[2023.8.23]

CRAN-SUBMISSION

@@ -1,3 +1,3 @@
-Version: 2023.8
-Date: 2023-08-08 10:17:47 UTC
-SHA: 29fdc28d5ddd19fa51b92b65f61362b3807df98a
+Version: 2023.8.23
+Date: 2023-08-23 22:24:41 UTC
+SHA: 97e68f27f3289f1c419d7a5e631452d74d236ec1

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: bruceR
 Title: Broadly Useful Convenient and Efficient R Functions
-Version: 2023.8
-Date: 2023-08-08
+Version: 2023.8.23
+Date: 2023-08-23
 Authors@R:
     c(person(given = "Han-Wu-Shuang",
              family = "Bao",

NEWS.md

@@ -1,5 +1,14 @@
 **Please check the [latest news (change log)](https://psychbruce.github.io/bruceR/news/index.html) and keep this package updated.**
 
+# bruceR 2023.9
+
+## Minor Changes
+
+-   Now `var` and `items` support more flexible input, e.g.:
+    -   `.mean(var="X", items=1:3)` matches `X1`, `X2`, `X3`
+    -   `.mean(var="X.{any_placeholder}.pre", items=1:3)` matches `X.1.pre`, `X.2.pre`, `X.3.pre`
+-   Use `\donttest{}` in more examples to avoid unnecessary errors.
+
 # bruceR 2023.8
 
 ## New Features

R/bruceR-stats_1_basic.R

@@ -185,7 +185,6 @@ added = function(data, expr, when, by, drop=FALSE) {
     dn.drop = base::setdiff(dn, dn.new)
     data[, (dn.drop) := NULL][]
   }
-  Print("<<green \u2714>> Raw data has already been changed. Please check.")
   invisible(data)
 }
 
@@ -618,7 +617,7 @@ Freq = function(
 #' (2) a \code{ggplot2} object if \code{plot=TRUE}.
 #'
 #' @examples
-#' Corr(airquality)
+#' \donttest{Corr(airquality)
 #' Corr(airquality, p.adjust="bonferroni",
 #'      plot.colors=c("#b2182b", "white", "#2166ac"))
 #'
@@ -633,7 +632,7 @@ Freq = function(
 #'   O = .mean("O", 1:5, rev=c(2,5), range=1:6)
 #' })
 #' Corr(d[, .(age, gender, education, E, A, C, N, O)])
-#'
+#' }
 #' @seealso
 #' \code{\link{Describe}}
 #'

R/bruceR-stats_2_scale.R

@@ -8,7 +8,7 @@
 #' Reverse scoring can also be easily implemented without saving extra variables.
 #' \code{\link{Alpha}} function uses a similar method to deal with reverse scoring.
 #'
-#' Three options to specify variables:
+#' Three ways to specify variables:
 #' \enumerate{
 #'   \item \strong{\code{var + items}}: common and unique parts of variable names (suggested).
 #'   \item \strong{\code{vars}}: a character vector of variable names (suggested).
@@ -17,30 +17,34 @@
 #'
 #' @param data Data frame.
 #' @param var \strong{[Option 1]}
-#' The common part across the variables. e.g., \code{"RSES"}
+#' Common part across variables: e.g., \code{"RSES"}, \code{"XX.{i}.pre"}
+#' (if \code{var} string has any placeholder in braces \code{{...}},
+#' then \code{items} will be pasted into the braces, see examples)
 #' @param items \strong{[Option 1]}
-#' The unique part across the variables. e.g., \code{1:10}
+#' Unique part across variables: e.g., \code{1:10}, \code{c("a", "b", "c")}
 #' @param vars \strong{[Option 2]}
-#' A character vector specifying the variables. e.g., \code{c("X1", "X2", "X3", "X4", "X5")}
+#' Character vector specifying variables: e.g., \code{c("X1", "X2", "X3", "X4", "X5")}
 #' @param varrange \strong{[Option 3]}
-#' A character string specifying the positions ("starting:stopping") of variables. e.g., \code{"A1:E5"}
+#' Character string specifying positions ("start:stop") of variables: e.g., \code{"A1:E5"}
 #' @param value [Only for \code{COUNT}] The value to be counted.
 #' @param rev [Optional] Variables that need to be reversed. It can be
 #' (1) a character vector specifying the reverse-scoring variables (recommended), or
 #' (2) a numeric vector specifying the item number of reverse-scoring variables (not recommended).
-#' @param range,likert [Optional] Range of likert scale (e.g., \code{1:5}, \code{c(1, 5)}).
+#' @param range,likert [Optional] Range of likert scale: e.g., \code{1:5}, \code{c(1, 5)}.
 #' If not provided, it will be automatically estimated from the given data (BUT you should use this carefully).
 #' @param na.rm Ignore missing values. Defaults to \code{TRUE}.
 #' @param values [Only for \code{CONSEC}] Values to be counted as consecutive identical values. Defaults to all numbers (\code{0:9}).
 #'
 #' @return A vector of computed values.
 #'
 #' @examples
-#' d = data.table(x1=1:5,
-#'                x4=c(2,2,5,4,5),
-#'                x3=c(3,2,NA,NA,5),
-#'                x2=c(4,4,NA,2,5),
-#'                x5=c(5,4,1,4,5))
+#' d = data.table(
+#'   x1 = 1:5,
+#'   x4 = c(2,2,5,4,5),
+#'   x3 = c(3,2,NA,NA,5),
+#'   x2 = c(4,4,NA,2,5),
+#'   x5 = c(5,4,1,4,5)
+#' )
 #' d
 #' ## I deliberately set this order to show you
 #' ## the difference between "vars" and "varrange".
@@ -71,11 +75,31 @@
 #' }, drop=TRUE)
 #' data
 #'
+#' ## ====== New Feature for `var` & `items` ====== ##
+#' d = data.table(
+#'   XX.1.pre = 1:5,
+#'   XX.2.pre = 6:10,
+#'   XX.3.pre = 11:15
+#' )
+#' add(d, { XX.mean = .mean("XX.{i}.pre", 1:3) })
+#' add(d, { XX.mean = .mean("XX.{items}.pre", 1:3) })  # the same
+#' add(d, { XX.mean = .mean("XX.{#$%^&}.pre", 1:3) })  # the same
+#'
 #' @name %%COMPUTE%%
-## @aliases COUNT SUM MEAN STD CONSEC
 NULL
 
 
+paste_var_items = function(var, items) {
+  if(grepl("\\{.*\\}", var)) {
+    var.split = strsplit(var, "\\{.*\\}")[[1]]
+    vars = paste0(var.split[1], items, var.split[2])
+  } else {
+    vars = paste0(var, items)
+  }
+  return(vars)
+}
+
+
 convert2vars = function(data,
                         var=NULL, items=NULL,
                         vars=NULL,
@@ -86,7 +110,7 @@ convert2vars = function(data,
     varrange = gsub(" ", "", strsplit(varrange, ":")[[1]])
     vars = dn[which(dn==varrange[1]):which(dn==varrange[2])]
   }
-  if(is.null(vars)) vars = paste0(var, items)
+  if(is.null(vars)) vars = paste_var_items(var, items)
   if(is.numeric(rev)) {
     if(is.null(var))
       stop("Argument `rev` must be character rather than numeric if you specify `vars` or `varrange`.", call.=FALSE)
@@ -165,8 +189,8 @@ SUM = function(data,
                 na.rm=TRUE) {
   Sum = glue("function(...) sum(..., na.rm={na.rm})")
   if(!is.null(varrange))
-    stop("Please specify either `vars` or `var` + `items`.", call.=FALSE)
-  if(is.null(vars)) vars = paste0(var, items)
+    stop("Please specify either `vars` or `var` + `items`. To specify `varrange`, please use `SUM()`.", call.=FALSE)
+  if(is.null(vars)) vars = paste_var_items(var, items)
   if(!is.null(rev) & is.null(range))
     stop("Please also specify the `range` argument!", call.=FALSE)
   if(is.numeric(rev)) {
@@ -217,8 +241,8 @@ MEAN = function(data,
                  na.rm=TRUE) {
   Mean = glue("function(...) mean(c(...), na.rm={na.rm})")
   if(!is.null(varrange))
-    stop("Please specify either `vars` or `var` + `items`.", call.=FALSE)
-  if(is.null(vars)) vars = paste0(var, items)
+    stop("Please specify either `vars` or `var` + `items`. To specify `varrange`, please use `MEAN()`.", call.=FALSE)
+  if(is.null(vars)) vars = paste_var_items(var, items)
   if(!is.null(rev) & is.null(range))
     stop("Please also specify the `range` argument!", call.=FALSE)
   if(is.numeric(rev)) {
@@ -310,7 +334,7 @@ CONSEC = function(data,
 #'
 #' @examples
 #' # ?psych::bfi
-#' data = psych::bfi
+#' \donttest{data = psych::bfi
 #' Alpha(data, "E", 1:5)   # "E1" & "E2" should be reversed
 #' Alpha(data, "E", 1:5, rev=1:2)            # correct
 #' Alpha(data, "E", 1:5, rev=cc("E1, E2"))   # also correct
@@ -320,7 +344,7 @@ CONSEC = function(data,
 #' # using dplyr::select()
 #' data %>% select(E1, E2, E3, E4, E5) %>%
 #'   Alpha(vars=names(.), rev=cc("E1, E2"))
-#'
+#' }
 #' @seealso
 #' \code{\link{MEAN}}, \code{\link{EFA}}, \code{\link{CFA}}
 #'
@@ -334,7 +358,7 @@ Alpha = function(
     varrange = gsub(" ", "", strsplit(varrange, ":")[[1]])
     vars = dn[which(dn==varrange[1]):which(dn==varrange[2])]
   }
-  if(is.null(vars)) vars = paste0(var, items)
+  if(is.null(vars)) vars = paste_var_items(var, items)
   if(is.numeric(rev)) rev = paste0(var, rev)
   n.total = nrow(data)
   data = na.omit(as.data.frame(data)[vars])
@@ -486,7 +510,7 @@ Alpha = function(
 #' \code{\link{MEAN}}, \code{\link{Alpha}}, \code{\link{CFA}}
 #'
 #' @examples
-#' data = psych::bfi
+#' \donttest{data = psych::bfi
 #' EFA(data, "E", 1:5)              # var + items
 #' EFA(data, "E", 1:5, nfactors=2)  # var + items
 #'
@@ -504,7 +528,7 @@ Alpha = function(
 #'       rotation="varimax",  # default
 #'       nfactors="parallel", # parallel analysis
 #'       hide.loadings=0.45)  # hide loadings < 0.45
-#'
+#' }
 #' @export
 EFA = function(
     data, var, items, vars=NULL, varrange=NULL, rev=NULL,
@@ -526,7 +550,7 @@ EFA = function(
     varrange = gsub(" ", "", strsplit(varrange, ":")[[1]])
     vars = dn[which(dn==varrange[1]):which(dn==varrange[2])]
   }
-  if(is.null(vars)) vars = paste0(var, items)
+  if(is.null(vars)) vars = paste_var_items(var, items)
   if(is.numeric(rev)) rev = paste0(var, rev)
   n.total = nrow(data)
   data = na.omit(as.data.frame(data)[vars])

R/bruceR-stats_3_manova.R

@@ -236,7 +236,7 @@ fix_long_data = function(data.long, ivs) {
 #'
 #' @examples
 #' #### Between-Subjects Design ####
-#'
+#' \donttest{
 #' between.1
 #' MANOVA(between.1, dv="SCORE", between="A")
 #'
@@ -281,7 +281,7 @@ fix_long_data = function(data.long, ivs) {
 #' MANOVA(mixed.2_1b1w, dvs="B1:B3", dvs.pattern="B(.)",
 #'        between="A", within="B", sph.correction="GG")
 #'
-#' \donttest{mixed.3_1b2w
+#' mixed.3_1b2w
 #' MANOVA(mixed.3_1b2w, dvs="B1C1:B2C2", dvs.pattern="B(.)C(.)",
 #'        between="A", within=c("B", "C"))
 #'
@@ -724,24 +724,24 @@ MANOVA = function(
 #'
 #' @examples
 #' #### Between-Subjects Design ####
-#'
+#' \donttest{
 #' between.1
 #' MANOVA(between.1, dv="SCORE", between="A") %>%
 #'   EMMEANS("A")
-#' \donttest{MANOVA(between.1, dv="SCORE", between="A") %>%
+#' MANOVA(between.1, dv="SCORE", between="A") %>%
 #'   EMMEANS("A", p.adjust="tukey")
 #' MANOVA(between.1, dv="SCORE", between="A") %>%
 #'   EMMEANS("A", contrast="seq")
 #' MANOVA(between.1, dv="SCORE", between="A") %>%
 #'   EMMEANS("A", contrast="poly")
-#' }
+#'
 #' between.2
 #' MANOVA(between.2, dv="SCORE", between=c("A", "B")) %>%
 #'   EMMEANS("A", by="B") %>%
 #'   EMMEANS("B", by="A")
 #' ## How to create an interaction plot using `emmeans::emmip()`?
 #' ## See help page: ?emmeans::emmip()
-#' \donttest{m = MANOVA(between.2, dv="SCORE", between=c("A", "B"))
+#' m = MANOVA(between.2, dv="SCORE", between=c("A", "B"))
 #' emmip(m, ~ A | B, CIs=TRUE)
 #' emmip(m, ~ B | A, CIs=TRUE)
 #' emmip(m, B ~ A, CIs=TRUE)
@@ -754,7 +754,7 @@ MANOVA = function(
 #'   EMMEANS("A", by=c("B", "C"))
 #' ## Just to name a few...
 #' ## You may test other combinations...
-#' }
+#'
 #'
 #' #### Within-Subjects Design ####
 #'
@@ -763,7 +763,7 @@ MANOVA = function(
 #'        within="A") %>%
 #'   EMMEANS("A")
 #'
-#' \donttest{within.2
+#' within.2
 #' MANOVA(within.2, dvs="A1B1:A2B3", dvs.pattern="A(.)B(.)",
 #'        within=c("A", "B")) %>%
 #'   EMMEANS("A", by="B") %>%
@@ -781,7 +781,7 @@ MANOVA = function(
 #'   EMMEANS("A", by=c("B", "C"))
 #' ## Just to name a few...
 #' ## You may test other combinations...
-#' }
+#'
 #'
 #' #### Mixed Design ####
 #'
@@ -791,7 +791,7 @@ MANOVA = function(
 #'   EMMEANS("A", by="B") %>%
 #'   EMMEANS("B", by="A")
 #'
-#' \donttest{mixed.3_1b2w
+#' mixed.3_1b2w
 #' MANOVA(mixed.3_1b2w, dvs="B1C1:B2C2", dvs.pattern="B(.)C(.)",
 #'        between="A", within=c("B", "C")) %>%
 #'   EMMEANS("A", by="B") %>%

R/bruceR-stats_4_regress.R

@@ -278,7 +278,7 @@ regress = function(
 #' \code{\link{PROCESS}}
 #'
 #' @examples
-#' #### Example 1: Linear Model ####
+#' \donttest{#### Example 1: Linear Model ####
 #' lm1 = lm(Temp ~ Month + Day, data=airquality)
 #' lm2 = lm(Temp ~ Month + Day + Wind + Solar.R, data=airquality)
 #' model_summary(lm1)
@@ -326,7 +326,7 @@ regress = function(
 #' model_summary(mn2)
 #' model_summary(mn2, file="Multinomial Logistic Model.doc")
 #' unlink("Multinomial Logistic Model.doc")  # delete file for code check
-#'
+#' }
 #' @export
 model_summary = function(
     model.list,
@@ -558,7 +558,7 @@ model_summary = function(
 #' @return No return value.
 #'
 #' @examples
-#' ## Example 1: OLS regression
+#' \donttest{## Example 1: OLS regression
 #' lm = lm(Temp ~ Month + Day + Wind + Solar.R, data=airquality)
 #' GLM_summary(lm)
 #' GLM_summary(lm, robust="HC1")
@@ -570,7 +570,7 @@ model_summary = function(
 #'           data=infert, family=binomial)
 #' GLM_summary(glm)
 #' GLM_summary(glm, robust="HC1", cluster="stratum")
-#'
+#' }
 #' @seealso
 #' \code{\link{print_table}} (print simple table)
 #'
@@ -835,7 +835,7 @@ HLM_ICC = function(model, digits=3) {
 #' @return No return value.
 #'
 #' @examples
-#' library(lmerTest)
+#' \donttest{library(lmerTest)
 #'
 #' ## Example 1: data from lme4::sleepstudy
 #' # (1) 'Subject' is a grouping/clustering variable
@@ -858,7 +858,7 @@ HLM_ICC = function(model, digits=3) {
 #'                (Sweetness | Consumer) + (1 | Product), data=carrots)
 #' HLM_summary(hlm.1)
 #' HLM_summary(hlm.2)
-#'
+#' }
 #' @references
 #' Hox, J. J. (2010).
 #' \emph{Multilevel analysis: Techniques and applications} (2nd ed.).
@@ -1181,7 +1181,7 @@ HLM_summary = function(
 #' \href{https://CRAN.R-project.org/package=multilevel}{R package "multilevel"}
 #'
 #' @examples
-#' data = lme4::sleepstudy  # continuous variable
+#' \donttest{data = lme4::sleepstudy  # continuous variable
 #' HLM_ICC_rWG(data, group="Subject", icc.var="Reaction")
 #'
 #' data = lmerTest::carrots  # 7-point scale
@@ -1191,7 +1191,7 @@ HLM_summary = function(
 #' HLM_ICC_rWG(data, group="Consumer", icc.var="Preference",
 #'             rwg.vars=c("Sweetness", "Bitter", "Crisp"),
 #'             rwg.levels=7)
-#'
+#' }
 #' @export
 HLM_ICC_rWG = function(data, group, icc.var,
                        rwg.vars=icc.var,