Release 0.8.1

Merge changes from #943

doc/templates/index.html

@@ -109,6 +109,8 @@ <h4 class="sk-landing-call-header">News</h4>
         <li><strong>On-going development:</strong>
         <a href="https://scikit-optimize.github.io/dev/whats_new.html"><strong>What's new</strong> (Changelog)</a>
         </li>
+		<li><strong>Sep 2020.</strong> scikit-optimize 0.8.1  (<a href="whats_new/v0.8.html#version-0-8-1">Changelog</a>).
+		<li><strong>Sep 2020.</strong> scikit-optimize 0.8  (<a href="whats_new/v0.8.html#version-0-8">Changelog</a>).
         <li><strong>Feb 2020.</strong> scikit-optimize 0.7.2  (<a href="whats_new/v0.7.html#version-0-7-2">Changelog</a>).
         <li><strong>Feb 2020.</strong> scikit-optimize 0.7.1  (<a href="whats_new/v0.7.html#version-0-7-1">Changelog</a>).
         <li><strong>Jan 2020.</strong> scikit-optimize 0.7  (<a href="whats_new/v0.7.html#version-0-7">Changelog</a>).

doc/whats_new/v0.8.rst

@@ -2,6 +2,15 @@
 
 .. currentmodule:: skopt
 
+.. _changes_0_8_1:
+
+Version 0.8.1
+=============
+**September 2020**
+
+- |Fix| GaussianProcessRegressor on sklearn 0.23 normalizes the
+  variance to 1, which needs to reverted on predict.
+
 .. _changes_0_8:
 
 Version 0.8.0

skopt/__init__.py

@@ -29,7 +29,7 @@
 # Dev branch marker is: 'X.Y.dev' or 'X.Y.devN' where N is an integer.
 # 'X.Y.dev0' is the canonical version of 'X.Y.dev'
 #
-__version__ = "0.8.0"
+__version__ = "0.8.1"
 
 if __SKOPT_SETUP__:
     import sys

skopt/learning/gaussian_process/gpr.py

@@ -224,10 +224,15 @@ def fit(self, X, y):
         self.K_inv_ = L_inv.dot(L_inv.T)
 
         # Fix deprecation warning #462
-        if int(sklearn.__version__[2:4]) >= 19:
+        if int(sklearn.__version__[2:4]) >= 23:
+            self.y_train_std_ = self._y_train_std
             self.y_train_mean_ = self._y_train_mean
+        elif int(sklearn.__version__[2:4]) >= 19:
+            self.y_train_mean_ = self._y_train_mean
+            self.y_train_std_ = 1
         else:
             self.y_train_mean_ = self.y_train_mean
+            self.y_train_std_ = 1
 
         return self
 
@@ -309,11 +314,14 @@ def predict(self, X, return_std=False, return_cov=False,
         else:  # Predict based on GP posterior
             K_trans = self.kernel_(X, self.X_train_)
             y_mean = K_trans.dot(self.alpha_)    # Line 4 (y_mean = f_star)
-            y_mean = self.y_train_mean_ + y_mean  # undo normal.
+            # undo normalisation
+            y_mean = self.y_train_std_ * y_mean + self.y_train_mean_
 
             if return_cov:
                 v = cho_solve((self.L_, True), K_trans.T)  # Line 5
                 y_cov = self.kernel_(X) - K_trans.dot(v)   # Line 6
+                # undo normalisation
+                y_cov = y_cov * self.y_train_std_**2
                 return y_mean, y_cov
 
             elif return_std:
@@ -330,17 +338,22 @@ def predict(self, X, return_std=False, return_cov=False,
                     warnings.warn("Predicted variances smaller than 0. "
                                   "Setting those variances to 0.")
                     y_var[y_var_negative] = 0.0
+                # undo normalisation
+                y_var = y_var * self.y_train_std_**2
                 y_std = np.sqrt(y_var)
 
             if return_mean_grad:
                 grad = self.kernel_.gradient_x(X[0], self.X_train_)
                 grad_mean = np.dot(grad.T, self.alpha_)
-
+                # undo normalisation
+                grad_mean = grad_mean * self.y_train_std_
                 if return_std_grad:
                     grad_std = np.zeros(X.shape[1])
                     if not np.allclose(y_std, grad_std):
                         grad_std = -np.dot(K_trans,
                                            np.dot(K_inv, grad))[0] / y_std
+                        # undo normalisation
+                        grad_std = grad_std * self.y_train_std_**2
                     return y_mean, y_std, grad_mean, grad_std
 
                 if return_std:

skopt/tests/test_acquisition.py

@@ -119,6 +119,19 @@ def test_acquisition_gradient():
         check_gradient_correctness(X_new, gpr, acq_func, np.max(y))
 
 
+@pytest.mark.fast_test
+def test_acquisition_gradient_cookbook():
+    rng = np.random.RandomState(0)
+    X = rng.randn(20, 5)
+    y = rng.randn(20)
+    X_new = rng.randn(5)
+    gpr = cook_estimator("GP", Space(((-5.0, 5.0),)), random_state=0)
+    gpr.fit(X, y)
+
+    for acq_func in ["LCB", "PI", "EI"]:
+        check_gradient_correctness(X_new, gpr, acq_func, np.max(y))
+
+
 @pytest.mark.fast_test
 @pytest.mark.parametrize("acq_func", ["EIps", "PIps"])
 def test_acquisition_per_second(acq_func):