FEAT add jac for narx

Author: MatthewSZhang

.github/workflows/ci.yml

@@ -22,7 +22,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Build wheels
-        uses: pypa/[email protected].1
+        uses: pypa/[email protected].2
         env:
           CIBW_BUILD: cp3*-*
           CIBW_SKIP: pp* *i686* *musllinux* *-macosx_universal2 *-manylinux_ppc64le *-manylinux_s390x

examples/plot_narx.py

@@ -125,11 +125,14 @@
 # In the printed NARX model, it is found that :class:`FastCan` selects the correct
 # terms and the coefficients are close to the true values.
 
-from fastcan.narx import NARX, print_narx
+from fastcan.narx import NARX, _pt2fd, print_narx
+
+# Convert poly_ids and time_shift_ids to feat_ids and delay_ids
+feat_ids, delay_ids = _pt2fd(selected_poly_ids, time_shift_ids)
 
 narx_model = NARX(
-    time_shift_ids=time_shift_ids,
-    poly_ids=selected_poly_ids,
+    feat_ids=feat_ids,
+    delay_ids=delay_ids,
 )
 
 narx_model.fit(X, y)

examples/plot_narx_msa.py

@@ -15,7 +15,7 @@
 # Nonlinear system
 # ----------------
 #
-# `Duffing equation <https://en.wikipedia.org/wiki/Duffing_equation>` is used to
+# `Duffing equation <https://en.wikipedia.org/wiki/Duffing_equation>`_ is used to
 # generate simulated data. The mathematical model is given by
 #
 # .. math::
@@ -130,7 +130,7 @@ def plot_prediction(ax, t, y_true, y_pred, title):
 y_train_osa_pred = narx_model.predict(u_train, y_init=y_train[:max_delay])
 y_test_osa_pred = narx_model.predict(u_test, y_init=y_test[:max_delay])
 
-narx_model.fit(u_train, y_train, coef_init="one_step_ahead", method="Nelder-Mead")
+narx_model.fit(u_train, y_train, coef_init="one_step_ahead")
 y_train_msa_pred = narx_model.predict(u_train, y_init=y_train[:max_delay])
 y_test_msa_pred = narx_model.predict(u_test, y_init=y_test[:max_delay])
 
@@ -169,7 +169,7 @@ def plot_prediction(ax, t, y_true, y_pred, title):
 y_train_osa_pred = narx_model.predict(u_train, y_init=y_train[:max_delay])
 y_test_osa_pred = narx_model.predict(u_test, y_init=y_test[:max_delay])
 
-narx_model.fit(u_all, y_all, coef_init="one_step_ahead", method="Nelder-Mead")
+narx_model.fit(u_all, y_all, coef_init="one_step_ahead")
 y_train_msa_pred = narx_model.predict(u_train, y_init=y_train[:max_delay])
 y_test_msa_pred = narx_model.predict(u_test, y_init=y_test[:max_delay])