immuneML.workflows.instructions.ml_model_application package¶

Submodules¶

class immuneML.workflows.instructions.ml_model_application.MLApplicationInstruction.MLApplicationInstruction(dataset: immuneML.data_model.dataset.Dataset.Dataset, label_configuration: immuneML.environment.LabelConfiguration.LabelConfiguration, hp_setting: immuneML.hyperparameter_optimization.HPSetting.HPSetting, number_of_processes: int, name: str, store_encoded_data: bool)[source]¶

Instruction which enables using trained ML models and encoders on new datasets which do not necessarily have labeled data.

The predictions are stored in the predictions.csv in the result path in the following format:

example_id	cmv	cmv_true_proba	cmv_false_proba
e1	True	0.8	0.2
e2	False	0.2	0.8
e3	True	0.78	0.22

Parameters

dataset – dataset for which examples need to be classified
config_path – path to the zip file exported from MLModelTraining instruction (which includes train ML model, encoder, preprocessing etc.)
number_of_processes (int) – number of processes to use for prediction
store_encoded_data (bool) – whether encoded dataset should be stored on disk; can be True or False; setting this argument to True might
the disk space usage (increase) –

Specification example for the MLApplication instruction:

instruction_name:
    type: MLApplication
    dataset: d1
    config_path: ./config.zip
    number_of_processes: 4
    store_encoded_data: False

class immuneML.workflows.instructions.ml_model_application.MLApplicationState.MLApplicationState(dataset: immuneML.data_model.dataset.Dataset.Dataset, hp_setting: immuneML.hyperparameter_optimization.HPSetting.HPSetting, label_config: immuneML.environment.LabelConfiguration.LabelConfiguration, pool_size: int, name: str, store_encoded_data: bool, path: pathlib.Path = None, predictions_path: pathlib.Path = None)[source]¶

Bases: object

label_config: immuneML.environment.LabelConfiguration.LabelConfiguration¶