doajValidate.md

check apc_de dataset against DOAJ journal master list

# load doaj data 

doaj <- read.csv("data/doaj/doajJournalList.csv", header = T, sep = ",")
doaj.eissn <- doaj[!doaj$EISSN == "",] # exclude empty Eissn

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

# read data set
apc.de <- read.csv("data/apc_de.csv", header =T, sep = ",", colClasses ="character")

# match
apc.de$DOAJ <- !is.na(match(apc.de$issn.1, doaj.issn) | match(apc.de$issn.2, doaj.issn))

#summary
table(apc.de$DOAJ)

## 
## FALSE  TRUE 
##    19   237

#table
apc.de[apc.de$DOAJ == FALSE,]

##                uni Period    EURO
## 35  Uni Regensburg   2012    1188
## 36  Uni Regensburg   2012  756.59
## 55  Uni Regensburg   2012   285.6
## 72  Uni Regensburg   2012 2084.16
## 73  Uni Regensburg   2012  723.28
## 109 Uni Regensburg   2013    1228
## 110 Uni Regensburg   2013    1236
## 111 Uni Regensburg   2013    1228
## 112 Uni Regensburg   2013    1296
## 113 Uni Regensburg   2013    1620
## 114 Uni Regensburg   2013  625.32
## 141 Uni Regensburg   2013     833
## 159 Uni Regensburg   2013     640
## 165  Uni Bielefeld   2013    1017
## 203  Uni Bielefeld   2013    1236
## 225  Uni Bielefeld   2012     900
## 254 Uni Regensburg   2012  745.25
## 255 Uni Regensburg   2013   192.8
## 256 Uni Regensburg   2012  761.05
##                                                  Publisher
## 35                       Springer Science + Business Media
## 36                     International Scientific Literature
## 55                                  Walter de Gruyter GmbH
## 72                                  OMICS Publishing Group
## 73                                  OMICS Publishing Group
## 109                      Springer Science + Business Media
## 110                      Springer Science + Business Media
## 111                      Springer Science + Business Media
## 112                      Springer Science + Business Media
## 113                      Springer Science + Business Media
## 114                    International Scientific Literature
## 141 Society for Publication of Acta Dermato-Venereologica 
## 159                                                 InTech
## 165                                     Informa UK Limited
## 203                      Springer Science + Business Media
## 225                                     Frontiers Media SA
## 254                                  e-Century Publ. Corp.
## 255                                 Food Science Publisher
## 256                                  e-Century Publ. Corp.
##                                                          Journal    issn.1
## 35                                  Arthritis Research & Therapy 1478-6354
## 36                                       Medical Science Monitor 1234-1010
## 55     Zeitschrift für Kristallographie - New Crystal Structures 1433-7266
## 72                                         J Neurol Neurophysiol 2155-9562
## 73                    Journal of Physical Chemistry & Biophysics      <NA>
## 109                                 Arthritis Research & Therapy 1478-6354
## 110                                                Critical Care 1364-8535
## 111                                                Critical Care 1364-8535
## 112                                                Critical Care 1364-8535
## 113                                                  Genome Biol 1465-6906
## 114                             American Journal of Case Reports 1941-5923
## 141                                   Acta Dermato-Venereologica      <NA>
## 159                                        Chromatin Remodelling      <NA>
## 165                    Health Psychology and Behavioral Medicine 2164-2850
## 203                                                  BMC Psychol 2050-7283
## 225             Frontiers in Cellular and Infection Microbiology 2235-2988
## 254 International Journal of Molecular Epidemiology and Genetics      <NA>
## 255                       Functional Foods in Health and Disease      <NA>
## 256 International Journal of Molecular Epidemiology and Genetics      <NA>
##     issn.2                          doi indexed_in_CrossRef     pmid
## 35    <NA>               10.1186/ar3852                TRUE 22621205
## 36    <NA>          10.12659/MSM.882463                TRUE     <NA>
## 55    <NA>       10.1524/ncrs.2012.0173                TRUE     <NA>
## 72    <NA>    10.4172/2155-9562.1000124                TRUE     <NA>
## 73    <NA>     10.4172/2161-0398.S1-001               FALSE     <NA>
## 109   <NA>               10.1186/ar4304                TRUE 24432363
## 110   <NA>              10.1186/cc12694                TRUE 23622019
## 111   <NA>              10.1186/cc12782                TRUE 23786965
## 112   <NA>              10.1186/cc12809                TRUE 23844607
## 113   <NA>     10.1186/gb-2013-14-5-r46                TRUE 23705593
## 114   <NA>         10.12659/AJCR.889672                TRUE     <NA>
## 141   <NA>        10.2340/00015555-1632               FALSE 23995048
## 159   <NA>                10.5772/55683                TRUE     <NA>
## 165   <NA> 10.1080/21642850.2013.809313                TRUE     <NA>
## 203   <NA>       10.1186/2050-7283-1-12                TRUE     <NA>
## 225   <NA>     10.3389/fcimb.2012.00070                TRUE 22919661
## 254   <NA>                         <NA>               FALSE     <NA>
## 255   <NA>                         <NA>               FALSE     <NA>
## 256   <NA>                         <NA>               FALSE     <NA>
##          pmcid                       base.url repo_id              ut
## 35  PMC3446503 http://epub.uni-regensburg.de/   25842 000314972600024
## 36        <NA> http://epub.uni-regensburg.de/   25863            <NA>
## 55        <NA> http://epub.uni-regensburg.de/   25530 000321004400040
## 72        <NA> http://epub.uni-regensburg.de/   23746            <NA>
## 73        <NA> http://epub.uni-regensburg.de/   29508            <NA>
## 109 PMC3978726 http://epub.uni-regensburg.de/   29543 000329737400024
## 110 PMC4056784 http://epub.uni-regensburg.de/   29513 000327887300045
## 111 PMC4056791 http://epub.uni-regensburg.de/   28775 000329431100027
## 112 PMC4056110 http://epub.uni-regensburg.de/   29514 000331539700004
## 113 PMC4053946 http://epub.uni-regensburg.de/   28789 000325680100006
## 114       <NA> http://epub.uni-regensburg.de/   29520            <NA>
## 141       <NA> http://epub.uni-regensburg.de/   28743 000332820000007
## 159       <NA> http://epub.uni-regensburg.de/   28798            <NA>
## 165       <NA>   http://pub.uni-bielefeld.de/ 2566281            <NA>
## 203       <NA>   http://pub.uni-bielefeld.de/ 2610712            <NA>
## 225 PMC3417467   http://pub.uni-bielefeld.de/ 2510371 000324627400016
## 254       <NA> http://epub.uni-regensburg.de/   23616            <NA>
## 255       <NA> http://epub.uni-regensburg.de/   28794            <NA>
## 256       <NA> http://epub.uni-regensburg.de/   26556            <NA>
##      DOAJ
## 35  FALSE
## 36  FALSE
## 55  FALSE
## 72  FALSE
## 73  FALSE
## 109 FALSE
## 110 FALSE
## 111 FALSE
## 112 FALSE
## 113 FALSE
## 114 FALSE
## 141 FALSE
## 159 FALSE
## 165 FALSE
## 203 FALSE
## 225 FALSE
## 254 FALSE
## 255 FALSE
## 256 FALSE