Adding predtermined_norm_calc to gqr

Author: niharika2999

pysensors/optimizers/_gqr.py

@@ -95,6 +95,8 @@ def fit(
                 dlens_updated = norm_calc_max_n_const_sensors(self.constrainedIndices,dlens,p,j, self.nConstrainedSensors,self.all_sensorloc,self.nSensors) 
             elif self.constraint_option == "exact_n_const_sensors" : 
                 dlens_updated = norm_calc_exact_n_const_sensors(self.constrainedIndices,dlens,p,j,self.nConstrainedSensors)
+            elif self.constraint_option == "predetermined_end":
+                dlens_updated = predetermined_norm_calc(self.constrainedIndices, dlens, p, j, self.nConstrainedSensors, self.nSensors)
 
             # Choose pivot
             i_piv = np.argmax(dlens_updated)
@@ -202,6 +204,38 @@ def norm_calc_max_n_const_sensors(lin_idx, dlens, piv, j, const_sensors,all_sens
                 dlens[didx] = 0
     return dlens
 
+def predetermined_norm_calc(lin_idx, dlens, piv, j, n_const_sensors, n_sensors):
+    """
+    Function for mapping constrained sensor locations with the QR procedure.
+
+    Parameters
+        ----------
+        lin_idx: np.ndarray, shape [No. of constrained locations]
+            Array which contains the constrained locationsof the grid in terms of column indices of basis_matrix.
+        dlens: np.ndarray, shape [Variable based on j]
+            Array which contains the norm of columns of basis matrix.
+        piv: np.ndarray, shape [n_features]
+            Ranked list of sensor locations.
+        n_const_sensors: int,
+            Number of sensors to be placed in the constrained area.
+        j: int,
+            Iterative variable in the QR algorithm.
+
+        Returns
+        -------
+        dlens : np.darray, shape [Variable based on j] with constraints mapped into it.
+    """
+    if (n_sensors - n_const_sensors) <= j <= n_sensors: # force sensors into constraint region
+        #idx = np.arange(dlens.shape[0])
+        #dlens[np.delete(idx, lin_idx)] = 0
+
+        didx = np.isin(piv[j:],lin_idx,invert=True)
+        dlens[didx] = 0
+    else:
+        didx = np.isin(piv[j:],lin_idx,invert=False)
+        dlens[didx] = 0
+    return dlens
+
 
 
 if __name__ == '__main__':

pysensors/utils/_validation.py

@@ -23,14 +23,11 @@ def determinant(top_sensors, n_features, basis_matrix):
     """
 
     c = np.zeros([len(top_sensors),n_features])
-    print(c.shape)
     for i in range(len(top_sensors)):
         c[i,top_sensors[i]] = 1
-    print(c)
     phi = basis_matrix
     optimality = np.linalg.det((c@phi).T @ (c@phi))
-    print(optimality)
-    return (c,phi,optimality)
+    return optimality
 
 def relative_reconstruction_error(data, prediction):
     """
@@ -47,6 +44,5 @@ def relative_reconstruction_error(data, prediction):
         error_val : Float, 
             The relative error calculated.
     """
-    error_val = (np.linalg.norm((data - prediction)/np.linalg.norm(data)))*100
-    print(error_val)
+    error_val = (np.linalg.norm((data - prediction)/(data)))*100
     return (error_val)