library(tidyverse)
library(stringr)
library(tidyr)
library(dplyr)
library(purrr)

main_csv <- "~/analysis_data/100625_unified_w_affil.csv"
main_df <- read.csv(main_csv, header = TRUE) 

duplicates <- main_df[duplicated(main_df[, c("comment_text", "TaskPHID", "AuthorPHID")]) |
                   duplicated(main_df[, c("comment_text", "TaskPHID", "AuthorPHID")], fromLast = TRUE), ]
pulling <- main_df |>
  filter(id == "24695" | id == "24696")