Refering to latest released version of Cyclops. Regenerating document…

…ation.
OHDSI · Jun 17, 2021 · 59b30ad · 59b30ad
1 parent 4ff55e0
commit 59b30ad
Show file tree

Hide file tree

Showing 78 changed files with 670 additions and 173 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -2,7 +2,7 @@ Package: CohortMethod
 Type: Package
 Title: New-User Cohort Method with Large Scale Propensity and Outcome Models
 Version: 4.2.0
-Date: 2021-06-16
+Date: 2021-06-17
 Authors@R: c(
 	person("Martijn", "Schuemie", , "[email protected]", role = c("aut", "cre")),
 	person("Marc", "Suchard", role = c("aut")),
@@ -28,9 +28,9 @@ BugReports: https://github.com/OHDSI/CohortMethod/issues
 Depends:
 	R (>= 3.5.0),
 	DatabaseConnector (>= 4.0.0),
-	Cyclops (>= 3.1.1),
+	Cyclops (>= 3.1.2),
 	FeatureExtraction  (>= 3.0.0),
-	Andromeda (>= 0.3.0)
+	Andromeda (>= 0.4.0)
 Imports:
 	methods,
 	ggplot2,
@@ -55,8 +55,7 @@ Suggests:
 	EmpiricalCalibration,
 	Eunomia
 Remotes:
-	ohdsi/FeatureExtraction,
-	ohdsi/Cyclops
+	ohdsi/FeatureExtraction
 LinkingTo: Rcpp
 NeedsCompilation: yes
 RoxygenNote: 7.1.1

diff --git a/NEWS.md b/NEWS.md
@@ -5,7 +5,7 @@ Changes:
 
 1. Adding the `trimByIptw()` function.
 
-2. Adding the `estimator` argument to the `fitOutcomeModel()` function to select 'ate' (average treatment effect) or 'att' (average treatement effect in the treated) when performing IPTW.
+2. Adding the `estimator` argument to the `fitOutcomeModel()` function to select 'ate' (average treatment effect) or 'att' (average treatment effect in the treated) when performing IPTW.
 
 3. Added the `maxWeight` argument to the `fitOutcomeModel()` function. Weights greater than this value will be set to this value.
 
@@ -26,7 +26,7 @@ CohortMethod 4.1.0
 
 Changes: 
 
-1. Dropped `insertDbPopulation()` function. This didn't seem to be used by anyone, and would have required carying the person ID throughout the pipeline.
+1. Dropped `insertDbPopulation()` function. This didn't seem to be used by anyone, and would have required carrying the person ID throughout the pipeline.
 
 2. Introducing new unique person identified called `personSeqId`, generated during data extraction. Person ID is now downloaded as string to avoid issues with 64-bit integers. Person ID is not used by CohortMethod, and is provided for reference only.
 

diff --git a/R/Analyses.R b/R/Analyses.R
@@ -207,7 +207,7 @@ loadCmAnalysisList <- function(file) {
 #'                                      provided instead. In the analysis, the name of the number to be
 #'                                      used can be specified using the #' \code{comparatorType}
 #'                                      parameter in the [createCmAnalysis()] function.
-#' @param outcomeIds                    A vector of concept IDs indentifying the outcome(s) in the
+#' @param outcomeIds                    A vector of concept IDs identifying the outcome(s) in the
 #'                                      outcome table.
 #' @param excludedCovariateConceptIds   A list of concept IDs that cannot be used to construct
 #'                                      covariates. This argument is to be used only for exclusion

diff --git a/R/CreateArgFunctions.R b/R/CreateArgFunctions.R
@@ -1,4 +1,4 @@
-# This file has been autogenerated. Do not change by hand. 
+# This file has been autogenerated. Do not change by hand.
 
 #' Create a parameter object for the function getDbCohortMethodData
 #'
@@ -129,7 +129,7 @@ createCreateStudyPopulationArgs <- function(firstExposureOnly = FALSE,
 #'                                  the treatment assignment. If any covariate has an unusually high
 #'                                  correlation (either positive or negative), this will throw and
 #'                                  error.
-#' @param stopOnError               If an error occurr, should the function stop? Else, the two cohorts
+#' @param stopOnError               If an error occur, should the function stop? Else, the two cohorts
 #'                                  will be assumed to be perfectly separable.
 #' @param prior                     The prior used to fit the model. See Cyclops::createPrior() for
 #'                                  details.

diff --git a/R/PsFunctions.R b/R/PsFunctions.R
@@ -42,7 +42,7 @@
 #'                                 the treatment assignment. If any covariate has an unusually high
 #'                                 correlation (either positive or negative), this will throw and
 #'                                 error.
-#' @param stopOnError              If an error occurr, should the function stop? Else, the two cohorts
+#' @param stopOnError              If an error occur, should the function stop? Else, the two cohorts
 #'                                 will be assumed to be perfectly separable.
 #' @param prior                    The prior used to fit the model. See
 #'                                 [Cyclops::createPrior()] for details.

diff --git a/R/StudyPopulation.R b/R/StudyPopulation.R
@@ -240,9 +240,11 @@ createStudyPopulation <- function(cohortMethodData,
   idx <- population$riskEnd > population$daysToObsEnd
   population$riskEnd[idx] <- population$daysToObsEnd[idx]
 
-  idx <- population$riskEnd > population$riskStart + maxDaysAtRisk
-  if (any(idx)) {
-    population$riskEnd[idx] <- population$riskStart[idx] + maxDaysAtRisk
+  if (!missing(maxDaysAtRisk) && !is.null(maxDaysAtRisk)) {
+    idx <- population$riskEnd > population$riskStart + maxDaysAtRisk
+    if (any(idx)) {
+      population$riskEnd[idx] <- population$riskStart[idx] + maxDaysAtRisk
+    }
   }
   if (censorAtNewRiskWindow) {
     ParallelLogger::logInfo("Censoring time at risk of recurrent subjects at start of new time at risk")
@@ -338,10 +340,10 @@ getCounts <- function(population, description = "") {
   targetExposures <- length(population$personSeqId[population$treatment == 1])
   comparatorExposures <- length(population$personSeqId[population$treatment == 0])
   counts <- dplyr::tibble(description = description,
-                           targetPersons = targetPersons,
-                           comparatorPersons = comparatorPersons,
-                           targetExposures = targetExposures,
-                           comparatorExposures = comparatorExposures)
+                          targetPersons = targetPersons,
+                          comparatorPersons = comparatorPersons,
+                          targetExposures = targetExposures,
+                          comparatorExposures = comparatorExposures)
   return(counts)
 }
 
@@ -468,17 +470,17 @@ plotTimeToEvent <- function(cohortMethodData,
     idxInPeriod <- outcomes$daysToEvent >= start & outcomes$daysToEvent < end
     idxPopInPeriod <- -population$daysFromObsStart <= start & population$daysToObsEnd >= end
     dplyr::tibble(number = number,
-                   start = start,
-                   end = end,
-                   eventsExposed = 0,
-                   eventsUnexposed = 0,
-                   observed = 0,
-                   eventsExposedTarget = sum(idxInPeriod & idxExposed & idxTarget),
-                   eventsExposedComparator = sum(idxInPeriod & idxExposed & !idxTarget),
-                   eventsUnexposedTarget = sum(idxInPeriod & !idxExposed & idxTarget),
-                   eventsUnexposedComparator = sum(idxInPeriod & !idxExposed & !idxTarget),
-                   observedTarget = sum(idxPopInPeriod & population$treatment),
-                   observedComparator = sum(idxPopInPeriod & !population$treatment))
+                  start = start,
+                  end = end,
+                  eventsExposed = 0,
+                  eventsUnexposed = 0,
+                  observed = 0,
+                  eventsExposedTarget = sum(idxInPeriod & idxExposed & idxTarget),
+                  eventsExposedComparator = sum(idxInPeriod & idxExposed & !idxTarget),
+                  eventsUnexposedTarget = sum(idxInPeriod & !idxExposed & idxTarget),
+                  eventsUnexposedComparator = sum(idxInPeriod & !idxExposed & !idxTarget),
+                  observedTarget = sum(idxPopInPeriod & population$treatment),
+                  observedComparator = sum(idxPopInPeriod & !population$treatment))
   }
   periods <- lapply(-floor(numberOfPeriods/2):ceiling(numberOfPeriods/2), createPeriod)
   periods <- do.call("rbind", periods)
@@ -489,25 +491,25 @@ plotTimeToEvent <- function(cohortMethodData,
   periods$rateTarget <- (periods$eventsExposedTarget + periods$eventsUnexposedTarget) / periods$observedTarget
   periods$rateComparator <- (periods$eventsExposedComparator + periods$eventsUnexposedComparator) / periods$observedComparator
   vizData <- rbind(dplyr::tibble(start = periods$start,
-                                  end = periods$end,
-                                  rate = periods$rateExposedTarget,
-                                  status = "Exposed events",
-                                  type = targetLabel),
+                                 end = periods$end,
+                                 rate = periods$rateExposedTarget,
+                                 status = "Exposed events",
+                                 type = targetLabel),
                    dplyr::tibble(start = periods$start,
-                                  end = periods$end,
-                                  rate = periods$rateUnexposedTarget,
-                                  status = "Unexposed events",
-                                  type = targetLabel),
+                                 end = periods$end,
+                                 rate = periods$rateUnexposedTarget,
+                                 status = "Unexposed events",
+                                 type = targetLabel),
                    dplyr::tibble(start = periods$start,
-                                  end = periods$end,
-                                  rate = periods$rateExposedComparator,
-                                  status = "Exposed events",
-                                  type = comparatorLabel),
+                                 end = periods$end,
+                                 rate = periods$rateExposedComparator,
+                                 status = "Exposed events",
+                                 type = comparatorLabel),
                    dplyr::tibble(start = periods$start,
-                                  end = periods$end,
-                                  rate = periods$rateUnexposedComparator,
-                                  status = "Unexposed events",
-                                  type = comparatorLabel))
+                                 end = periods$end,
+                                 rate = periods$rateUnexposedComparator,
+                                 status = "Unexposed events",
+                                 type = comparatorLabel))
   vizData$type <- factor(vizData$type, levels = c(targetLabel, comparatorLabel))
 
   plot <- ggplot2::ggplot(vizData, ggplot2::aes(x = .data$start + periodLength / 2,

diff --git a/_pkgdown.yml b/_pkgdown.yml
@@ -28,6 +28,7 @@ reference:
       - matchOnPsAndCovariates
       - trimByPs
       - trimByPsToEquipoise
+      - trimByIptw
       - stratifyByPs
       - stratifyByPsAndCovariates
   - title: "Outcome models"

diff --git a/docs/404.html b/docs/404.html
diff --git a/docs/articles/MultipleAnalyses.html b/docs/articles/MultipleAnalyses.html
diff --git a/docs/articles/SingleStudies.html b/docs/articles/SingleStudies.html
diff --git a/docs/articles/index.html b/docs/articles/index.html
diff --git a/docs/authors.html b/docs/authors.html