In msperlin/afedR: Data and Functions for Book "Analyzing Financial and Economical Data with R"

# set function that will download the files
read_cranlogs_files <- function(date_in) {
  # Reads log files from http://cran-logs.rstudio.com/
  #
  # ARGS: date_in - date of log data
  require(tidyverse)
  require(lubridate)

  url_dl <- paste0('http://cran-logs.rstudio.com/', year(date_in), '/',
                   date_in, '-r.csv.gz')

  cat('\nReading ', url_dl)

  df <- read_csv(url_dl, col_types = cols())

  return(df)
}

# find out the availabe dates in url
library(rvest)
library(lubridate)

available_links <- read_html('http://cran-logs.rstudio.com/') %>%
  html_nodes(css = 'a') %>%
  html_attr('href')

# only keep links for R download (those with -r.csv.gz pattern)
idx <- str_detect(available_links, '-r.csv.gz')
r_links <- available_links[idx]

# find out dates 
dates_dls <- ymd(basename(r_links))
max_date <- max(dates_dls)

first_date <- as.Date('2020-01-01')
last_date <- as.Date('2020-01-15')

my_dates <- seq(first_date, 
                last_date, 
                by = '1 day')

library(purrr) 
library(tidyverse)

l_out <- map(my_dates, 
             safely(read_cranlogs_files, 
                    otherwise = tibble())) # return empty tibble in case of error

df_cranlogs <- bind_rows(map(l_out, 'result'))

# solution 
my_sol <- names(sort(table(df_cranlogs$country), 
               decreasing = TRUE)[1])

candidates <- unique(na.omit(df_cranlogs$country))
my_answers <- make_random_answers(my_sol, candidates)

Question

On the Rstudio CRAN logs website^[http://cran-logs.rstudio.com/] you will find data on download statistics for the base distribution of R in the Daily R downloads section. Using your programming skills, import all available data between r first_date and r last_date and aggregate them into a single table. Which country has the highest download count for R?

exams::answerlist(my_answers, markup = "markdown")

Solution

Meta-information

extype: schoice exsolution: r mchoice2string(c(TRUE, FALSE, FALSE, FALSE, FALSE), single = TRUE) exname: "batchgetsymbols dplyr" exshuffle: TRUE

msperlin/afedR documentation built on Sept. 11, 2022, 9:49 a.m.