6.3.1 release

.Rbuildignore

@@ -3,17 +3,22 @@
 ^\.Rproj\.user$
 ^LICENSE.md$
 ^azure-pipelines\.yml$
+^opal_azure-pipelines\.yml$
+^armadillo_azure-pipelines\.yml$
 ^azure-pipelines_site\.pp$
 ^azure-pipelines_site-dsdanger\.pp$
 ^azure-pipelines_check\.Rout$
 ^azure-pipelines_test\.Rout$
+^tests/docker/armadillo/standard/log/.gitkeep$
 ^checkDocumentationUpdated\.sh$
 ^docker-compose_armadillo\.yml$
 ^docker-compose_opal\.yml$
 ^docker-compose\.yml$
 ^R/secure.global.ranking.md$
 ^_pkgdown\.yml$
 ^docs$
-^dsBase_6.3.0.tar.gz$
-^dsBase_6.3.0-permissive.tar.gz$
-^dsDanger_6.3.0.tar.gz$
+^dsBase_6.3.1.tar.gz$
+^dsBase_6.3.1-permissive.tar.gz$
+^dsDanger_6.3.1.tar.gz$
+^\.circleci$
+^\.circleci/config\.yml$

.circleci/config.yml

@@ -0,0 +1,51 @@
+# Copyright (c) 2024 Arjuna Technologies, Newcastle upon Tyne. All rights reserved.
+
+version: 2.1
+
+jobs:
+  dsbaseclient:
+    docker:
+      - image: cimg/base:current
+    resource_class: small
+    steps:
+      - checkout
+      - setup_remote_docker:
+          docker_layout_caching: true
+      - run: |
+          echo "Building"
+          echo "  Repo Name: " $CIRCLE_PROJECT_REPONAME
+          echo "  Branch:    " $CIRCLE_BRANCH
+          echo "  Tag:       " $CIRCLE_TAG
+      - run:
+          command: |
+              sudo apt-get update -y
+              sudo apt-get install -y r-base-core cmake
+      - run:
+          command: |
+              sudo apt-get install -y libxml2-dev
+              sudo apt-get install -y libfontconfig1-dev
+              sudo apt-get install -y libudunits2-dev
+              sudo apt-get install -y libharfbuzz-dev
+              sudo apt-get install -y libfribidi-dev
+              sudo apt-get install -y libfreetype6-dev
+              sudo apt-get install -y libpng-dev
+              sudo apt-get install -y libtiff5-dev
+              sudo apt-get install -y libjpeg-dev
+      - run:
+          command: |
+              sudo Rscript -e "install.packages('fields', dependencies=TRUE)"
+              sudo Rscript -e "install.packages('metafor', dependencies=TRUE)"
+              sudo Rscript -e "install.packages('meta', dependencies=TRUE)"
+              sudo Rscript -e "install.packages('ggplot2', dependencies=TRUE)"
+              sudo Rscript -e "install.packages('gridExtra', dependencies=TRUE)"
+              sudo Rscript -e "install.packages('data.table', dependencies=TRUE)"
+              sudo Rscript -e "install.packages('panelaggregation', dependencies=TRUE)"
+              sudo Rscript -e "install.packages('methods', dependencies=TRUE)"
+              sudo Rscript -e "install.packages('dplyr', dependencies=TRUE)"
+      - run:
+          command: |
+              sudo Rscript -e 'library(covr); covr::codecov(token = "'$CODECOV_TOKEN'", quiet=FALSE)'
+workflows:
+  build:
+    jobs:
+      - dsbaseclient

.gitignore

@@ -10,3 +10,5 @@
 inst/tests/test-template.R
 azure-pipelines.Rout
 tests/testthat/connection_to_datasets/local_settings.csv
+tests/docker/armadillo/standard/logs/
+tests/docker/armadillo/standard/data/

DESCRIPTION

@@ -1,13 +1,13 @@
 Package: dsBaseClient
 Title: DataSHIELD Client Functions
-Version: 6.3.0
+Version: 6.3.1
 Author: DataSHIELD Developers <datashield@liverpool.ac.uk>
 Maintainer: DataSHIELD Developers <datashield@liverpool.ac.uk>
 Description: DataSHIELD client functions for the client side.
 License: GPL-3
 Depends:
-    R (>= 3.5.0),
-    DSI (>= 1.3.0)
+    R (>= 4.0.0),
+    DSI (>= 1.7.1)
 Imports:
     fields,
     metafor,
@@ -18,5 +18,7 @@ Imports:
     panelaggregation,
     methods,
     dplyr
-RoxygenNote: 7.2.3
+Suggests:
+    testthat
+RoxygenNote: 7.3.2
 Encoding: UTF-8

R/ds.glm.R

@@ -46,7 +46,7 @@
 #' 
 #' In the \code{family} argument can be specified three types of models to fit:
 #' 
-#'  \itemize{
+#'  \describe{
 #'    \item{\code{"gaussian"}}{: conventional linear model with normally distributed errors} 
 #'    \item{\code{"binomial"}}{: conventional unconditional logistic regression model}
 #'    \item{\code{"poisson"}}{: Poisson regression model which is the most used in survival analysis. 
@@ -63,7 +63,7 @@
 #' The \code{data} argument avoids you having to specify the name of the
 #' data frame in front of each covariate in the formula. 
 #' For example, if the data frame is called \code{DataFrame} you
-#' avoid having to write: \eqn{DataFrame$y~DataFrame$a+DataFrame$b+DataFrame$c+DataFrame$d}
+#' avoid having to write: \eqn{DataFrame\$y ~ DataFrame\$a + DataFrame\$b + DataFrame\$c + DataFrame\$d}
 #' 
 #' The \code{checks} argument verifies that the variables in the model are all defined (exist) 
 #' on the server-side at every study
@@ -190,7 +190,7 @@
 #' @return \code{family}: error family and link function.
 #' @return \code{formula}: model formula, see description of formula as an input parameter (above).
 #' @return \code{coefficients}: a matrix with 5 columns:
-#'    \itemize{
+#'    \describe{
 #'    \item{First}{: the names of all of the regression parameters (coefficients) in the model}
 #'    \item{second}{: the estimated values}
 #'    \item{third}{: corresponding standard errors of the estimated values}

R/ds.glmSLMA.R

@@ -91,7 +91,7 @@
 #' relatively widely.
 #' 
 #' The standard models include:
-#'  \itemize{
+#'  \describe{
 #'    \item{\code{"gaussian"}}{: conventional linear model with normally distributed errors} 
 #'    \item{\code{"binomial"}}{: conventional unconditional logistic regression model}
 #'    \item{\code{"poisson"}}{: Poisson regression model which is often used in epidemiological
@@ -134,7 +134,7 @@
 #' The \code{dataName} argument avoids you having to specify the name of the
 #' data frame in front of each covariate in the formula. 
 #' For example, if the data frame is called \code{DataFrame} you
-#' avoid having to write: \eqn{DataFrame$y~DataFrame$a+DataFrame$b+DataFrame$c+DataFrame$d}
+#' avoid having to write: \eqn{DataFrame\$y ~ DataFrame\$a + DataFrame\$b + DataFrame\$c + DataFrame\$d}
 #' 
 #' The \code{checks} argument verifies that the variables in the model are all defined (exist) 
 #' on the server-site at every study
@@ -199,7 +199,7 @@
 #' a series of other list objects that represent inferences aggregated across studies.
 #' @return the study specific items include: 
 #' @return \code{coefficients}: a matrix with 5 columns:
-#'    \itemize{
+#'    \describe{
 #'    \item{First}{: the names of all of the regression parameters (coefficients) in the model} 
 #'    \item{second}{: the estimated values} 
 #'    \item{third}{: corresponding standard errors of the estimated values} 

R/ds.glmerSLMA.R

@@ -34,7 +34,7 @@
 #' The \code{dataName} argument avoids you having to specify the name of the
 #' data frame in front of each covariate in the formula. 
 #' For example, if the data frame is called \code{DataFrame} you avoid having to write: 
-#' \eqn{DataFrame$y~DataFrame$a+DataFrame$b+(1|DataFrame$c)}.
+#' \eqn{DataFrame\$y ~ DataFrame\$a + DataFrame\$b + (1 | DataFrame\$c)}.
 #' 
 #' The \code{checks} argument verifies that the variables in the model are all defined (exist) 
 #' on the server-site at every study
@@ -44,7 +44,7 @@
 #' 
 #' 
 #' In the \code{family} argument can be specified two types of models to fit:
-#'  \itemize{
+#'  \describe{
 #'    \item{\code{"binomial"}}{: logistic regression models}
 #'    \item{\code{"poisson"}}{: poisson regression models}
 #' }
@@ -133,7 +133,7 @@
 #' The list of elements returned by \code{ds.glmerSLMA} is mentioned below: 
 #' 
 #' @return \code{coefficients}: a matrix with 5 columns:
-#'    \itemize{
+#'    \describe{
 #'    \item{First}{: the names of all of the regression parameters (coefficients) in the model} 
 #'    \item{second}{: the estimated values} 
 #'    \item{third}{: corresponding standard errors of the estimated values} 

R/ds.heatmapPlot.R

@@ -11,19 +11,19 @@
 #' minimum and maximum value. This was done to reduce the risk of potential disclosure.
 #' 
 #' In the argument \code{type} can be specified two types of graphics to display:
-#'  \itemize{
+#'  \describe{
 #'    \item{\code{'combine'}}{: a combined heat map plot is displayed} 
 #'    \item{\code{'split'}}{: each heat map is plotted separately}
 #'     }
 #'
 #' In the argument \code{show} can be specified two options:
-#'  \itemize{
+#'  \describe{
 #'    \item{\code{'all'}}{: the ranges of the variables are used as plot limits} 
 #'    \item{\code{'zoomed'}}{: the plot is zoomed to the region where the actual data are}
 #'     }
 #' 
 #' In the argument \code{method} can be specified 3 different heat map to be created:
-#'  \itemize{
+#'  \describe{
 #'    \item{\code{'smallCellsRule'}}{: the heat map of the actual variables is
 #'     created but grids with low counts are replaced with grids with zero counts} 
 #'    \item{\code{'deterministic'}}{: the heat map of the scaled centroids of each 

R/ds.histogram.R

@@ -6,13 +6,13 @@
 #' the single plots.
 #' 
 #' In the argument \code{type} can be specified two types of graphics to display:
-#'  \itemize{
+#'  \describe{
 #'    \item{\code{'combine'}}{: a histogram that merges the single plot is displayed.} 
 #'    \item{\code{'split'}}{: each histogram is plotted separately.}
 #'     }
 #'     
 #' In the argument \code{method} can be specified 3 different histograms to be created:
-#'  \itemize{
+#'  \describe{
 #'    \item{\code{'smallCellsRule'}}{: the histogram of the actual variable is
 #'           created but bins with low counts are removed.} 
 #'    \item{\code{'deterministic'}}{: the histogram of the scaled centroids of each 
@@ -48,7 +48,7 @@
 #' By default the value of noise is set to be equal to 0.25.
 #' 
 #' In the argument  \code{vertical.axis} can be specified two types of histograms:
-#' \itemize{
+#' \describe{
 #'    \item{\code{'Frequency'}}{: the histogram of the frequencies
 #'     is returned.} 
 #'    \item{\code{'Density'}}{: the histogram of the densities

R/ds.lmerSLMA.R

@@ -18,20 +18,20 @@
 #' 
 #' In \code{formula} most shortcut notation allowed by  \code{lmer()} function is
 #' also allowed by \code{ds.lmerSLMA}. Many LMEs can be fitted very simply using a formula like:
-#' \deqn{y~a+b+(1|c)}
+#' \deqn{y ~ a + b + (1 | c)}
 #' which simply means fit an LME with \code{y} as the outcome variable with \code{a} and \code{b}
 #' as fixed effects, and \code{c} as a random effect or grouping factor.
 #' 
 #' It is also possible to fit models with random slopes by specifying a model such as 
-#' \deqn{y~a+b+(1+b|c)} 
+#' \deqn{y ~ a + b + (1 + b | c)}
 #' where the effect of \code{b} can vary randomly between groups defined by \code{c}.
-#' Implicit nesting can be specified with formulae such as \eqn{y~a+b+(1|c/d)}
-#' or \eqn{y~a+b+(1|c)+(1|c:d)}. 
+#' Implicit nesting can be specified with formulae such as \eqn{y ~ a + b + (1 | c / d)}
+#' or \eqn{y ~ a + b + (1 | c) + (1 | c : d)}.
 #' 
 #' The \code{dataName} argument avoids you having to specify the name of the
 #' data frame in front of each covariate in the formula. 
 #' For example, if the data frame is called \code{DataFrame} you avoid having to write: 
-#' \eqn{DataFrame$y~DataFrame$a+DataFrame$b+(1|DataFrame$c)}.
+#' \eqn{DataFrame\$y ~ DataFrame\$a + DataFrame\$b + (1 | DataFrame\$c)}.
 #' 
 #' The \code{checks} argument verifies that the variables in the model are all defined (exist) 
 #' on the server-site at every study
@@ -124,7 +124,7 @@
 #' @return \code{ds.lmerSLMA} returns a list of  elements mentioned 
 #' below separately for each study.  
 #' @return \code{coefficients}: a matrix with 5 columns:
-#'    \itemize{
+#'    \describe{
 #'    \item{First}{: the names of all of the regression parameters (coefficients) in the model} 
 #'    \item{second}{: the estimated values} 
 #'    \item{third}{: corresponding standard errors of the estimated values} 
@@ -192,7 +192,7 @@
 #'  
 #'   # Fit the lmer
 #'   
-#'   ds.lmerSLMA(formula = "BMI ~  incid_rate + diabetes + (1 | Male)",
+#'   ds.lmerSLMA(formula = "BMI ~ incid_rate + diabetes + (1 | Male)",
 #'                dataName = "D.comp",
 #'                datasources = connections)
 #'   

R/ds.names.R

@@ -6,7 +6,7 @@
 #' for example, it only works to extract names that already exist,
 #' not to create new names for objects. The function is restricted to objects of
 #' type list, but this includes objects that have a primary class other than list but which
-#' return TRUE to the native R function {is.list}. As an example this includes
+#' return TRUE to the native R function \code{is.list}. As an example this includes
 #' the multi-component object created by fitting a generalized linear model
 #' using ds.glmSLMA. The resultant object saved on each server separately
 #' is formally of class "glm" and "ls" but responds TRUE to is.list(),

R/ds.sample.R

@@ -4,8 +4,8 @@
 #' on the serverside
 #' or - as a special case - randomly permutes a vector, dataframe or matrix.
 #' @details Clientside function ds.sample calls serverside
-#' assign function sampleDS. Based on the native R function {sample()} but deals
-#' slightly differently with data.frames and matrices. Specifically the {sample()}
+#' assign function sampleDS. Based on the native R function \code{sample()} but deals
+#' slightly differently with data.frames and matrices. Specifically the \code{sample()}
 #' function in R identifies the length of an object and then samples n components
 #' of that length. But length(data.frame) in native R returns the number of columns
 #' not the number of rows. So if you have a data.frame with 71 rows and 10 columns,
@@ -63,11 +63,11 @@
 #' that is a randomly permuted sample of the vector 1:923, or (if [replace]
 #' = FALSE, a full random permutation of that same vector. For further details
 #' of using ds.sample with x set as an integer/numeric please see help for
-#' the {sample} function in native R. But if x is set as a character string
+#' the \code{sample} function in native R. But if x is set as a character string
 #' denoting a vector, matrix or data.frame on the serverside, please note
-#' that although {ds.sample} effectively calls {sample} on the serverside
-#' it behaves somewhat differently to {sample} - for the reasons identified
-#' at the top of 'details' and so help for {sample} should be used as a guide
+#' that although \code{ds.sample} effectively calls \code{sample} on the serverside
+#' it behaves somewhat differently to \code{sample} - for the reasons identified
+#' at the top of 'details' and so help for \code{sample} should be used as a guide
 #' only.
 #' @param size a numeric/integer scalar indicating the size of the sample to
 #' be drawn. If the [x] argument is a vector, matrix or data.frame on the
@@ -102,18 +102,18 @@
 #' @param replace a Boolean indicator (TRUE or FALSE) specifying whether the
 #' sample should be drawn with or without replacement. Default is FALSE so
 #' the sample is drawn without replacement. For further details see
-#' help for {sample} in native R.
+#' help for \code{sample} in native R.
 #' @param prob a character string containing the name of a numeric vector
 #' of probability weights on the serverside that is associated with each of the
 #' elements of the vector to be sampled enabling the drawing of a sample
 #' with some elements given higher probability of being drawn than others.
-#' For further details see help for {sample} in native R.
+#' For further details see help for \code{sample} in native R.
 #' @param newobj This a character string providing a name for the output
 #' data.frame which defaults to 'newobj.sample' if no name is specified.
 #' @param datasources specifies the particular opal object(s) to use. If the <datasources>
 #' argument is not specified the default set of opals will be used. The default opals
 #' are called default.opals and the default can be set using the function
-#' {ds.setDefaultOpals}. If the <datasources> is to be specified, it should be set without
+#' \code{ds.setDefaultOpals}. If the <datasources> is to be specified, it should be set without
 #' inverted commas: e.g. datasources=opals.em or datasources=default.opals. If you wish to
 #' apply the function solely to e.g. the second opal server in a set of three,
 #' the argument can be specified as: e.g. datasources=opals.em[2].