Version 6.3.8 (#446)

* new external validation function based on validationDesign * fix imports of sklearn modules and classes (#442) * remove version from is_installed (#444) * fix NOTES about documentation * preserve randomness in table generation in tests
OHDSI · Apr 26, 2024 · c5176a2 · c5176a2
1 parent 9e37b51
commit c5176a2
Show file tree

Hide file tree

Showing 118 changed files with 4,561 additions and 2,745 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -11,3 +11,5 @@ compare_versions
 docs/*
 _pkgdown.yml
 ^vignettes/articles$
+^doc$
+^Meta$
diff --git a/.github/workflows/R_CMD_check_Hades.yaml b/.github/workflows/R_CMD_check_Hades.yaml
@@ -45,7 +45,7 @@ jobs:
       CDM5_SQL_SERVER_USER: ${{ secrets.CDM5_SQL_SERVER_USER }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-r@v2
         with:
@@ -66,7 +66,7 @@ jobs:
           done < <(Rscript -e 'writeLines(remotes::system_requirements("ubuntu", "22.04"))')
           
       - name: Setup conda
-        uses: conda-incubator/setup-miniconda@v2
+        uses: conda-incubator/setup-miniconda@v3
 
       - uses: r-lib/actions/setup-r-dependencies@v2
         with:
@@ -81,7 +81,7 @@ jobs:
 
       - name: Upload source package
         if: success() && runner.os == 'macOS' && github.event_name != 'pull_request' && github.ref == 'refs/heads/main'
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: package_tarball
           path: check/*.tar.gz
@@ -110,7 +110,7 @@ jobs:
 
     steps:
 
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0    
 
@@ -136,7 +136,7 @@ jobs:
           draft: false
           prerelease: false
 
-      - uses: r-lib/actions/setup-r@v1
+      - uses: r-lib/actions/setup-r@v2
         if: ${{ env.new_version != '' }}
 
       - name: Install drat
@@ -152,7 +152,7 @@ jobs:
           
       - name: Download package tarball
         if: ${{ env.new_version != '' }}
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v4
         with:
           name: package_tarball    
 

diff --git a/.github/workflows/R_CMD_check_main_weekly.yaml b/.github/workflows/R_CMD_check_main_weekly.yaml
@@ -45,7 +45,7 @@ jobs:
       CDM5_SPARK_CONNECTION_STRING: ${{ secrets.CDM5_SPARK_CONNECTION_STRING }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       - uses: r-lib/actions/setup-r@v2
         with:

diff --git a/.gitignore b/.gitignore
@@ -23,3 +23,5 @@ standalone/build/*
 /python_models/*
 /mycache/*
 /inst/shiny/DiagnosticsExplorer/rsconnect/*
+/doc/
+/Meta/
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -2,8 +2,8 @@ Package: PatientLevelPrediction
 Type: Package
 Title: Developing patient level prediction using data in the OMOP Common Data
     Model
-Version: 6.3.7
-Date: 2024-04-04
+Version: 6.3.8
+Date: 2024-04-26
 Authors@R: c(
     person("Jenna", "Reps", email = "[email protected]", role = c("aut", "cre")),
     person("Martijn", "Schuemie", role = c("aut")),
@@ -71,7 +71,6 @@ Suggests:
     lightgbm
 Remotes:
     ohdsi/BigKnn,
-    ohdsi/Eunomia,
     ohdsi/FeatureExtraction,
     ohdsi/ShinyAppBuilder,
     ohdsi/ResultModelManager,

diff --git a/NAMESPACE b/NAMESPACE
@@ -37,6 +37,7 @@ export(createStudyPopulation)
 export(createStudyPopulationSettings)
 export(createTempModelLoc)
 export(createUnivariateFeatureSelection)
+export(createValidationDesign)
 export(createValidationSettings)
 export(diagnoseMultiplePlp)
 export(diagnosePlp)
@@ -110,6 +111,7 @@ export(sklearnFromJson)
 export(sklearnToJson)
 export(splitData)
 export(toSparseM)
+export(validateExternal)
 export(validateMultiplePlp)
 export(viewDatabaseResultPlp)
 export(viewMultiplePlp)

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,11 @@
+PatientLevelPrediction 6.3.8
+======================
+- Add support for R4.4 
+- Fix notes around documentation (vignette engine and brackets in itemize)
+- Use webp image format where possible (not in pdfs) for smaller size
+- Make sure random table names are unique in tests
+- Remove remote info for Eunomia since it's in CRAN
+
 PatientLevelPrediction 6.3.7
 ======================
 - Clean up dependencies, tibble removed and IHT and ParallelLogger from CRAN

diff --git a/R/AdditionalCovariates.R b/R/AdditionalCovariates.R
@@ -32,6 +32,7 @@
 #' @param aggregated  whether the covariate should be aggregated
 #' @param cohortIds  cohort id for the target cohort
 #' @param covariateSettings  settings for the covariate cohorts and time periods
+#' @param ...  additional arguments from FeatureExtraction
 #'
 #' @return
 #' The models will now be in the package
@@ -46,7 +47,8 @@ getCohortCovariateData <- function(
   rowIdField = "row_id",
   aggregated,
   cohortIds,
-  covariateSettings
+  covariateSettings,
+  ...
   ){
 
   # Some SQL to construct the covariate:

diff --git a/R/DataSplitting.R b/R/DataSplitting.R
@@ -17,7 +17,7 @@
 
 
 #' Create the settings for defining how the plpData are split into test/validation/train sets using 
-#' default splitting functions (either random stratified by outcome, time or subject splitting).
+#' default splitting functions (either random stratified by outcome, time or subject splitting)
 #'
 #' @details
 #' Returns an object of class \code{splitSettings} that specifies the splitting function that will be called and the settings
@@ -28,9 +28,9 @@
 #' @param nfold             (numeric) An integer > 1 specifying the number of folds used in cross validation
 #' @param splitSeed         (numeric) A seed to use when splitting the data for reproducibility (if not set a random number will be generated)
 #' @param type              (character) Choice of:  \itemize{
-#'                                         \item{'stratified'}{ Each data point is randomly assigned into the test or a train fold set but this is done stratified such that the outcome rate is consistent in each partition }
-#'                                         \item{'time')}{ Older data are assigned into the training set and newer data are assigned into the test set}
-#'                                         \item{'subject'}{ Data are partitioned by subject, if a subject is in the data more than once, all the data points for the subject are assigned either into the test data or into the train data (not both).}
+#'                                         \item'stratified' Each data point is randomly assigned into the test or a train fold set but this is done stratified such that the outcome rate is consistent in each partition 
+#'                                         \item'time' Older data are assigned into the training set and newer data are assigned into the test set
+#'                                         \item'subject' Data are partitioned by subject, if a subject is in the data more than once, all the data points for the subject are assigned either into the test data or into the train data (not both).
 #'                                         } 
 #'
 #' @return
@@ -87,17 +87,17 @@ createDefaultSplitSetting <- function(testFraction=0.25,
 #'
 #' @details
 #' Returns a list containing the training data (Train) and optionally the test data (Test).  Train is an Andromeda object containing
-#' \itemize{\item{covariates}{ a table (rowId, covariateId, covariateValue) containing the covariates for each data point in the train data }
-#'          \item{covariateRef}{ a table with the covariate information}
-#'          \item{labels)}{ a table (rowId, outcomeCount, ...) for each data point in the train data (outcomeCount is the class label) }
-#'          \item{folds}{ a table (rowId, index) specifying which training fold each data point is in.}
+#' \itemize{\item covariates: a table (rowId, covariateId, covariateValue) containing the covariates for each data point in the train data
+#'          \item covariateRef: a table with the covariate information
+#'          \item labels: a table (rowId, outcomeCount, ...) for each data point in the train data (outcomeCount is the class label) 
+#'          \item folds: a table (rowId, index) specifying which training fold each data point is in.
 #'          } 
 #' Test is an Andromeda object containing
-#' \itemize{\item{covariates}{ a table (rowId, covariateId, covariateValue) containing the covariates for each data point in the test data }
-#'          \item{covariateRef}{ a table with the covariate information}
-#'          \item{labels)}{ a table (rowId, outcomeCount, ...) for each data point in the test data (outcomeCount is the class label) }
+#' \itemize{\item covariates: a table (rowId, covariateId, covariateValue) containing the covariates for each data point in the test data 
+#'          \item covariateRef: a table with the covariate information
+#'          \item labels: a table (rowId, outcomeCount, ...) for each data point in the test data (outcomeCount is the class label) 
 #'          } 
-#' 
+#'   
 #' 
 #'
 #' @param plpData                          An object of type \code{plpData} - the patient level prediction

diff --git a/R/DiagnosePlp.R b/R/DiagnosePlp.R
@@ -213,16 +213,12 @@ diagnoseMultiplePlp <- function(
 #'                                   and whether to normalise the covariates before training  
 #' @param modelSettings              An object of class \code{modelSettings} created using one of the function:
 #'                                         \itemize{
-#'                                         \item{setLassoLogisticRegression()}{ A lasso logistic regression model}
-#'                                         \item{setGradientBoostingMachine()}{ A gradient boosting machine}
-#'                                         \item{setAdaBoost()}{ An ada boost model}
-#'                                         \item{setRandomForest()}{ A random forest model}
-#'                                         \item{setDecisionTree()}{ A decision tree model}
-#'                                         \item{setCovNN())}{ A convolutional neural network model}
-#'                                         \item{setCIReNN()}{ A recurrent neural network model}
-#'                                         \item{setMLP()}{ A neural network model}
-#'                                         \item{setDeepNN()}{ A deep neural network model}
-#'                                         \item{setKNN()}{ A KNN model}
+#'                                         \item setLassoLogisticRegression() A lasso logistic regression model
+#'                                         \item setGradientBoostingMachine() A gradient boosting machine
+#'                                         \item setAdaBoost() An ada boost model
+#'                                         \item setRandomForest() A random forest model
+#'                                         \item setDecisionTree() A decision tree model
+#'                                         \item setKNN() A KNN model
 #'                                         
 #'                                         } 
 #' @param logSettings           An object of \code{logSettings} created using \code{createLogSettings}
-Original file line number
+Diff line change
@@ Expand Up / @@ -11,3 +11,5 @@ compare_versions @@
     docs/*
     _pkgdown.yml
     ^vignettes/articles$
+    ^doc$
+    ^Meta$