minor changes

cbhurley · Aug 2, 2024 · bd35e56 · bd35e56
1 parent 6c856e3
commit bd35e56
Show file tree

Hide file tree

Showing 17 changed files with 40 additions and 36 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -5,7 +5,8 @@ Authors@R:
     c(person(given = "Amit", family = "Chinwan", email = "amit.chinwan.2019@mumail.ie", role = c("aut")),
     person(given = "Catherine", family = "Hurley", email = "catherine.hurley@mu.ie", role = c("aut", "cre")))
 Description: We provide a tidy data structure and visualisations for multiple or grouped  variable correlations, 
-    general association measures and other pairwise scores  suitable for numerical, ordinal and nominal variables.
+    general association measures scagnostics and other pairwise scores  suitable for numerical, ordinal and nominal variables. 
+    Supported measures include distance correlation, maximal information, ace correlation, Kendall's tau, and polychoric corrrelation.
 License: MIT + file LICENSE
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)

diff --git a/NAMESPACE b/NAMESPACE
@@ -17,7 +17,6 @@ export(pair_gkGamma)
 export(pair_gkTau)
 export(pair_methods)
 export(pair_mine)
-export(pair_multi)
 export(pair_nmi)
 export(pair_polychor)
 export(pair_polyserial)
@@ -26,6 +25,7 @@ export(pair_tau)
 export(pair_uncertainty)
 export(pairwise)
 export(pairwise_by)
+export(pairwise_multi)
 export(pairwise_scores)
 export(plot_pairwise)
 export(plot_pairwise_linear)

diff --git a/R/pair_methods.R b/R/pair_methods.R
@@ -401,7 +401,7 @@ pair_uncertainty <- function(d,handle.na=TRUE,...){
 #' @return A tibble of class `pairwise` with Goodman Kruskal's Tau for every factor variable pair,
 #' or NULL if there are not at least two factor variables
 #' @details The Goodman Kruskal's Tau coefficient is calculated using \code{\link[DescTools]{GoodmanKruskalTau}}
-#' function from the \code{DescTools} package, and assumes factor levels are in the given order.
+#' function from the \code{DescTools} package.
 #' @export
 #'
 #' @examples
@@ -586,7 +586,7 @@ pair_methods <- dplyr::tribble(
   "pair_polyserial", FALSE, FALSE, TRUE, "polycor::polyserial", "[-1,1]","factor treated as ordinal",
   "pair_tau", FALSE, TRUE, FALSE, "DescTools::KendalTauA,B,C,W", "[-1,1]","factors treated as ordinal",
   "pair_gkGamma", FALSE,  TRUE, FALSE, "DescTools::GoodmanKruskalGamma", "[-1,1]","factors treated as ordinal",
-  "pair_gkTau", FALSE,  TRUE, FALSE, "DescTools::GoodmanKruskalTau", "[0,1]","factors treated as ordinal",
+  "pair_gkTau", FALSE,  TRUE, FALSE, "DescTools::GoodmanKruskalTau", "[0,1]","",
   "pair_uncertainty", FALSE,  TRUE, FALSE, "DescTools::UncertCoef", "[0,1]","",
   "pair_chi", FALSE,  TRUE,  FALSE, "DescTools::ContCoef", "[0,1]","",
   "pair_scag", TRUE, FALSE,  FALSE, "scagnostics::scagnostics", "[0,1]","",

diff --git a/R/pairwise.R b/R/pairwise.R
@@ -3,7 +3,7 @@
 #' Creates a data structure for every variable pair in a dataset.
 #'
 #' @param x A dataframe or symmetric matrix.
-#' @param score a character string indicating the value of association.
+#' @param score a character string indicating the value of association, either "nn", "fn", "ff".
 #' @param pair_type a character string specifying the type of variable pair.
 #' @return A tbl_df of class `pairwise` for pairs of variables with a column `value` for the score value,
 #' `score` for a type of association value and `pair_type` for the type of variable pair.
@@ -39,7 +39,7 @@ pairwise.matrix <- function(x, score=NA_character_, pair_type=NA_character_){
   m <- x
   if (!isSymmetric(m))
     stop("Input must be a symmetric matrix")
-
+ 
   xindex <- as.vector(row(m))
   yindex <- as.vector(col(m))
   rnames <- rownames(m) %||% paste0("V", seq_along(xindex))

diff --git a/R/pair_multi.R → R/pairwise_multi.R b/R/pair_multi.R → R/pairwise_multi.R
@@ -15,10 +15,10 @@
 #' @examples
 #' iris1 <- iris
 #' iris1$Sepal.Length <- cut(iris1$Sepal.Length,3)
-#' pair_multi(iris1)
+#' pairwise_multi(iris1)
 
 
-pair_multi <- function(d,scores=c("pair_cor", "pair_dcor","pair_mine","pair_ace",
+pairwise_multi <- function(d,scores=c("pair_cor", "pair_dcor","pair_mine","pair_ace",
                                     "pair_cancor","pair_nmi","pair_uncertainty",
                                     "pair_chi"),
                          handle.na=T) {

diff --git a/R/pairwise_scores.R b/R/pairwise_scores.R
@@ -24,14 +24,15 @@
 #' irisc <- pairwise_scores(iris, control=pair_control(fn="pair_ace"))
 #'
 #' #Lots of numerical measures
-#' irisc <- pairwise_scores(iris, control=pair_control(nn="pair_multi", fn=NULL))
-#' irisc <- pairwise_scores(iris, control=pair_control(nn="pair_multi", nnargs="pair_cor", fn=NULL))
+#' irisc <- pairwise_scores(iris, control=pair_control(nn="pairwise_multi", fn=NULL))
+#' irisc <- pairwise_scores(iris, 
+#'              control=pair_control(nn="pairwise_multi",  nnargs="pair_cor", fn=NULL))
 
 #' #conditional measures
 #' cond_iris <- pairwise_scores(iris, by = "Species") 
 #' cond_iris_wo <- pairwise_scores(iris, by = "Species",ungrouped=FALSE) # without overall
-#' irisc <- pairwise_scores(iris, control=pair_control(nn="pair_multi", fn=NULL))
-#' irisc <- pairwise_scores(iris, by = "Species",control=pair_control(nn="pair_multi", fn=NULL))
+#' irisc <- pairwise_scores(iris, control=pair_control(nn="pairwise_multi", fn=NULL))
+#' irisc <- pairwise_scores(iris, by = "Species",control=pair_control(nn="pairwise_multi", fn=NULL))
 #'
 #' #scagnostics
 #' sc <- pairwise_scores(iris, control=pair_control(nn="pair_scagnostics", fn=NULL)) # ignore fn pairs

diff --git a/R/plot_pairwise.R b/R/plot_pairwise.R
@@ -169,7 +169,7 @@ plot_pairwise_prep <- function(scores, score_limits=NULL, var_order=NULL, ignore
 #' @examples
 #' plot_pairwise_linear(pairwise_scores(iris))
 #' plot_pairwise_linear(pairwise_scores(iris,by="Species"))
-#' plot_pairwise_linear(pair_multi(iris), geom="point")
+#' plot_pairwise_linear(pairwise_multi(iris), geom="point")
 #' @export
 #' 
 

diff --git a/man/bullseye-package.Rd b/man/bullseye-package.Rd
diff --git a/man/pair_gkTau.Rd b/man/pair_gkTau.Rd
diff --git a/man/pairwise.Rd b/man/pairwise.Rd
diff --git a/man/pair_multi.Rd → man/pairwise_multi.Rd b/man/pair_multi.Rd → man/pairwise_multi.Rd
diff --git a/man/pairwise_scores.Rd b/man/pairwise_scores.Rd
diff --git a/man/plot_pairwise_linear.Rd b/man/plot_pairwise_linear.Rd
diff --git a/tests/testthat/test-pair_methods.R b/tests/testthat/test-pair_methods.R
@@ -97,7 +97,7 @@ test_that("pair ace", {
 
 
 test_that("pair multi", {
-  p <- pair_multi(iris)
+  p <- pairwise_multi(iris)
   expect_s3_class(p, "pairwise")
   expect_identical(dim(p), c(54L,6L))
 })

diff --git a/vignettes/calc_pairwise.Rmd b/vignettes/calc_pairwise.Rmd
@@ -14,7 +14,7 @@ knitr::opts_chunk$set(
 )
 ```
 
-`bullseye` is an R package which calculates measures of association and other scores for pairs of variables in a dataset and helps in visualising these measures in different layouts. The package also calculates and visualises the pairwise measures for different levels of a grouping variable. 
+`bullseye` is an R package which calculates measures of correlation and other association scores for pairs of variables in a dataset and offers visualisations of these measures in different layouts. The package also calculates and visualises the pairwise scores for different levels of a grouping variable. 
 
 This vignette gives an overview of how these pairwise variable measures  are calculated. Visualisations of these calculated measures are provided in the accompanying vignette.  
 
@@ -81,14 +81,14 @@ If you want for instance to compare distance correlation and mutual information
 bind_rows(sc_dcor, sc_nmi) |> arrange(x,y)
 ```
 
-We provide another function `pair_multi` which calculates multiple association measures for every variable pair in a dataset.
+We provide another function `pairwise_multi` which calculates multiple association measures for every variable pair in a dataset.
 By default this function combines the results of `pair_cor`, `pair_dcor`,`pair_mine`,`pair_ace`,
                                     `pair_cancor`,`pair_nmi`,`pair_uncertainty`,
                                     `pair_chi`, but any subset of the `pair_` functions may be supplied as an argument, as in the second example below.
 
 ```{r}
-pair_multi(penguins)
-dcor_nmi <- pair_multi(penguins, c("pair_dcor", "pair_nmi"))
+pairwise_multi(penguins)
+dcor_nmi <- pairwise_multi(penguins, c("pair_dcor", "pair_nmi"))
 ```
 
 
@@ -115,7 +115,7 @@ sc_sex |> distinct(group)
 If you want to calculate different scores to the default, specify this via the `control` argument:
 
 ```{r}
-pc <- pair_control(nn="pair_multi", nnargs= c("pair_dcor", "pair_ace"), fn=NULL, ff=NULL)
+pc <- pair_control(nn="pairwise_multi", nnargs= c("pair_dcor", "pair_ace"), fn=NULL, ff=NULL)
 sc_sex <- pairwise_scores(penguins, by="species", control=pc, ungrouped=FALSE) 
 ```
 

diff --git a/vignettes/integrating.Rmd b/vignettes/integrating.Rmd
@@ -85,8 +85,9 @@ plot(as.pairwise(sc_cor))
 
 Multiple measures from `correlation` can also be used:
 ```{r}
-sc_multi<- bind_rows(as.pairwise(correlation::correlation(peng, method = "pearson")),
-                              as.pairwise(correlation::correlation(peng, method = "blomqvist")),
-                              as.pairwise(correlation::correlation(peng, method = "biweight")))
+sc_multi<- bind_rows(
+  as.pairwise(correlation::correlation(peng, method = "pearson")),
+  as.pairwise(correlation::correlation(peng, method = "blomqvist")),
+  as.pairwise(correlation::correlation(peng, method = "biweight")))
 plot(sc_multi)
 ```
diff --git a/vignettes/vis_pairwise.Rmd b/vignettes/vis_pairwise.Rmd
@@ -176,7 +176,7 @@ kableExtra::kbl(df, booktabs = T, caption = "Variable description of the acs12 d
 ```{r}
 acs12 <- openintro::acs12
 
-scores <- pair_multi(acs12)
+scores <- pairwise_multi(acs12)
 ```
 The `scores` contains various pairwise measures for the 78 variable pairs. Many of the scores will be low,
 so we pick out the pairs with a score of .25 or above to display: