library(tidyverse)

dsl_csv <-"~/dsl/121625_DSL_frame.csv"
dsl_df <- read.csv(dsl_csv, header = TRUE) 

ttr_trajectory <- dsl_df |>
  mutate(ttr_weeks = TTR_hours / 168) |>
  mutate(isTriaged = if_else(priority == 'Needs Triage',
                                "Not Triaged",
                                "Triaged")) |>
  group_by(week_index, isTriaged, source) |>
  summarise(
    count = n(),
    mean_ttr = mean(ttr_weeks, na.rm = TRUE),
    sd_ttr = sd(ttr_weeks, na.rm = TRUE)
  )

ggplot(ttr_trajectory, aes(x = week_index)) +
  # Line for mean TTR
  geom_line(aes(y = mean_ttr, color = "Mean TTR"), size = 1) +
  # Ribbon for standard deviation
  geom_ribbon(aes(ymin = mean_ttr - sd_ttr, ymax = mean_ttr + sd_ttr),
              fill = "lightblue", alpha = 0.4) +
  # Line for count of tasks
  geom_line(aes(y = count, 
                color = "Count of New Tasks"), size = 1, linetype = "dashed") +
  # Facet the plot by source and triaged status
  facet_wrap(source ~ isTriaged, scales = "free_y") +
  labs(
    title = "TTR by Source and Triage Status (TODO)",
    x = "Week Index",
    y = "Mean TTR (in weeks)",
    color = "Metrics"
  ) +
  scale_color_manual(values = c("Mean TTR" = "blue", "Count of New Tasks" = "red")) +
  theme_minimal() +
  theme(
    strip.text = element_text(face = "bold", size = 12),
    axis.text = element_text(size = 10),
    axis.title = element_text(size = 12)
  )

dsl_df |>
  filter(week_index >= 4)|>
  filter(source == "c1") |>
  filter(priority == "Needs Triage")|>
  mutate(ttr_weeks = TTR_hours / 168) |>
  group_by(isAuthorWMF) |>
  summarise(
    mean_ttr = mean(ttr_weeks, na.rm = TRUE),
    sd_ttr = sd(ttr_weeks, na.rm = TRUE)
  )

triage <- dsl_df |>
  group_by(source, isAuthorWMF, priority)|>
  summarise(
    count = n()
  )