Merge pull request #171 from ESHackathon/asysd_fixes

As discussed

R/count.R

@@ -112,25 +112,24 @@ record_counts <- function(unique_citations, citations, db_colname) {
 #'
 #' @return A dataframe with counts of distinct records, imported records, and unique records for each source, including total counts and several calculated ratios and percentages.
 #' @examples
-# unique_citations <- data.frame(
-#   db_source = c("Database1", "Database1", "Database2", "Database3", "Database3", "Database3"),
-#   other_data = 1:6
-# )
-# 
-# citations <- data.frame(
-#   db_source = c("Database1", "Database1", "Database1", "Database2", "Database2", "Database3"),
-#   other_data = 7:12
-# )
-# 
-# n_unique <- data.frame(
-#   cite_source = c("Database1", "Database2", "Database2", "Database3", "Database3", "Database3"),
-#   cite_label = c("search", "final", "search", "search", "search", "final"),
-#   unique = c(1, 0, 1, 1, 1, 0)
-# )
-# 
-# result <- calculate_record_counts(unique_citations, citations, n_unique, "db_source")
-# result
-
+#' unique_citations <- data.frame(
+#'   db_source = c("Database1", "Database1", "Database2", "Database3", "Database3", "Database3"),
+#'   other_data = 1:6
+#' )
+#' 
+#' citations <- data.frame(
+#'   db_source = c("Database1", "Database1", "Database1", "Database2", "Database2", "Database3"),
+#'   other_data = 7:12
+#' )
+#'
+#' n_unique <- data.frame(
+#'   cite_source = c("Database1", "Database2", "Database2", "Database3", "Database3", "Database3"),
+#'  cite_label = c("search", "final", "search", "search", "search", "final"),
+#'   unique = c(1, 0, 1, 1, 1, 0)
+#' )
+#' 
+#' result <- calculate_record_counts(unique_citations, citations, n_unique, "db_source")
+#' print(result)
 
 calculate_record_counts <- function(unique_citations, citations, n_unique, db_colname) {
 
@@ -222,21 +221,21 @@ calculate_record_counts <- function(unique_citations, citations, n_unique, db_co
 #' and recall for each source, as well as totals.
 #'
 #' @examples
-# unique_citations <- data.frame(
-#   db_source = c("Database1", "Database1", "Database2", "Database3", "Database3", "Database3"),
-#   cite_label = c("screened", "final", "screened", "final", "screened", "final"),
-#   duplicate_id = c(102, 102, 103, 103, 104, 104),
-#   other_data = 1:6
-# )
-# 
-# citations <- data.frame(
-#   db_source = c("Database1", "Database1", "Database1", "Database2", "Database2", "Database3"),
-#   cite_label = c("screened", "final", "screened", "final", "screened", "final"),
-#   other_data = 7:12
-# )
-# 
-# result <- calculate_phase_count(unique_citations, citations, "db_source")
-# result
+#' unique_citations <- data.frame(
+#' db_source = c("Database1", "Database1", "Database2", "Database3", "Database3", "Database3"),
+#' cite_label = c("screened", "final", "screened", "final", "screened", "final"),
+#' duplicate_id = c(102, 102, 103, 103, 104, 104),
+#' other_data = 1:6
+#' )
+#' 
+#' citations <- data.frame(
+#' db_source = c("Database1", "Database1", "Database1", "Database2", "Database2", "Database3"),
+#' cite_label = c("screened", "final", "screened", "final", "screened", "final"),
+#' other_data = 7:12
+#' )
+#' 
+#' result <- calculate_phase_count(unique_citations, citations, "db_source")
+#' result
 
 
 calculate_phase_count <- function(unique_citations, citations, db_colname) {

R/dedup.R

@@ -6,7 +6,7 @@
 #' @export
 #' @param raw_citations Citation dataframe with relevant columns
 #' @param manual logical. If TRUE, manually specify pairs of duplicates to merge. Default is FALSE.
-#' @param shiny_progress logical. If TRUE, show a progress bar in the Shiny app. Default is FALSE.
+#' @param show_unknown_tags When a label, source, or other merged field is missing, do you want this to show as "unknown"?
 #' @return unique citations formatted for CiteSource
 #' @examples
 #' # Load example data from the package
@@ -17,7 +17,7 @@
 #' dedup_results <- dedup_citations(examplecitations)
 #' 
 
-dedup_citations <- function(raw_citations, manual=FALSE, shiny_progress=FALSE, show_unknown_tags=FALSE){
+dedup_citations <- function(raw_citations, manual=FALSE, show_unknown_tags=FALSE){
 
   # rename or coalesce columns
   targets <- c("journal", "number", "pages", "isbn", "record_id")
@@ -37,7 +37,7 @@ dedup_citations <- function(raw_citations, manual=FALSE, shiny_progress=FALSE, s
   raw_citations$source <- raw_citations$cite_source
   raw_citations$label <- raw_citations$cite_label
 
-  dedup_results <- ASySD::dedup_citations(raw_citations, merge_citations = TRUE, extra_merge_fields = "cite_string", shiny_progress=shiny_progress, show_unknown_tags = show_unknown_tags)
+  dedup_results <- ASySD::dedup_citations(raw_citations, merge_citations = TRUE, extra_merge_fields = "cite_string", show_unknown_tags = show_unknown_tags)
 
   if(manual == FALSE){
 

inst/shiny-app/CiteSource/app.R

@@ -1,4 +1,6 @@
 library(DT)
+library(CiteSource)
+library(dplyr)
 
 # Set background colour
 shiny::tags$head(shiny::tags$style(
@@ -342,7 +344,7 @@ server <- function(input, output, session) {
       suggested_source <- stringr::str_replace_all(input$file$name, ".ris", "")
       suggested_source <- stringr::str_replace_all(suggested_source, ".bib", "")
       suggested_source <- stringr::str_replace_all(suggested_source, ".txt", "")
-      upload_df <- read_citations(
+      upload_df <- CiteSource::read_citations(
         files = input$file$datapath,
         cite_sources = suggested_source,
         cite_labels = rep("", length(input$file$datapath)),
@@ -479,10 +481,22 @@ server <- function(input, output, session) {
     rv$upload_df <- rv$upload_df %>% dplyr::mutate(record_id = as.character(1000 + dplyr::row_number()))
 
     # results of auto dedup
-    dedup_results <- dedup_citations(rv$upload_df, manual = TRUE, shiny_progress = TRUE, show_unknown_tags=TRUE)
+    dedup_results <- CiteSource::dedup_citations(rv$upload_df, manual = TRUE, show_unknown_tags=TRUE)
 
-    # unique and pairs to check sent to reactive values
-    rv$pairs_to_check <- dedup_results$manual_dedup 
+    # Possible way of PRIORITISING manual dedup 
+    # priority_df <- rv$upload_df %>%
+    #   filter(cite_label %in% c("final", "screened")) %>%
+    #   select(record_id)
+
+    # manual_to_review <- dedup_results$manual_dedup %>%
+    #   mutate(match_score_ls = RecordLinkage::levenshteinSim(title1, title2)) %>%
+    #   arrange(desc(match_score_ls)) %>%
+    #   mutate(priority = ifelse(record_id1 %in% priority_df$record_id, "Yes", "No")) %>%
+    #   mutate(priority = ifelse(record_id2 %in% priority_df$record_id, "Yes", priority)) %>%
+    #   arrange(desc(priority)) %>%
+    #   filter(priority == "Yes")
+
+    rv$pairs_to_check <- dedup_results$manual_dedup
     rv$latest_unique <- dedup_results$unique
 
     # generate shiny alert with dedup results
@@ -597,9 +611,8 @@ server <- function(input, output, session) {
 
     datatable(data,
               options = list(
-                dom = "t",
-                pageLength = 10,
-                lengthMenu = c(10, 20, 30, 40),
+                pageLength = 100, info = FALSE,
+                               lengthMenu = list(c(100, -1), c("100", "All")),
                 columnDefs =
                   list(
                     list(visible = FALSE,