1
0
mw-lifecycle-analysis/analysis_data/data_verification_3.R
2025-10-27 10:28:08 -07:00

138 lines
4.2 KiB
R

library(tidyverse)
library(stringr)
library(tidyr)
library(dplyr)
library(purrr)
main_csv <- "~/analysis_data/stale_unifieds/100625_unified_w_affil.csv"
main_df <- read.csv(main_csv, header = TRUE)
#filter out existing olmo stuff
main_df <- main_df |>
select(-starts_with("olmo"))
#dedupe Task with changed title and duplicate entries
first_rows <- main_df |>
filter(id %in% c(20846, 20847)) |>
distinct(id, .keep_all = TRUE)
others <- main_df |>
filter(!(id %in% c(20846, 20847))) |>
filter(id != 23366)
main_df <- bind_rows(others, first_rows)
desc_info <- main_df %>%
filter(comment_type == "task_description") %>%
group_by(TaskPHID) %>%
ungroup() %>%
transmute(
TaskPHID,
task_desc_author = AuthorPHID,
task_desc_dateClosed = as.POSIXct(date_closed, origin = "1970-01-01", tz = "UTC")
)
#identifying comments in ADAC set
main_df <- main_df |>
mutate(created = as.POSIXct(date_created, origin = "1970-01-01", tz = "UTC")) |>
left_join(desc_info, by = "TaskPHID") |>
mutate(
ADAC = as.integer(
!is.na(task_desc_author) &
AuthorPHID == task_desc_author &
(is.na(task_desc_dateClosed) | created < task_desc_dateClosed)
)
)
# add dictionary values
modal_verb_list <- c("will", "may", "can", "shall", "must",
"ought", "do", "need", "dare",
"will not", "may not", "cannot", "shall not",
"must not", "do not", "don't", "need not",
"dare not", "won't", "can't")
modal_regex <- paste0("\\b(", paste(modal_verb_list, collapse = "|"), ")\\b")
main_df <- main_df |>
mutate(
comment_text = dplyr::coalesce(comment_text, ""), # handle NA
modal_verbs = stringr::str_count(comment_text, stringr::regex(modal_regex, ignore_case = TRUE)),
log1p_mv = log1p(modal_verbs)
)
pca_csv <- "~/analysis_data/102125_constituent_dfs/102025_total_pca_df.csv"
pca_df <- read.csv(pca_csv, header = TRUE)
pca_df <- pca_df |>
select(starts_with("PC"),
id)
first_join <- main_df|>
left_join(
pca_df,
by = "id"
)
olmo_csv <- "~/analysis_data/102125_constituent_dfs/all_102125_olmo_batched_categorized.csv"
olmo_df <- read.csv(olmo_csv, header = TRUE)
olmo_df <- olmo_df |>
mutate(olmo_cleaned_sentences = cleaned_sentences,
olmo_sentence_labels = sentence_categories)|>
select(id, olmo_cleaned_sentences, olmo_sentence_labels)
second_join <- first_join|>
left_join(
olmo_df,
by = "id"
)
#wrangling human labels
large_human_labels_csv <- "~/analysis_data/102125_constituent_dfs/102025_human_labels.csv"
large_human_labels_df <- read.csv(large_human_labels_csv, header = TRUE)
small_human_labels_csv <- "~/analysis_data/102125_constituent_dfs/102125_human_info_sample.csv"
small_human_labels_df <- read.csv(small_human_labels_csv, header = TRUE)
#TODO
# [ x ] collate the two samples into one
large_human_labels_df <- large_human_labels_df |> select(id, cleaned_sentences, human_label)
small_human_labels_df <- small_human_labels_df |> select(id, cleaned_sentences, human_label)
human_labels_df <- rbind(large_human_labels_df, small_human_labels_df)
# [ x ] aggregate sentence level rows into comment level
human_labels_reduced <- human_labels_df %>%
group_by(id) %>%
summarise(
cleaned_sentences = list(cleaned_sentences),
human_labels = list(str_squish(human_label)),
.groups = "drop"
)
# [ x ] merge into unified data set
third_join <- second_join |>
left_join(
human_labels_reduced,
by="id"
)
# [ x ] clean/drop needless fields
unified_df <- third_join |>
select(-same_author) |>
mutate(across(c(human_labels, cleaned_sentences),
~ {
x <- as.character(.x)
x_trim <- str_squish(x)
ifelse(x_trim == "NULL",
NA_character_,
x)
}))
# [ x ] verify set
length(unique(unified_df$TaskPHID))
length(unique(unified_df$id))
pulling <- unified_df |>
filter(id == "24695" | id == "24696")
pulling <- unified_df |>
filter(id == "23366" | id == "20846" | id == "20847")
write.csv(unified_df, "102725_unified.csv", row.names = FALSE)