library(tidyverse)
library(dsl)

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

dsl_df <- dsl_df |>
  dplyr::mutate(ttr_days = TTR_hours / 24) |>
  dplyr::mutate(task_resolution = dsl_score)

dev_model <- dsl(
  model = "logit", 
  formula = task_resolution ~ human_EP_prop_adac + human_TSOL_prop_adac + human_RK_prop_adac 
    + median_PC4_adac + median_PC3_adac + n_comments_before 
    + median_gerrit_reviewers + week_index + as.factor(isAuthorWMF) * as.factor(source),
  predicted_var = c("human_EP_prop_adac", "human_TSOL_prop_adac", "human_RK_prop_adac"),
  prediction = c("olmo_EP_prop_adac", "olmo_TSOL_prop_adac", "olmo_RK_prop_adac"),
  sample_prob = "sampling_prob", 
  cluster="source",
  cross_fit = 3,
  sample_split = 20,
  data=dsl_df
)
summary(dev_model)
#saveRDS(dev_model, "121625_logit_dsl.RDS")
dev_model <- readRDS("dsl/121625_logit_dsl.RDS")
summary(dev_model)
library(broom)
library(dplyr)
tidy.dsl <- function(x, conf.int = FALSE, conf.level = 0.95, exponentiate = FALSE, ...) {
  res <- suppressMessages(dsl:::summary.dsl(object = x, ci = conf.level, ...))
  terms <- row.names(res)
  cols <- c("estimate" = "Estimate", "std.error" = "Std. Error", "p.value" = "p value")
  if (conf.int) {
    cols <- c(cols, "conf.low" = "CI Lower", "conf.high" = "CI Upper")
  }
  out <- as.list(res)[cols]
  names(out) <- names(cols)
  out <- as_tibble(as.data.frame(out))
  out <- dplyr::bind_cols(term = terms, out)
  if (exponentiate)
    out <- broom:::exponentiate(out)
  return(out)
}
coef_df <- tidy.dsl(dev_model)
coef_df <- coef_df |>
  mutate(
    term = recode(term,
                  "week_index" = "Weeks from deployment",
                  "(Intercept)" = "Intercept",
                  "n_comments_before" = "# of comments prior to resolution",
                  "median_PC4_adac" = "Median Author PC4 Pre-resolution",
                  "median_PC3_adac" = "Median Author PC3 Pre-resolution",
                  "median_gerrit_reviewers" = "Median # of Code Reviewers (Gerrit)",
                  "human_TSOL_prop_adac" = "% of sentences discussing 'Solutions'",
                  "human_RK_prop_adac" = "% of sentences discussing 'Record Keeping'",
                  "human_EP_prop_adac" = "% of sentences discussing 'Existent Problems'",
                  "as.factor(source)c3" = "HTTP-deprecation (factor)",
                  "as.factor(source)c2" = "HTTPS-login (factor)",
                  "as.factor(isAuthorWMF)TRUE" = "WMF-affiliated Author (factor)",
                  "as.factor(isAuthorWMF)FALSE" = "Nonaffiliated Author (factor)",
                  "as.factor(isAuthorWMF)FALSE:as.factor(source)c2" = "Nonaffiliated Author:HTTPS-login",
                  "as.factor(isAuthorWMF)FALSE:as.factor(source)c3" = "Nonaffiliated Author:HTTP-deprecation",
                  "as.factor(isAuthorWMF)TRUE:as.factor(source)c2" = "WMF-affiliated Author:HTTPS-login",
                  "as.factor(isAuthorWMF)TRUE:as.factor(source)c3" = "WMF-affiliated Author:HTTP-deprecation",
                  ),
    term = factor(term, levels = rev(c(
      "Intercept",   
      "% of sentences discussing 'Existent Problems'",        
      "% of sentences discussing 'Solutions'",
      "% of sentences discussing 'Record Keeping'",
      "Median Author PC4 Pre-resolution",
      "Median Author PC3 Pre-resolution",
      "# of comments prior to resolution",
      "Median # of Code Reviewers (Gerrit)",
      "Weeks from deployment",
      "HTTPS-login (factor)",
      "HTTP-deprecation (factor)",
      "Nonaffiliated Author (factor)",
      "WMF-affiliated Author (factor)",
      "Nonaffiliated Author:HTTPS-login",
      "WMF-affiliated Author:HTTPS-login",
      "Nonaffiliated Author:HTTP-deprecation",
      "WMF-affiliated Author:HTTP-deprecation"
    )))
  )
dsl_coefs <- ggplot(coef_df, aes(x = estimate, y = term)) +
  geom_point(size = 1) +
  geom_errorbar(aes(xmin = estimate - 1.96*std.error, xmax = estimate + 1.96 *std.error), height = 0.2) +
  geom_vline(xintercept = 0, linetype = "dashed", color = "red") +
  labs(x = "Log-odds Coefficient Estimate",
       y = "Variable") +
  theme_minimal()
dsl_coefs
ggsave(
  filename = "121625_dsl_coefs.png",
  plot = dsl_coefs,
  width = 6,    # inches
  height = 6,   # inches
  dpi = 800     # high resolution
)