scikit-learn · fractionalhare · Jul 9, 2022 · Jul 9, 2022 · Jul 9, 2022 · Jul 9, 2022
diff --git a/doc/whats_new/v1.2.rst b/doc/whats_new/v1.2.rst
@@ -107,6 +107,14 @@ Changelog
  :class:`cluster.AgglomerativeClustering` and will be renamed to `metric` in v1.4.
  :pr:`23470` by :user:`Meekail Zain <micky774>`.

+:mod:`sklearn.cross_decomposition`
+..................................
+
+- |Enhancement| The Dayal-MacGregor kernel algorithm was implemented for
+  :class:`cross_decomposition.PLSRegression` with the `algorithm="dayalmacgregor"`
+  parameter, which provides an asymptotic performance improvement over the default
+  algorithm, NIPALS. :pr:`23876` by :user:`Dylan Houlihan <fractionalhare>`.
+
 :mod:`sklearn.datasets`
 .......................


diff --git a/examples/cross_decomposition/plot_compare_cross_decomposition.py b/examples/cross_decomposition/plot_compare_cross_decomposition.py
@@ -136,7 +136,7 @@
 # each Yj = 1*X1 + 2*X2 + noize
 Y = np.dot(X, B) + np.random.normal(size=n * q).reshape((n, q)) + 5

-pls2 = PLSRegression(n_components=3)
+pls2 = PLSRegression(n_components=3, algorithm="dayalmacgregor")
 pls2.fit(X, Y)
 print("True B (such that: Y = XB + Err)")
 print(B)
@@ -153,7 +153,7 @@
 p = 10
 X = np.random.normal(size=n * p).reshape((n, p))
 y = X[:, 0] + 2 * X[:, 1] + np.random.normal(size=n * 1) + 5
-pls1 = PLSRegression(n_components=3)
+pls1 = PLSRegression(n_components=3, algorithm="dayalmacgregor")
 pls1.fit(X, y)
 # note that the number of components exceeds 1 (the dimension of y)
 print("Estimated betas")

diff --git a/examples/cross_decomposition/plot_pcr_vs_pls.py b/examples/cross_decomposition/plot_pcr_vs_pls.py
@@ -112,7 +112,7 @@
 pcr.fit(X_train, y_train)
 pca = pcr.named_steps["pca"]  # retrieve the PCA step of the pipeline

-pls = PLSRegression(n_components=1)
+pls = PLSRegression(n_components=1, algorithm="dayalmacgregor")
 pls.fit(X_train, y_train)

 fig, axes = plt.subplots(1, 2, figsize=(10, 3))