library(tidyverse)
library(stringr)
library(tidyr)
library(dplyr)
library(purrr)
# TODO
    # join the label data with the existing data from 0714 master
    # download and set up DSL library 
    # figure out how to use the sentence-level variables 
    # get the categorical variables encoded as integers, then wrapped as factors
    # figure out power at 200, 400, 500, 750, and 1000 
#joining sentences with their 
olmo_categorization_csv <-"~/dsl/inter_090725_sent_cats.csv"
sl_olmo_categorization_df <- read.csv(olmo_categorization_csv, header = TRUE) 

main_csv <- "~/p2/071425_master_discussion_data.csv"
main_df <- read.csv(main_csv, header = TRUE) 

joined_df <- left_join(
  sl_olmo_categorization_df,
  main_df %>% select(id, AuthorPHID),
  by = "id"
)