Spaces:
Running
Running
Update OpenAlexEdges.R
Browse files- OpenAlexEdges.R +85 -2
OpenAlexEdges.R
CHANGED
|
@@ -26,8 +26,91 @@ authorPubEdges <- function(keywords,pub_start_date,pub_end_date){
|
|
| 26 |
|
| 27 |
}
|
| 28 |
|
| 29 |
-
#
|
| 30 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
# run author nodes function
|
| 33 |
author_nodes <- authorPubNodes(keywords,pub_start_date,pub_end_date)
|
|
|
|
| 26 |
|
| 27 |
}
|
| 28 |
|
| 29 |
+
# define nodes function
|
| 30 |
+
authorPubNodes <- function(keywords,pub_start_date,pub_end_date){
|
| 31 |
+
|
| 32 |
+
keywords <- keywords
|
| 33 |
+
pub_start_date <- pub_start_date
|
| 34 |
+
pub_end_date <- pub_end_date
|
| 35 |
+
|
| 36 |
+
# create search engine function
|
| 37 |
+
search_engine <- function(keywords,pub_start_date,pub_end_date){
|
| 38 |
+
suppressPackageStartupMessages(library(openalexR))
|
| 39 |
+
suppressPackageStartupMessages(library(tidyverse))
|
| 40 |
+
|
| 41 |
+
options(openalexR.mailto = "[email protected]")
|
| 42 |
+
|
| 43 |
+
# search engine
|
| 44 |
+
works_search <- oa_fetch(
|
| 45 |
+
entity = "works",
|
| 46 |
+
title.search = keywords,
|
| 47 |
+
cited_by_count = ">50",
|
| 48 |
+
from_publication_date = pub_start_date,
|
| 49 |
+
to_publication_date = pub_end_date,
|
| 50 |
+
options = list(sort = "cited_by_count:desc"),
|
| 51 |
+
verbose = FALSE
|
| 52 |
+
)
|
| 53 |
+
|
| 54 |
+
return(works_search)
|
| 55 |
+
|
| 56 |
+
}
|
| 57 |
+
|
| 58 |
+
search_data <- search_engine(keywords,pub_start_date,pub_end_date)
|
| 59 |
+
|
| 60 |
+
# grab authors and group them according to collaboration
|
| 61 |
+
authors_collaboration_groups <- list()
|
| 62 |
+
for (i in 1:nrow(search_data)){
|
| 63 |
+
authors_collaboration_groups[[i]] <- search_data$author[[i]][2]
|
| 64 |
+
}
|
| 65 |
+
|
| 66 |
+
# grab all authors
|
| 67 |
+
all_authors <- c()
|
| 68 |
+
for (i in 1:length(authors_collaboration_groups)) {
|
| 69 |
+
all_authors <- c(all_authors,authors_collaboration_groups[[i]][[1]])
|
| 70 |
+
}
|
| 71 |
+
|
| 72 |
+
# get length of each authors collaboration
|
| 73 |
+
authors_length <- c()
|
| 74 |
+
for(authors in 1:length(authors_collaboration_groups)){
|
| 75 |
+
authors_length <- c(authors_length,authors_collaboration_groups[[authors]] |> nrow())
|
| 76 |
+
}
|
| 77 |
+
|
| 78 |
+
# grab all publications
|
| 79 |
+
publications <- list()
|
| 80 |
+
for (i in 1:nrow(search_data)){
|
| 81 |
+
publications[[i]] <- rep(search_data$display_name[i], each = authors_length[i])
|
| 82 |
+
}
|
| 83 |
+
|
| 84 |
+
# place all publications in a vector
|
| 85 |
+
all_publications <- c()
|
| 86 |
+
for(i in 1:length(publications)){
|
| 87 |
+
all_publications <- c(all_publications,publications[[i]])
|
| 88 |
+
}
|
| 89 |
+
|
| 90 |
+
# create author_to_publication data frame
|
| 91 |
+
authors_to_publications <- data.frame(
|
| 92 |
+
Authors = all_authors,
|
| 93 |
+
Publications = all_publications
|
| 94 |
+
)
|
| 95 |
+
|
| 96 |
+
# stack the df so that authors and publications
|
| 97 |
+
# are together as one column
|
| 98 |
+
stacked_df <- stack(authors_to_publications)
|
| 99 |
+
stacked_df <- unique.data.frame(stacked_df) # remove duplicate rows
|
| 100 |
+
stacked_df <- stacked_df[-2] # delete second column in df
|
| 101 |
+
|
| 102 |
+
# create author_publications_nodes df
|
| 103 |
+
author_publication_nodes <- data.frame(
|
| 104 |
+
Id = 1:nrow(stacked_df),
|
| 105 |
+
Nodes = stacked_df$values,
|
| 106 |
+
Label = stacked_df$values
|
| 107 |
+
)
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
return(author_publication_nodes)
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
}
|
| 114 |
|
| 115 |
# run author nodes function
|
| 116 |
author_nodes <- authorPubNodes(keywords,pub_start_date,pub_end_date)
|