Update autode to 1.3.3 #121

juraskov · 2024-12-06T17:56:41Z

Preliminary update to autode v1.3.3. Update to the latest version will continue once I figure out the source of npz loading issue which started to occur in v1.3.4

codecov-commenter · 2024-12-06T17:59:06Z

Codecov Report

Attention: Patch coverage is 45.45455% with 12 lines in your changes missing coverage. Please review.

Project coverage is 64.69%. Comparing base (b99faae) to head (7dcd999).

Files with missing lines	Patch %	Lines
mlptrain/configurations/configuration_set.py	44.44%	10 Missing ⚠️
mlptrain/configurations/calculate.py	50.00%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #121      +/-   ##
==========================================
- Coverage   64.99%   64.69%   -0.30%     
==========================================
  Files          37       37              
  Lines        4268     4280      +12     
==========================================
- Hits         2774     2769       -5     
- Misses       1494     1511      +17

Flag	Coverage Δ
python-3.9	`60.74% <45.45%> (-0.29%)`	⬇️
python-3.9-ace	`60.74% <45.45%> (-0.29%)`	⬇️
python-3.9-mace	`64.50% <45.45%> (-0.30%)`	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

juraskov · 2025-01-24T18:27:54Z

Error observed when loading mg_aqua_mace_al.npz file (prepared with autode1.1.3) using autode1.4.4

>>> data = mlt.ConfigurationSet()
>>> data.load('mg_aqua_mace_al.npz')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Users/veronikajuraskova/SOFTWARE/mlp-train/mlptrain/configurations/configuration_set.py", line 493, in load
    self._load_npz(filename)
  File "/Users/veronikajuraskova/SOFTWARE/mlp-train/mlptrain/configurations/configuration_set.py", line 685, in _load_npz
    if data['F_true'].ndim > 0:
  File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap/lib/python3.9/site-packages/numpy/lib/npyio.py", line 256, in __getitem__
    return format.read_array(bytes,
  File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap/lib/python3.9/site-packages/numpy/lib/format.py", line 800, in read_array
    array = pickle.load(fp, **pickle_kwargs)
  File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap/lib/python3.9/site-packages/autode/values.py", line 667, in __setstate__
    self.__dict__.update(state[-1])
TypeError: cannot convert dictionary update sequence element #0 to a sequence

Hanwen1018 · 2025-01-25T22:55:20Z

allow training MACE with dipole
update mace
allow multi-head fine-tuning
allow mace training on multi-GPU cores

juraskov · 2025-01-27T19:38:14Z

Error observed with using autode v1.1.3 to 1.3.3, most probably data set specific:

import numpy as np
data_np = np.load('mg_aqua_mace_al.npz',allow_pickle=True)
data_np['F_true']
Traceback (most recent call last):
File "", line 1, in
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/numpy/core/arrayprint.py", line 1612, in _array_str_implementation
return array2string(a, max_line_width, precision, suppress_small, ' ', "")
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/numpy/core/arrayprint.py", line 736, in array2string
return _array2string(a, options, separator, prefix)
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/numpy/core/arrayprint.py", line 513, in wrapper
return f(self, *args, **kwargs)
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/numpy/core/arrayprint.py", line 546, in _array2string
lst = _formatArray(a, format_function, options['linewidth'],
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/numpy/core/arrayprint.py", line 889, in _formatArray
return recurser(index=(),
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/numpy/core/arrayprint.py", line 845, in recurser
word = recurser(index + (-i,), next_hanging_indent, next_width)
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/numpy/core/arrayprint.py", line 799, in recurser
return format_function(a[index])
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/numpy/core/arrayprint.py", line 395, in _object_format
return fmt.format(o)
File "/Users/veronikajuraskova/miniconda3/envs/mlptrain-gap-old/lib/python3.9/site-packages/autode/values.py", line 592, in repr
return f'Gradients({np.ndarray.str(self)} {self.units.name})'
AttributeError: 'Gradient' object has no attribute 'units'

mlptrain/configurations/configuration_set.py

Co-authored-by: Daniel Hollas <[email protected]>

…into autode-update-latest

This reverts commit 4ff68a9.

This reverts commit 6ec6778.

This reverts commit 1bba565.

danielhollas

Looks great, just some minor comments.

danielhollas · 2025-01-28T14:07:41Z

.pre-commit-config.yaml

@@ -11,7 +11,7 @@ repos:
        exclude: examples/WTMetaD_paper/r2/free_energy/wtmetad_ib/accumulated_bias/bias_after_iter_15.dat
      - id: check-added-large-files
        args: ['--maxkb=500', '--enforce-all']
-        exclude: tests/data/data.zip
+        exclude: (?x)^(tests/data/data.zip | tests/data/water_al.npz)$


I think we could still try to make this file smaller, i.e. by reading it and saving using the old mlptrain version and making sure we use old numpy as well? Worth a try.

danielhollas · 2025-01-28T14:09:19Z

mlptrain/configurations/configuration_set.py

-            if data['R_plumed'].ndim > 0:
-                config.plumed_coordinates = np.array(
-                    data['R_plumed'][i], dtype=float
+            try:


Just a note that this is fixing an issue unrelated to autoDE, where the code could not load npz files that were created before the Plumed integration was merged. Might be nice to document this problem in an issue and link it to this PR.

danielhollas · 2025-01-28T14:11:51Z

tests/test_configuration_set.py

@@ -137,6 +139,41 @@ def test_configurations_load_with_energies_forces():
            )


+@work_in_tmp_dir()
+def test_configurations_load_with_energies_forces_diff_sizes(


Great to have this test! Would be good to add a docstring to explain what we're testing here (loading configurations with different molecules)

danielhollas · 2025-01-28T14:14:33Z

tests/test_configuration_set.py

+    for attr in ('energy', 'forces'):
+        for kind in ('predicted', 'true'):
+            assert np.allclose(
+                getattr(getattr(loaded_configs[0], attr), kind),


This is clever but hard to read. I would trade the for loops for a bit of (straightforward) code repetition.

danielhollas · 2025-01-28T14:15:53Z

tests/test_configuration_set.py

@@ -161,6 +198,19 @@ def test_configurations_load_xyz():
        assert config.mult == 2


+def test_configurations_load_numpy_compatibility():


Here again having a docstring explaining why this test is here would be good.

Update autode to 1.4.4

4eb47ca

juraskov added 2 commits December 9, 2024 13:25

Change atomic charges to point charges

3c31a91

Change charges to partial charges

75e99fe

juraskov added 3 commits January 27, 2025 12:34

Update test_configuration_set

f522c79

Update _load_npz to ensure old npz compatibility

d111711

Change to version 1.3.3

4ff68a9

juraskov changed the title ~~WIP: Update autode to 1.4.4~~ WIP: Update autode to 1.3.3 Jan 27, 2025

danielhollas reviewed Jan 27, 2025

View reviewed changes

mlptrain/configurations/configuration_set.py Outdated Show resolved Hide resolved

juraskov and others added 8 commits January 28, 2025 00:26

Remove debugging print

273aa43

Co-authored-by: Daniel Hollas <[email protected]>

Updated test with failing file

75cc107

Merge branch 'autode-update-latest' of github.com:juraskov/mlp-train …

8b33762

…into autode-update-latest

Correct file path

1cca300

Revert "Change to version 1.3.3"

1bba565

This reverts commit 4ff68a9.

Test different numpy

6ec6778

Revert "Test different numpy"

30bf494

This reverts commit 6ec6778.

Revert "Revert "Change to version 1.3.3""

7dcd999

This reverts commit 1bba565.

juraskov marked this pull request as ready for review January 28, 2025 00:19

juraskov requested review from danielhollas and Hanwen1018 and removed request for danielhollas January 28, 2025 00:20

danielhollas reviewed Jan 28, 2025

View reviewed changes

juraskov changed the title ~~WIP: Update autode to 1.3.3~~ Update autode to 1.3.3 Jan 28, 2025

Hanwen1018 approved these changes Jan 31, 2025

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Update autode to 1.3.3 #121

Update autode to 1.3.3 #121

juraskov commented Dec 6, 2024 •

edited

Loading

codecov-commenter commented Dec 6, 2024 •

edited

Loading

juraskov commented Jan 24, 2025 •

edited

Loading

Hanwen1018 commented Jan 25, 2025

juraskov commented Jan 27, 2025

danielhollas left a comment

danielhollas Jan 28, 2025

danielhollas Jan 28, 2025

danielhollas Jan 28, 2025

danielhollas Jan 28, 2025

danielhollas Jan 28, 2025

		@@ -161,6 +198,19 @@ def test_configurations_load_xyz():
		assert config.mult == 2


		def test_configurations_load_numpy_compatibility():

Update autode to 1.3.3 #121

Are you sure you want to change the base?

Update autode to 1.3.3 #121

Conversation

juraskov commented Dec 6, 2024 • edited Loading

codecov-commenter commented Dec 6, 2024 • edited Loading

Codecov Report

juraskov commented Jan 24, 2025 • edited Loading

Hanwen1018 commented Jan 25, 2025

juraskov commented Jan 27, 2025

danielhollas left a comment

Choose a reason for hiding this comment

danielhollas Jan 28, 2025

Choose a reason for hiding this comment

danielhollas Jan 28, 2025

Choose a reason for hiding this comment

danielhollas Jan 28, 2025

Choose a reason for hiding this comment

danielhollas Jan 28, 2025

Choose a reason for hiding this comment

danielhollas Jan 28, 2025

Choose a reason for hiding this comment

juraskov commented Dec 6, 2024 •

edited

Loading

codecov-commenter commented Dec 6, 2024 •

edited

Loading

juraskov commented Jan 24, 2025 •

edited

Loading