A Tiny Analysis of Simply Statistics Posts

Simply Statistics is the internet’s favorite statistics blog which is lovingly maintained by Rafa Irizarry, Roger Peng, and Jeff Leek. I wanted to analyze their blog posts so these are just some initial scratchings:

library(dplyr)
library(git2r)

temp <- file.path(tempdir(), "simplystats.github.io")
if(!file.exists(temp) || !in_repository(temp)){
  dir.create(temp)
  clone("https://github.com/simplystats/simplystats.github.io.git", temp)  
}

posts <- data_frame(
  File_Name = list.files(file.path(temp, "_posts")),
  Full_Name = list.files(file.path(temp, "_posts"), full.names = TRUE)) %>% 
  mutate(Date = substring(File_Name, 1, 10)) %>% 
  mutate(Month = substring(Date, 1, 7)) %>% 
  mutate(Month = paste0(Month, "-01")) %>% 
  mutate(Month = as.Date(Month))

posts %>% 
  group_by(Month) %>% 
  summarize(Count = n()) %>% 
  with(., plot(Month, Count, type = "l", 
               xlab = "Date", ylab = "Number of Posts",
               main = "Number of Posts Over Time"))