library(tidyverse)
library(dsl)

dsl_csv <-"111725_DSL_frame.csv"
dsl_df <- read.csv(dsl_csv, header = TRUE) 

base_model <- dsl(
  model = "logit", 
  formula = dsl_score ~ human_EP_prop_adac,
  predicted_var = "human_EP_prop_adac",
  prediction = "olmo_EP_prop_adac",
  sample_prob = "sampling_prob",
  data=dsl_df
)
summary(base_model)

case_model <- dsl(
  model = "logit", 
  formula = dsl_score ~ human_EP_prop_adac + as.factor(source),
  predicted_var = "human_EP_prop_adac",
  prediction = "olmo_EP_prop_adac",
  sample_prob = "sampling_prob",
  data=dsl_df
)
summary(case_model)

trial_model <- dsl(
  model = "logit", 
  formula = dsl_score ~ human_EP_prop_adac + human_TSOL_prop_adac + human_RK_prop_adac 
    + as.factor(source) + week_index + as.factor(isAuthorWMF) + median_PC4_adac + n_comments_before,
  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",
  data=dsl_df
)
summary(trial_model)

anova(dsl_df$olmo_RK_prop, dsl_df$median_gerrit_reviewers)
chisq.test(table(dsl_df$isAuthorWMF, dsl_df$author_closer))

c1_df <- dsl_df |>
  dplyr::filter(source=="c1")

felm_model <- dsl(
  model = "felm", 
  formula = TTR ~ human_EP_prop_adac + human_TSOL_prop_adac + human_RK_prop_adac 
  + week_index + as.factor(isAuthorWMF) + median_PC4_adac + n_comments_before,
  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",
  fixed_effect = "oneway",
  index = c("source"),
  cluster="source",
  data=dsl_df
)
summary(felm_model)

#https://github.com/naoki-egami/dsl/blob/537664a54163dda52ee277071fdfd9e8df2572a6/R/estimate_g.R#L39
felm_df <- dsl_df |>
  dplyr::mutate(ttr_days = TTR / 24)
felm_model <- dsl(
  model = "felm", 
  formula = ttr_days ~ human_EP_prop_adac,
  predicted_var = c("human_EP_prop_adac"),
  prediction = c("olmo_EP_prop_adac"),
  sample_prob = "sampling_prob",
  fixed_effect = "oneway",
  index = c("phase"),
  cluster="phase",
  data=felm_df
)
summary(felm_model)