V6.3.4 dev

.Rbuildignore

@@ -17,8 +17,9 @@
 ^R/secure.global.ranking.md$
 ^_pkgdown\.yml$
 ^docs$
-^dsBase_6.3.2.tar.gz$
-^dsBase_6.3.2-permissive.tar.gz$
-^dsDanger_6.3.1.tar.gz$
+^dsBase_6.3.4.tar.gz$
+^dsBase_6.3.4-permissive.tar.gz$
+^dsDanger_6.3.4.tar.gz$
 ^\.circleci$
 ^\.circleci/config\.yml$
+^\.github$

.github/.gitignore

@@ -0,0 +1 @@
+*.html

.github/workflows/pkgdown.yaml

@@ -0,0 +1,49 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+name: pkgdown.yaml
+
+permissions: read-all
+
+jobs:
+  pkgdown:
+    runs-on: ubuntu-latest
+    # Only restrict concurrency for non-PR jobs
+    concurrency:
+      group: pkgdown-${{ github.event_name != 'pull_request' || github.run_id }}
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::pkgdown, local::.
+          needs: website
+
+      - name: Build site
+        run: pkgdown::build_site_github_pages(new_process = FALSE, install = FALSE)
+        shell: Rscript {0}
+
+      - name: Deploy to GitHub pages 🚀
+        if: github.event_name != 'pull_request'
+        uses: JamesIves/github-pages-deploy-action@v4.5.0
+        with:
+          clean: false
+          branch: gh-pages
+          folder: docs

DESCRIPTION

@@ -1,23 +1,27 @@
 Package: dsBaseClient
-Title: DataSHIELD Client Functions
-Version: 6.3.3
-Description: Base DataSHIELD functions for the client side. DataSHIELD is a software package which allows
-    you to do non-disclosive federated analysis on sensitive data. DataSHIELD analytic functions have
+Title: 'DataSHIELD' Client Side Base Functions
+Version: 6.3.4
+Description: Base 'DataSHIELD' functions for the client side. 'DataSHIELD' is a software package which allows
+    you to do non-disclosive federated analysis on sensitive data. 'DataSHIELD' analytic functions have
     been designed to only share non disclosive summary statistics, with built in automated output
     checking based on statistical disclosure control. With data sites setting the threshold values for
-    the automated output checks.
+    the automated output checks. For more details, see 'citation("dsBaseClient")'.
 Authors@R: c(person(given = "Paul",
                     family = "Burton",
-                    role = c("aut")),
+                    role = c("aut"),
+                    comment = c(ORCID = "0000-0001-5799-9634")),
              person(given = "Rebecca",
                     family = "Wilson",
-                    role = c("aut")),
+                    role = c("aut"),
+                    comment = c(ORCID = "0000-0003-2294-593X")),
              person(given = "Olly",
                     family = "Butters",
-                    role = c("aut")),
+                    role = c("aut"),
+                    comment = c(ORCID = "0000-0003-0354-8461")),
              person(given = "Patricia",
                     family = "Ryser-Welch",
-                    role = c("aut")),
+                    role = c("aut"),
+                    comment = c(ORCID = "0000-0002-0070-0264")),
              person(given = "Alex",
                     family = "Westerberg",
                     role = c("aut")),
@@ -32,11 +36,26 @@ Authors@R: c(person(given = "Paul",
                     family = "Avraam",
                     role = c("aut"),
                     comment = c(ORCID = "0000-0001-8908-2441")),
+             person(given = "Demetris",
+                    family = "Avraam",
+                    role = c("aut"),
+                    comment = c(ORCID = "0000-0001-8908-2441")),
              person(given = "Yannick",
                     family = "Marcon",
                     role = c("aut"),
                     email = "yannick.marcon@obiba.org",
                     comment = c(ORCID = "0000-0003-0138-2023")),
+             person(given = "Tom",
+                    family = "Bishop",
+                    role = c("aut")),
+             person(given = "Amadou",
+                    family = "Gaye",
+                    role = c("aut"),
+                    comment = c(ORCID = "0000-0002-1180-2792")),
+             person(given = "Xavier",
+                    family = "Escribà-Montagut",
+                    role = c("aut"),
+                    comment = c(ORCID = "0000-0003-2888-8948")),
              person(given = "Stuart",
                     family = "Wheater",
                     role = c("aut", "cre"),
@@ -58,12 +77,14 @@ Imports:
 Suggests:
     lme4,
     httr,
+    spelling,
     tibble,
     testthat,
     e1071,
     DescTools,
     DSOpal,
     DSMolgenisArmadillo,
     DSLite
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 Encoding: UTF-8
+Language: en-GB

R/ds.asNumeric.R

@@ -5,7 +5,7 @@
 #' @details This function is based on the native R function \code{as.numeric}.
 #' However, it behaves differently with some specific classes of variables. For example, if the input 
 #' object is of class factor, it first converts its values into characters and then convert those to
-#' numerics. This behavior is important for the case where the input object is of class factor having
+#' numerics. This behaviour is important for the case where the input object is of class factor having
 #' numbers as levels. In that case, the native R 
 #' \code{as.numeric} function returns the underlying level codes and not the values as numbers. 
 #' For example \code{as.numeric} in R converts the factor vector: \cr

R/ds.corTest.R

@@ -10,7 +10,7 @@
 #' used for the test. One of "pearson", "kendall", or "spearman", can be abbreviated. 
 #' Default is set to "pearson".
 #' @param exact a logical indicating whether an exact p-value should be computed. Used for
-#' Kendall's tau and Spearman's rho. See ‘Details’ of R stats function \code{cor.test} for
+#' Kendall's tau and Spearman's rho. See \emph{Details} of R stats function \code{cor.test} for
 #' the meaning of NULL (the default).
 #' @param conf.level confidence level for the returned confidence interval. Currently
 #' only used for the Pearson product moment correlation coefficient if there are at least

R/ds.dataFrameSubset.R

@@ -12,7 +12,7 @@
 #' 
 #' Server functions called: \code{dataFrameSubsetDS1} and \code{dataFrameSubsetDS2}
 #' 
-#' @param df.name a character string providing the name of the data frame to be subseted. 
+#' @param df.name a character string providing the name of the data frame to be subset. 
 #' @param V1.name  A character string specifying the name of the vector 
 #' to which the Boolean operator is to be applied to define the subset.
 #' For more information see details. 

R/ds.dmtC2S.R

@@ -29,7 +29,7 @@
 #' wish to change the connections you wish to use by default the call
 #' datashield.connections_default('opals.a') will set 'default.connections'
 #' to be 'opals.a' and so in the absence of specific instructions to the contrary
-#' (e.g. by specifiying a particular dataset to be used via the <datasources>
+#' (e.g. by specifying a particular dataset to be used via the <datasources>
 #' argument) all subsequent function calls will be to the datasets held in opals.a.
 #' If the <datasources> argument is specified, it should be set without
 #' inverted commas: e.g. datasources=opals.a or datasources=default.connections.

R/ds.elspline.R

@@ -13,7 +13,7 @@
 #' @param x the name of the input numeric variable
 #' @param n integer greater than 2, knots are computed such that they cut n equally-spaced
 #' intervals along the range of x
-#' @param marginal logical, how to parametrize the spline, see Details
+#' @param marginal logical, how to parametrise the spline, see Details
 #' @param names character, vector of names for constructed variables
 #' @param newobj a character string that provides the name for the output 
 #' variable that is stored on the data servers. Default \code{elspline.newobj}. 

R/ds.forestplot.R

@@ -1,10 +1,10 @@
 #' @title Forestplot for SLMA models
-#' @description Draws a foresplot of the coefficients for Study-Level Meta-Analysis performed with
+#' @description Draws a forestplot of the coefficients for Study-Level Meta-Analysis performed with
 #' DataSHIELD
 #'
-#' @param mod \code{list} List outputed by any of the SLMA models of DataSHIELD (\code{ds.glmerSLMA}, 
+#' @param mod \code{list} List outputted by any of the SLMA models of DataSHIELD (\code{ds.glmerSLMA}, 
 #' \code{ds.glmSLMA}, \code{ds.lmerSLMA})
-#' @param variable \code{character} (default \code{NULL}) Variable to meta-analyze and visualize, by setting this 
+#' @param variable \code{character} (default \code{NULL}) Variable to meta-analyse and visualise, by setting this 
 #' argument to \code{NULL} (default) the first independent variable will be used.
 #' @param method \code{character} (Default \code{"ML"}) Method to estimate the between study variance. 
 #' See details from \code{?meta::metagen} for the different options.

R/ds.glmPredict.R

@@ -91,7 +91,7 @@
 #' wish to change the connections you wish to use by default the call
 #' datashield.connections_default('opals.a') will set 'default.connections'
 #' to be 'opals.a' and so in the absence of specific instructions to the contrary
-#' (e.g. by specifiying a particular dataset to be used via the <datasources>
+#' (e.g. by specifying a particular dataset to be used via the <datasources>
 #' argument) all subsequent function calls will be to the datasets held in opals.a.
 #' If the <datasources> argument is specified, it should be set without
 #' inverted commas: e.g. datasources=opals.a or datasources=default.connections.
@@ -116,7 +116,7 @@
 #' the name - if one was specified - of the dataframe being used as the basis for predictions,
 #' the output.type specified ('link', 'response' or 'terms'), the value of the
 #' dispersion parameter if one had been specified and the residual scale parameter (which is
-#' multipled by sqrt(dispersion parameter) if one has been set). If output.type = 'terms',
+#' multiplied by sqrt(dispersion parameter) if one has been set). If output.type = 'terms',
 #' the summary statistics for the fit and se.fit vectors are replaced by equivalent
 #' summary statistics for each column in fit and se.fit matrices which each have k columns
 #' if k terms are being summarised.

R/ds.glmSLMA.R

@@ -263,7 +263,7 @@
 #' them into their meta-analysis package of choice.
 #' @return \code{is.object.created} and \code{validity.check} are standard
 #' items returned by an assign function when the designated newobj appears to have
-#' been successfuly created on the serverside at each study. This output is
+#' been successfully created on the serverside at each study. This output is
 #' produced specifically by the assign function \code{glmSLMADS.assign} that writes
 #' out the glm object on the serverside 
 #' @author Paul Burton, for DataSHIELD Development Team 07/07/20

R/ds.glmSummary.R

@@ -48,7 +48,7 @@
 #' wish to change the connections you wish to use by default the call
 #' datashield.connections_default('opals.a') will set 'default.connections'
 #' to be 'opals.a' and so in the absence of specific instructions to the contrary
-#' (e.g. by specifiying a particular dataset to be used via the <datasources>
+#' (e.g. by specifying a particular dataset to be used via the <datasources>
 #' argument) all subsequent function calls will be to the datasets held in opals.a.
 #' If the <datasources> argument is specified, it should be set without
 #' inverted commas: e.g. datasources=opals.a or datasources=default.connections.

R/ds.igb_standards.R

@@ -20,11 +20,20 @@
 #' used: see \code{\link[DSI]{datashield.connections_default}}.
 #' @note For gestational ages between 24 and 33 weeks, the INTERGROWTH very early preterm 
 #' standard is used.
-#' @references International standards for newborn weight, length, and head circumference by 
-#' gestational age and sex: the Newborn Cross-Sectional Study of the INTERGROWTH-21st Project
-#' Villar, José et al. The Lancet, Volume 384, Issue 9946, 857-868
-#' INTERGROWTH-21st very preterm size at birth reference charts. Lancet 2016 
-#' doi.org/10.1016/S0140-6736(16) 00384-6. Villar, José et al.
+#' @references 
+#' \itemize{
+#'  \item Villar, J., Ismail, L.C., Victora, C.G., Ohuma, E.O., Bertino, E., 
+#'  Altman, D.G., Lambert, A., Papageorghiou, A.T., Carvalho, M., Jaffer, Y.A., 
+#'  Gravett, M.G., Purwar, M., Frederick, I.O., Noble, A.J., Pang, R., Barros, 
+#'  F.C., Chumlea, C., Bhutta, Z.A., Kennedy, S.H., 2014. International 
+#'  standards for newborn weight, length, and head circumference by gestational 
+#'  age and sex: the Newborn Cross-Sectional Study of the INTERGROWTH-21st 
+#'  Project. The Lancet 384, 857--868. https://doi.org/10.1016/S0140-6736(14)60932-6
+#'  \item Villar, J., Giuliani, F., Fenton, T.R., Ohuma, E.O., Ismail, L.C., 
+#'  Kennedy, S.H., 2016. INTERGROWTH-21st very preterm size at birth reference 
+#'  charts. The Lancet 387, 844--845. https://doi.org/10.1016/S0140-6736(16)00384-6
+#'  
+#' }
 #' @return assigns the converted measurement as a new object on the server-side
 #' @author Demetris Avraam for DataSHIELD Development Team
 #' @export

R/ds.ls.R

@@ -41,7 +41,7 @@
 #' Server function called: \code{lsDS}. 
 #' 
 #' @param search.filter character string (potentially including \code{*} symbol) specifying the filter 
-#' for the object name that you want to find in the enviroment. For more information see \strong{Details}. 
+#' for the object name that you want to find in the environment. For more information see \strong{Details}. 
 #' @param env.to.search an integer (e.g. in \code{2} or \code{2L} format) specifying the position
 #' in the search path of the environment to be explored. \code{1L} is the current active analytic
 #' environment on the server-side and is the default value of \code{env.to.search}.

R/ds.lspline.R

@@ -10,7 +10,7 @@
 #' in slope as compared to the previous segment.
 #' @param x the name of the input numeric variable
 #' @param knots numeric vector of knot positions
-#' @param marginal logical, how to parametrize the spline, see Details
+#' @param marginal logical, how to parametrise the spline, see Details
 #' @param names character, vector of names for constructed variables
 #' @param newobj a character string that provides the name for the output 
 #' variable that is stored on the data servers. Default \code{lspline.newobj}. 

R/ds.matrix.R

@@ -27,7 +27,7 @@
 #' 
 #' @param mdata a character string specifying
 #' the name of a server-side scalar or vector. Also, a numeric value representing a
-#' scalar specified from the client-side can be speficied. 
+#' scalar specified from the client-side can be specified 
 #' Zeros, negative values and NAs are all allowed.
 #' For more information see \strong{Details}. 
 #' @param from a character string specifying the source and nature of \code{mdata}.

R/ds.matrixDiag.R

@@ -37,7 +37,7 @@
 #' Server function called: \code{matrixDiagDS}
 #' @param x1 a character string specifying
 #' the name of a server-side scalar or vector. Also, a numeric value or vector
-#' specified from the client-side can be speficied. This argument depends 
+#' specified from the client-side can be specified. This argument depends 
 #' on the value specified in \code{aim}.
 #' For more information see \strong{Details}. 
 #' @param aim a character string specifying the behaviour of the function.

R/ds.ns.R

@@ -8,7 +8,7 @@
 #' sequence of interior knots, and the natural boundary conditions. These enforce the constraint
 #' that the function is linear beyond the boundary knots, which can either be supplied or default
 #' to the extremes of the data.
-#' A primary use is in modeling formula to directly specify a natural spline term in a model.
+#' A primary use is in modelling formula to directly specify a natural spline term in a model.
 #' @param x the predictor variable. Missing values are allowed.
 #' @param df degrees of freedom. One can supply df rather than knots; ns() then chooses 
 #' df - 1 - intercept knots at suitably chosen quantiles of x (which will ignore missing values).

R/ds.qlspline.R

@@ -18,7 +18,7 @@
 #' intervals along x or a vector of numbers in (0; 1) specifying the quantiles explicitly.
 #' @param na.rm logical, whether NA should be removed when calculating quantiles, passed
 #' to na.rm of quantile. Default set to TRUE
-#' @param marginal logical, how to parametrize the spline, see Details
+#' @param marginal logical, how to parametrise the spline, see Details
 #' @param names character, vector of names for constructed variables
 #' @param newobj a character string that provides the name for the output 
 #' variable that is stored on the data servers. Default \code{qlspline.newobj}. 

R/ds.ranksSecure.R

@@ -1,7 +1,7 @@
 # ds.ranksSecure
 #' @title Secure ranking of a vector across all sources
 #' @description Securely generate the ranks of a numeric vector and estimate
-#' true qlobal quantiles across all data sources simultaneously 
+#' true global quantiles across all data sources simultaneously 
 #' @details ds.ranksSecure is a clientside function which calls a series of
 #' other clientside and serverside functions to securely generate the global
 #' ranks of a numeric vector "V2BR" (vector to be ranked)
@@ -43,7 +43,7 @@
 #' of the clusters of values that are being ranked such that some values are
 #' treated as being missing and the processing stops, then setting
 #' generate.quantiles to FALSE allows the generation of ranks to complete so
-#' they can then be used for non-parameteric analysis, even if the key values
+#' they can then be used for non-parametric analysis, even if the key values
 #' cannot be estimated. A real example of an unusual configuration was in a
 #' reasonably large dataset of survival times, where a substantial proportion
 #' of survival profiles were censored at precisely 10 years. This meant that

R/ds.recodeValues.R

@@ -4,7 +4,7 @@
 #' @details This function recodes individual values with new individual values. This can
 #' apply to numeric and character values, factor levels and NAs. One particular use of
 #' \code{ds.recodeValues} is to convert NAs to an explicit value. This value is specified
-#' in the argument \code{missing}. If tthe user want to recode only missing values, then it
+#' in the argument \code{missing}. If the user want to recode only missing values, then it
 #' should also specify an identical vector of values in both arguments \code{values2replace.vector}
 #' and \code{new.values.vector} (see Example 2 below).
 #' Server function called: \code{recodeValuesDS}

R/ds.sample.R

@@ -45,7 +45,7 @@
 #' case with the default name 'newobj.sample) using ds.dataFrameSort with the
 #' 'sampling.order' vector as the sort key, the output object is rendered
 #' equivalent to PRWa but with the rows randomly permuted (so the column reflecting
-#' the vector 'sample.order' now runs from 1:length of obejct, while the
+#' the vector 'sample.order' now runs from 1:length of object, while the
 #' column reflecting 'ID.seq' denoting the original order is now randomly ordered.
 #' If you need to return to the original order you can simply us ds.dataFrameSort
 #' again using the column reflecting 'ID.seq' as the sort key:

R/ds.scatterPlot.R

@@ -6,7 +6,7 @@
 #' permitted in DataSHIELD, this function allows the user to plot non-disclosive scatter plots.
 #' 
 #' If the argument \code{method} is set to \code{'deterministic'}, the server-side function searches
-#' for the \code{k-1} nearest neighbors of each single data point and calculates the centroid 
+#' for the \code{k-1} nearest neighbours of each single data point and calculates the centroid 
 #' of such \code{k} points. 
 #' The proximity is defined by the minimum Euclidean distances of z-score transformed data.
 #' 
@@ -52,7 +52,7 @@
 #' This argument can be set as \code{'deteministic'} or \code{'probabilistic'}.
 #' Default \code{'deteministic'}. 
 #' For more information see \strong{Details}. 
-#' @param k the number of the nearest neighbors  for which their centroid is calculated.
+#' @param k the number of the nearest neighbours  for which their centroid is calculated.
 #' Default 3. 
 #' For more information see \strong{Details}. 
 #' @param noise the percentage of the initial variance that is used as the variance of the embedded