CLN: Align a few bits and pieces to trapping-resolve

pysindy/optimizers/trapping_sr3.py

@@ -71,28 +71,15 @@ class TrappingSR3(ConstrainedSR3):
 
     Parameters
     ----------
-    threshold : float, optional (default 0.1)
-        Determines the strength of the regularization. When the
-        regularization function R is the L0 norm, the regularization
-        is equivalent to performing hard thresholding, and lambda
-        is chosen to threshold at the value given by this parameter.
-        This is equivalent to choosing lambda = threshold^2 / (2 * nu).
-
     eta : float, optional (default 1.0e20)
-        Determines the strength of the stability term ||Pw-A||^2 in the
+        Determines the strength of the stability term :math:`||Pw-A||^2` in the
         optimization. The default value is very large so that the
         algorithm default is to ignore the stability term. In this limit,
         this should be approximately equivalent to the ConstrainedSR3 method.
 
-    alpha_m : float, optional (default eta * 0.1)
-        Determines the step size in the prox-gradient descent over m.
-        For convergence, need alpha_m <= eta / ||w^T * PQ^T * PQ * w||.
-        Typically 0.01 * eta <= alpha_m <= 0.1 * eta.
-
-    alpha_A : float, optional (default eta)
-        Determines the step size in the prox-gradient descent over A.
-        For convergence, need alpha_A <= eta, so typically
-        alpha_A = eta is used.
+    eps_solver : float, optional (default 1.0e-7)
+        If threshold != 0, this specifies the error tolerance in the
+        CVXPY (OSQP) solve. Default is 1.0e-3 in OSQP.
 
     alpha : float, optional (default 1.0e20)
         Determines the strength of the local stability term ||Qijk||^2 in the
@@ -105,6 +92,22 @@ class TrappingSR3(ConstrainedSR3):
         optimization. The default value is very large so that the
         algorithm default is to ignore this term.
 
+    mod_matrix:
+        Lyapunov matrix.  Trapping theorems apply to energy
+        :math:`\\propto \\dot y \\cdot y`, but also to any
+        :math:`\\propto \\dot y P \\cdot y` for Lyapunov matrix :math:`P`.
+        Defaults to the identity matrix.
+
+    alpha_A : float, optional (default eta)
+        Determines the step size in the prox-gradient descent over A.
+        For convergence, need alpha_A <= eta, so typically
+        alpha_A = eta is used.
+
+    alpha_m : float, optional (default eta * 0.1)
+        Determines the step size in the prox-gradient descent over m.
+        For convergence, need alpha_m <= eta / ||w^T * PQ^T * PQ * w||.
+        Typically 0.01 * eta <= alpha_m <= 0.1 * eta.
+
     gamma : float, optional (default 0.1)
         Determines the negative interval that matrix A is projected onto.
         For most applications gamma = 0.1 - 1.0 works pretty well.
@@ -123,28 +126,6 @@ class TrappingSR3(ConstrainedSR3):
         could be straightforwardly implemented, but L0 requires
         reformulation because of nonconvexity.
 
-    thresholds : np.ndarray, shape (n_targets, n_features), optional \
-            (default None)
-        Array of thresholds for each library function coefficient.
-        Each row corresponds to a measurement variable and each column
-        to a function from the feature library.
-        Recall that SINDy seeks a matrix :math:`\\Xi` such that
-        :math:`\\dot{X} \\approx \\Theta(X)\\Xi`.
-        ``thresholds[i, j]`` should specify the threshold to be used for the
-        (j + 1, i + 1) entry of :math:`\\Xi`. That is to say it should give the
-        threshold to be used for the (j + 1)st library function in the equation
-        for the (i + 1)st measurement variable.
-
-    eps_solver : float, optional (default 1.0e-7)
-        If threshold != 0, this specifies the error tolerance in the
-        CVXPY (OSQP) solve. Default is 1.0e-3 in OSQP.
-
-    inequality_constraints : bool, optional (default False)
-        If True, CVXPY methods are used.
-
-    max_iter : int, optional (default 30)
-        Maximum iterations of the optimization algorithm.
-
     accel : bool, optional (default False)
         Whether or not to use accelerated prox-gradient descent for (m, A).
 
@@ -156,26 +137,6 @@ class TrappingSR3(ConstrainedSR3):
         Initial guess for vector A in the optimization. Otherwise
         A is initialized as A = diag(gamma).
 
-    fit_intercept : boolean, optional (default False)
-        Whether to calculate the intercept for this model. If set to false, no
-        intercept will be used in calculations.
-
-    copy_X : boolean, optional (default True)
-        If True, X will be copied; else, it may be overwritten.
-
-    normalize_columns : boolean, optional (default False)
-        Normalize the columns of x (the SINDy library terms) before regression
-        by dividing by the L2-norm. Note that the 'normalize' option in sklearn
-        is deprecated in sklearn versions >= 1.0 and will be removed.
-
-    verbose : bool, optional (default False)
-        If True, prints out the different error terms every iteration.
-
-    verbose_cvxpy : bool, optional (default False)
-        Boolean flag which is passed to CVXPY solve function to indicate if
-        output should be verbose or not. Only relevant for optimizers that
-        use the CVXPY package in some capabity.
-
     Attributes
     ----------
     coef_ : array, shape (n_features,) or (n_targets, n_features)
@@ -386,6 +347,8 @@ def __post_init_guard(self):
             raise ValueError(
                 "Ineq. constr. -> threshold!=0 + relax_optim=True or relax_optim=False."
             )
+        if self.mod_matrix is None:
+            self.mod_matrix = np.eye(self._n_tgts)
 
     def set_params(self, **kwargs):
         super().set_params(**kwargs)
@@ -702,9 +665,6 @@ def _reduce(self, x, y):
         )
         var_len = n_features * n_tgts
 
-        if self.mod_matrix is None:
-            self.mod_matrix = np.eye(n_tgts)
-
         # Define PL, PQ, PT and PM tensors, only relevant if the stability term in
         # trapping SINDy is turned on.
         (