Problem with scaling parametrs pluging

[DavideDC95]

Describe the bug If in plugins it is passed a scaler for the parametrs there is an inconsistency between predict and thruth solution

To Reproduce pod = POD() rbf = RBF() db = Database(param, snapshots.T) rom = ROM(db, pod, rbf, plugins=[ DatabaseScaler(StandardScaler(), 'reduced', 'snapshots'), DatabaseScaler(StandardScaler(), 'reduced', 'parameters') ]) rom.fit() test_param = param[2] truth_sol = db.snapshots_matrix[2] predicted_sol = rom.predict(test_param).snapshots_matrix[0] np.testing.assert_allclose(predicted_sol, truth_sol, rtol=1e-5, atol=1e-5)

Expected behavior AssertionError: Not equal to tolerance rtol=1e-05, atol=1e-05

Output E Mismatched elements: 2500 / 2500 (100%) E Max absolute difference among violations: 32.81964758 E Max relative difference among violations: 47.42442793 E ACTUAL: array([ 8.536083, 8.370944, 8.204127, ..., 0.628054, -0.241309, E -1.047201], shape=(2500,)) E DESIRED: array([ 6.31744 , 6.15722 , 5.99945 , ..., 0.53165 , -0.714494, E -1.77711 ], shape=(2500,), dtype=float32)

Additional context For the moment this possibility is removed since in erzb.plugin.scaler.py I added

" if target == 'parameters': #TODO raise NotImplementedError("Scaling of parameters not implemented yet.") " that block the scaling on parameter. The bug remains to be solved