library(tidyverse)

neurobiber_description_pca_csv <-"~/p2/quest/092325_description_PCA_df.csv"
neurobiber_description_pca_df <- read.csv(neurobiber_description_pca_csv  , header = TRUE) 

neurobiber_subcomment_pca_csv <-"~/p2/quest/092325_subcomment_PCA_df.csv"
neurobiber_subcomment_pca_df <- read.csv(neurobiber_subcomment_pca_csv  , header = TRUE)


# Add comment_type column to each df
neurobiber_description_pca_df$comment_type <- "task_description"
neurobiber_subcomment_pca_df$comment_type <- "subcomment"

# Combine them
unified_df <- rbind(neurobiber_description_pca_df, neurobiber_subcomment_pca_df)

# look at correlation between PC1, PC2, and different outcome variables 
library(dplyr)
description_anova_results <- neurobiber_description_pca_df %>%
  group_by(source) %>%
  group_map(~ summary(aov(PC2 ~ phase, data = .x)), .keep = TRUE)
description_anova_results

discussion_anova_results <- neurobiber_subcomment_pca_df %>%
  group_by(source) %>%
  group_map(~ summary(aov(PC2 ~ phase, data = .x)), .keep = TRUE)
discussion_anova_results

# look at the representative comments for PC1 and PC2
top5 <- neurobiber_description_pca_df %>%
  arrange(desc(PC1)) %>%
  slice(500:510) %>%
  pull(text)

bottom5 <- neurobiber_description_pca_df %>%
  arrange(PC1) %>%
  slice(500:510) %>%
  pull(text)

cat("Top 10:20 comment_text by score:\n")
print(top5)

cat("\nBottom 10:20 comment_text by score:\n")
print(bottom5)


aggregated_neurobiber_description_pca_df <- neurobiber_description_pca_df |>
  group_by(AuthorWMFAffil, week_index, source, priority, closed_relevance, phase) %>%
  summarise(mean_PC1 = median(PC1),
            mean_PC2 = median(PC2),
            mean_PC3 = median(PC3),
            mean_PC4 = median(PC4),
            mean_PC5 = median(PC5))
library(scales)
library(ggplot2)


affiliationColors <-
  setNames( c('#5da2d8', '#c7756a')
            ,c("False", "True"))


long_df <- aggregated_neurobiber_description_pca_df %>%
  tidyr::pivot_longer(
    cols = starts_with("mean_PC"),
    names_to = "PC",
    values_to = "PC_value"
  )

unified_df$AuthorWMFAffil <- factor(unified_df$AuthorWMFAffil, levels = c("False", "True"))
unified_df <- unified_df[order(unified_df$AuthorWMFAffil), ]
ggplot(unified_df, aes(x = PC3, y = PC4, fill = AuthorWMFAffil)) +
  geom_point(shape = 21, alpha=0.3, size=2) +
  facet_grid(source ~ phase) +
  scale_fill_viridis_d() + # Or scale_fill_brewer/palette of your choice
  theme_minimal() +
  labs(
    title = "PCs for All Comments (Faceted by Source and Phase)",
    x = "PC3",
    y = "PC4",
    fill = "Comment Type"
  )