Merge pull request #179 from darwin-eu-dev/hotfix-3.3.3

Hotfix 3.3.3

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: CdmOnboarding
 Title: Generate report on an OMOP CDM instance
-Version: 3.3.2
+Version: 3.3.3
 Authors@R: 
   c(person(given = "Peter",
            family = "Rijnbeek",
@@ -50,7 +50,8 @@ Imports:
     scales,
     stringr,
     httr,
-    utils
+    utils,
+    tictoc
 Suggests:
     RPostgres,
     flextable,

NEWS.md

@@ -1,3 +1,7 @@
+# CdmOnboarding 3.3.3
+
+ * Fix execution of CohortBenchmark and CdmConnectorBenchmark
+
 # CdmOnboarding 3.3.2
 
  * Fix generating applied indexes section when no indexes have been applied

R/CohortBenchmark.R

@@ -21,18 +21,16 @@
 # @author Maxim Moinat
 
 
-#' Generate cohorts
+#' Generate predefined set of cohorts
 #' @param connectionDetails An R object of type \code{connectionDetails} created using the function \code{createConnectionDetails} in the \code{DatabaseConnector} package.
 #' @param cdmDatabaseSchema Fully qualified name of database schema that contains OMOP CDM schema.
 #'                          On SQL Server, this should specifiy both the database and the schema, so for example, on SQL Server, 'cdm_instance.dbo'.
 #' @param scratchDatabaseSchema Fully qualified name of database schema where temporary tables can be written.
-#' @param cohortPath Path to the folder containing cohort definitions in JSON format
 #' @returns list of DED diagnostics_summary and duration
 .runCohortBenchmark <- function(
   connectionDetails,
   cdmDatabaseSchema,
-  scratchDatabaseSchema,
-  cohortPath = "inst/json/cohorts"
+  scratchDatabaseSchema
 ) {
   # Connect to the database with CDMConnector
   connection <- .getCdmConnection(
@@ -57,7 +55,9 @@
     .soft_validation = TRUE
   )
 
-  cohort_set_definition <- CDMConnector::read_cohort_set(cohortPath)
+  cohort_set_definition <- CDMConnector::read_cohort_set(
+    path = system.file("json", "cohorts", package = "CdmOnboarding")
+  )
   n_cohorts <- nrow(cohort_set_definition)
 
   # Generate each cohort definition one by one to capture time taken and possible errors
@@ -100,7 +100,7 @@
     }
   }
 
-  n_subject_bins <- cut(n_subjects, breaks = c(0, 100, 1000, 10000, 100000, 1000000, Inf), labels = c("0-100", "100-1k", "1k-10k", "10k-100k", "100k-1M", "1M+"))
+  n_subject_bins <- cut(as.integer(n_subjects), breaks = c(0, 100, 1000, 10000, 100000, 1000000, Inf), labels = c("0-100", "100-1k", "1k-10k", "10k-100k", "100k-1M", "1M+"))
 
   data.frame(
     cohort_name = cohort_set_definition$cohort_name,

R/GenerateResultsDocument.R

@@ -133,13 +133,6 @@ generateResultsDocument <- function(results, outputFolder, authors) {
       officer::body_add_par("Performance checks have not been executed, runPerformanceChecks = FALSE?", style = pkg.env$styles$highlight)
   }
 
-  if (!is.null(results$cohortBenchmark)) {
-    doc <- generateCohortBenchmarkSection(doc, results$cohortBenchmark)
-  } else {
-    doc <- doc %>%
-      officer::body_add_par("Cohort Benchmark results are missing, runCohortBenchmark = FALSE?", style = pkg.env$styles$highlight)
-  }
-
   doc <- doc %>%
     officer::body_add_par("Appendix", style = pkg.env$styles$heading1)
   if (!is.null(results$vocabularyResults)) {

R/generatePerformanceSection.R

@@ -94,6 +94,13 @@ generatePerformanceSection <- function(doc, results) {
       officer::body_add_par("CDMConnector benchmark of the OMOP CDM tables could not be retrieved", style = pkg.env$styles$highlight)
   }
 
+  if (!is.null(results$cohortBenchmark)) {
+    doc <- generateCohortBenchmarkSection(doc, results$cohortBenchmark)
+  } else {
+    doc <- doc %>%
+      officer::body_add_par("Cohort Benchmark results are missing, runCohortBenchmark = FALSE?", style = pkg.env$styles$highlight)
+  }
+
   doc <- doc %>%
     officer::body_add_par("Applied indexes", style = pkg.env$styles$heading2)
   if (!is.null(df$appliedIndexes$result)) {

inst/sql/sql_server/checks/source_to_concept_map_frequency.sql

@@ -1,6 +1,6 @@
 -- source_to_concept_map
 
-select source_vocabulary_id, target_vocabulary_id, count_big(*)
+select source_vocabulary_id, target_vocabulary_id, count_big(*) as count 
 from @cdmDatabaseSchema.source_to_concept_map
 group by source_vocabulary_id, target_vocabulary_id
 order by source_vocabulary_id, target_vocabulary_id