splitData: Split the plpData into test/train sets using a splitting...

In OHDSI/PatientLevelPrediction: Develop Clinical Prediction Models Using the Common Data Model

Split the plpData into test/train sets using a splitting settings of class splitSettings

Description

Split the plpData into test/train sets using a splitting settings of class splitSettings

Usage

splitData(
  plpData = plpData,
  population = population,
  splitSettings = createDefaultSplitSetting(splitSeed = 42)
)

Arguments

plpData	An object of type plpData - the patient level prediction data extracted from the CDM.
population	The population created using createStudyPopulation that define who will be used to develop the model
splitSettings	An object of type splitSettings specifying the split - the default can be created using createDefaultSplitSetting

Value

Returns a list containing the training data (Train) and optionally the test data (Test). Train is an Andromeda object containing

• covariates: a table (rowId, covariateId, covariateValue) containing the covariates for each data point in the train data

• covariateRef: a table with the covariate information

• labels: a table (rowId, outcomeCount, ...) for each data point in the train data (outcomeCount is the class label)

• folds: a table (rowId, index) specifying which training fold each data point is in.

Test is an Andromeda object containing

• covariates: a table (rowId, covariateId, covariateValue) containing the covariates for each data point in the test data

• covariateRef: a table with the covariate information

• labels: a table (rowId, outcomeCount, ...) for each data point in the test data (outcomeCount is the class label)

Examples

data("simulationProfile")
plpData <- simulatePlpData(simulationProfile, n = 1000)
population <- createStudyPopulation(plpData)
splitSettings <- createDefaultSplitSetting(testFraction = 0.50, 
                                           trainFraction = 0.50, nfold = 5)
data = splitData(plpData, population, splitSettings)
# test data should be ~500 rows (changes because of study population)
nrow(data$Test$labels)
# train data should be ~500 rows
nrow(data$Train$labels)
# should be five fold in the train data
length(unique(data$Train$folds$index))

OHDSI/PatientLevelPrediction documentation built on Feb. 14, 2025, 9:44 a.m.