Refactoring solvers by dario-coscia · Pull Request #541 · mathLab/PINA

dario-coscia · 2025-04-08T14:56:58Z

Simplify logic compile
Improve and update doc
Create SupervisedSolverInterface
Specialize SupervisedSolver and ReducedOrderModelSolver
Create EnsembleSolverInterface + EnsembleSupervisedSolver
Create tests ensemble solvers

* Simplify logic compile * Improve and update doc * Create SupervisedSolverInterface * Specialize SupervisedSolver and ReducedOrderModelSolver * Create EnsembleSolverInterface + EnsembleSupervisedSolver * Create tests ensemble solvers

github-actions · 2025-04-08T15:03:32Z

Code Coverage Summary

Filename                                                   Stmts    Miss  Cover    Missing
-------------------------------------------------------  -------  ------  -------  ---------------------------------------------------------------------------------------------------------------------
__init__.py                                                    7       0  100.00%
collector.py                                                  40       1  97.50%   46
graph.py                                                     114      11  90.35%   99-100, 112, 124, 126, 142, 144, 166, 169, 182, 271
label_tensor.py                                              248      32  87.10%   81, 121, 144-148, 165, 177, 182, 188-193, 273, 280, 332, 334, 348, 444-447, 490, 548, 632, 652-654, 667-676, 691, 713
operator.py                                                   68       5  92.65%   250-268, 457
operators.py                                                   6       6  0.00%    3-12
plotter.py                                                     1       1  0.00%    3
trainer.py                                                    75       6  92.00%   195-204, 293, 314, 318, 322
utils.py                                                      56       8  85.71%   113, 150, 153, 156, 192-195
adaptive_function/__init__.py                                  3       0  100.00%
adaptive_function/adaptive_function.py                        55       0  100.00%
adaptive_function/adaptive_function_interface.py              51       6  88.24%   98, 141, 148-151
adaptive_functions/__init__.py                                 6       6  0.00%    3-12
callback/__init__.py                                           5       0  100.00%
callback/adaptive_refinement_callback.py                       8       1  87.50%   37
callback/linear_weight_update_callback.py                     28       1  96.43%   63
callback/optimizer_callback.py                                22       1  95.45%   34
callback/processing_callback.py                               49       5  89.80%   42-43, 73, 168, 171
callbacks/__init__.py                                          6       6  0.00%    3-12
condition/__init__.py                                          7       0  100.00%
condition/condition.py                                        35       8  77.14%   23, 127-128, 131-132, 135-136, 151
condition/condition_interface.py                              32       3  90.62%   31, 76, 100
condition/data_condition.py                                   26       1  96.15%   56
condition/domain_equation_condition.py                        19       0  100.00%
condition/input_equation_condition.py                         44       1  97.73%   129
condition/input_target_condition.py                           44       1  97.73%   125
data/__init__.py                                               3       0  100.00%
data/data_module.py                                          204      22  89.22%   42-53, 133, 173, 194, 233, 314-318, 324-328, 400, 467, 547, 638, 640
data/dataset.py                                               80       6  92.50%   42, 123-126, 291
domain/__init__.py                                            10       0  100.00%
domain/cartesian.py                                          112      10  91.07%   37, 47, 75-76, 92, 97, 103, 246, 256, 264
domain/difference_domain.py                                   25       2  92.00%   54, 87
domain/domain_interface.py                                    20       5  75.00%   37-41
domain/ellipsoid.py                                          104      24  76.92%   52, 56, 127, 250-257, 269-282, 286-287, 290, 295
domain/exclusion_domain.py                                    28       1  96.43%   86
domain/intersection_domain.py                                 28       1  96.43%   85
domain/operation_interface.py                                 26       1  96.15%   88
domain/simplex.py                                             72      14  80.56%   62, 207-225, 246-247, 251, 256
domain/union_domain.py                                        25       2  92.00%   43, 114
equation/__init__.py                                           4       0  100.00%
equation/equation.py                                          11       0  100.00%
equation/equation_factory.py                                  24      10  58.33%   37, 62-75, 97-110, 132-145
equation/equation_interface.py                                 4       0  100.00%
equation/system_equation.py                                   22       0  100.00%
geometry/__init__.py                                           7       7  0.00%    3-15
loss/__init__.py                                               7       0  100.00%
loss/loss_interface.py                                        17       2  88.24%   45, 51
loss/lp_loss.py                                               15       0  100.00%
loss/ntk_weighting.py                                         26       0  100.00%
loss/power_loss.py                                            15       0  100.00%
loss/scalar_weighting.py                                      16       0  100.00%
loss/weighting_interface.py                                    6       0  100.00%
model/__init__.py                                             10       0  100.00%
model/average_neural_operator.py                              31       2  93.55%   73, 82
model/deeponet.py                                             93      13  86.02%   187-190, 209, 240, 283, 293, 303, 313, 323, 333, 488, 498
model/feed_forward.py                                         89      11  87.64%   58, 195, 200, 278-292
model/fourier_neural_operator.py                              78      10  87.18%   96-100, 110, 155-159, 218, 220, 242, 342
model/graph_neural_operator.py                                40       2  95.00%   58, 60
model/kernel_neural_operator.py                               34       6  82.35%   83-84, 103-104, 123-124
model/low_rank_neural_operator.py                             27       2  92.59%   89, 98
model/multi_feed_forward.py                                   12       5  58.33%   25-31
model/spline.py                                               89      37  58.43%   30, 41-66, 69, 128-132, 135, 159-177, 180
model/block/__init__.py                                       12       0  100.00%
model/block/average_neural_operator_block.py                  12       0  100.00%
model/block/convolution.py                                    64      13  79.69%   77, 81, 85, 91, 97, 111, 114, 151, 161, 171, 181, 191, 201
model/block/convolution_2d.py                                146      27  81.51%   155, 162, 282, 314, 379-433, 456
model/block/embedding.py                                      48       7  85.42%   93, 143-146, 155, 168
model/block/fourier_block.py                                  31       0  100.00%
model/block/gno_block.py                                      22       4  81.82%   73-77, 87
model/block/integral.py                                       18       4  77.78%   22-25, 71
model/block/low_rank_block.py                                 24       0  100.00%
model/block/orthogonal.py                                     37       0  100.00%
model/block/pod_block.py                                      65       9  86.15%   54-57, 69, 99, 134-139, 170, 195
model/block/rbf_block.py                                     179      25  86.03%   18, 42, 53, 64, 75, 86, 97, 223, 280, 282, 298, 301, 329, 335, 363, 367, 511-524
model/block/residual.py                                       46       0  100.00%
model/block/spectral.py                                       83       4  95.18%   132, 140, 262, 270
model/block/stride.py                                         28       7  75.00%   55, 58, 61, 67, 72-74
model/block/utils_convolution.py                              22       3  86.36%   58-60
model/layers/__init__.py                                       6       6  0.00%    3-12
optim/__init__.py                                              5       0  100.00%
optim/optimizer_interface.py                                   7       0  100.00%
optim/scheduler_interface.py                                   7       0  100.00%
optim/torch_optimizer.py                                      14       0  100.00%
optim/torch_scheduler.py                                      19       2  89.47%   5-6
problem/__init__.py                                            6       0  100.00%
problem/abstract_problem.py                                  104      14  86.54%   52, 61, 101-106, 135, 147, 165, 239, 243, 272
problem/inverse_problem.py                                    22       0  100.00%
problem/parametric_problem.py                                  8       1  87.50%   29
problem/spatial_problem.py                                     8       0  100.00%
problem/time_dependent_problem.py                              8       0  100.00%
problem/zoo/__init__.py                                        8       0  100.00%
problem/zoo/advection.py                                      33       7  78.79%   36-38, 52, 108-110
problem/zoo/allen_cahn.py                                     20       6  70.00%   20-22, 34-36
problem/zoo/diffusion_reaction.py                             29       5  82.76%   94-104
problem/zoo/helmholtz.py                                      30       6  80.00%   36-42, 103-107
problem/zoo/inverse_poisson_2d_square.py                      31       0  100.00%
problem/zoo/poisson_2d_square.py                              19       3  84.21%   65-70
problem/zoo/supervised_problem.py                             11       0  100.00%
solver/__init__.py                                             6       0  100.00%
solver/garom.py                                              107       2  98.13%   129-130
solver/solver.py                                             177       9  94.92%   184, 207, 264, 267-268, 327, 483, 524, 530
solver/ensemble_solver/__init__.py                             4       0  100.00%
solver/ensemble_solver/ensemble_pinn.py                       23       1  95.65%   104
solver/ensemble_solver/ensemble_solver_interface.py           27       0  100.00%
solver/ensemble_solver/ensemble_supervised.py                  9       0  100.00%
solver/physics_informed_solver/__init__.py                     8       0  100.00%
solver/physics_informed_solver/causal_pinn.py                 47       3  93.62%   157, 166-167
solver/physics_informed_solver/competitive_pinn.py            58       0  100.00%
solver/physics_informed_solver/gradient_pinn.py               17       0  100.00%
solver/physics_informed_solver/pinn.py                        18       0  100.00%
solver/physics_informed_solver/pinn_interface.py              66       0  100.00%
solver/physics_informed_solver/rba_pinn.py                    35       3  91.43%   155-158
solver/physics_informed_solver/self_adaptive_pinn.py          90       3  96.67%   315-318
solver/supervised_solver/__init__.py                           4       0  100.00%
solver/supervised_solver/reduced_order_model.py               24       1  95.83%   137
solver/supervised_solver/supervised.py                         7       0  100.00%
solver/supervised_solver/supervised_solver_interface.py       25       1  96.00%   90
solvers/__init__.py                                            6       6  0.00%    3-12
solvers/pinns/__init__.py                                      6       6  0.00%    3-12
TOTAL                                                       4465     493  88.96%

Results for commit: f82085d

Minimum allowed coverage is 80.123%

♻️ This comment has been updated with latest results

dario-coscia · 2025-04-08T17:18:29Z

Tried to fix some codacy errors but there are two which we cannot fix:

too-many-positional-arguments (R0917) -> unfortunately, this is something all solvers face
redefined-builtin (W0622) -> I changed input_pts, output_pts to input, target, unfortunately input is also a builtin python method.

We can easily fix it my removing it from pylint, but let's discuss it and fix it in another PR in case

GiovanniCanali

Thank you for the nice enhancements, @dario-coscia!
I have left several minor comments. Please, address them before merging.

FilippoOlivo

Personally, I do not like the the way in which the solver are subdivided. Specifically, I would avoid the ensemble solver folder, while, I will put ensemble_supervised into supervised_solver folder and ensemble_pinn into pinn physics_informed_solver

dario-coscia · 2025-04-09T09:14:16Z

Personally, I do not like the the way in which the solver are subdivided. Specifically, I would avoid the ensemble solver folder, while, I will put ensemble_supervised into supervised_solver folder and ensemble_pinn into pinn physics_informed_solver

I did this to have flexibility in the future, I think other ensemble methods will be added. Like this, we have a dedicated module for ensembles, which is reasonable to me

FilippoOlivo · 2025-04-09T09:18:22Z

Personally, I do not like the the way in which the solver are subdivided. Specifically, I would avoid the ensemble solver folder, while, I will put ensemble_supervised into supervised_solver folder and ensemble_pinn into pinn physics_informed_solver

I did this to have flexibility in the future, I think other ensemble methods will be added. Like this, we have a dedicated module for ensembles, which is reasonable to me

I get what you mean but, in my opinion they still belong to supervised/physics_informed solvers. @GiovanniCanali @ndem0 what do you think?

dario-coscia · 2025-04-09T09:25:29Z

@GiovanniCanali I fixed the issues, check the one unresolved if you agree. Also I speeded up a bit the test by decreasing number of points evaluations in the solvers, now we go a 15% faster in testing

GiovanniCanali · 2025-04-09T09:51:35Z

Personally, I do not like the the way in which the solver are subdivided. Specifically, I would avoid the ensemble solver folder, while, I will put ensemble_supervised into supervised_solver folder and ensemble_pinn into pinn physics_informed_solver

I did this to have flexibility in the future, I think other ensemble methods will be added. Like this, we have a dedicated module for ensembles, which is reasonable to me

I get what you mean but, in my opinion they still belong to supervised/physics_informed solvers. @GiovanniCanali @ndem0 what do you think?

Personally, I appreciate the proposed logic. Anyway, I will spend some time thinking about this.

GiovanniCanali

No further suggestions. Thank you @dario-coscia!

* Refactoring solvers * Simplify logic compile * Improve and update doc * Create SupervisedSolverInterface * Specialize SupervisedSolver and ReducedOrderModelSolver * Create EnsembleSolverInterface + EnsembleSupervisedSolver * Create tests ensemble solvers * formatter * codacy * fix issues + speedup test

Refactoring solvers

ee11345

* Simplify logic compile * Improve and update doc * Create SupervisedSolverInterface * Specialize SupervisedSolver and ReducedOrderModelSolver * Create EnsembleSolverInterface + EnsembleSupervisedSolver * Create tests ensemble solvers

dario-coscia added enhancement New feature or request pr-to-review Label for PR that are ready to been reviewed labels Apr 8, 2025

dario-coscia requested review from FilippoOlivo and GiovanniCanali April 8, 2025 14:56

dario-coscia self-assigned this Apr 8, 2025

dario-coscia force-pushed the new_solvers branch from f4b9503 to 9c59f14 Compare April 8, 2025 16:49

formatter

746c2f3

dario-coscia force-pushed the new_solvers branch from 9c59f14 to 746c2f3 Compare April 8, 2025 17:04

codacy

05f7d2f

GiovanniCanali requested changes Apr 9, 2025

View reviewed changes

FilippoOlivo reviewed Apr 9, 2025

View reviewed changes

Comment thread pina/solver/__init__.py Outdated

FilippoOlivo suggested changes Apr 9, 2025

View reviewed changes

Comment thread pina/solver/ensemble_solver/ensemble_solver_interface.py

Comment thread pina/solver/supervised_solver/supervised_solver_interface.py

fix issues + speedup test

f82085d

dario-coscia requested review from FilippoOlivo and GiovanniCanali April 9, 2025 09:23

GiovanniCanali approved these changes Apr 9, 2025

View reviewed changes

Comment thread pina/solver/ensemble_solver/ensemble_solver_interface.py

dario-coscia removed the request for review from FilippoOlivo April 9, 2025 11:12

FilippoOlivo self-requested a review April 9, 2025 11:25

FilippoOlivo approved these changes Apr 9, 2025

View reviewed changes

dario-coscia merged commit ed1b64c into dev Apr 9, 2025
18 of 19 checks passed

dario-coscia deleted the new_solvers branch April 9, 2025 12:51

dario-coscia mentioned this pull request Apr 23, 2025

Dev updates #557

Merged

Conversation

dario-coscia commented Apr 8, 2025

Uh oh!

github-actions Bot commented Apr 8, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Code Coverage Summary

Uh oh!

dario-coscia commented Apr 8, 2025

Uh oh!

GiovanniCanali left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

FilippoOlivo left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

dario-coscia commented Apr 9, 2025

Uh oh!

Uh oh!

Uh oh!

FilippoOlivo commented Apr 9, 2025

Uh oh!

dario-coscia commented Apr 9, 2025

Uh oh!

GiovanniCanali commented Apr 9, 2025

Uh oh!

GiovanniCanali left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

github-actions Bot commented Apr 8, 2025 •

edited

Loading