Update NEWS, adds make_newdata function + cleans up

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: survHE
 Title: Survival Analysis in Health Economic Evaluation
-Version: 2.0.1
-Date: 2023-05-23
+Version: 2.0.2
+Date: 2024-10-03
 Authors@R: c(
     person(given = "Gianluca",family = "Baio",role = c("aut", "cre"),email = "[email protected]"),
     person("Andrea","Berardi",role="ctb",email="[email protected]"),
@@ -27,7 +27,7 @@ License: GPL (>=3)
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.2
 Biarch: true
 Depends: 
     methods,
@@ -39,7 +39,8 @@ Imports:
     rms,
     xlsx,
     tools,
-    tibble
+    tibble,
+    tidyr
 Suggests:
     survHEinla,
     survHEhmc,

NAMESPACE

@@ -27,8 +27,9 @@ importFrom("utils", "read.table","write.table","head","tail","modifyList")
 importFrom("stats", "terms","as.formula","model.frame","model.matrix","dexp",
            "pexp","dweibull","pweibull","dgamma","pgamma","median","var","time",
            "update","dt","profile","dlnorm","plnorm","dlogis","plogis","sd",
-           "quantile","qnorm")
+           "quantile","qnorm","model.matrix.lm")
 importFrom("grDevices", "colors","adjustcolor","colorRampPalette")
 importFrom("tools", "file_ext")
 importFrom("rms", "npsurv","survplot")
 importFrom("tibble", "rownames_to_column")
+importFrom("tidyr", "unite")

NEWS.md

@@ -22,4 +22,6 @@ geom_step(data = datakm, aes(x = time, y = S, group=as.factor(strata:object_name
                   aes(x = time, y = S, ymin=lower, ymax=upper, group=as.factor(strata:object_name)),
                   alpha = 0.2) 
 ```
-This means that when plotting two or more `survHE` objects, the KM is added and displayed correctly
+This means that when plotting two or more `survHE` objects, the KM is added and displayed correctly
+
+* Adds a utility function `make_newdata` that can be used to generate profiles of covariates, to then plot specific groups of individuals' survival or hazard curves.

R/survHE-package.R

@@ -1,36 +1,6 @@
-#' Survival Analysis in Health Economic Evaluation
-#' 
-#' Contains a suite of functions to perform survival analysis with the aim of
-#' aiding in health economic modelling (extrapolation, model checking and PSA)
-#' 
-#' \tabular{ll}{ Package: \tab survHE\cr Type: \tab Package\cr Version: \tab
-#' 2.0.1\cr Date: \tab 2023-03-10\cr License: \tab GPL2 \cr LazyLoad: \tab
-#' yes\cr } Contains a suite of functions to perform survival analysis with the
-#' aim of aiding in health economic modelling (extrapolation, model checking
-#' and PSA)
-#' 
-#' @name survHE-package
-#' @aliases survHE-package 
-#' @aliases survHE
-#' @docType package
-#' @author Gianluca Baio
-#' 
-#' Maintainer: Gianluca Baio
-#' @template refs
-#' @keywords Survival Modelling Health Economic Evaluation
-#' @examples
-#' \dontrun{ 
-#' # Loads some survival data
-#' data(bc)
-#' # Fits a parametric model
-#' m <- fit.models(formula=Surv(recyrs,censrec)~group,data=bc,
-#'     distr="exp",method="mle")
-#' # Print output in tabular format
-#' print(m)
-#' # Visualise output in terms of survival curves
-#' plot(m)
-#' }
-NULL
-
-
+#' @keywords internal
+"_PACKAGE"
 
+## usethis namespace: start
+## usethis namespace: end
+NULL

R/utils_plot_survHE.R

@@ -234,6 +234,74 @@ plot_ggplot_survHE <- function(exArgs) {
   surv.curv
 }
 
+#' Creates a 'newdata' list to modify the plots for specific individual
+#' profiles (with respect to the covariates)
+#' 
+#' @param data The original dataset that has been used as input to the call
+#' to 'fit.models'
+#' @param vars A vector of strings, including the names of the variables that
+#' are to be used to construct specific profiles of individual covariates
+#' @param conts A subset of 'vars', which include the named covariates that
+#' are continuous. These will be averaged over, while for the remaining 
+#' covariates (assumed to be factors), the specific profiles will be listed. 
+#' Defaults to NULL
+#' @return \item{newdata}{The list 'newdata' to be passed as optional argument
+#' to a call to the 'plot' method}
+#' @return \item{labs}{A vector of labels (say to use in the plot, for each 
+#' profile)}
+#' @note Something will go here
+#' @author Gianluca Baio
+#' @keywords Parametric survival models
+#' @examples
+#' \dontrun{
+#' data(bc)
+#' 
+#' # Fits a model using the 'bc' data
+#' mle = fit.models(formula=Surv(recyrs,censrec)~group,data=bc,
+#'     distr="exp",method="mle")
+#' # Now makes the default plot
+#' plot(mle)
+#' # Now creates a 'newdata' list to modify the plot for selected profiles
+#' newdata=make_newdata(data=bc,vars="group")
+#' # And can plot, say, only two of the three treatment arms
+#' plot(mle,newdata=newdata$newdata[c(1,3)],lab.profile=newdata$labs[c(1,3)])
+#' }
+#' 
+#' @export make_newdata
+
+make_newdata=function(data,vars,conts=NULL) {
+  df= 
+    # Takes the original data
+    data |> 
+    # Selects the relevant variables to construct the profiles
+    select(all_of(vars)) |> 
+    # Takes the mean for the continuous variables
+    mutate(across(all_of(conts),~mean(.x))) |> 
+    # Takes only the unique combinations
+    unique() 
+
+  # Creates a vector of labels (say to use in the plot, for each profile)
+  labs=df |> 
+    # Don't need to keep the continuous variables as they've been averaged over
+    select(-conts) |> 
+    # Uses 'unite' to turn into vectors
+    tidyr::unite(labs,sep=", ") |> 
+    # NB: needs to remove names in the vector or else won't work in the plot(...)
+    unlist(use.names=F)
+
+  # Creates the list 'newdata' to pass to the plot function
+  newdata = df |> 
+    # And then transforms into a list of values
+    (function(.) split(.,f=seq(nrow(.))))() 
+
+  # Returns the output
+  list(
+    newdata=newdata,
+    labs=labs
+  )
+}
+
+
 
 #' Make the dataset to be used by \code{ggplot2} to plot the survival curves
 #'