space
 # maps. We will need a kernel method to effectively separate the moon classes.
 
-mixing = 0.10
+mixing = 0.5
 alpha_d = 0.5
 alpha_p = 0.4
 
@@ -95,6 +96,7 @@
         n_components=n_components,
         random_state=random_state,
         mixing=mixing,
+        scale_z=scale_z,
         classifier=LinearSVC(),
     ): "PCovC",
 }
@@ -138,6 +140,7 @@
         random_state=random_state,
         mixing=mixing,
         center=center,
+        scale_z=scale_z,
         **kernel_params,
     ): {"title": "Kernel PCovC", "eps": 2},
 }
@@ -220,6 +223,7 @@
         mixing=mixing,
         classifier=model,
         center=center,
+        scale_z=scale_z,
         **models[model]["kernel_params"],
     )
     t_kpcovc_train = kpcovc.fit_transform(X_train_scaled, y_train)

examples/pcovc/KPCovC_Hyperparameters.py

@@ -65,7 +65,8 @@
 fig, axs = plt.subplots(2, len(kernels), figsize=(len(kernels) * 4, 8))
 
 center = True
-mixing = 0.10
+mixing = 0.5
+scale_z = True
 
 for i, kernel in enumerate(kernels):
     kpca = KernelPCA(
@@ -83,6 +84,7 @@
         random_state=random_state,
         **kernel_params.get(kernel, {}),
         center=center,
+        scale_z=scale_z,
     )
     t_kpcovc = kpcovc.fit_transform(X_scaled, y)
 
@@ -118,7 +120,7 @@
     kpcovc = KernelPCovC(
         n_components=n_components,
         random_state=random_state,
-        mixing=mixing,
+        mixing=0.1,
         center=center,
         kernel="rbf",
         gamma=gamma,

examples/pcovc/PCovC_Hyperparameters.py

@@ -77,6 +77,7 @@
         n_components=n_components,
         random_state=random_state,
         classifier=LogisticRegressionCV(),
+        scale_z=True,
     )
 
     pcovc.fit(X_scaled, y)
@@ -120,6 +121,7 @@
         n_components=n_components,
         random_state=random_state,
         classifier=model,
+        scale_z=True,
     )
 
     pcovc.fit(X_scaled, y)

src/skmatter/decomposition/_kernel_pcovc.py

@@ -1,3 +1,4 @@
+import warnings
 import numpy as np
 
 from sklearn import clone
@@ -17,7 +18,7 @@
 from sklearn.linear_model._base import LinearClassifierMixin
 from sklearn.utils.multiclass import check_classification_targets, type_of_target
 
-from skmatter.preprocessing import KernelNormalizer
+from skmatter.preprocessing import KernelNormalizer, StandardFlexibleScaler
 from skmatter.utils import check_cl_fit
 from skmatter.decomposition import _BaseKPCov
 
@@ -99,6 +100,9 @@ class KernelPCovC(LinearClassifierMixin, _BaseKPCov):
         constructed, with ``sklearn.linear_model.LogisticRegression()`` models used for each
         label.
 
+    scale_z: bool, default=False
+        Whether to scale Z prior to eigendecomposition.
+
     kernel : {"linear", "poly", "rbf", "sigmoid", "precomputed"} or callable, default="linear"
         Kernel.
 
@@ -129,6 +133,14 @@ class KernelPCovC(LinearClassifierMixin, _BaseKPCov):
         and for matrix inversions.
         Must be of range [0.0, infinity).
 
+    z_mean_tol: float, default=1e-12
+        Tolerance for the column means of Z.
+        Must be of range [0.0, infinity).
+
+    z_var_tol: float, default=1.5
+        Tolerance for the column variances of Z.
+        Must be of range [0.0, infinity).
+
     n_jobs : int, default=None
         The number of parallel jobs to run.
         :obj:`None` means 1 unless in a :obj:`joblib.parallel_backend` context.
@@ -185,14 +197,17 @@ class KernelPCovC(LinearClassifierMixin, _BaseKPCov):
         The data used to fit the model. This attribute is used to build kernels
         from new data.
 
+    scale_z: bool
+        Whether Z is being scaled prior to eigendecomposition.
+
     Examples
     --------
     >>> import numpy as np
     >>> from skmatter.decomposition import KernelPCovC
     >>> from sklearn.preprocessing import StandardScaler
     >>> X = np.array([[-2, 3, -1, 0], [2, 0, -3, 1], [3, 0, -1, 3], [2, -2, 1, 0]])
     >>> X = StandardScaler().fit_transform(X)
-    >>> Y = np.array([[2], [0], [1], [2]])
+    >>> Y = np.array([2, 0, 1, 2])
     >>> kpcovc = KernelPCovC(
     ...     mixing=0.1,
     ...     n_components=2,
@@ -218,6 +233,7 @@ def __init__(
         n_components=None,
         svd_solver="auto",
         classifier=None,
+        scale_z=False,
         kernel="linear",
         gamma=None,
         degree=3,
@@ -226,6 +242,8 @@ def __init__(
         center=False,
         fit_inverse_transform=False,
         tol=1e-12,
+        z_mean_tol=1e-12,
+        z_var_tol=1.5,
         n_jobs=None,
         iterated_power="auto",
         random_state=None,
@@ -247,6 +265,9 @@ def __init__(
             fit_inverse_transform=fit_inverse_transform,
         )
         self.classifier = classifier
+        self.scale_z = scale_z
+        self.z_mean_tol = z_mean_tol
+        self.z_var_tol = z_var_tol
 
     def fit(self, X, Y, W=None):
         r"""Fit the model with X and Y.
@@ -368,6 +389,25 @@ def fit(self, X, Y, W=None):
                 W = self.z_classifier_.coef_.T
 
         Z = K @ W
+        if self.scale_z:
+            Z = StandardFlexibleScaler().fit_transform(Z)
+
+        z_means_ = np.mean(Z, axis=0)
+        z_vars_ = np.var(Z, axis=0)
+
+        if np.max(np.abs(z_means_)) > self.z_mean_tol:
+            warnings.warn(
+                "This class does not automatically center Z, and the column means "
+                "of Z are greater than the supplied tolerance. We recommend scaling "
+                "Z (and the weights) by setting `scale_z=True`."
+            )
+
+        if np.max(z_vars_) > self.z_var_tol:
+            warnings.warn(
+                "This class does not automatically scale Z, and the column variances "
+                "of Z are greater than the supplied tolerance. We recommend scaling "
+                "Z (and the weights) by setting `scale_z=True`."
+            )
 
         self._fit(K, Z, W)