Najko Jahn njahn82

Licenses found

download_apc <- function(path = NULL, dir = "tmp", file = "apc_de.csv"){
  if(is.null(path)) {
    path <- c("https://raw.githubusercontent.com/OpenAPC/openapc-de/master/data/apc_de.csv")
  } 
  dir.create(dir) 
  download.file(url = path, destfile = paste(dir, file, sep = "/"), method = "curl")

Using Catmandu within R

system("catmandu convert YAML < example.yaml", intern = TRUE) %>%
  jsonlite::fromJSON()

Proposed datasets

Sci-Hub usage

In spring 2016, [Science featured a dataset on global usage of Sci-Hub](http://www.sciencemag.org/news/2016/04/whos-downloading-pirated-papers- everyone), a prominent shadow library for scholarly literature. The dataset, openly available via Dryad, tracks more than 28 Mio Sci-Hub usage events over a period of six month on the article-level. Tab-separated files contain timestamps, geo-locations (latitude, longitude), and the Digital Object Identifiers (DOI) of each requested full text.

  ## ngram following http://tidytextmining.com/ngrams.html
    library(dplyr)
    library(tidytext)
    library(tidyr)

    # load manually downloaded web of science data dump
    tt <- jsonlite::stream_in(file("data/wos_total.json"), verbose = FALSE) %>% 
      filter(!is.na(AB))

	---
	title: "Mean APC per Institution"
	author: "Najko Jahn"
	date: "28. April 2015"
	output: html_document
	---

	```{r, echo =FALSE}

	knitr::opts_knit$set(base.url = "/")

	require(ropenaire)
	require(dplyr)

	# fetch ugoe projects
	ugoe <- roa_projects(org = "UGOE")
	# fetch publications
	tt <- plyr::ldply(as.character(ugoe$grantID), roa_pubs)
	# tidy up: split collapsed ec projects
	tmp <-
	tidyr::separate(

	```{r, echo = FALSE}
	knitr::opts_knit$set(base.url = "/")
	knitr::opts_chunk$set(
	comment = "#>",
	collapse = TRUE,
	warning = FALSE,
	message = FALSE,
	echo = TRUE,
	fig.width = 9,
	fig.height = 6,

	# load ISI spradsheet
	vu_amst <- read.csv("pubs_2012-14 V5 CSV.csv", header = TRUE, sep =";",
	na.strings = "")

	vu_amst$SN <- as.character(vu_amst$SN)
	# load DOAJ spreadsheet
	doaj <- httr::content(httr::GET("http://doaj.org/csv"))

	# join ISSN and EISSN as vector
	doaj.issn <- c(as.character(doaj$Journal.ISSN..print.version.),


	## Load Data

	```{r}
	require(dplyr)
	# load ISI spradsheet and select only columns needed
	vu_amst <- read.csv("pubs_2012-14 V5 CSV.csv", header = TRUE, sep =";",
	na.strings = "") %>%
	select(JI, PY, SN, PU, DI, UT)
	tbl_df(vu_amst)

	---
	layout: null
	---
	<?xml version="1.0" encoding="UTF-8"?>
	<rdf:RDF
	xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
	xmlns="http://purl.org/rss/1.0/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:prism="http://prismstandard.org/namespaces/1.2/basic/">