feat: make create_dist dynamic

Changes to underlying cut_hour()

R/create_dist.R

@@ -81,23 +81,22 @@ create_dist <- function(data,
   ## Create buckets of collaboration hours
   plot_data <-
     plot_data %>%
-    mutate(bucket_hours = cut_hour(!!sym(metric),
-                                          cuts = cut))
+    mutate(bucket_hours = cut_hour(!!sym(metric), cuts = cut))
 
   ## Employee count / base size table
   plot_legend <-
     plot_data %>%
     group_by(group) %>%
-    summarize(Employee_Count=first(Employee_Count)) %>%
+    summarize(Employee_Count = first(Employee_Count)) %>%
     mutate(Employee_Count = paste("n=",Employee_Count))
 
   ## Data for bar plot
   plot_table <-
     plot_data %>%
     group_by(group, bucket_hours) %>%
-    summarize(Employees=n(),
-              Employee_Count=first(Employee_Count),
-              percent= Employees / Employee_Count ) %>%
+    summarize(Employees = n(),
+              Employee_Count = first(Employee_Count),
+              percent = Employees / Employee_Count ) %>%
     arrange(group, desc(bucket_hours))
 
   ## Table for annotation

R/cut_hour.R

@@ -10,7 +10,7 @@
 #' and the function returns a character vector
 #'
 #' @param metric A numeric variable representing hours.
-#' @param cuts A numeric variable of length 3 to represent the
+#' @param cuts A numeric variable of minimum length 3 to represent the
 #' cut points required.
 #'
 #' @family General
@@ -27,22 +27,33 @@
 cut_hour <- function(metric, cuts){
 
 
-  label1 <- paste0("< ", cuts[1], " hours")
-  label2 <- paste0(cuts[1], " - ", cuts[2], " hours")
-  label3 <- paste0(cuts[2], " - ", cuts[3], " hours")
-  label4 <- paste0(cuts[3], "+ hours")
+  cuts <- unique(cuts) # No duplicates allowed
+  ncuts <- length(cuts)
 
-  out <-
-    cut(metric,
-        breaks = c(0, cuts, 100),
-        include.lowest = TRUE,
-        labels = c(label1,
-                   label2,
-                   label3,
-                   label4))
+  if(ncuts < 3){
+    stop("Please provide a numeric vector of at least length 3 to `cuts`")
+  }
 
-  # out <- as.character(out)
-  return(out)
+
+  # Extract min, max, and middle values
+  mincut <- min(cuts, na.rm = TRUE)
+  maxcut <- max(cuts, na.rm = TRUE)
+  midcut <- cuts[!cuts %in% mincut] # Excludes mincut only
+  midcut_min_1 <- cuts[match(midcut, cuts) - 1] # one value smaller
+
+  # Individual labels
+  label_mincut <- paste0("< ", mincut, " hours")
+  label_maxcut <- paste0(maxcut, "+ hours")
+  label_midcut <- paste0(midcut_min_1, " - ", midcut, " hours")
+
+  # All labels
+  all_labels <- c(label_mincut, label_midcut, label_maxcut)
+
+
+  cut(metric,
+      breaks = c(0, cuts, 100),
+      include.lowest = TRUE,
+      labels = all_labels)
 }
 
 

man/cut_hour.Rd

@@ -9,7 +9,7 @@ cut_hour(metric, cuts)
 \arguments{
 \item{metric}{A numeric variable representing hours.}
 
-\item{cuts}{A numeric variable of length 3 to represent the
+\item{cuts}{A numeric variable of minimum length 3 to represent the
 cut points required.}
 }
 \description{

man/validation_report.Rd

@@ -34,6 +34,15 @@ for the Analyst pre-analysis.
 For your input data or meeting_data, please use the function wpa::import_wpa()'
 to import your csv query files into R. This function will standardize format
 and prepare the data as input for this report.
+}
+\examples{
+\dontrun{
+validation_report(dv_data,
+                  meeting_data = mt_data,
+                  hrvar = "Organization")
+
+}
+
 }
 \seealso{
 Other Reports: