Codemetar Analysis

Michael Rustler

2021-07-12

Topics

library(jsonld)
library(jsonlite)
library(magrittr)
library(codemetar)
library(purrr)
#> 
#> Attaching package: 'purrr'
#> The following object is masked from 'package:magrittr':
#> 
#>     set_names
#> The following object is masked from 'package:jsonlite':
#> 
#>     flatten
library(dplyr)
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
library(printr)
#> Registered S3 method overwritten by 'printr':
#>   method                from     
#>   knit_print.data.frame rmarkdown
library(tibble)
##################################################################
### Importing "codemetar.json" 
##################################################################

### Option 1:
### Not working correctly (-> gives list that is twice as long as just
### using jsonlite::fromJSON as defined below

# frame <- system.file("schema/frame_schema.json", package="codemetar")
# 
# corpus <- jsonld::jsonld_frame("codemetar.json", frame) %>%
#  jsonlite::fromJSON("codemetar.json",
#                              simplifyVector = FALSE) %>%
#   getElement("@graph")


#"https://kwb-r.github.io/pkgmeta/codemetar.json" %>%  
#  jsonlite::fromJSON() %>% 
#  jsonlite::write_json("codemetar.json")

### Option 2: working as expected

corpus <- jsonlite::fromJSON("codemetar.json",
                             simplifyVector = FALSE)

### add Github topics to R package names
pkg_topics <- tibble::tibble(
       name = purrr::map_chr(corpus, "identifier"),
       topic = purrr::map_chr(
               lapply(purrr::map(corpus, "keywords"), 
                      function(x) {paste(unlist(x), 
                                         collapse = ", ")}),1))
pkg_topics

name	topic
aquanes.report	r, rstats, data-import, data-visualisation, automated-reporting, data-aggregation, data-export, project-aquanes
kwb.base	r, rstats
kwb.code	r, rstats, project-fakin
kwb.datetime	r, rstats
kwb.db	r, rstats, data-import
kwb.default	r, rstats
kwb.demeau	r, rstats, groundwater-modelling, project-demeau
kwb.dwa.m150	r, rstats
kwb.en13508.2	r, rstats
kwb.endnote	data-management, project-fakin, knowledge-repo, publication, literature-data-management
kwb.event	r, rstats
kwb.fakin	r, rstats, project-fakin, research-data-management
kwb.file	r, rstats, project-fakin
kwb.geosalz	r, rstats, data-import, data-cleaning, data-visualization, project-fakin, project-geosalz
kwb.hantush	r, rstats, infiltration-basin, groundwater-mounding, groundwater-modelling, project-demeau
kwb.lca	r, rstats, data-import, data-aggregation, data-visualisation, data-export, project-fakin, life-cycle-assessment
kwb.logger	r, rstats, data-import
kwb.monitoring	r, rstats
kwb.orcid	r, rstats, data-management, publication, project-fakin
kwb.pkgbuild	r, rstats, r-package-automation, data-management, publication, project-fakin
kwb.pkgstatus	r, rstats, data-management, publication, project-fakin
kwb.plot	r, rstats
kwb.pubs	r, rstats, hugo-academic, knowledge-repo, project-fakin, publications, publication
kwb.qmra	r, rstats, project-demoware, project-aquanes, qmra-webapp-backend-engine
kwb.readxl	r, rstats, data-import, project-fakin
kwb.resilience	r, rstats, project-fakin, project-networks4
kwb.test	r, rstats
kwb.umberto	r, rstats, data-import, data-aggregation, data-visualisation, lca-modelling, modelling, project-fakin, life-cycle-assessment
kwb.utils	r, rstats
kwb.vs2dh	r, rstats, groundwater-modelling, project-demeau
kwb.wtaq	r, rstats, groundwater-modelling, drawdown-model, project-optiwells2
pkgmeta	r, rstats, project-fakin, knowledge-repo

topics <- tidyr::separate_rows(pkg_topics, topic, sep = ",\\s+") %>% 
  dplyr::count(topic) %>% 
  dplyr::filter(!topic %in% c("r", "rstats")) %>% 
  dplyr::arrange(dplyr::desc(n)) %>% 
  dplyr::rename(word = topic,
                freq = n) 


knitr::kable(topics)

word	freq
project-fakin	14
data-import	7
publication	5
data-management	4
groundwater-modelling	4
data-aggregation	3
data-visualisation	3
knowledge-repo	3
project-demeau	3
data-export	2
life-cycle-assessment	2
project-aquanes	2
automated-reporting	1
data-cleaning	1
data-visualization	1
drawdown-model	1
groundwater-mounding	1
hugo-academic	1
infiltration-basin	1
lca-modelling	1
literature-data-management	1
modelling	1
project-demoware	1
project-geosalz	1
project-networks4	1
project-optiwells2	1
publications	1
qmra-webapp-backend-engine	1
r-package-automation	1
research-data-management	1

wordcloud2::wordcloud2(topics)

Authors

## deal with nulls explicitly by starting with map
pkgs <- purrr::map(corpus, "name") %>%
  purrr::compact() %>%
  as.character()

# keep only those with package identifiers (names)
keep <- purrr::map_lgl(corpus, ~ length(.x$identifier) > 0)
corpus <- corpus[keep]

## now we can just do
all_pkgs <- purrr::map_chr(corpus, "name")
head(all_pkgs)
#> [1] "aquanes.report: Automated Reporting Tool for Water Suppliers"
#> [2] "kwb.base: Functions supporting data analysis with R at KWB"  
#> [3] "kwb.code: Analyse Your R Code!"                              
#> [4] "kwb.datetime: Functions for date/time objects"               
#> [5] "kwb.db: Functions supporting data base access"               
#> [6] "kwb.default: Get and Set Function Argument Defaults"

## 3 unique maintainers
purrr::map(corpus, "maintainer") %>%  
  purrr::map(1) %>%  
  purrr::map("familyName") %>% 
  unique() %>%
  length()
#> [1] 3

Maintainer

## Mostly Hauke
maintainer <- purrr::map(corpus, "maintainer") %>%  
  purrr::map(1) %>%  
  purrr::map("familyName") %>%
  unlist() %>% 
  tibble::enframe(name = NULL) %>%
  dplyr::group_by(value) %>%
  dplyr::tally(sort=TRUE) %>%
  dplyr::rename(word = value,
                freq = n) 

knitr::kable(maintainer)

word	freq
Sonnenberg	18
Rustler	13
Matzinger	1

wordcloud2::wordcloud2(maintainer,
                       minSize = 0.4, 
                       size = 0.6)

## number of co-authors ...
purrr::map_int(corpus, function(r) length(r$author)) %>%
  tibble::enframe() %>%
  dplyr::group_by(value) %>%
  dplyr::tally(sort=TRUE) 

value	n
1	32

## Contributors isn't used as much...
purrr::map_int(corpus, function(r) length(r$contributor)) %>%
  tibble::enframe() %>%
  dplyr::group_by(value) %>%
  dplyr::tally(sort=TRUE)

value	n
0	23
1	8
2	1

Package Dependencies

Depends Imports

purrr::map_int(corpus, function(r) length(r$softwareRequirements))  %>%
  tibble::enframe() %>%
  dplyr::group_by(value) %>%
  dplyr::tally(sort=TRUE)

value	n
2	4
3	4
4	3
6	3
0	2
1	2
8	2
11	2
13	2
15	2
5	1
7	1
9	1
10	1
18	1
26	1

corpus %>%
  map_df(function(x){
    ## single, unboxed dep
    if("name" %in% names(x$softwareRequirements))
      dep <- x$identifier
    else if("name" %in% names(x$softwareRequirements))
      dep <- map_chr(x$softwareRequirements, "name")
    else { ## No requirements
      dep <- NA
    }

    tibble(identifier = x$identifier, dep = dep)
  }) 

identifier	dep
aquanes.report	NA
kwb.base	NA
kwb.code	NA
kwb.datetime	NA
kwb.db	NA
kwb.default	NA
kwb.demeau	NA
kwb.dwa.m150	NA
kwb.en13508.2	NA
kwb.endnote	NA
kwb.event	NA
kwb.fakin	NA
kwb.file	NA
kwb.geosalz	NA
kwb.hantush	NA
kwb.lca	NA
kwb.logger	NA
kwb.monitoring	NA
kwb.orcid	NA
kwb.pkgbuild	NA
kwb.pkgstatus	NA
kwb.plot	NA
kwb.pubs	NA
kwb.qmra	NA
kwb.readxl	NA
kwb.resilience	NA
kwb.test	NA
kwb.umberto	NA
kwb.utils	NA
kwb.vs2dh	NA
kwb.wtaq	NA
pkgmeta	NA

deps_df <- tibble(identifier = purrr::map_chr(corpus, "identifier"),
       deps = lapply(purrr::map(corpus, "softwareRequirements"), 
                     FUN = function(x) {
                       deps <- purrr::map_chr(x, "name") %>%  
                         unlist() %>%  
                         paste(collapse = ",") %>% 
                         as.character()
                       
                       deps <- ifelse(stringr::str_length(deps) > 0, deps, NA_character_)}))

dep_df <- tidyr::separate_rows(deps_df, deps, sep = ",") %>% 
  dplyr::select(deps, identifier) %>%
  dplyr::arrange(deps, identifier) %>% 
  dplyr::rename(dependancy = deps, used_in_r_package = identifier)




#which dependencies are used most frequently?
dep_count <- dep_df %>%
  dplyr::group_by(dependancy) %>%
  dplyr::tally(sort = TRUE) %>%
  dplyr::rename(word = dependancy,
                freq = n)

knitr::kable(dep_count)

word	freq
kwb.utils	21
dplyr	12
magrittr	11
stringr	11
R	7
tidyr	7
fs	6
ggplot2	6
data.table	5
lattice	5
kwb.datetime	4
kwb.event	4
kwb.plot	4
lubridate	4
readxl	4
xml2	4
digest	3
hydroGOF	3
janitor	3
kwb.db	3
openxlsx	3
plyr	3
readr	3
rlang	3
yaml	3
cellranger	2
crayon	2
forcats	2
ggforce	2
gh	2
httr	2
jsonlite	2
kwb.fakin	2
kwb.file	2
rmarkdown	2
rvest	2
shiny	2
tibble	2
usethis	2
withr	2
xts	2
NA	2
assertthat	1
blogdown	1
callr	1
codemetar	1
colorRamps	1
dbplyr	1
desc	1
dygraphs	1
EnvStats	1
fasttime	1
fst	1
glue	1
gplots	1
gridExtra	1
kwb.base	1
kwb.code	1
kwb.pkgstatus	1
kwb.read	1
kwb.readxl	1
kwb.vs2dh	1
latticeExtra	1
leaflet	1
magick	1
manipulate	1
openssl	1
pkgdown	1
plotrix	1
purrr	1
qmrparser	1
RCurl	1
rematch2	1
remotes	1
reshape	1
RMySQL	1
RODBC	1
rorcid	1
scales	1
sessioninfo	1
sfsmisc	1
shapefiles	1
shinythemes	1
sp	1
stringi	1
travis	1
treemap	1
wordcloud2	1
XML	1

wordcloud2::wordcloud2(dep_count,
                       minSize = 0.4, 
                       size = 1)

Depends Imports and Suggests

#Alternate approach using a frame instead of purrr functions for subsetting the
#Note that this gets all Depends and suggests (really all SoftwareApplication
#types mentioned)
dep_frame <- '{
  "@context": "https://raw.githubusercontent.com/codemeta/codemeta/master/codemeta.jsonld",
"@explicit": "true",
"name": {}
}'
dep_sug_count <- jsonld_frame("codemetar.json", dep_frame) %>%
  fromJSON() %>%
  getElement("@graph") %>%
  filter(type == "SoftwareApplication") %>%
  group_by(name) %>%
  tally(sort = TRUE) %>%
  dplyr::rename(word = name,
                freq = n) 

knitr::kable(dep_sug_count)

word	freq
testthat	28
kwb.utils	22
knitr	18
rmarkdown	18
covr	15
dplyr	12
magrittr	11
stringr	11
ggplot2	8
R	7
tidyr	7
fs	6
kwb.datetime	6
data.table	5
lattice	5
lubridate	5
kwb.event	4
kwb.plot	4
readxl	4
xml2	4
digest	3
hydroGOF	3
janitor	3
jsonlite	3
kwb.db	3
openxlsx	3
plyr	3
readr	3
rlang	3
tibble	3
withr	3
yaml	3
cellranger	2
crayon	2
devtools	2
forcats	2
ggforce	2
gh	2
httr	2
kwb.fakin	2
kwb.file	2
rvest	2
shiny	2
usethis	2
xts	2
assertthat	1
blogdown	1
callr	1
codemetar	1
colorRamps	1
compare	1
dbplyr	1
desc	1
dygraphs	1
EnvStats	1
fasttime	1
fst	1
ggrepel	1
glue	1
gplots	1
gridExtra	1
jsonld	1
kwb.base	1
kwb.code	1
kwb.endnote	1
kwb.logger	1
kwb.pkgstatus	1
kwb.read	1
kwb.readxl	1
kwb.vs2dh	1
latticeExtra	1
leaflet	1
magick	1
manipulate	1
networkD3	1
openssl	1
pkgdown	1
pkgnet	1
PKI	1
plotrix	1
printr	1
purrr	1
qmrparser	1
RCurl	1
rematch2	1
remotes	1
reshape	1
RMySQL	1
RODBC	1
rorcid	1
scales	1
sessioninfo	1
sfsmisc	1
shapefiles	1
shinythemes	1
sp	1
stringi	1
travis	1
treemap	1
wordcloud2	1
XML	1

wordcloud2::wordcloud2(dep_sug_count,
                       minSize = 0.4, 
                       size = 1)

7 Session Info

Plattform

name	value
version	R version 4.1.0 (2021-05-18)
os	macOS Catalina 10.15.7
system	x86_64, darwin17.0
ui	X11
language	(EN)
collate	en_US.UTF-8
ctype	en_US.UTF-8
tz	UTC
date	2021-07-12

Packages

#>  package     * version date       lib source                              
#>  assertthat    0.2.1   2019-03-21 [1] CRAN (R 4.1.0)                      
#>  bslib         0.2.5.1 2021-05-18 [1] CRAN (R 4.1.0)                      
#>  cachem        1.0.5   2021-05-15 [1] CRAN (R 4.1.0)                      
#>  cli           3.0.0   2021-06-30 [1] CRAN (R 4.1.0)                      
#>  codemetar   * 0.3.0   2021-07-12 [1] Github (ropensci/codemetar@5d8a3c5) 
#>  crayon        1.4.1   2021-02-08 [1] CRAN (R 4.1.0)                      
#>  curl          4.3.2   2021-06-23 [1] CRAN (R 4.1.0)                      
#>  DBI           1.1.1   2021-01-15 [1] CRAN (R 4.1.0)                      
#>  desc          1.3.0   2021-03-05 [1] CRAN (R 4.1.0)                      
#>  digest        0.6.27  2020-10-24 [1] CRAN (R 4.1.0)                      
#>  dplyr       * 1.0.7   2021-06-18 [1] CRAN (R 4.1.0)                      
#>  ellipsis      0.3.2   2021-04-29 [1] CRAN (R 4.1.0)                      
#>  evaluate      0.14    2019-05-28 [1] CRAN (R 4.1.0)                      
#>  fansi         0.5.0   2021-05-25 [1] CRAN (R 4.1.0)                      
#>  fastmap       1.1.0   2021-01-25 [1] CRAN (R 4.1.0)                      
#>  fs            1.5.0   2020-07-31 [1] CRAN (R 4.1.0)                      
#>  generics      0.1.0   2020-10-31 [1] CRAN (R 4.1.0)                      
#>  glue          1.4.2   2020-08-27 [1] CRAN (R 4.1.0)                      
#>  highr         0.9     2021-04-16 [1] CRAN (R 4.1.0)                      
#>  htmltools     0.5.1.1 2021-01-22 [1] CRAN (R 4.1.0)                      
#>  htmlwidgets   1.5.3   2020-12-10 [1] CRAN (R 4.1.0)                      
#>  jquerylib     0.1.4   2021-04-26 [1] CRAN (R 4.1.0)                      
#>  jsonld      * 2.2     2020-05-27 [1] CRAN (R 4.1.0)                      
#>  jsonlite    * 1.7.2   2020-12-09 [1] CRAN (R 4.1.0)                      
#>  knitr         1.33    2021-04-24 [1] CRAN (R 4.1.0)                      
#>  lifecycle     1.0.0   2021-02-15 [1] CRAN (R 4.1.0)                      
#>  magrittr    * 2.0.1   2020-11-17 [1] CRAN (R 4.1.0)                      
#>  memoise       2.0.0   2021-01-26 [1] CRAN (R 4.1.0)                      
#>  pillar        1.6.1   2021-05-16 [1] CRAN (R 4.1.0)                      
#>  pingr         2.0.1   2020-06-22 [1] CRAN (R 4.1.0)                      
#>  pkgconfig     2.0.3   2019-09-22 [1] CRAN (R 4.1.0)                      
#>  pkgdown       1.6.1   2020-09-12 [1] CRAN (R 4.1.0)                      
#>  printr      * 0.1.1   2021-01-27 [1] CRAN (R 4.1.0)                      
#>  processx      3.5.2   2021-04-30 [1] CRAN (R 4.1.0)                      
#>  ps            1.6.0   2021-02-28 [1] CRAN (R 4.1.0)                      
#>  purrr       * 0.3.4   2020-04-17 [1] CRAN (R 4.1.0)                      
#>  R6            2.5.0   2020-10-28 [1] CRAN (R 4.1.0)                      
#>  ragg          1.1.3   2021-06-09 [1] CRAN (R 4.1.0)                      
#>  Rcpp          1.0.7   2021-07-07 [1] CRAN (R 4.1.0)                      
#>  rlang         0.4.11  2021-04-30 [1] CRAN (R 4.1.0)                      
#>  rmarkdown     2.9     2021-06-15 [1] CRAN (R 4.1.0)                      
#>  rprojroot     2.0.2   2020-11-15 [1] CRAN (R 4.1.0)                      
#>  sass          0.4.0   2021-05-12 [1] CRAN (R 4.1.0)                      
#>  sessioninfo   1.1.1   2018-11-05 [1] CRAN (R 4.1.0)                      
#>  stringi       1.6.2   2021-05-17 [1] CRAN (R 4.1.0)                      
#>  stringr       1.4.0   2019-02-10 [1] CRAN (R 4.1.0)                      
#>  systemfonts   1.0.2   2021-05-11 [1] CRAN (R 4.1.0)                      
#>  textshaping   0.3.5   2021-06-09 [1] CRAN (R 4.1.0)                      
#>  tibble      * 3.1.2   2021-05-16 [1] CRAN (R 4.1.0)                      
#>  tidyr         1.1.3   2021-03-03 [1] CRAN (R 4.1.0)                      
#>  tidyselect    1.1.1   2021-04-30 [1] CRAN (R 4.1.0)                      
#>  utf8          1.2.1   2021-03-12 [1] CRAN (R 4.1.0)                      
#>  V8            3.4.2   2021-05-01 [1] CRAN (R 4.1.0)                      
#>  vctrs         0.3.8   2021-04-29 [1] CRAN (R 4.1.0)                      
#>  withr         2.4.2   2021-04-18 [1] CRAN (R 4.1.0)                      
#>  wordcloud2    0.2.2   2021-07-12 [1] Github (Lchiffon/wordcloud2@8a12a3b)
#>  xfun          0.24    2021-06-15 [1] CRAN (R 4.1.0)                      
#>  yaml          2.2.1   2020-02-01 [1] CRAN (R 4.1.0)                      
#> 
#> [1] /Users/runner/work/_temp/Library
#> [2] /Library/Frameworks/R.framework/Versions/4.1/Resources/library

Pandoc

pandoc_directory	pandoc_version
/usr/local/bin/pandoc	2.7.3