diff --git a/CRAN-SUBMISSION b/CRAN-SUBMISSION index 4d2e72f..494e5be 100644 --- a/CRAN-SUBMISSION +++ b/CRAN-SUBMISSION @@ -1,3 +1,3 @@ -Version: 3.11.0 -Date: 2025-09-01 15:11:02 UTC -SHA: 784c4a8dcda6fc0301c8b0823efdfccb1291745e +Version: 3.12.0 +Date: 2025-10-28 09:25:00 UTC +SHA: 0fb802cd699b4e4ec12b59f3d7f232c5d236cecf diff --git a/DESCRIPTION b/DESCRIPTION index 0decc0a..4c1e6a3 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,8 +1,8 @@ Package: FeatureExtraction Type: Package Title: Generating Features for a Cohort -Version: 3.11.0 -Date: 2025-09-01 +Version: 3.12.0 +Date: 2025-10-28 Authors@R: c( person("Martijn", "Schuemie", , "schuemie@ohdsi.org", role = c("aut")), person("Marc", "Suchard", role = c("aut")), diff --git a/NEWS.md b/NEWS.md index f3d1347..6ddbdc4 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,3 +1,8 @@ +FeatureExtraction 3.12.0 +======================= + +- Fix non reproducible behavior in removing redundant covariates when they are equally prevalent (#315) + FeatureExtraction 3.11.0 ======================= diff --git a/R/Normalization.R b/R/Normalization.R index a86ab7b..45cace8 100644 --- a/R/Normalization.R +++ b/R/Normalization.R @@ -159,7 +159,7 @@ tidyCovariateData <- function(covariateData, inner_join(covariateData$valueCounts, by = "covariateId") %>% select(.data$analysisId, .data$covariateId, n) %>% collect() - valueCounts <- valueCounts[order(valueCounts$analysisId, -valueCounts$n), ] + valueCounts <- valueCounts[order(valueCounts$analysisId, -valueCounts$n, valueCounts$covariateId), ] deleteCovariateIds <- c(deleteCovariateIds, valueCounts$covariateId[!duplicated(valueCounts$analysisId)]) ignoreCovariateIds <- valueCounts$covariateId ParallelLogger::logInfo("Removing ", length(deleteCovariateIds), " redundant covariates") diff --git a/docs/404.html b/docs/404.html index 5373286..69a032d 100644 --- a/docs/404.html +++ b/docs/404.html @@ -32,7 +32,7 @@ FeatureExtraction - 3.11.0 + 3.12.0 @@ -74,7 +74,7 @@