Skip to content

Commit 2c6f37f

Browse files
committed
update 20230529 for preprints posted up until 20230528. Dataset (csv) will be posted separately to Figshare due to file size.
1 parent 524d0ab commit 2c6f37f

13 files changed

+8
-8
lines changed

covid19_preprints.Rmd

+1-2
Original file line numberDiff line numberDiff line change
@@ -276,7 +276,6 @@ rm(covid_preprints_previous)
276276
277277
#crawl SSRN to retrieve posted dates
278278
cr_ssrn_covid <- cr_ssrn_covid %>%
279-
filter(is.na(posted_date)) %>%
280279
# Retrieve 'real' posted dates from the SSRN website. Warning: slow
281280
mutate(posted_date = ymd(map_chr(identifier, getSSRNPublicationDate)),
282281
source = "SSRN") %>%
@@ -477,7 +476,7 @@ dc_covid <- dc_preprints_df %>%
477476
# Select only relevant fields with unique values
478477
distinct(source, identifier, identifier_type, posted_date, title, abstract)
479478
480-
rrm(dc_preprints_df)
479+
rm(dc_preprints_df)
481480
482481
```
483482

covid19_preprints.md

+4-3
Original file line numberDiff line numberDiff line change
@@ -45,7 +45,7 @@ Deduplicate final dataset to filter out records that are sampled twice.
4545

4646
```r
4747
sample_date_until<- Sys.Date()
48-
#sample_data_until <- as.Date("2022-11-03")
48+
#sample_data_until <- as.Date("2023-04-30")
4949

5050
posted_date_until<-floor_date(sample_date_until, "week") #set to last Sunday prior to sample date
5151

@@ -341,7 +341,7 @@ purrr::map.
341341
```r
342342
##specify years to include
343343
#dc_years <- c("2020", "2021", "2022")
344-
dc_years<-"2022"# for iterative update, only need to use 2022
344+
dc_years<-c("2023")# for iterative update, only need to use 2023 from next update onwards
345345

346346
###include (not: replace) query for types.resourceTypeGeneral:Preprint as per DataCite metadata schema 4.4
347347
dc_types<- c("types.resourceType:Preprint",
@@ -704,7 +704,8 @@ metadata <- list()
704704
metadata$release_date<-release_date
705705
metadata$sample_date<-sample_date_until
706706
metadata$posted_date<-posted_date_until
707-
metadata$url<-"https://github.com/nicholasmfraser/covid19_preprints/blob/master/data/covid19_preprints.csv?raw=true"
707+
metadata$url_data<-"https://doi.org/10.6084/m9.figshare.22707346"
708+
metadata$url_repository<-"https://github.com/nicholasmfraser/covid19_preprints"
708709

709710
# Save as json file
710711
metadata_json<- toJSON(metadata, pretty=TRUE, auto_unbox=TRUE)
Loading
Loading
Loading
Loading
Loading

data/metadata.json

+3-3
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
{
2-
"release_date": "2023-05-02",
3-
"sample_date": "2023-04-30",
4-
"posted_date": "2023-04-30",
2+
"release_date": "2023-05-29",
3+
"sample_date": "2023-05-29",
4+
"posted_date": "2023-05-28",
55
"url_data": "https://doi.org/10.6084/m9.figshare.22707346",
66
"url_repository": "https://github.com/nicholasmfraser/covid19_preprints"
77
}
4.64 KB
Loading
1.06 KB
Loading
1.8 KB
Loading

0 commit comments

Comments
 (0)
close