Calculate match success rate

NAMESPACE

@@ -1,13 +1,15 @@
 # Generated by roxygen2: do not edit by hand
 
 export("%>%")
+export(calculate_match_success_rate)
 export(crucial_lbk)
 export(match_name)
 export(prioritize)
 export(prioritize_level)
 importFrom(data.table,":=")
 importFrom(data.table,setDT)
 importFrom(data.table,setkey)
+importFrom(dplyr,"%>%")
 importFrom(dplyr,all_of)
 importFrom(dplyr,distinct)
 importFrom(dplyr,filter)

NEWS.md

@@ -1,5 +1,7 @@
 # r2dii.match (development version)
 
+* `calculate_match_success_rate()` added to facilitate analyzing the success rate of the matching process
+
 # r2dii.match 0.4.0
 
 * `data_dictionary` dataset added to define the columns in each dataset used or exported by the functions in this package

R/calculate_match_success_rate.R

@@ -0,0 +1,47 @@
+#' Calculate the success rate of the matching process
+#'
+#' @param matched A data frame like the validated output of [match_name()].
+#'
+#' @param loanbook A data frame structured like [r2dii.data::loanbook_demo].
+#'
+#' @return A data frame.
+#'
+#' @examples
+#' matched <- match_name(r2dii.data::loanbook_demo, r2dii.data::abcd_demo)
+#' calculate_match_success_rate(matched, r2dii.data::loanbook_demo)
+#'
+#' @family main functions
+#'
+#' @importFrom dplyr %>%
+#'
+#' @export
+
+calculate_match_success_rate <- function(matched, loanbook) {
+  merge_by <-
+    c(
+      sector_classification_system = "code_system",
+      sector_classification_direct_loantaker = "code"
+    )
+
+  loanbook_with_sectors <-
+    loanbook %>%
+    purrr::modify_at(names(merge_by), as.character) %>%
+    dplyr::left_join(r2dii.data::sector_classifications, by = merge_by)
+
+  by_cols <- names(matched)[names(matched) %in% names(loanbook_with_sectors)]
+
+  dplyr::left_join(loanbook_with_sectors, matched, by = by_cols) %>%
+    dplyr::mutate(
+      loan_size_outstanding = as.numeric(.data$loan_size_outstanding),
+      loan_size_credit_limit = as.numeric(.data$loan_size_credit_limit),
+      matched = dplyr::case_when(
+        score == 1   ~ "Matched",
+        is.na(score) ~ "Not Matched",
+        TRUE         ~ "Not Matched"
+      ),
+      sector = dplyr::case_when(
+        borderline == TRUE & matched == "Not Matched" ~ "not in scope",
+        TRUE ~ sector
+      )
+    )
+}

tests/testthat/test-calculate_match_success_rate.R

@@ -0,0 +1,14 @@
+test_that("returns expected output", {
+  loanbook <- fake_lbk(
+    name_direct_loantaker = c("Steckel GmbH", "XXX"),
+    sector_classification_direct_loantaker = c("C29.1", "C29.1"),
+    loan_size_outstanding = c(1e6, 1e6),
+    loan_size_credit_limit = c(1e7, 1e7)
+  )
+  matched <- match_name(loanbook = loanbook, abcd = r2dii.data::abcd_demo)
+  out <- calculate_match_success_rate(matched = matched, loanbook = loanbook)
+
+  expect_s3_class(object = out, class = "data.frame")
+  expect_contains(object = names(out), expected = "matched")
+  expect_identical(object = out$matched, expected = c("Matched", "Not Matched"))
+})