R/CohortDiagnostics.R

In cukarthik/CancerTreatmentCharacterization: What the package does (short line)

# Copyright 2020 Observational Health Data Sciences and Informatics
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

#' Execute the cohort diagnostics
#'
#' @details
#' This function executes the cohort diagnostics.
#'
#' @param connectionDetails    An object of type \code{connectionDetails} as created using the
#'                             \code{\link[DatabaseConnector]{createConnectionDetails}} function in the
#'                             DatabaseConnector package.
#' @param cdmDatabaseSchema    Schema name where your patient-level data in OMOP CDM format resides.
#'                             Note that for SQL Server, this should include both the database and
#'                             schema name, for example 'cdm_data.dbo'.
#' @param cohortDatabaseSchema Schema name where intermediate data can be stored. You will need to have
#'                             write priviliges in this schema. Note that for SQL Server, this should
#'                             include both the database and schema name, for example 'cdm_data.dbo'.
#' @param cohortTable          The name of the table that will be created in the work database schema.
#'                             This table will hold the exposure and outcome cohorts used in this
#'                             study.
#' @param oracleTempSchema     Should be used in Oracle to specify a schema where the user has write
#'                             priviliges for storing temporary tables.
#' @param outputFolder         Name of local folder to place results; make sure to use forward slashes
#'                             (/). Do not use a folder on a network drive since this greatly impacts
#'                             performance.
#' @param databaseId           A short string for identifying the database (e.g.
#'                             'Synpuf').
#' @param databaseName         The full name of the database (e.g. 'Medicare Claims
#'                             Synthetic Public Use Files (SynPUFs)').
#' @param databaseDescription  A short description (several sentences) of the database.
#' @param createCohorts        Create the cohortTable table with the exposure and outcome cohorts?
#' @param runInclusionStatistics      Generate and export statistic on the cohort incusion rules?
#' @param runIncludedSourceConcepts   Generate and export the source concepts included in the cohorts?
#' @param runOrphanConcepts           Generate and export potential orphan concepts?
#' @param runTimeDistributions        Generate and export cohort time distributions?
#' @param runBreakdownIndexEvents     Generate and export the breakdown of index events?
#' @param runIncidenceRates      Generate and export the cohort incidence rates?
#' @param runCohortOverlap            Generate and export the cohort overlap?
#' @param runCohortCharacterization   Generate and export the cohort characterization?
#' @param runTemporalCohortCharacterization Generate and export the temporal cohort characterization? 
#' @param minCellCount         The minimum number of subjects contributing to a count before it can be included 
#'                             in packaged results.
#'
#' @export
runCohortDiagnostics <- function(connection, package,
                                 cdmDatabaseSchema,
                                 cohortDatabaseSchema,
                                 cohortTable = "cohort",
                                 oracleTempSchema = cohortDatabaseSchema,
                                 outputFolder,
                                 databaseId = "Unknown",
                                 databaseName = "Unknown",
                                 databaseDescription = "Unknown",
                                 runInclusionStatistics = TRUE,
                                 runIncludedSourceConcepts = TRUE,
                                 runOrphanConcepts = TRUE,
                                 runTimeDistributions = TRUE,
                                 runBreakdownIndexEvents = TRUE,
                                 runIncidenceRates = TRUE,
                                 runCohortOverlap = TRUE,
                                 runCohortCharacterization = TRUE,
                                 runTemporalCohortCharacterization = TRUE,
                                 minCellCount = 5) {
  if (!file.exists(outputFolder))
    dir.create(outputFolder, recursive = TRUE)

  ParallelLogger::addDefaultFileLogger(file.path(outputFolder, "log.txt"))
  ParallelLogger::addDefaultErrorReportLogger(file.path(outputFolder, "errorReportR.txt"))
  on.exit(ParallelLogger::unregisterLogger("DEFAULT_FILE_LOGGER", silent = TRUE))
  on.exit(ParallelLogger::unregisterLogger("DEFAULT_ERRORREPORT_LOGGER", silent = TRUE), add = TRUE)

  ParallelLogger::logInfo("Running study diagnostics")
  CohortDiagnostics::runCohortDiagnostics(packageName = package,
                        connection = connection,
                                          cdmDatabaseSchema = cdmDatabaseSchema,
                                          tempEmulationSchema = oracleTempSchema,
                                          cohortDatabaseSchema = cohortDatabaseSchema,
                                          cohortTable = cohortTable,
                                          inclusionStatisticsFolder = outputFolder,
                                          exportFolder = file.path(outputFolder, "diagnosticsExport"),
                                          databaseId = databaseId,
                                          databaseName = databaseName,
                                          databaseDescription = databaseDescription,
                                          runInclusionStatistics = runInclusionStatistics,
                                          runIncludedSourceConcepts = runIncludedSourceConcepts,
                                          runOrphanConcepts = runOrphanConcepts,
                                          runTimeDistributions = runTimeDistributions,
                                          runBreakdownIndexEvents = runBreakdownIndexEvents,
                                          runIncidenceRate = runIncidenceRates,
                                          runCohortOverlap = runCohortOverlap,
                                          runCohortCharacterization = runCohortCharacterization,
                                          runTemporalCohortCharacterization = runTemporalCohortCharacterization,
                                          minCellCount = minCellCount)
}