Create a parameter object for the function runPlp

Usage

createRunPlpAnalysesArgs(
  outcomeId = NULL,
  splitSettings = PatientLevelPrediction::createDefaultSplitSetting(),
  sampleSettings = PatientLevelPrediction::createSampleSettings(),
 
    featureEngineeringSettings = PatientLevelPrediction::createFeatureEngineeringSettings(),
  preprocessSettings = PatientLevelPrediction::createPreprocessSettings(),
  modelSettings = PatientLevelPrediction::setLassoLogisticRegression(),
  logSettings = PatientLevelPrediction::createLogSettings(),
  executeSettings = PatientLevelPrediction::createDefaultExecuteSettings(),
  matchingSettings = CohortMethod::createMatchOnPsArgs(),
  timepoint = NULL
)

Arguments

outcomeId: The outcomeId for the prediction.
splitSettings: An object of type splitSettings that specifies how to split the data into train/validation/test. The default settings can be created using createDefaultSplitSetting
sampleSettings: An object of type sampleSettings that specifies any under/over sampling to be done. Should be created with createSampleSettings
featureEngineeringSettings: An object of featureEngineeringSettings specifying any feature engineering to be learned (using the train data)
preprocessSettings: An object of preprocessSettings. This setting specifies the minimum fraction of target population who must have a covariate for it to be included in the model training and whether to normalise the covariates before training. Should be created with createPreprocessSettings.
modelSettings: An object of class modelSettings.
logSettings: An object of logSettings created using createLogSettings specifying how the logging is done.
executeSettings: An object of type executeSettings specifying which parts of the analysis to run. Should be created using createExecuteSettings.
matchingSettings: The settings for the construction of the population on which the prediction model will be developed.
timepoint: The timepoint to predict risk (survival models only)

Details

Create an object defining the parameter values.