getPredictionHyperParamSearch: Extract hyper parameters details

View source: R/PredictionQueries.R

getPredictionHyperParamSearchR Documentation

Extract hyper parameters details

Description

This function extracts the hyper parameters details

Usage

getPredictionHyperParamSearch(
  connectionHandler,
  schema,
  plpTablePrefix = "plp_",
  modelDesignId = NULL,
  databaseId = NULL
)

Arguments

connectionHandler

A connection handler that connects to the database and extracts sql queries. Create a connection handler via 'ResultModelManager::ConnectionHandler$new()'.

schema

The result database schema (e.g., 'main' for sqlite)

plpTablePrefix

The prefix used for the patient level prediction results tables

modelDesignId

The identifier for a model design to restrict to

databaseId

The identifier for the development database to restrict to

Details

Specify the connectionHandler, the resultDatabaseSettings, the modelDesignId and the databaseId

Value

Returns a data.frame with the columns:

  • metric the hyperparameter optimization metric

  • fold the fold in cross validation

  • value the metric value for the fold with the specified hyperparameter combination

plus columns for all the hyperparameters and their values

See Also

Other Prediction: getPredictionCohorts(), getPredictionDiagnosticTable(), getPredictionDiagnostics(), getPredictionIntercept(), getPredictionModelDesigns(), getPredictionPerformanceTable(), getPredictionPerformances(), getPredictionTopPredictors()

Examples

conDet <- getExampleConnectionDetails()

connectionHandler <- ResultModelManager::ConnectionHandler$new(conDet)

hyperParams <- getPredictionHyperParamSearch(
  connectionHandler = connectionHandler, 
  schema = 'main'
)


OhdsiReportGenerator documentation built on April 12, 2025, 2:09 a.m.