library(tidyverse)
#library(dsl)
library(dplyr)
dsl_csv <-"~/dsl/110925_DSL_df_adac.csv"
dsl_df <- read.csv(dsl_csv, header = TRUE) 


outcome_summary <- dsl_df |>
  group_by(source, isAuthorWMF)|>
  summarise(
    total_sum = sum(!is.na(resolution_outcome)),
    count_resolution_outcome = sum(resolution_outcome),
    success_prop = count_resolution_outcome / total_sum,
    median_ttr_days = median(TTR, na.rm = TRUE) / 24,
    median_comments_before_resolution = median(n_comments_before)
    )


library(ggplot2)
library(ggdist)


ggplot(
  dsl_df, 
  aes(
    x=n_comments_before,
    color=source,
    fill=source
  )
) +
  facet_grid(~isAuthorWMF) +
  stat_halfeye() +
  theme_minimal() 

dsl_df <- dsl_df |>
  mutate(priority = factor(priority, 
         levels = c("Unbreak Now!", "High", "Medium", "Low", "Lowest", "Needs Triage")))

ggplot(dsl_df, 
       aes(
         fill=resolution_outcome, 
         x=priority
       )) + 
  facet_grid(~source) +
  geom_bar() +
theme_minimal() 


signed_power <- function(x, p) {
  sign(x) * abs(x) ^ p
}

signed_log <- function(x) sign(x) * log1p(abs(x))  
dsl_df <- dsl_df |>
  mutate(
    sp_med_pc3_adac = signed_power(median_PC3_adac, 0.2),
    sp_med_pc4_adac = signed_power(median_PC4_adac, 0.2),
    sl_med_pc4_adac = signed_log(median_PC4_adac),
    sl_med_pc3_adac = signed_log(median_PC3_adac)
  )


ggplot(dsl_df, aes(
  y= log1p(TTR/24),
  x=sl_med_pc4_adac,
  shape=isAuthorWMF,
  color=isAuthorWMF
                   )) +
  facet_grid(~source) +
  theme_minimal() + 
  geom_smooth(method="loess", span=0.5) + 
  geom_point() + 
  scale_color_viridis_d()