agentlib_mpc.machine_learning_plugins.physXAI package

Submodules

agentlib_mpc.machine_learning_plugins.physXAI.model_config_creation module

agentlib_mpc.machine_learning_plugins.physXAI.model_config_creation.model_path_generation(run_id: str, output_name: str) → str[source]

Generates the relative model path based on run_id and output_name. :param run_id: The unique identifier for the mpc run. :type run_id: str :param output_name: The name of the output feature. :type output_name: str

Returns:

The relative path to the model file.

Return type:

str

agentlib_mpc.machine_learning_plugins.physXAI.model_config_creation.physXAI_2_agentlib_json(run_id: str, preprocessing_dict: dict, model_dict: dict = None, training_dict: dict = None, model_type: str = 'ANN') → dict[source]

Converts physXAI model configurations to an AgentLib-MPC compatible JSON format. :param run_id: The unique identifier for the mpc run. :type run_id: str :param preprocessing_dict: The preprocessing configuration from physXAI. :type preprocessing_dict: dict :param model_dict: The model configuration from physXAI. Defaults to None. :type model_dict: dict, optional :param training_dict: The training configuration from physXAI. Defaults to None. :type training_dict: dict, optional :param model_type: The type of model (‘ANN’ or ‘LinReg’). Defaults to ‘ANN’. :type model_type: str, optional

Returns:

The converted configuration in AgentLib-MPC JSON format.

Return type:

dict

agentlib_mpc.machine_learning_plugins.physXAI.model_generation module

agentlib_mpc.machine_learning_plugins.physXAI.model_generation.generate_physxai_model(models: list[str] | dict[str, str] | str, physXAI_scripts_path: str, training_data_path: str, run_id: str, time_step: int = 900) → list[str][source]

Generate physXAI models

Parameters:

  • models (Union[list[str], dict[str, str], str]) – Define Models to be generated by physXAI. If a single string is given, it is assumed to be an id to an existing model folder. In this case, the existing models are copied to a new folder with the given new run_id. If a list of strings is given, each string is assumed to be a physXAI script filename (with or without .py ending) to be executed for model training. The output model names will be determined by the physXAI scripts. If a dict is given, each key is the desired output model name, and each value is the physXAI script filename (with or without .py ending) to be executed for model training.

  • physXAI_scripts_path (str) – Base path to physXAI scripts

  • training_data_path (str) – Path to training data csv file

  • run_id (str) – Run identifier

  • time_step (int, optional) – Time step for training. Defaults to 900.

Returns:

List of generated model file paths

Return type:

List[str]

agentlib_mpc.machine_learning_plugins.physXAI.model_generation.use_existing_models(old_id: str, new_id: str, model_save_path: str) → list[str][source]

Use existing physXAI models by copying them to a new folder with a new run_id.

Parameters:

  • old_id (str) – Existing model run identifier

  • new_id (str) – New model run identifier

  • model_save_path (str) – Path where models are saved

Returns:

List of generated model file paths

Return type:

List[str]