# Load data
data <- read.csv(file = "https://doaj.org/csv")
#summary(data)
#str(data)

names(data)
##  [1] "Journal.title"                                                              
##  [2] "Journal.URL"                                                                
##  [3] "Alternative.title"                                                          
##  [4] "Journal.ISSN..print.version."                                               
##  [5] "Journal.EISSN..online.version."                                             
##  [6] "Publisher"                                                                  
##  [7] "Society.or.institution"                                                     
##  [8] "Platform..host.or.aggregator"                                               
##  [9] "Country.of.publisher"                                                       
## [10] "Journal.article.processing.charges..APCs."                                  
## [11] "APC.information.URL"                                                        
## [12] "APC.amount"                                                                 
## [13] "Currency"                                                                   
## [14] "Journal.article.submission.fee"                                             
## [15] "Submission.fee.URL"                                                         
## [16] "Submission.fee.amount"                                                      
## [17] "Submission.fee.currency"                                                    
## [18] "Number.of.articles.publish.in.the.last.calendar.year"                       
## [19] "Number.of.articles.information.URL"                                         
## [20] "Journal.waiver.policy..for.developing.country.authors.etc."                 
## [21] "Waiver.policy.information.URL"                                              
## [22] "Digital.archiving.policy.or.program.s."                                     
## [23] "Archiving..national.library"                                                
## [24] "Archiving..other"                                                           
## [25] "Archiving.infomation.URL"                                                   
## [26] "Journal.full.text.crawl.permission"                                         
## [27] "Permanent.article.identifiers"                                              
## [28] "Journal.provides.download.statistics"                                       
## [29] "Download.statistics.information.URL"                                        
## [30] "First.calendar.year.journal.provided.online.Open.Access.content"            
## [31] "Full.text.formats"                                                          
## [32] "Keywords"                                                                   
## [33] "Full.text.language"                                                         
## [34] "URL.for.the.Editorial.Board.page"                                           
## [35] "Review.process"                                                             
## [36] "Review.process.information.URL"                                             
## [37] "URL.for.journal.s.aims...scope"                                             
## [38] "URL.for.journal.s.instructions.for.authors"                                 
## [39] "Journal.plagiarism.screening.policy"                                        
## [40] "Plagiarism.information.URL"                                                 
## [41] "Average.number.of.weeks.between.submission.and.publication"                 
## [42] "URL.for.journal.s.Open.Access.statement"                                    
## [43] "Machine.readable.CC.licensing.information.embedded.or.displayed.in.articles"
## [44] "URL.to.an.example.page.with.embedded.licensing.information"                 
## [45] "Journal.license"                                                            
## [46] "License.attributes"                                                         
## [47] "URL.for.license.terms"                                                      
## [48] "Does.this.journal.allow.unrestricted.reuse.in.compliance.with.BOAI."        
## [49] "Deposit.policy.directory"                                                   
## [50] "Author.holds.copyright.without.restrictions"                                
## [51] "Copyright.information.URL"                                                  
## [52] "Author.holds.publishing.rights.without.restrictions"                        
## [53] "Publishing.rights.information.URL"                                          
## [54] "DOAJ.Seal"                                                                  
## [55] "Tick..Accepted.after.March.2014"                                            
## [56] "Added.on.Date"                                                              
## [57] "Subjects"

Timeline of journals added to DOAJ

library("lubridate")
## 
## Attaching package: 'lubridate'
## The following object is masked from 'package:base':
## 
##     date
# parse dates
data[, "Added.on.Date"] <- ymd_hms(x = data[, "Added.on.Date"])
data <- cbind(data, "Added.in.year" = year(data[, "Added.on.Date"]))
aggAdded <- aggregate(data[, "Added.in.year"], by = list(data[, "Added.in.year"]), FUN = length)
#aggAdded
plot(aggAdded$Group.1, aggAdded$x)

Should we only count the ones with a “seal”?

summary(data$"DOAJ.Seal")
##   No  Yes 
## 8680  393
summary(data$"Does.this.journal.allow.unrestricted.reuse.in.compliance.with.BOAI.")
##       Yes 
## 4855 4218

Timeline of journals first publishing OA

firstPublishOAYear <- data$"First.calendar.year.journal.provided.online.Open.Access.content"
summary(firstPublishOAYear)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1874    2005    2009    2007    2012    2016
aggFirstOAYear <- aggregate(firstPublishOAYear, by = list(firstPublishOAYear), FUN = length)
#aggFirstOAYear
plot(aggFirstOAYear)