library(tidyverse)

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

human_csv <-"~/analysis_data/102025_human_labels.csv"
human_df <- read.csv(human_csv, header = TRUE)  
selected_task_phids <- unique(human_df$TaskPHID)

set.seed(1893) # For reproducibility

# moment 1 of sampling 
#sampled_df <- main_df %>%
#  group_by(source) %>%
#  mutate(sampled_TaskPHID = TaskPHID %in% sample(unique(TaskPHID), 40)) %>%
#  ungroup() %>%
#  filter(sampled_TaskPHID) %>%
#  select(-sampled_TaskPHID) 

# moment 2 of sampling
sampled_tasks <- main_df |>
  filter(!(TaskPHID %in% selected_task_phids),
         source=="c1",
         phase=="3",
         isAuthorWMF=="TRUE",
         comment_type=="task_description")|>
  mutate(sampled_TaskPHID = TaskPHID %in% sample(unique(TaskPHID), 10)) %>%
  filter(sampled_TaskPHID) %>%
  select(-sampled_TaskPHID) 

sampled_task_phids <- unique(sampled_tasks$TaskPHID)

sampled_df <- main_df |>
  filter(TaskPHID %in% sampled_task_phids)

#labeling_sampled_df <- sampled_df %>%
#  group_by(source) %>%
#  mutate(
#    verification_sample = if_else(
#      TaskPHID %in% sample(unique(TaskPHID), min(8, length(unique(TaskPHID)))), 1L, 0L
#    )
#  ) %>%
#  ungroup()
  
#sentence_level_sample <- labeling_sampled_df |>
sentence_level_sample <- sampled_df |>
  mutate(
    cleaned_sentences = lapply(
      olmo_cleaned_sentences,
      function(x) {
        m <- str_match_all(x, "'([^']*)'|\"([^\"]*)\"")[[1]]
        # Both columns 2 and 3 may exist, but only one will be filled for each match
        vals <- c(m[,2], m[,3])
        vals <- vals[vals != "" & !is.na(vals)]
        return(vals)
      }
    )
  )|>
  unnest(cleaned_sentences)|>
  filter(cleaned_sentences != ", ") |>
  select(-olmo_sentence_categories, -starts_with("normalized"), -contains("gerrit"))


table(sentence_level_sample$verification_sample)
(nrow(sentence_level_sample) / 293) * 1.5
length(unique(sentence_level_sample$TaskPHID))

write.csv(sentence_level_sample, "102125_human_info_sample.csv", row.names = FALSE)