ml4chem package

Subpackages

• ml4chem.atomistic package
  • Subpackages
    • ml4chem.atomistic.features package
      • Submodules
      • ml4chem.atomistic.features.aev module
      • ml4chem.atomistic.features.autoencoders module
      • ml4chem.atomistic.features.base module
      • ml4chem.atomistic.features.cartesian module
      • ml4chem.atomistic.features.coulombmatrix module
      • ml4chem.atomistic.features.cutoff module
      • ml4chem.atomistic.features.gaussian module
      • Module contents
    • ml4chem.atomistic.models package
      • Submodules
      • ml4chem.atomistic.models.autoencoders module
      • ml4chem.atomistic.models.base module
      • ml4chem.atomistic.models.gaussian_process module
      • ml4chem.atomistic.models.kernelridge module
      • ml4chem.atomistic.models.loss module
      • ml4chem.atomistic.models.merger module
      • ml4chem.atomistic.models.neuralnetwork module
      • ml4chem.atomistic.models.se3net module
      • Module contents
  • Submodules
  • ml4chem.atomistic.potentials module
  • Module contents
• ml4chem.backends package
  • Submodules
  • ml4chem.backends.available module
    • available_backends()
    • cuda_is_available()
  • ml4chem.backends.operations module
    • BackendOperations
      • BackendOperations.divide()
      • BackendOperations.dot()
      • BackendOperations.exp()
      • BackendOperations.from_numpy()
      • BackendOperations.log10()
      • BackendOperations.logspace()
      • BackendOperations.norm()
      • BackendOperations.sum()
      • BackendOperations.to_numpy()
  • Module contents
• ml4chem.data package
  • Submodules
  • ml4chem.data.handler module
  • ml4chem.data.parser module
  • ml4chem.data.preprocessing module
    • Preprocessing
      • Preprocessing.fit()
      • Preprocessing.save_to_file()
      • Preprocessing.set()
      • Preprocessing.transform()
  • ml4chem.data.serialization module
    • dump()
    • load()
  • ml4chem.data.utils module
  • Module contents
• ml4chem.optim package
  • Submodules
  • ml4chem.optim.LBFGS module
  • ml4chem.optim.handler module
    • get_lr()
    • get_lr_scheduler()
    • get_optimizer()
  • Module contents

Submodules

ml4chem.active module

class ml4chem.active.ActiveLearning(labeled, unlabeled, atomistic=True)

Bases: object

Active Learning

Parameters:

• labeled (list) – List of graphs or objects.

• unlabeled (object) – List of graphs or objects.

• atomistic (bool, optional) – Atomistic similarities?, by default False.

run(kernel, max_variance=10, max_iter=None)

Run the ActiveLearning class

Parameters:

• kernel (object) – A kernel to measure similarity.

• max_variance (float, optional) – Maximum variance allowed, by default 10.

• max_iter (int, optional) – Maximum number of iterations allowed, by default None.

ml4chem.metrics module

ml4chem.metrics.compute_mae(outputs, targets, atoms_per_image=None)

Compute MAE

Useful when using futures.

Parameters:

• outputs (list) – List of outputs.

• targets (list) – List if targets.

• atoms_per_image (list) – List of atoms per image.

Returns:

mae – Mean absolute error.

Return type:

float

ml4chem.metrics.compute_mse(outputs, targets, atoms_per_image=None)

Compute MSE

Useful when using futures.

Parameters:

• outputs (list) – List of outputs.

• targets (list) – List if targets.

• atoms_per_image (list) – List of atoms per image.

Returns:

mse – Mean squared error.

Return type:

float

ml4chem.metrics.compute_rmse(outputs, targets, atoms_per_image=None)

Compute RMSE

Useful when using futures.

Parameters:

• outputs (list) – List of outputs.

• targets (list) – List if targets.

• atoms_per_image (list) – List of atoms per image.

Returns:

rmse – Root-mean squared error.

Return type:

float

ml4chem.utils module

ml4chem.visualization module

Module contents