DOC: Add new example notebooks for TPGR optimizers, update existing notebooks

Author: yb6599

examples/cost_constrained_qr.ipynb

@@ -124,7 +124,7 @@
    "outputs": [],
    "source": [
     "# Interpolation using the points selected by the SSPOR\n",
-    "pysense_interp = model.predict(f[sensors])"
+    "pysense_interp = model.predict(f[sensors], method='unregularized')"
    ]
   },
   {
@@ -210,7 +210,7 @@
     "model.set_number_of_sensors(5)\n",
     "sensors = model.get_selected_sensors()\n",
     "\n",
-    "pysense_interp = model.predict(f[sensors])\n",
+    "pysense_interp = model.predict(f[sensors], method='unregularized')\n",
     "\n",
     "fig, ax = plt.subplots(1, 1, figsize=(10, 4))\n",
     "ax.plot(x[sensors], f[sensors], 'bo')\n",
@@ -278,7 +278,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.10.16"
   },
   "toc": {
    "base_numbering": 1,

examples/cross_validation.ipynb

@@ -79,7 +79,7 @@ class SSPOR(BaseEstimator):
     >>> print(x[model.selected_sensors])
     [1.    0.754 0.    0.92  0.37  0.572 0.134]
     >>> f = np.sin(3*x)
-    >>> f_pred = model.predict(f[model.selected_sensors])
+    >>> f_pred = model.predict(f[model.selected_sensors], method='unregularized')
     >>> print(np.linalg.norm(f - f_pred))
     0.022405698005838044
     """
@@ -493,12 +493,18 @@ def score(self, x, y=None, score_function=None, score_kws={}, solve_kws={}):
         sensors = self.get_selected_sensors()
         if score_function is None:
             return -np.sqrt(
-                np.mean((self.predict(x[:, sensors], **solve_kws) - x) ** 2)
+                np.mean(
+                    (
+                        self.predict(x[:, sensors], method="unregularized", **solve_kws)
+                        - x
+                    )
+                    ** 2
+                )
             )
         else:
             return score_function(
                 x,
-                self.predict(x[:, sensors], **solve_kws),
+                self.predict(x[:, sensors], method="unregularized", **solve_kws),
                 **score_kws,
             )