50 v20 function to process scopus download in csv format

DESCRIPTION

@@ -2,7 +2,7 @@ Type: Package
 Package: refsplitr
 Title: author name disambiguation, author georeferencing, and mapping of 
     coauthorship networks with 'Web of Science' data 
-Version: 1.2.2
+Version: 1.2.3
 Authors@R: 
     c(person(given = "Auriel M.V.",
              family = "Fournier",

NEWS.md

@@ -2,6 +2,14 @@
 
 
 
+refsplitr 1.2.3 (2026-06-16)
+=========================
+
+
+### MINOR IMPROVEMENTS 
+  * Further refining of the algorithm to match authors under a single group_id.
+
+
 refsplitr 1.2.2 (2026-06-16)
 =========================
 

R/authors_match.R

@@ -67,7 +67,56 @@ authors_match <- function(data){
   # n_n |> group_by(groupID) |> summarize(n=n_distinct(OI)) |> filter(n>1)
   # 
   # Now match by much less used RI
-  unique_ri <- n_n$RI[!is.na(n_n$RI) & is.na(n_n$groupID)]
+  & is.na(n_n$OI)
+
+  # n_n |> mutate_all(trimws) |> group_by(OI) |> summarize(n=n_distinct(RI)) |> filter(n>1) |> summarize(n_distinct(OI)).  arrange(desc(n)) 
+  # n_n |> mutate_all(trimws) |> group_by(RI) |> summarize(n=n_distinct(OI)) |> filter(n>1) |> summarize(n_distinct(RI))
+  # n_n |> mutate_all(trimws) |> group_by(RI) |> summarize(n=n_distinct(OI)) |> filter(n<=1) |> tally()
+
+# test --------------------------------------------------------------------
+
+
+  # RI<-c("1","2","3","3","4")
+  # OI<-c("a","a","b","c","d")
+  # df<-data.frame(RI,OI)
+  # # Count how many times each OI value appears
+  # oi_counts <- table(df$OI)
+  # # Find OI values with more than one RI
+  # multiple_ri <- names(oi_counts[oi_counts > 1])
+  # rows_to_remove_oi <- which(df$OI %in% multiple_ri)
+  # df_clean <- df[-rows_to_remove_oi, ]
+  # # Find OI values with more than one RI
+  # ri_counts <- table(df_clean$RI)
+  # multiple_oi <- names(ri_counts[ri_counts > 1])
+  # # Identify rows to remove
+  # rows_to_remove_ri <- which(df_clean$RI %in% multiple_oi)
+  # # Remove those rows
+  # df_clean <- df_clean[-rows_to_remove_ri, ]
+
+
+
+
+  # # Count how many times each OI value appears
+  # oi_counts <- table(n_n$OI)
+  # # Find OI values with more than one RI
+  # multiple_ri <- names(oi_counts[oi_counts > 1])
+  # # ID the rows to remove 
+  # rows_to_remove_oi <- which(n_n$OI %in% multiple_ri)
+  # # remove them
+  # n_n_clean <- n_n[-rows_to_remove_oi, ]
+  # # Find RI values with more than one OI
+  # ri_counts <- table(n_n_clean$RI)
+  # multiple_oi <- names(ri_counts[ri_counts > 1])
+  # # Identify rows to remove
+  # rows_to_remove_ri <- which(n_n_clean$RI %in% multiple_oi)
+  # # Remove those rows
+  # n_n_clean <-n_n_clean[-rows_to_remove_ri, ]
+
+
+
+
+  unique_ri <- n_n_clean$RI[!is.na(n_n_clean$RI) & is.na(n_n_clean$groupID)]
+  # unique_ri <- n_n$RI[!is.na(n_n$RI) & is.na(n_n$groupID)]
   unique_ri <- names(table(unique_ri))[table(unique_ri) > 1]
   if (is.null(unique_ri)) unique_ri <- NA
   unique_ri <- unique_ri[!is.na(unique_ri)]
@@ -81,9 +130,31 @@ authors_match <- function(data){
     } else {
       groupid <- min(n_n$ID[choice], na.rm = TRUE)
     }
-
+    
     n_n$groupID[which(n_n$RI == l)] <- groupid
   }
+# test end-----------------------------------------------------------------
+  # 
+  # original, using above instead to filter outr OI/RI dupes
+  # 
+  # unique_ri <- n_n$RI[!is.na(n_n$RI) & is.na(n_n$groupID)]
+  # # unique_ri <- n_n$RI[!is.na(n_n$RI) & is.na(n_n$groupID)]
+  # unique_ri <- names(table(unique_ri))[table(unique_ri) > 1]
+  # if (is.null(unique_ri)) unique_ri <- NA
+  # unique_ri <- unique_ri[!is.na(unique_ri)]
+  # unique_ri <- as.character(unique_ri)
+  # for (l in unique_ri) {
+  #   choice <- which(n_n$RI == l)
+  #   groupid <- n_n$groupID[choice]
+  #   groupid <- groupid[!is.na(groupid)]
+  #   if (length(groupid) > 0) {
+  #     groupid <- min(groupid)
+  #   } else {
+  #     groupid <- min(n_n$ID[choice], na.rm = TRUE)
+  #   }
+  # 
+  #   n_n$groupID[which(n_n$RI == l)] <- groupid
+  # }
 
   # n_n |> group_by(OI) |> summarize(n=n_distinct(groupID)) |> filter(n>1)
   # n_n |> group_by(groupID) |> filter(!is.na(OI)) |> summarize(n=n_distinct(OI)) |> filter(n>1)

README.Rmd

@@ -86,15 +86,15 @@ The Refsplitr package has been described in an article in the [_Journal of Open
 
 ### Citation: Refsplitr Package
 
-Fournier, Auriel M.V., Matthew E. Boone, Forrest R. Stevens, and Emilio M. Bruna (2026). refsplitr: author name disambiguation, author georeferencing, and mapping of coauthorship networks with Web of Science data. R package version 1.2.2. <https://github.com/ropensci/refsplitr>
+Fournier, Auriel M.V., Matthew E. Boone, Forrest R. Stevens, and Emilio M. Bruna (2026). refsplitr: author name disambiguation, author georeferencing, and mapping of coauthorship networks with Web of Science data. R package version 1.2.3. <https://github.com/ropensci/refsplitr>
 
     @Manual{refsplitr2025,
     title = {refsplitr: author name disambiguation, author georeferencing, 
     and mapping of coauthorship networks with Web of Science data.},
     author = {Fournier, Auriel M.V., Matthew E. Boone, Forrest R. Stevens, 
     and Emilio M. Bruna},
     year = {2026},
-    note = {R package version 1.2.2.},
+    note = {R package version 1.2.3.},
     url ={https://github.com/ropensci/refsplitr}
     }
 

README.html

@@ -467,14 +467,14 @@ <h3>Citation: Refsplitr Package</h3>
 <p>Fournier, Auriel M.V., Matthew E. Boone, Forrest R. Stevens, and
 Emilio M. Bruna (2026). refsplitr: author name disambiguation, author
 georeferencing, and mapping of coauthorship networks with Web of Science
-data. R package version 1.2.2. <a href="https://github.com/ropensci/refsplitr" class="uri">https://github.com/ropensci/refsplitr</a></p>
+data. R package version 1.2.3. <a href="https://github.com/ropensci/refsplitr" class="uri">https://github.com/ropensci/refsplitr</a></p>
 <pre><code>@Manual{refsplitr2025,
 title = {refsplitr: author name disambiguation, author georeferencing, 
 and mapping of coauthorship networks with Web of Science data.},
 author = {Fournier, Auriel M.V., Matthew E. Boone, Forrest R. Stevens, 
 and Emilio M. Bruna},
 year = {2026},
-note = {R package version 1.2.2.},
+note = {R package version 1.2.3.},
 url ={https://github.com/ropensci/refsplitr}
 }</code></pre>
 </div>

README.md

@@ -112,7 +112,7 @@ Auriel M.V. Fournier, Matthew E. Boone, Forrest R. Stevens, and
     and mapping of coauthorship networks with Web of Science data.},
     author = {Fournier, Auriel M.V., Matthew E. Boone, Forrest R. Stevens, and Emilio M. Bruna},
     year = {2026},
-    note = {R package version 1.2.2.},
+    note = {R package version 1.2.3.},
     url={https://github.com/ropensci/refsplitr}
     }
 

codemeta.json

@@ -8,7 +8,7 @@
   "codeRepository": "https://github.com/ropensci/refsplitr",
   "issueTracker": "https://github.com/ropensci/refsplitr/issues",
   "license": "https://spdx.org/licenses/GPL-3.0",
-  "version": "1.2.2",
+  "version": "1.2.3",
   "programmingLanguage": {
     "@type": "ComputerLanguage",
     "name": "R",

inst/CITATION

@@ -5,8 +5,8 @@ citEntry(
   title    = "refsplitr: Author name disambiguation, author georeferencing, 
   and mapping of coauthorship networks with Web of Science data.",
   author   = "Auriel M.V. Fournier and Matthew E. Boone and Forrest R. Stevens and Emilio M. Bruna",
-  note     = "R package version 1.2.0.",
-  year     = "2025",
+  note     = "R package version 1.2.3.",
+  year     = "2026",
   url      = "https://github.com/ropensci/refsplitr",
   textVersion = paste("Fournier, Auriel M.V., Matthew E. Boone, ",
       "Forrest R. Stevens, and Emilio M. Bruna (2025).",