njahn82

Abstracts in Crossref

Get abstract counts per year and publisher

SELECT
cr_year,
publisher,
COUNT(DISTINCT doi) AS cr_articles,

njahn82

#' Manipulating, analyzing and exporting data with tidyverse
#' https://datacarpentry.org/R-ecology-lesson/03-dplyr.html

library(tidyverse)

#' dplyr
#' - the most common data manipulation tasks
#' - https://github.com/rstudio/cheatsheets/raw/master/data-transformation.pdf
#' tidyr
#' - reshape your data

njahn82

library(tidyverse)
library(bigrquery)
library(DBI)

Connection

njahn82

library(tidyverse)
#> Warning: package 'tibble' was built under R version 4.1.1
#> Warning: package 'readr' was built under R version 4.1.1
library(biblids) # install via GitHub https://github.com/subugoe/biblids

tt <- readr::read_csv("~/Downloads/DOIs.txt")
#> Rows: 40479 Columns: 1
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: ","

njahn82

library(tidyverse)
# raw subject table
subject_mag_raw <- readr::read_csv("data/NPL_DOI_FOS.csv",
  col_types =  cols(.default = "c"))
subject_mag_raw %>%
  # Represents https://academic.microsoft.com/paper/2518129109/
  filter(doi == "10.7717/peerj.2369") %>%
  # Only top level subjects
  filter(is.na(fos_1)) %>%

njahn82

library(rvest)
library(tidyverse)
library(janitor)
#> 
#> Attaching package: 'janitor'
#> The following objects are masked from 'package:stats':
#> 
#>     chisq.test, fisher.test
esac <-

njahn82

library(rcrossref)
library(purrr)

my_dois <-
  c(
    "skksks",
    "10.5281/zenodo.4032609",
    "10.1667/rr13708.1",
    "10.1016/s0021-9258(19)52311-0",

njahn82

#' Get most current Open APC snapshot
#'
#' Open APC shares several csv files via GitHub, which contain data about
#' institutional spending for open access articles.
#'
#'
#' @param open_apc_cols character vector representing Open APC collections.
#'   See `open_apc_collections()` for an overview.
#'
#' @importFrom dplyr filter `%>%` inner_join

njahn82

# import csv file
tt <- read.delim("~/Downloads/vanished_v2.csv", sep = ";")
# table dimensions
dim(tt)
#> [1] 807  61
# empty rows at bottom like row 635
tt[635,]
#>     Source If.Identified.by.second.source Journal.Name ISSN E.ISSN URL
#> 635                                                                   

njahn82

library(tidyverse)
my_df <- readr::read_csv("data/u4_13_17.csv") 
no_group <- my_df %>%
  filter(is.na(CA)) 
no_group %>%
  select(PY, UT, C1) %>%
  mutate(adresses = strsplit(C1, "; \\[")) -> tt
tt %>%
  unnest() %>%
  tidyr::separate(adresses, sep ="] ", c("authors", "address"), fill = "left") %>%