Rename 'split.data.by.bins' to 'split.datafame.by.bins'

This renaming makes sense as the method only splits dataframes. Rename
'split.data.by.bins.vector' to 'split.data.by.bins' as it is more readable
and easier to understand.

This works towards #239.

Signed-off-by: Maximilian Löffler <[email protected]>

tests/test-split-misc.R

@@ -42,10 +42,10 @@ if (!dir.exists(CF.DATA)) CF.DATA = file.path(".", "tests", "codeface-data")
 ## Split raw data (data and networks by bins) ------------------------------
 
 ##
-## Tests for split.data.by.bins and split.network.by.bins
+## Tests for split.dataframe.by.bins and split.network.by.bins
 ##
 
-test_that("Split network and data on low level (split.data.by.bins, split.network.by.bins).", {
+test_that("Split network and data on low level (split.dataframe.by.bins, split.network.by.bins).", {
 
     length.dates = 15
     length.bins = 5
@@ -69,7 +69,7 @@ test_that("Split network and data on low level (split.data.by.bins, split.networ
     ## sprintf("c(\"%s\")", paste( sample(bins, size = length.dates, replace = TRUE), collapse = "', '") )
 
     ##
-    ## split.data.by.bins
+    ## split.dataframe.by.bins
     ##
 
     ## generate data frame with dates and IDs
@@ -86,7 +86,7 @@ test_that("Split network and data on low level (split.data.by.bins, split.networ
         "4" = df[ c(4, 11, 13), ],
         "5" = df[ c(3, 10, 15), ]
     )
-    results = split.data.by.bins(df, bins.vector)
+    results = split.dataframe.by.bins(df, bins.vector)
 
     ## check result
     expect_equal(results, expected, info = "Split data by bins.")

util-misc.R

@@ -998,7 +998,7 @@ get.data.from.range = function(range, data) {
 
     ## split data by this bin; this gives a list of three data frames, "0" contains the data before the range, "1" the
     ## data within the range and "2" the holds the data after the range
-    split.data = split.data.by.bins(data, df.bins)
+    split.data = split.dataframe.by.bins(data, df.bins)
 
     ## look for the element with name "1", as we are interested in the data within the range
     ## if there is no data, return an empty data frame corresponding to the data we want to cut

util-split.R

@@ -83,7 +83,7 @@ split.data.time.based = function(project.data, time.period = "3 months", bins =
 #' @return the list of RangeData objects, each referring to one bin
 #'
 #' @seealso split.get.bins.activity.based
-split.data.by.bins.vector = function(project.data, activity.amount, bins, split.basis = c("commits", "mails", "issues"),
+split.data.by.bins = function(project.data, activity.amount, bins, split.basis = c("commits", "mails", "issues"),
                                      sliding.window) {
     split = split.data.by.time.or.bins(project.data, activity.amount, bins, split.by.time = FALSE,
                                         sliding.window = sliding.window, split.basis = split.basis)
@@ -94,9 +94,9 @@ split.data.by.bins.vector = function(project.data, activity.amount, bins, split.
 #'
 #' @param project.data the *Data object from which the data is retrieved
 #' @param splitting.length either \code{time.period} from \code{split.data.time.based}
-#'                         or \code{activity.amount} from\code{split.data.by.bins.vector}
+#'                         or \code{activity.amount} from\code{split.data.by.bins}
 #' @param bins either formatted as the \code{bins} parameter of \code{split.data.time.based}
-#'             or as the \code{bins} parameter of \code{split.data.by.bins.vector}
+#'             or as the \code{bins} parameter of \code{split.data.by.bins}
 #' @param split.by.time logical indicating whether splitting is done time-based or activity-bins-based
 #' @param number.windows see \code{number.windows} from \code{split.data.time.by.bins.vector}
 #'                       [default: NULL]
@@ -111,7 +111,7 @@ split.data.by.bins.vector = function(project.data, activity.amount, bins, split.
 #' @return the list of RangeData objects, each referring to one time period
 #'
 #' @seealso split.data.time.based
-#' @seealso split.data.by.bins.vector
+#' @seealso split.data.by.bins
 split.data.by.time.or.bins = function(project.data, splitting.length, bins, split.by.time,
                                       number.windows = NULL, split.basis = c("commits", "mails", "issues"),
                                       sliding.window = FALSE, project.conf.new = NULL) {
@@ -435,7 +435,7 @@ split.data.activity.based = function(project.data, activity.type = c("commits",
 
     ## split the data based on the extracted timestamps
     logging::logdebug("Splitting data based on time windows arising from activity bins.")
-    cf.data = split.data.by.bins.vector(project.data, bins = bins.data, activity.amount = activity.amount,
+    cf.data = split.data.by.bins(project.data, bins = bins.data, activity.amount = activity.amount,
                                      sliding.window = sliding.window, split.basis = activity.type)
 
     ## perform additional steps for sliding-window approach:
@@ -1015,16 +1015,16 @@ split.network.time.based.by.ranges = function(network, ranges, remove.isolates =
 ## / / / / / / / / / / / / / / / / / / / / / / / / / / / / / / / / / / / / /
 ## Split raw data ----------------------------------------------------------
 
-#' Split the given data by the given bins.
+#' Split the given datafame by the given bins.
 #'
 #' @param df a data.frame to be split
 #' @param bins a vector with the length of 'nrow(df)' assigning a bin for each row of 'df'
 #'
 #' @return a list of data.frames, with the length of 'unique(bins)'
-split.data.by.bins = function(df, bins) {
-    logging::logdebug("split.data.by.bins: starting.")
+split.dataframe.by.bins = function(df, bins) {
+    logging::logdebug("split.dataframe.by.bins: starting.")
     df.split = split(df, bins)
-    logging::logdebug("split.data.by.bins: finished.")
+    logging::logdebug("split.dataframe.by.bins: finished.")
     return(df.split)
 }