update

Zitationsanalyse_AUF-HRO.Rmd

@@ -128,23 +128,8 @@ res
 
 
 ```{r retrieve, message=FALSE, warning=FALSE, results='hide'}
-FUN <- function(id) {
-  if(!is.na(id)) {
-    df <- author_df(au_id = id, count = 100)
-    #  prism:url"               "dc:identifier"           "eid"                     "dc:title"                "dc:creator"             
-    # "prism:publicationName"   "prism:issn"              "prism:eIssn"             "prism:volume"            "prism:issueIdentifier"   "prism:pageRange"
-    # "prism:coverDate"         "prism:coverDisplayDate"  "prism:doi"               "pii"                     "dc:description"          "citedby-count
-    # "prism:aggregationType"   "subtype"                 "subtypeDescription"      "author-count.@limit"     "author-count.@total"     "author-count.$"
-    # "authkeywords"            "source-id"               "fund-acr"                "fund-no"                 "fund-sponsor"            "openaccess"
-    # "openaccessFlag"          "freetoread.value.$"      "freetoreadLabel.value.$" "entry_number"            "article-number"          "pubmed-id"
-    out <- df[, c('dc:creator', 'prism:publicationName', 'prism:issn', 'prism:eIssn', 'prism:volume', 'prism:issueIdentifier', 'prism:pageRange', 'prism:coverDate', 'prism:doi', 'citedby-count')]
-    out$id <- id
-  return(out)
-  }
-}
-suppressMessages(
-  scopus.list <- sapply(res$SCOPUS, function(x) FUN(x))
-)
+library(plyr)
+sc.df <- rbind.fill(sapply(res$SCOPUS, function(x) author_df(au_id = x, count = 100)))
 ```
 
 ### Filter by year
@@ -153,12 +138,13 @@ Bitte das gewünschte Jahr eintragen.
 
 ```{r byYear}
 year <- 2020
-scopus.year <- lapply(scopus.list, function(x) x <- x[grepl(year, x$`prism:coverDate`), ])
+scopus.year <- sc.df[grepl(year, sc.df$`prism:coverDate`), ]
 ```
 
 ## Researcher performance
 ```{r, overallCitations}
-res$ScopusCitations <- sapply(scopus.list, function(x) sum(as.numeric(x$'citedby-count')))
+author.cit <- tapply(as.numeric(sc.df$`citedby-count`), sc.df$au_id, sum)
+res$ScopusCitations <- author.cit[match(res$SCOPUS, names(author.cit))]
 ```
 
 
@@ -166,10 +152,8 @@ res$ScopusCitations <- sapply(scopus.list, function(x) sum(as.numeric(x$'citedby
 Publikationen zählen nur einmal pro AG.
 ```{r}
 ## no duplicates in AG
-ag.list <- tapply(scopus.year, res$AG, function(x) do.call('rbind', x))
-ag.list <- lapply(ag.list, function(x) x <- x[!duplicated(x$`prism:doi`), ])
-result <- do.call('rbind', ag.list)
-result$AG <- res$AG[match(result$id, res$SCOPUS)]
+sc.df$AG <- res$AG[match(sc.df$au_id, res$SCOPUS)]
+sc.df$Duplicates <- duplicated(sc.df$`dc:identifier`, sc.df$AG)
 ```
 
 # Ergebnisse
@@ -180,17 +164,17 @@ Es geht aber natürlich auch gleich im Script:
 
 ```{r}
 ### Zahl der Publikationen pro AG
-table(result$AG)
+table(sc.df$AG[!sc.df$Duplicates])
 ```
 
 
 ```{r}
 # Zahl der Zitationen pro AG
-tapply(as.numeric(result$`citedby-count`), result$AG, sum)
+tapply(as.numeric(sc.df$`citedby-count`[!sc.df$Duplicates]), sc.df$AG[!sc.df$Duplicates], sum)
 ```
 
 ```{r writeResults}
-write.xlsx(result, 'Zitationsanalyse_AUF_AGs.xlsx')
+write.xlsx(sc.df, 'Zitationsanalyse_AUF_AGs.xlsx')
 write.xlsx(res, 'Zitationsanalyse_AUF_Forschende.xlsx')
 ```
 

Zitationsanalyse_AUF-HRO_cache/latex/__packages

@@ -2,3 +2,4 @@ base
 rscopus
 rorcid
 openxlsx
+plyr