Enhanced StructGen ANN functionality #482

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Merged

rolan701 merged 16 commits into hjkgrp:main from rolan701:main

Oct 30, 2025

Contributor

rolan701 commented Oct 30, 2025

Added a number of things to ensure safe building with the --ANN flag

rolan701 and others added 9 commits

October 30, 2025 17:23


          Update globalvars.py

23f5d2c


          Update enhanced_structgen.py

6a09f49

added ANN support


          Update tf_nn_prep.py

a026a67

fixed keras versioning causing issues with loading ANN


          Update tf_ANN.py

3cef8e0

fixed keras versioning, made it safer, accepts more errors with ease and grace


          Update RACassemble.py

Updated to better handle keras 3 and safer


          Update io.py

d5b6128


          Update __main__.py

52f0d62

added enhanced structgen ANN functionality


          [pre-commit.ci] auto fixes from pre-commit hooks

c5131c3


          Update RACassemble.py

2274dc3

github-advanced-security bot found potential problems

View reviewed changes

molSimplify/Scripts/enhanced_structgen.py

    
                          new_true = np.where((~prev) & curr)[0] + 1  # +1 for 1-based indexing

                          batslist.append(list(new_true))

                          # Update stored state

                          prev = curr.copy()

Check warning

Code scanning / CodeQL

Variable defined multiple times Warning

This assignment to 'prev' is unnecessary as it is

before this value is used.

molSimplify/Scripts/enhanced_structgen.py

    
                  """

                  # initialize ANN

                  globs = globalvars()

Check notice

Code scanning / CodeQL

Unused local variable Note

Variable globs is not used.

molSimplify/Scripts/tf_nn_prep.py

    
                          [f"{float(i):.2f}" for i in r_ls[0]]) + ' angstrom')

                      print('ANN high spin bond length (ax1/ax2/eq) is predicted to be: ' + " /".join(

                          [f"{float(i):.2f}" for i in r_hs[0]]) + ' angstrom')

                  except:

Check notice

Code scanning / CodeQL

Except block handles 'BaseException' Note

Except block directly handles BaseException.

molSimplify/__main__.py

    
              # fix OB bug: https://github.com/openbabel/openbabel/issues/1983

              import sys

              import os

              import numpy as np

Check notice

Code scanning / CodeQL

Unused import Note

Import of 'np' is not used.

molSimplify/__main__.py

    
                                                       parseCLI)

              from molSimplify.Scripts.generator import startgen

              from molSimplify.Classes.globalvars import globalvars

              from molSimplify.Classes.globalvars import globalvars, geometry_vectors

Check notice

Code scanning / CodeQL

Unused import Note

Import of 'geometry_vectors' is not used.

molSimplify/python_nn/tf_ANN.py

    
                      mod_name = "sklearn.grid_search"

                      if mod_name not in sys.modules:

                          sys.modules[mod_name] = _ms

                  except Exception:

Check notice

Code scanning / CodeQL

Empty except Note

'except' clause does nothing but pass and there is no explanatory comment.

molSimplify/python_nn/tf_ANN.py

    
                      mod_name = "sklearn.cross_validation"

                      if mod_name not in sys.modules:

                          sys.modules[mod_name] = _ms2

                  except Exception:

Check notice

Code scanning / CodeQL

Empty except Note

'except' clause does nothing but pass and there is no explanatory comment.

molSimplify/python_nn/tf_ANN.py

    
                  try:

                      loaded_model = load_keras_ann(predictor)

                      result = data_rescale(loaded_model.predict(excitation, verbose=0), train_mean_y, train_var_y, debug=debug)

                  except:

Check notice

Code scanning / CodeQL

Except block handles 'BaseException' Note

Except block directly handles BaseException.

molSimplify/python_nn/tf_ANN.py

    
                  loaded_model = load_keras_ann(predictor)

                  try:

                      loaded_model = load_keras_ann(predictor)

                  except:

Check notice

Code scanning / CodeQL

Except block handles 'BaseException' Note

Except block directly handles BaseException.

molSimplify/python_nn/tf_ANN.py

    
                          try:

                              latent_train_row = get_layer_outputs(loaded_model, len(loaded_model.layers) - 2,

                                                                   [np.array([scaled_row])], training_flag=False)

                          except:

Check notice

Code scanning / CodeQL

Except block handles 'BaseException' Note

Except block directly handles BaseException.

rolan701 and others added 7 commits

October 30, 2025 18:04


          Update tf_ANN.py

e9f0a08


          [pre-commit.ci] auto fixes from pre-commit hooks

bf379fa


          Update tf_ANN.py

4d24d2f


          Update tf_ANN.py

9852a4e


          Update tf_ANN.py

6ddce19


          Update tf_ANN.py

c280b76


          [pre-commit.ci] auto fixes from pre-commit hooks

409e053

github-advanced-security bot found potential problems

View reviewed changes

molSimplify/python_nn/tf_ANN.py

    
                      try:

                          from keras.saving.legacy.model_config import model_from_json as _legacy_model_from_json

                      except Exception:

                          _legacy_model_from_json = None

Check notice

Code scanning / CodeQL

Unused local variable Note

Variable _legacy_model_from_json is not used.

molSimplify/python_nn/tf_ANN.py

    
                      except Exception:

                          _legacy_model_from_json = None

                  except Exception:

                      _legacy_model_from_json = None

Check notice

Code scanning / CodeQL

Unused local variable Note

Variable _legacy_model_from_json is not used.

codecov bot commented Oct 30, 2025 •

edited

Loading

Codecov Report

❌ Patch coverage is 10.35503% with 303 lines in your changes missing coverage. Please review.
✅ Project coverage is 39.75%. Comparing base (7304fd4) to head (409e053).
⚠️ Report is 17 commits behind head on main.

Files with missing lines	Patch %	Lines
molSimplify/python_nn/tf_ANN.py	13.52%	179 Missing ⚠️
molSimplify/Scripts/enhanced_structgen.py	0.00%	84 Missing ⚠️
molSimplify/__main__.py	9.09%	30 Missing ⚠️
molSimplify/Scripts/tf_nn_prep.py	28.57%	10 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #482      +/-   ##
==========================================
- Coverage   40.12%   39.75%   -0.37%     
==========================================
  Files          93       93              
  Lines       29560    29886     +326     
==========================================
+ Hits        11861    11882      +21     
- Misses      17699    18004     +305

Flag	Coverage Δ
unittests	`39.75% <10.35%> (-0.37%)`	⬇️

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.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

rolan701 merged commit bd92d20 into hjkgrp:main

10 checks passed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet