immuneML.workflows.instructions.ml_model_application package¶
Submodules¶
immuneML.workflows.instructions.ml_model_application.MLApplicationInstruction module¶
-
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)[source]¶ Bases:
immuneML.workflows.instructions.Instruction.Instruction
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
Specification example for the MLApplication instruction:
instruction_name: type: MLApplication dataset: d1 config_path: ./config.zip number_of_processes: 4
immuneML.workflows.instructions.ml_model_application.MLApplicationState module¶
-
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, path: pathlib.Path = None, predictions_path: pathlib.Path = None)[source]¶ Bases:
object
-
name
: str¶
-
path
: pathlib.Path = None¶
-
pool_size
: int¶
-
predictions_path
: pathlib.Path = None¶
-