scripts for wrangling data

01-get_data.R

@@ -0,0 +1,14 @@
+library(googledrive)
+library(fs)
+
+usage_reports <- drive_ls("https://drive.google.com/drive/folders/1E3LuHI1jTm22cz7xXAjScMkQcMupuH8M")
+purrr::walk2(usage_reports$id, usage_reports$name, \(id, name) {
+  dir_create(path("data", "usage"))
+  drive_download(id, path = path("data", "usage", name))
+})
+
+registration_reports <- drive_ls("https://drive.google.com/drive/folders/1DOVUhsCiW-nE-6q3ehsjBEYulzt_l4Pl")
+purrr::walk2(registration_reports$id, registration_reports$name, \(id, name) {
+  dir_create(path("data", "registration"))
+  drive_download(id, path = path("data", "registration", name))
+})

02-wrangle_data.R

@@ -0,0 +1,69 @@
+library(readr)
+library(dplyr)
+library(fs)
+library(purrr)
+library(janitor)
+
+usage_reports <- dir_ls(path("data", "usage"))
+reg_reports <- dir_ls(path("data", "registration"))
+
+read_wrangle_usage <- function(usage_report) {
+  # check that metadata exists
+  if (!grepl(pattern = "Topic", readLines(usage_report, n = 1))) {
+    warning("Usage report doesn't contain meeting information")
+    #return
+    main <- read_csv(usage_report) |>
+      clean_names() |> 
+      rename(name = name_original_name, attendance_duration = total_duration_minutes)
+    #add meeting ID from filename
+    ID <-
+      path_file(usage_report) |> 
+      path_ext_remove() |> 
+      gsub("participants_", "", x = _)
+
+    #return:
+    main |> 
+      mutate(id = ID, .before = everything()) 
+
+  } else {
+
+    main <- read_csv(usage_report, skip = 3) |>
+      clean_names() |> 
+      rename(name = name_original_name, attendance_duration = total_duration_minutes)
+    head <- read_csv(usage_report, n_max = 1, col_types = cols(ID = col_character())) |> 
+      clean_names() |> 
+      rename(meeting_duration = duration_minutes)
+
+    #return:
+    bind_cols(head, main)
+  }
+}
+
+usage <- map(usage_reports, read_wrangle_usage) |> list_rbind()
+usage
+
+
+read_wrangle_registration <- function(reg_report) {
+  df <- read_csv(reg_report, id = "file")
+  df <- df |> clean_names() |>
+    rename(
+      college = contains("college"),
+      department = contains("department"),
+      career_stage = contains("career_stage"),
+      how_discovered = contains("how_did_you_hear"),
+      mailing_list = contains("mailing_list")
+    ) |> 
+    # get meeting ID
+    mutate(
+      id = path_file(file) |> fs::path_ext_remove() |> gsub("_RegistrationReport", "", x = _),
+      .before = file
+    ) |> 
+    select(-any_of(c("x11", "file")))
+  df
+}
+
+registration <- map(reg_reports, read_wrangle_registration) |> list_rbind()
+
+attended <- left_join(usage, registration)
+
+write_csv(attended, "data/attended.csv")