ggcorrmat legend changed to account for NAs; CRAN resubmission 0.0.6

IndrajeetPatil · Sep 30, 2018 · cb87614 · cb87614
1 parent 9772657
commit cb87614
Show file tree

Hide file tree

Showing 49 changed files with 595 additions and 141 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -1,3 +1,5 @@
+^Meta$
+^doc$
 ^.*\.Rproj$
 ^\.Rproj\.user$
 ^README\.Rmd$

diff --git a/.gitignore b/.gitignore
@@ -1,49 +1,41 @@
+Meta
+doc
 # Windows image file caches
 Thumbs.db
 ehthumbs.db
 
 # Folder config file
 Desktop.ini
-
 # Recycle Bin used on file shares
 $RECYCLE.BIN/
-
 # Windows Installer files
 *.cab
 *.msi
 *.msm
 *.msp
-
 # Windows shortcuts
 *.lnk
-
 # =========================
-
 # Operating System Files
-
 # OSX
 .DS_Store
 .AppleDouble
 .LSOverride
-
 # Thumbnails
 ._*
-
 # Files that might appear in the root of a volume
 .DocumentRevisions-V100
 .fseventsd
 .Spotlight-V100
 .TemporaryItems
 .Trashes
 .VolumeIcon.icns
-
 # Directories potentially created on remote AFP share
 .AppleDB
 .AppleDesktop
 Network Trash Folder
 Temporary Items
 .apdisk
-
 # R Studio files
 .Rproj.user
 .Rhistory

diff --git a/CRAN-RELEASE b/CRAN-RELEASE
@@ -1,2 +1,2 @@
-This package was submitted to CRAN on 2018-09-26.
-Once it is accepted, delete this file and tag the release (commit e50fcf3def).
+This package was submitted to CRAN on 2018-09-30.
+Once it is accepted, delete this file and tag the release (commit 9772657f8b).
diff --git a/NAMESPACE b/NAMESPACE
@@ -69,6 +69,7 @@ importFrom(dplyr,mutate_at)
 importFrom(dplyr,mutate_if)
 importFrom(dplyr,n)
 importFrom(dplyr,select)
+importFrom(dplyr,select_if)
 importFrom(dplyr,summarize)
 importFrom(dplyr,vars)
 importFrom(effsize,cohen.d)
@@ -91,7 +92,9 @@ importFrom(paletteer,scale_fill_paletteer_d)
 importFrom(psych,cohen.d.ci)
 importFrom(psych,corr.p)
 importFrom(psych,corr.test)
+importFrom(purrr,flatten_dbl)
 importFrom(purrr,is_bare_double)
+importFrom(purrr,is_bare_numeric)
 importFrom(purrr,map)
 importFrom(purrr,map_dfr)
 importFrom(purrr,set_names)
@@ -111,6 +114,7 @@ importFrom(stats,cor)
 importFrom(stats,cor.test)
 importFrom(stats,kruskal.test)
 importFrom(stats,lm)
+importFrom(stats,median)
 importFrom(stats,na.omit)
 importFrom(stats,oneway.test)
 importFrom(stats,qt)
@@ -120,6 +124,7 @@ importFrom(stats,shapiro.test)
 importFrom(stats,t.test)
 importFrom(stats,var.test)
 importFrom(stats,wilcox.test)
+importFrom(tibble,as.tibble)
 importFrom(tibble,as_data_frame)
 importFrom(tibble,rowid_to_column)
 importFrom(tibble,rownames_to_column)

diff --git a/R/ggbetweenstats.R b/R/ggbetweenstats.R
@@ -144,10 +144,10 @@
 #' \url{https://cran.r-project.org/package=ggstatsplot/vignettes/ggbetweenstats.html}
 #'
 #' @examples
-#'
+#' 
 #' # to get reproducible results from bootstrapping
 #' set.seed(123)
-#'
+#' 
 #' # simple function call with the defaults
 #' ggstatsplot::ggbetweenstats(
 #'   data = mtcars,
@@ -157,7 +157,7 @@
 #'   caption = "Transmission (0 = automatic, 1 = manual)",
 #'   bf.message = TRUE
 #' )
-#'
+#' 
 #' # more detailed function call
 #' ggstatsplot::ggbetweenstats(
 #'   data = datasets::morley,

diff --git a/R/ggcorrmat.R b/R/ggcorrmat.R
@@ -15,7 +15,9 @@
 #'   `"plot"` (for visualization matrix) or `"correlations"` (or `"corr"` or
 #'   `"r"`; for correlation matrix) or `"p-values"` (or `"p.values"` or `"p"`;
 #'   for a matrix of *p*-values) or `"ci"` (for a tibble with confidence
-#'   intervals for unique correlation pairs; not available for robust correlation).
+#'   intervals for unique correlation pairs; not available for robust
+#'   correlation) or `"n"` (or `"sample.size"` for a tibble with sample sizes
+#'   for each correlation pair).
 #' @param matrix.type Character, `"full"` (default), `"upper"` or `"lower"`, display
 #'   full matrix, lower triangular or upper triangular matrix.
 #' @param method Character argument that decides the visualization method of
@@ -118,6 +120,7 @@
 #' @importFrom WRS2 pball
 #' @importFrom psych corr.test
 #' @importFrom psych corr.p
+#' @importFrom purrr flatten_dbl
 #'
 #' @seealso \code{\link{grouped_ggcorrmat}} \code{\link{ggscatterstats}}
 #'   \code{\link{grouped_ggscatterstats}}
@@ -224,6 +227,12 @@ ggcorrmat <-
     df <- data %>%
       dplyr::select(.data = ., !!rlang::enquo(cor.vars))
 
+    # counting number of NAs present in the dataframe
+    na_total <- df %>%
+      purrr::map_df(.x = ., .f = ~sum(is.na(.))) %>%
+      purrr::flatten_dbl(.x = .) %>%
+      sum(., na.rm = TRUE)
+
     # renaming the columns if so desired (must be equal to the number of number of cor.vars)
     if (!is.null(cor.vars.names)) {
       # check if number of cor.vars is equal to the number of names entered
@@ -278,6 +287,13 @@ ggcorrmat <-
 
       # compute a correlation matrix of p-values
       p.mat <- corr_df$p
+
+      # in case of NAs, compute minimum and maximum sample sizes of pairs
+      if (na_total != 0) {
+
+        # dataframe with minimum, median, and maximum sample sizes
+        n_summary <- numdf_n_summary(df = corr_df$n)
+      }
     } else if (corr.method == "robust") {
 
       # this is just get a matrix of samples sizes to be used `n` argument in
@@ -291,6 +307,14 @@ ggcorrmat <-
         ci = FALSE
       )
 
+      # in case of NAs, compute minimum, median, and maximum sample sizes of
+      # pairs
+      if (na_total != 0) {
+
+        # dataframe with minimum, median, and maximum sample sizes
+        n_summary <- numdf_n_summary(df = n_df$n)
+      }
+
       # computing the percentage bend correlation matrix
       rob_cor <- WRS2::pball(x = df, beta = beta)
 
@@ -331,6 +355,41 @@ ggcorrmat <-
     # creating the basic plot
     if (output == "plot") {
       if (corr.method %in% c("pearson", "spearman", "kendall", "robust")) {
+
+        # legend title with information about correlation type and sample
+        if (na_total == 0) {
+          legend.title.text <-
+            bquote(atop(
+              atop(
+                bold("sample size:"),
+                italic(n) ~ "=" ~ .(nrow(x = data))
+              ),
+              atop(
+                bold("correlation:"),
+                .(corr.method)
+              )
+            ))
+        } else {
+          legend.title.text <-
+            bquote(atop(
+              atop(
+                atop(
+                  bold("sample size:"),
+                  italic(n)[min] ~ "=" ~ .(n_summary$n_min[[1]])
+                ),
+                atop(
+                  italic(n)[median] ~ "=" ~ .(n_summary$n_median[[1]]),
+                  italic(n)[max] ~ "=" ~ .(n_summary$n_max[[1]])
+                )
+              ),
+              atop(
+                bold("correlation:"),
+                .(corr.method)
+              )
+            ))
+        }
+
+
         # plotting the correlalogram
         plot <- ggcorrplot::ggcorrplot(
           corr = corr.mat,
@@ -344,7 +403,7 @@ ggcorrmat <-
           outline.color = outline.color,
           ggtheme = ggtheme,
           colors = colors,
-          legend.title = paste("n = ", nrow(x = data), "\n", corr.method, sep = ""),
+          legend.title = legend.title.text,
           lab_col = lab.col,
           lab_size = lab.size,
           insig = insig,
@@ -460,14 +519,32 @@ ggcorrmat <-
 
       # return the tibble
       return(corr.mat)
+    } else if (output %in% c("n", "sample.size")) {
+      if (corr.method %in% c("pearson", "spearman", "kendall")) {
+        # sample size matrix
+        sample_size_df <- corr_df$n %>%
+          base::as.data.frame(x = .) %>%
+          tibble::rownames_to_column(., var = "variable") %>%
+          tibble::as_data_frame(x = .)
+
+        return(sample_size_df)
+      } else {
+        # sample size matrix
+        sample_size_df <- n_df$n %>%
+          base::as.data.frame(x = .) %>%
+          tibble::rownames_to_column(., var = "variable") %>%
+          tibble::as_data_frame(x = .)
+
+        return(sample_size_df)
+      }
     } else if (output %in% c("p-values", "p.values", "p")) {
 
       # if p-values were adjusted, notify how they are going to be displayed
       if (p.adjust.method != "none") {
         base::message(cat(
           crayon::green("Note: "),
           crayon::blue(
-            "In the correlation matrix, the upper triangle denotes p-values adjusted for multiple comparisons, while the lower triangle denotes unadjusted p-values.\n"
+            "In the correlation matrix, the upper triangle denotes p-values adjusted for multiple comparisons,\nwhile the lower triangle denotes unadjusted p-values.\n"
           ),
           sep = ""
         ))
@@ -500,7 +577,7 @@ ggcorrmat <-
         base::message(cat(
           crayon::red("Warning: "),
           crayon::blue(
-            "Confidence intervals for correlations are currently not available for robust correlation.\n"
+            "Confidence intervals are currently not available for robust correlations.\n"
           ),
           sep = ""
         ))
@@ -512,7 +589,7 @@ ggcorrmat <-
         base::message(cat(
           crayon::green("Note: "),
           crayon::blue(
-            "In the correlation matrix, the upper triangle is based on p-values adjusted for multiple comparisons, while the lower triangle is based on unadjusted p-values.\n"
+            "In the correlation matrix, the upper triangle is based on p-values adjusted for multiple comparisons,\nwhile the lower triangle is based on unadjusted p-values.\n"
           ),
           sep = ""
         ))