library(tidyverse)

c1_count <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/062725_c1_cleaned_phab.csv"
c1_input_df <- read.csv(c1_count , header = TRUE) 

c2_count <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/062725_c2_cleaned_phab.csv"
c2_input_df <- read.csv(c2_count , header = TRUE) 

c3_count <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case3/062725_c3_cleaned_phab.csv"
c3_input_df <- read.csv(c3_count , header = TRUE) 

#phase of feature deployments 
# pre opt-in (0)
# opt-in beta (1)
# post-announcement pre-deployment (2)
# post-deployment opt-out (3) 
# c1 key dates
# opt-in = as.Date("2012-12-11)
# deployment announcement = as.Date("2013-06-06")
# deployment_date <- as.Date("2013-07-01")

c1_input_df <- c1_input_df |> 
  mutate(date_created = as.numeric(as.POSIXct(date_created, tz = "UTC"))) |>
  mutate(source = "c1") |>
  mutate(phase = case_when(
    date_created < as.numeric(as.POSIXct("2012-12-11", tz = "UTC")) ~ 0,                                 # pre opt-in
    date_created >= as.numeric(as.POSIXct("2012-12-11", tz = "UTC")) & date_created < as.numeric(as.POSIXct("2013-06-06", tz = "UTC")) ~ 1,  # opt-in beta
    date_created >=  as.numeric(as.POSIXct("2013-06-06", tz = "UTC"))  & date_created < as.numeric(as.POSIXct("2013-07-01", tz = "UTC")) ~ 2, # post-announcement pre-deployment
    date_created >= as.numeric(as.POSIXct("2013-07-01", tz = "UTC"))~ 3                             # post-deployment opt-out
  ))


# c2 key dates
# opt-in = as.Date("2011-10-03)
# deployment announcement = as.Date("2013-08-01")
# deployment_date <- as.Date("2013-08-28")

c2_input_df <- c2_input_df |>
  mutate(date_created = as.numeric(as.POSIXct(date_created, tz = "UTC"))) |>
  mutate(source = "c2") |>
  mutate(phase = case_when(
    date_created < as.numeric(as.POSIXct("2011-10-03", tz = "UTC")) ~ 0,                                 # pre opt-in
    date_created >= as.numeric(as.POSIXct("2011-10-03", tz = "UTC")) & date_created < as.numeric(as.POSIXct("2013-08-01", tz = "UTC")) ~ 1,  # opt-in beta
    date_created >=  as.numeric(as.POSIXct("2013-08-01", tz = "UTC"))  & date_created < as.numeric(as.POSIXct("2013-08-28", tz = "UTC")) ~ 2, # post-announcement pre-deployment
    date_created >= as.numeric(as.POSIXct("2013-08-28", tz = "UTC"))~ 3                             # post-deployment opt-out
  ))

# c3 key dates 
# opt-in = as.Date("2013-08-01)
# deployment announcement = as.Date("2015-06-12")
# deployment_date <- as.Date("2015-07-02")
c3_input_df <- c3_input_df %>%  
  mutate(date_created = as.numeric(as.POSIXct(date_created, tz = "UTC"))) |>
  mutate(source = "c3") |>
  mutate(phase = case_when(
    date_created < as.numeric(as.POSIXct("2013-08-01", tz = "UTC")) ~ 0,                                 # pre opt-in
    date_created >= as.numeric(as.POSIXct("2013-08-01", tz = "UTC")) & date_created < as.numeric(as.POSIXct("2015-06-12", tz = "UTC")) ~ 1,  # opt-in beta
    date_created >=  as.numeric(as.POSIXct("2015-06-12", tz = "UTC"))  & date_created < as.numeric(as.POSIXct("2015-07-02", tz = "UTC")) ~ 2, # post-announcement pre-deployment
    date_created >= as.numeric(as.POSIXct("2015-07-02", tz = "UTC"))~ 3                             # post-deployment opt-out
  ))

# Combine the dataframes into one
combined_df <- bind_rows(c1_input_df, c2_input_df, c3_input_df)

combined_task_df <- combined_df %>% 
  filter(comment_type == "task_description") |>
  mutate(time_to_close = date_closed - date_created,
         time_to_close_hours = as.numeric(difftime(date_closed, date_created, units = "hours"))
  ) 

ggplot(combined_task_df, aes(x = priority_score, y = phase, color = source)) +
  geom_point(alpha = 0.6) +                # Points, with some transparency
  geom_smooth(method = "loess", se = TRUE) + # LOESS curve, no confidence band
  theme_minimal()