This R script creates a visualization showing CRAN packages by year added. Current (partial year excluded)

CRAN_package_count_by_year_visualization.R

#This R script create a visualization showing CRAN packages by year added.
library(rvest)
library(ggplot2)
library(cowplot) 

URL<- "https://cran.r-project.org/web/packages/available_packages_by_date.html"
#scrape table data from CRAN website
getthis<- xml2::read_html(URL) 
cran_df<-rvest::html_table(getthis) %>% data.frame(.)

#Summarize data by year
new_by_year<- as.Date(cran_df$Date) %>%
  format(., "%Y") %>% table(.) %>% data.frame(.)
names(new_by_year)[1]<-"year"

#get today's date
today_is<-Sys.Date()

#Exclude data for the current (partial) year
new_by_year <- new_by_year[!new_by_year$year == (today_is %>% format(., "%Y")),]

#plot 
p<-ggplot(new_by_year, mapping=aes(year, Freq))+
  geom_col(fill = "skyblue2", alpha = 0.7) + 
  scale_y_continuous(expand = expansion(mult = c(0, 0.05))) +
  theme_minimal_hgrid(11)+
  ggtitle("Available CRAN packages By Publication Date")+
  labs(subtitle = paste0("Data captured: ", today_is," Excludes current year."))+
  ylab("# of packages")
  
p<-p+ theme(plot.title = element_text(size=32),
            plot.subtitle = element_text(size=16),
            axis.text = element_text(size = 15),
            axis.title = element_text(size = 15))
p
png(file="cran.png",
    width=1200, height=700)
p
dev.off()