Revert "More checks"

This reverts commit 4f86b2c.

.Rbuildignore

@@ -20,5 +20,5 @@ target/
 docs
 compare_versions
 _pkgdown.yml
-examplePhenotypeLibraryPackage
+exampleComparativeCohortStudy
 examplePackage

.gitignore

@@ -5,7 +5,6 @@
 *.RData
 inst/shiny/DiagnosticsExplorer/data/phenotypeDescription.csv
 inst/shiny/DiagnosticsExplorer/data/cohortDescription.csv
+inst/shiny/DiagnosticsExplorer/data/cohortDescription.csv
+inst/shiny/DiagnosticsExplorer/data/phenotypeDescription.csv
 *.zip
-errorReportSql.txt
-errorReportR.txt
-*.tex

.travis.yml

@@ -1,12 +1,10 @@
 language: R
 cache: packages
+sudo: false
 
 branches:
   except:
     - /^*-v[0-9]/
-
-before_install:
-  - sudo $(which R) CMD javareconf
 
 r_packages:
   - covr

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: CohortDiagnostics
 Type: Package
 Title: Diagnostics for OHDSI Studies
-Version: 2.0.0
-Date: 2020-09-15
+Version: 1.2.7
+Date: 2020-09-08
 Authors@R: c(
     person("Gowtham", "Rao", email = "[email protected]", role = c("aut", "cre")),
     person("Martijn", "Schuemie", email = "[email protected]", role = c("aut")),
@@ -14,42 +14,41 @@ Maintainer: Gowtham Rao <[email protected]>
 Description: Diagnostics for studies that use the OMOP Common Data Model and the OHDSI tools.
 Depends:
 	DatabaseConnector (>= 3.0.0),
-	FeatureExtraction (>= 3.1.0),
 	R (>= 3.5.0)
 Imports:
   Andromeda,
   checkmate,
   digest,
   dplyr (>= 1.0.0),
+  FeatureExtraction (>= 3.0.1),
   ggplot2,
   ParallelLogger (>= 2.0.0),
   readr,
   rlang,
   RJSONIO,
-  ROhdsiWebApi (>= 1.1.2),
+  ROhdsiWebApi (>= 1.1.0),
   SqlRender (>= 1.6.7),
   stringr,
+  tibble (>= 3.0.0),
   tidyr (>= 1.0.0)
 Suggests:
-  shiny,
-  shinydashboard,
-  shinyWidgets,
   DT,
-  plotly,
-  VennDiagram,
+  Eunomia,
+  RSQLite (> 2.2.0),
   htmltools,
-  RColorBrewer,
-  scales,
   knitr,
+  plotly,
+  RColorBrewer,
   rmarkdown,
-  Eunomia,
-  testthat,
-  RSQLite (>= 2.2.0)
+  scales,
+  shiny,
+  shinydashboard,
+  VennDiagram,
+  testthat
 Remotes:
   ohdsi/Eunomia,
   ohdsi/FeatureExtraction,
   ohdsi/ROhdsiWebApi,
-  ohdsi/DatabaseConnector,
   r-dbi/RSQLite
 License: Apache License
 VignetteBuilder: knitr

NAMESPACE

@@ -1,9 +1,7 @@
 # Generated by roxygen2: do not edit by hand
 
 export(breakDownIndexEvents)
-export(buildPostgresDatabaseSchema)
 export(compareCohortCharacteristics)
-export(compareCovariateValueResult)
 export(computeCohortOverlap)
 export(createCohortTable)
 export(createConceptCountsTable)
@@ -13,41 +11,24 @@ export(findCohortIncludedSourceConcepts)
 export(findCohortOrphanConcepts)
 export(findOrphanConcepts)
 export(getCohortCharacteristics)
-export(getCohortCountResult)
 export(getCohortCounts)
-export(getCohortOverlapResult)
-export(getCohortReference)
 export(getCohortsJsonAndSql)
-export(getConceptReference)
-export(getConceptSetDiagnosticsResults)
-export(getCovariateReference)
-export(getCovariateValueResult)
-export(getDatabaseReference)
 export(getIncidenceRate)
-export(getIncidenceRateResult)
 export(getInclusionStatistics)
 export(getInclusionStatisticsFromFiles)
-export(getRecordCountOfInstantiatedCohorts)
-export(getResultsDataModelSpecifications)
-export(getTimeDistributionResult)
 export(getTimeDistributions)
-export(getTimeReference)
-export(importCsvFilesToPostgres)
+export(getUniqueConceptIds)
 export(instantiateCohort)
 export(instantiateCohortSet)
 export(launchCohortExplorer)
 export(launchDiagnosticsExplorer)
-export(plotCohortComparisonStandardizedDifference)
-export(plotCohortOverlapVennDiagram)
-export(plotIncidenceRate)
-export(plotTimeDistribution)
+export(plotincidenceRate)
 export(preMergeDiagnosticsFiles)
 export(runCohortDiagnostics)
 export(runCohortDiagnosticsUsingExternalCounts)
+export(writeOmopvocabularyTables)
 import(DatabaseConnector)
 import(dplyr)
-importFrom(FeatureExtraction,createDefaultCovariateSettings)
-importFrom(FeatureExtraction,createTemporalCovariateSettings)
 importFrom(grDevices,rgb)
 importFrom(rlang,.data)
 importFrom(stats,aggregate)

NEWS.md

@@ -1,15 +1,25 @@
-CohortDiagnostics 2.0.0
+CohortDiagnostics 1.2.7
 =======================
-Unreleased version
+Note: 
+
+1.2.x is last release of v 1.x.x series. Future releases with new functionality are expected to have breaking changes with no backward compatability and will be 2.x.x series.
+
+Bug fixes:
+
+1. Temporal choice error message during mismatch with temporal characterization output not having timeId
 
-- working on eunomia
-- use of tidy r
 
 CohortDiagnostics 1.2.6
 =======================
-Note: 
 
-1.2.x is last release of v 1.x.x series. Future releases with new functionality are expected to have breaking changes with no backward compatability and will be 2.x.x series.
+
+Bug fixes:
+
+1. Additional bug fixes for characterization/temporal characterization.
+
+
+CohortDiagnostics 1.2.5
+=======================
 
 Bug fixes:
 

R/CohortCharacterizationDiagnostics.R

@@ -28,20 +28,14 @@
 #'
 #' @template CohortTable
 #'
-#' @param cohortIds           A vector of cohortIds (1 or more) used to reference the cohort in the cohort
-#'                            table. 
-#'
-#' @template  cdmVersion
-#' 
+#' @param cohortId            The cohort definition ID used to reference the cohort in the cohort
+#'                            table.
 #' @param covariateSettings   Either an object of type \code{covariateSettings} as created using one of
 #'                            the createCovariate functions in the FeatureExtraction package, or a list
 #'                            of such objects.
-#'                            
-#' @param batchSize           Maximum number of cohorts to characterize at once. A larger batch size will
-#'                            be quicker, but may run out of resources on the server.
 #'
 #' @return
-#' An Andromeda object with information on the covariates.
+#' A data frame with cohort characteristics.
 #'
 #' @export
 getCohortCharacteristics <- function(connectionDetails = NULL,
@@ -50,100 +44,96 @@ getCohortCharacteristics <- function(connectionDetails = NULL,
                                      oracleTempSchema = NULL,
                                      cohortDatabaseSchema = cdmDatabaseSchema,
                                      cohortTable = "cohort",
-                                     cohortIds,
-                                     cdmVersion = 5,
-                                     covariateSettings,
-                                     batchSize = 100) {
-  startTime <- Sys.time()
+                                     cohortId,
+                                     covariateSettings) {
+  start <- Sys.time()
+  result <- tidyr::tibble()
+  output <- list()
+
   if (is.null(connection)) {
     connection <- DatabaseConnector::connect(connectionDetails)
     on.exit(DatabaseConnector::disconnect(connection))
   }
-  results <- Andromeda::andromeda()
-  for (start in seq(1, length(cohortIds), by = batchSize)) {
-    end <- min(start + batchSize - 1, length(cohortIds))
-    if (length(cohortIds) > batchSize) {
-      ParallelLogger::logInfo(sprintf("Batch characterization. Processing cohorts %s through %s",
-                                      start,
-                                      end))
-    }
-    featureExtractionOutput <- FeatureExtraction::getDbCovariateData(connection = connection,
-                                                                     oracleTempSchema = oracleTempSchema,
-                                                                     cdmDatabaseSchema = cdmDatabaseSchema,
-                                                                     cohortDatabaseSchema = cohortDatabaseSchema,
-                                                                     cdmVersion = cdmVersion,
-                                                                     cohortTable = cohortTable,
-                                                                     cohortId = cohortIds[start:end],
-                                                                     covariateSettings = covariateSettings,
-                                                                     aggregated = TRUE)
-
-    populationSize <- attr(x = featureExtractionOutput, which = "metaData")$populationSize
-    populationSize <- dplyr::tibble(cohortId = names(populationSize),
-                                    populationSize = populationSize)
-
-    if (!"analysisRef" %in% names(results)) {
-      results$analysisRef <- featureExtractionOutput$analysisRef
-    }
-    if (!"covariateRef" %in% names(results)) {
-      results$covariateRef <- featureExtractionOutput$covariateRef 
-    } else {
-      covariateIds <- results$covariateRef %>%
-        dplyr::select(.data$covariateId) 
-      Andromeda::appendToTable(results$covariateRef, featureExtractionOutput$covariateRef %>% 
-                                 dplyr::anti_join(covariateIds, by = "covariateId", copy = TRUE))
-    }
-    if ("timeRef" %in% names(featureExtractionOutput) && !"timeRef" %in% names(results)) {
-      results$timeRef <- featureExtractionOutput$timeRef
-    }
-
-    if ("covariates" %in% names(featureExtractionOutput) && 
-        dplyr::pull(dplyr::count(featureExtractionOutput$covariates)) > 0) {
-
-      covariates <- featureExtractionOutput$covariates %>% 
-        dplyr::rename(cohortId = .data$cohortDefinitionId) %>% 
-        dplyr::left_join(populationSize, by = "cohortId", copy = TRUE) %>% 
-        dplyr::mutate(sd = sqrt(((populationSize * .data$sumValue) + .data$sumValue)/(populationSize^2))) %>% 
-        dplyr::rename(mean = .data$averageValue) %>% 
-        dplyr::select(-.data$sumValue, -.data$populationSize)
-
-      if (FeatureExtraction::isTemporalCovariateData(featureExtractionOutput)) {
-        covariates <- covariates %>% 
-          dplyr::select(.data$cohortId, .data$timeId, .data$covariateId, .data$mean, .data$sd)
-      } else {
-        covariates <- covariates %>% 
-          dplyr::select(.data$cohortId, .data$covariateId, .data$mean, .data$sd)
-      }
-      if ("covariates" %in% names(results)) {
-        Andromeda::appendToTable(results$covariates, covariates) 
-      } else {
-        results$covariates <- covariates
-      }
-    }
-
-    if ("covariatesContinuous" %in% names(featureExtractionOutput) && 
-        dplyr::pull(dplyr::count(featureExtractionOutput$covariatesContinuous)) > 0) {
-      covariates <- featureExtractionOutput$covariatesContinuous %>% 
-        dplyr::rename(mean = .data$averageValue, 
-                      sd = .data$standardDeviation, 
-                      cohortId = .data$cohortDefinitionId)
-      if (FeatureExtraction::isTemporalCovariateData(featureExtractionOutput)) {
-        covariates <- covariates %>% 
-          dplyr::select(.data$cohortId, .data$timeId, .data$covariateId, .data$mean, .data$sd)
-      } else {
-        covariates <- covariates %>% 
-          dplyr::select(.data$cohortId, .data$covariateId, .data$mean, .data$sd)
-      }
-      if ("covariates" %in% names(results)) {
-        Andromeda::appendToTable(results$covariates, covariates) 
-      } else {
-        results$covariates <- covariates
-      }
-    }
+
+  if (!checkIfCohortInstantiated(connection = connection,
+                                 cohortDatabaseSchema = cohortDatabaseSchema,
+                                 cohortTable = cohortTable,
+                                 cohortId = cohortId)) {
+    ParallelLogger::logWarn("\nCohort with ID ", cohortId, " appears to be empty. \n",
+                            "Was it instantiated? Skipping Characterization.")
+    delta <- Sys.time() - start
+    ParallelLogger::logInfo(paste("Cohort characterization took",
+                                  signif(delta, 3),
+                                  attr(delta, "units")))
+    return(output)
+  }
+
+  featureExtractionOutput <- FeatureExtraction::getDbCovariateData(connection = connection,
+                                                                   oracleTempSchema = oracleTempSchema,
+                                                                   cdmDatabaseSchema = cdmDatabaseSchema,
+                                                                   cohortDatabaseSchema = cohortDatabaseSchema,
+                                                                   cohortTable = cohortTable,
+                                                                   cohortId = cohortId,
+                                                                   covariateSettings = covariateSettings,
+                                                                   aggregated = TRUE)
+
+  if (!(exists("featureExtractionOutput") && 
+        (FeatureExtraction::isCovariateData(featureExtractionOutput) ||
+         FeatureExtraction::isTemporalCovariateData(featureExtractionOutput)))) {
+    ParallelLogger::logWarn("\nNo characterization result return for ", cohortId, ".\n",
+                            "No covariate data. Skipping Characterization.")
+    delta <- Sys.time() - start
+    ParallelLogger::logInfo(paste("Cohort characterization took",
+                                  signif(delta, 3),
+                                  attr(delta, "units")))
+    return(output)
+  }
+
+  n <- attr(x = featureExtractionOutput, which = "metaData")$populationSize
+  attr(output, "cohortSize") <- attr(featureExtractionOutput, "metaData")$populationSize
+  output$analysisRef <- featureExtractionOutput$analysisRef %>% 
+    dplyr::collect()
+  output$covariateRef <- featureExtractionOutput$covariateRef %>% 
+    dplyr::collect()
+  if ("timeRef" %in% names(featureExtractionOutput)) {
+    output$timeRef <- featureExtractionOutput$timeRef %>% 
+      dplyr::collect()
+  }
+
+  if (!is.null(featureExtractionOutput$covariates) && 
+      dplyr::count(featureExtractionOutput$covariates) %>% dplyr::pull() > 0) {
+    output$covariates <- featureExtractionOutput$covariates %>% 
+      dplyr::collect() %>% 
+      dplyr::mutate(sd = sqrt(((n * .data$sumValue) + .data$sumValue)/(n^2))) %>% 
+      dplyr::rename(mean = .data$averageValue) %>% 
+      dplyr::mutate(cohortId = cohortId) %>% 
+      dplyr::select(-.data$sumValue)
+    result <- dplyr::bind_rows(result, output$covariates) %>% 
+      dplyr::distinct()
+  }
+
+  if (!is.null(featureExtractionOutput$covariatesContinuous) && 
+      dplyr::count(featureExtractionOutput$covariatesContinuous) %>% dplyr::pull() > 0) {
+    output$covariatesContinuous <- featureExtractionOutput$covariatesContinuous %>% 
+      dplyr::collect() %>% 
+      dplyr::rename(mean = .data$averageValue, sd = .data$standardDeviation) %>%
+      dplyr::mutate(cohortId = cohortId)
+    result <- dplyr::bind_rows(result, output$covariatesContinuous) %>% dplyr::distinct()
+  }
+
+  if (FeatureExtraction::isTemporalCovariateData(featureExtractionOutput)) {
+    output$result <- result %>% 
+      dplyr::select(.data$cohortId, .data$timeId, .data$covariateId, .data$mean, .data$sd)
+  } else {
+    output$result <- result %>% 
+      dplyr::select(.data$cohortId, .data$covariateId, .data$mean, .data$sd)
   }
 
-  delta <- Sys.time() - startTime
-  ParallelLogger::logInfo("Cohort characterization took ", signif(delta, 3), " ", attr(delta, "units"))
-  return(results)
+  delta <- Sys.time() - start
+  ParallelLogger::logInfo(paste("Cohort characterization took",
+                                signif(delta, 3),
+                                attr(delta, "units")))
+  return(output)
 }
 
 #' Compare cohort characteristics