## Examples for searching for packages
## Example 1 Roc function-------------------
## Some R Packages for ROC Curves
## https://rviews.rstudio.com/2019/03/01/some-r-packages-for-roc-curves/
## how to search CRAN for packages to plot ROC curves,
## and highlight six useful packages.
## Gábor Csárdi’s relatively new package pkgsearch to search through CRAN and see what’s out there.
## The package_search() function takes a text string as input and uses basic text mining techniques to search all of CRAN.
library(tidyverse) # for data manipulation
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2 ✓ purrr 0.3.4
## ✓ tibble 3.0.4 ✓ dplyr 1.0.2
## ✓ tidyr 1.1.2 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(dlstats) # for package download stats
library(pkgsearch) # for searching packages
## query for searching a number of interesting ROC-related packages.
rocPkg <- pkg_search(query="ROC",size=200) #87 packages
head(rocPkg)
## # A tibble: 6 x 14
## score package version title description date maintainer_name
## <dbl> <chr> <pckg_> <chr> <chr> <dttm> <chr>
## 1 9381. pROC 1.16.2 "Dis… "Tools for… 2020-03-19 16:30:07 Xavier Robin
## 2 4230. caTools 1.18.0 "Too… "Contains … 2020-01-17 08:40:26 Michael Dietze
## 3 1960. PRROC 1.3.1 "Pre… "Computes … 2018-06-19 09:42:55 Jan Grau
## 4 1592. surviv… 1.0.3 "Tim… "Compute t… 2013-01-13 19:38:55 Paramita Saha-…
## 5 1510. cvAUC 1.1.0 "Cro… "This pack… 2014-12-09 07:12:38 Erin LeDell
## 6 1406. precrec 0.11.2 "Cal… "Accurate … 2020-05-28 11:20:02 Takaya Saito
## # … with 7 more variables: maintainer_email <chr>, revdeps <int>,
## # downloads_last_month <int>, license <chr>, url <chr>, bugreports <chr>,
## # package_data <I<list>>
## narrowed down to orphaned packages and packages with a score less than 190.
rocPkgShort <- rocPkg %>% #55 packages
filter(maintainer_name != "ORPHANED", score > 190) %>%
select(score, package, downloads_last_month) %>%
arrange(desc(downloads_last_month))
length(rocPkgShort$package)
## [1] 55
head(rocPkgShort)
## # A tibble: 6 x 3
## score package downloads_last_month
## <dbl> <chr> <int>
## 1 4230. caTools 157700
## 2 9381. pROC 117782
## 3 924. ROCR 77549
## 4 1960. PRROC 11317
## 5 853. sROC 5823
## 6 229. riskRegression 4332
## the chosen ones (after browsing the documentation for the packages)
shortList <- c("pROC","precrec","ROCit", "PRROC","ROCR","plotROC")
downloads <- cran_stats(shortList)
head(downloads)
## start end downloads package
## 1 2015-01-01 2015-01-31 4617 pROC
## 5 2015-02-01 2015-02-28 4532 pROC
## 9 2015-03-01 2015-03-31 6254 pROC
## 13 2015-04-01 2015-04-30 7285 pROC
## 17 2015-05-01 2015-05-31 9079 pROC
## 21 2015-06-01 2015-06-30 7330 pROC
names(downloads)
## [1] "start" "end" "downloads" "package"
ggplot(downloads, aes(end, downloads, group=package, color=package)) +
geom_line() + geom_point(aes(shape=package)) +
scale_y_continuous(trans = 'log2')
## Example 2 Cox function--------------------
## search another package for COX function package
coxPkg<- pkg_search(query="COX",size=200)
coxPkgShort <- coxPkg %>%
filter(maintainer_name != "ORPHANED", score > 190) %>%
select(score, package, downloads_last_month) %>%
arrange(desc(downloads_last_month))
head(coxPkgShort)
## # A tibble: 6 x 3
## score package downloads_last_month
## <dbl> <chr> <int>
## 1 4722. survival 181762
## 2 1793. glmnet 78938
## 3 1224. survey 60810
## 4 1095. gbm 34251
## 5 802. spatstat 31082
## 6 845. rms 29276
cox_shortList <- c("survival","glmnet","survey","gbm","spatstat","rms")
cox_downloads <- cran_stats(cox_shortList)
ggplot(cox_downloads, aes(end, downloads, group=package, color=package)) +
geom_line() + geom_point(aes(shape=package)) +
scale_y_continuous(trans = 'log2')
## Example 3 excess of mortality------------------------------
excessPkg<-pkg_search(query="excess of mortality",size=200)
head(excessPkg$maintainer_name)
## [1] "Y. Foucher" "Yohann Foucher" "Joonas Miettinen"
## [4] "Mathieu Fauvernier" "Rob J Hyndman" "Reinhold Kainhofer"
excessPkgShort <- excessPkg %>%
filter(maintainer_name != "ORPHANED", score > 100) %>%
select(score, package, downloads_last_month) %>%
arrange(desc(downloads_last_month))
head(excessPkgShort)
## # A tibble: 4 x 3
## score package downloads_last_month
## <dbl> <chr> <int>
## 1 144. popEpi 2026
## 2 115. survPen 544
## 3 183. RISCA 451
## 4 201. ROCt 201
excess_shortList <- c("popEpi","survPen","RISCA","ROCt")
excess_downloads <- cran_stats(excess_shortList)
ggplot(excess_downloads, aes(end, downloads, group=package, color=package)) +
geom_line() + geom_point(aes(shape=package)) +
scale_y_continuous(trans = 'log2')
## end------------------