Merge pull request #272 from OHDSI/develop

Release v3.7.0
OHDSI · Sep 3, 2024 · eabfb42 · eabfb42
2 parents a0bbc9b + 725aee8
commit eabfb42
Show file tree

Hide file tree

Showing 93 changed files with 335 additions and 313 deletions.
diff --git a/CRAN-SUBMISSION b/CRAN-SUBMISSION
@@ -1,3 +1,3 @@
-Version: 3.5.2
-Date: 2024-04-30 18:12:58 UTC
-SHA: fe1f8048024d84e8079e872e60c4623c9d0c5c5f
+Version: 3.7.0
+Date: 2024-09-03 08:24:46 UTC
+SHA: efa425b67203564c5a581de9180a87d14c28767e
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: FeatureExtraction
 Type: Package
 Title: Generating Features for a Cohort
-Version: 3.6.0
-Date: 2024-07-15
+Version: 3.7.0
+Date: 2024-09-02
 Authors@R: c(
   person("Martijn", "Schuemie", , "[email protected]", role = c("aut")),
   person("Marc", "Suchard", role = c("aut")),
@@ -45,6 +45,6 @@ VignetteBuilder: knitr
 URL: https://github.com/OHDSI/FeatureExtraction
 BugReports: https://github.com/OHDSI/FeatureExtraction/issues
 NeedsCompilation: no
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Encoding: UTF-8
 Language: en-US
diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,10 @@
+FeatureExtraction 3.7.0
+=======================
+
+- Deprecate oracleTempSchema param, add tempEmulationSchema param (#126)
+- Filter binary covariates server side (#255)
+- Limit tests that are run on CRAN (#267)
+
 FeatureExtraction 3.6.0
 =======================
 

diff --git a/R/DefaultCovariateSettings.R b/R/DefaultCovariateSettings.R
@@ -483,7 +483,7 @@
 #'   useMeasurementValueAsConceptAnyTimePrior = FALSE,
 #'   useMeasurementValueAsConceptLongTerm = TRUE,
 #'   useMeasurementValueAsConceptMediumTerm = FALSE,
-#'   useMeasurementValueAsConceptShortTerm = TRUE,       
+#'   useMeasurementValueAsConceptShortTerm = TRUE,
 #'   useObservationAnyTimePrior = FALSE,
 #'   useObservationLongTerm = TRUE,
 #'   useObservationMediumTerm = FALSE,
@@ -617,7 +617,7 @@ createCovariateSettings <- function(useDemographicsGender = FALSE,
                                     useObservationValueAsConceptAnyTimePrior = FALSE,
                                     useObservationValueAsConceptLongTerm = FALSE,
                                     useObservationValueAsConceptMediumTerm = FALSE,
-                                    useObservationValueAsConceptShortTerm = FALSE,                                    
+                                    useObservationValueAsConceptShortTerm = FALSE,
                                     useCharlsonIndex = FALSE,
                                     useDcsi = FALSE,
                                     useChads2 = FALSE,

diff --git a/R/GetCovariates.R b/R/GetCovariates.R
@@ -33,7 +33,7 @@
 #'                               \code{connect} function in the \code{DatabaseConnector} package.
 #'                               Either the \code{connection} or \code{connectionDetails} argument
 #'                               should be specified.
-#' @param oracleTempSchema       A schema where temp tables can be created in Oracle.
+#' @param oracleTempSchema       DEPRECATED: use \code{tempEmulationSchema} instead.
 #' @param cdmDatabaseSchema      The name of the database schema that contains the OMOP CDM instance.
 #'                               Requires read permissions to this database. On SQL Server, this should
 #'                               specify both the database and the schema, so for example
@@ -66,6 +66,9 @@
 #' @param minCharacterizationMean The minimum mean value for characterization output. Values below this will be cut off from output. This
 #'                                will help reduce the file size of the characterization output, but will remove information
 #'                                on covariates that have very low values. The default is 0.
+#' @param tempEmulationSchema    Some database platforms like Oracle and Impala do not truly support
+#'                               temp tables. To emulate temp tables, provide a schema with write
+#'                               privileges where temp tables can be created.
 #'
 #' @return
 #' Returns an object of type \code{covariateData}, containing information on the covariates.
@@ -82,7 +85,7 @@
 #' )
 #' covData <- getDbCovariateData(
 #'   connectionDetails = eunomiaConnectionDetails,
-#'   oracleTempSchema = NULL,
+#'   tempEmulationSchema = NULL,
 #'   cdmDatabaseSchema = "main",
 #'   cdmVersion = "5",
 #'   cohortTable = "cohort",
@@ -109,7 +112,8 @@ getDbCovariateData <- function(connectionDetails = NULL,
                                rowIdField = "subject_id",
                                covariateSettings,
                                aggregated = FALSE,
-                               minCharacterizationMean = 0) {
+                               minCharacterizationMean = 0,
+                               tempEmulationSchema = NULL) {
   if (is.null(connectionDetails) && is.null(connection)) {
     stop("Need to provide either connectionDetails or connection")
   }
@@ -123,6 +127,13 @@ getDbCovariateData <- function(connectionDetails = NULL,
     warning("cohortId argument has been deprecated, please use cohortIds")
     cohortIds <- cohortId
   }
+  if (!is.null(oracleTempSchema) && oracleTempSchema != "") {
+    rlang::warn("The 'oracleTempSchema' argument is deprecated. Use 'tempEmulationSchema' instead.",
+      .frequency = "regularly",
+      .frequency_id = "oracleTempSchema"
+    )
+    tempEmulationSchema <- oracleTempSchema
+  }
   errorMessages <- checkmate::makeAssertCollection()
   minCharacterizationMean <- utils::type.convert(minCharacterizationMean, as.is = TRUE)
   checkmate::assertNumeric(x = minCharacterizationMean, lower = 0, upper = 1, add = errorMessages)
@@ -149,7 +160,7 @@ getDbCovariateData <- function(connectionDetails = NULL,
   sql <- SqlRender::translate(
     sql = sql,
     targetDialect = attr(connection, "dbms"),
-    oracleTempSchema = oracleTempSchema
+    tempEmulationSchema = tempEmulationSchema
   )
   temp <- DatabaseConnector::querySql(connection, sql, snakeCaseToCamelCase = TRUE)
   if (aggregated) {
@@ -174,7 +185,7 @@ getDbCovariateData <- function(connectionDetails = NULL,
         fun <- attr(covariateSettings[[i]], "fun")
         args <- list(
           connection = connection,
-          oracleTempSchema = oracleTempSchema,
+          tempEmulationSchema = tempEmulationSchema,
           cdmDatabaseSchema = cdmDatabaseSchema,
           cohortTable = cohortDatabaseSchemaTable,
           cohortIds = cohortIds,

diff --git a/R/GetCovariatesFromCohortAttributes.R b/R/GetCovariatesFromCohortAttributes.R
@@ -45,7 +45,7 @@
 #'
 #' covData <- getDbCohortAttrCovariatesData(
 #'   connection = connection,
-#'   oracleTempSchema = NULL,
+#'   tempEmulationSchema = NULL,
 #'   cdmDatabaseSchema = "main",
 #'   cdmVersion = "5",
 #'   cohortTable = "cohort",
@@ -66,7 +66,8 @@ getDbCohortAttrCovariatesData <- function(connection,
                                           cdmVersion = "5",
                                           rowIdField = "subject_id",
                                           covariateSettings,
-                                          aggregated = FALSE) {
+                                          aggregated = FALSE,
+                                          tempEmulationSchema = NULL) {
   if (aggregated) {
     stop("Aggregation not implemented for covariates from cohort attributes.")
   }
@@ -77,6 +78,13 @@ getDbCohortAttrCovariatesData <- function(connection,
     warning("cohortId argument has been deprecated, please use cohortIds")
     cohortIds <- cohortId
   }
+  if (!is.null(oracleTempSchema) && oracleTempSchema != "") {
+    rlang::warn("The 'oracleTempSchema' argument is deprecated. Use 'tempEmulationSchema' instead.",
+      .frequency = "regularly",
+      .frequency_id = "oracleTempSchema"
+    )
+    tempEmulationSchema <- oracleTempSchema
+  }
   start <- Sys.time()
   writeLines("Constructing covariates from cohort attributes table")
 
@@ -93,7 +101,7 @@ getDbCohortAttrCovariatesData <- function(connection,
       dropTableIfExists = TRUE,
       createTable = TRUE,
       tempTable = TRUE,
-      oracleTempSchema = oracleTempSchema
+      tempEmulationSchema = tempEmulationSchema
     )
   }
   sql <- SqlRender::readSql(system.file("sql/sql_server/GetAttrCovariates.sql", package = "FeatureExtraction"))
@@ -108,12 +116,12 @@ getDbCohortAttrCovariatesData <- function(connection,
   renderedSql <- SqlRender::translate(
     sql = renderedSql,
     targetDialect = attr(connection, "dbms"),
-    oracleTempSchema = oracleTempSchema
+    tempEmulationSchema = tempEmulationSchema
   )
   # renderedSql <- SqlRender::loadRenderTranslateSql("GetAttrCovariates.sql",
   #                                                  packageName = "FeatureExtraction",
   #                                                  dbms = attr(connection, "dbms"),
-  #                                                  oracleTempSchema = oracleTempSchema,
+  #                                                  tempEmulationSchema = tempEmulationSchema,
   #                                                  attr_database_schema = covariateSettings$attrDatabaseSchema,
   #                                                  cohort_table = cohortTable,
   #                                                  row_id_field = rowIdField,
@@ -129,7 +137,7 @@ getDbCohortAttrCovariatesData <- function(connection,
   covariateRefSql <- SqlRender::translate(
     sql = covariateRefSql,
     targetDialect = attr(connection, "dbms"),
-    oracleTempSchema = oracleTempSchema
+    tempEmulationSchema = tempEmulationSchema
   )
   covariateRef <- DatabaseConnector::querySql(connection, covariateRefSql, snakeCaseToCamelCase = TRUE)
   covariateRef$analysisId <- rep(as.numeric(covariateSettings$analysisId), length = nrow(covariateRef))

diff --git a/R/GetCovariatesFromOtherCohorts.R b/R/GetCovariatesFromOtherCohorts.R
@@ -38,10 +38,12 @@ getDbCohortBasedCovariatesData <- function(connection,
                                            rowIdField = "subject_id",
                                            covariateSettings,
                                            aggregated = FALSE,
-                                           minCharacterizationMean = 0) {
+                                           minCharacterizationMean = 0,
+                                           tempEmulationSchema = NULL) {
   errorMessages <- checkmate::makeAssertCollection()
   checkmate::assertClass(connection, "DatabaseConnectorConnection", add = errorMessages)
   checkmate::assertCharacter(oracleTempSchema, len = 1, null.ok = TRUE, add = errorMessages)
+  checkmate::assertCharacter(tempEmulationSchema, len = 1, null.ok = TRUE, add = errorMessages)
   checkmate::assertCharacter(cdmDatabaseSchema, len = 1, null.ok = TRUE, add = errorMessages)
   checkmate::assertCharacter(cohortTable, len = 1, add = errorMessages)
   checkmate::assertIntegerish(cohortId, add = errorMessages)
@@ -56,6 +58,13 @@ getDbCohortBasedCovariatesData <- function(connection,
     warning("cohortId argument has been deprecated, please use cohortIds")
     cohortIds <- cohortId
   }
+  if (!is.null(oracleTempSchema) && oracleTempSchema != "") {
+    rlang::warn("The 'oracleTempSchema' argument is deprecated. Use 'tempEmulationSchema' instead.",
+      .frequency = "regularly",
+      .frequency_id = "oracleTempSchema"
+    )
+    tempEmulationSchema <- oracleTempSchema
+  }
 
   start <- Sys.time()
   message("Constructing covariates from other cohorts")
@@ -69,7 +78,7 @@ getDbCohortBasedCovariatesData <- function(connection,
     dropTableIfExists = TRUE,
     createTable = TRUE,
     tempTable = TRUE,
-    oracleTempSchema = oracleTempSchema,
+    tempEmulationSchema = tempEmulationSchema,
     camelCaseToSnakeCase = TRUE
   )
   if (is.null(covariateSettings$covariateCohortTable)) {
@@ -137,7 +146,7 @@ getDbCohortBasedCovariatesData <- function(connection,
   }
   result <- getDbDefaultCovariateData(
     connection = connection,
-    oracleTempSchema = oracleTempSchema,
+    tempEmulationSchema = tempEmulationSchema,
     cdmDatabaseSchema = cdmDatabaseSchema,
     cohortTable = cohortTable,
     cohortIds = cohortIds,
@@ -154,7 +163,7 @@ getDbCohortBasedCovariatesData <- function(connection,
     sql = sql,
     progressBar = FALSE,
     reportOverallTime = FALSE,
-    oracleTempSchema = oracleTempSchema
+    tempEmulationSchema = tempEmulationSchema
   )
   return(result)
 }