library(tidyverse)

main_csv <- "~/dsl/102725_DSL_df_adac.csv"
main_df <- read.csv(main_csv  , header = TRUE)

main_df <- main_df |>
  mutate(
    pc_adac_delta = median_PC4_no_adac - median_PC4_adac,
    olmo_BI_adac_delta = olmo_BI_prop_no_adac - olmo_BI_prop_adac
  )

ggplot(main_df, aes(
  x = as.factor(phase),    # x-axis grouping
  y = olmo_BI_adac_delta,
  fill = resolution_outcome
)) +
  ylim(-3, 3) +
  geom_boxplot(alpha = 0.7, position = position_dodge(width = 0.9)) +
  facet_grid(. ~ source, scales = "fixed") +   # Facet by source; adjust as needed
  scale_fill_viridis_d() +
  theme_minimal() +
  labs(
    title = "Boxplot of PC4",
    x = "Comment_type",
    y = "PC4",
    fill = "isAuthorWMF?"
  )

ggplot(main_df, aes(x = week_index, 
                    y = median_PC3_adac, fill = resolution_outcome)) +
  facet_grid(~source, scales="fixed") +
  geom_point(shape = 21, alpha=0.3, size=2) +
  scale_fill_viridis_d() +
  theme_minimal() +
  labs(
    title = "PCs for Task Comments (Faceted by source and phase)",
    x = "PC4",
    y = "PC3",
  )

lm(main_df$human_BE_prop ~ main_df$median_PC1)