library(tidyverse)
library(dsl)

dsl_csv <-"~/dsl/102725_DSL_df_adac.csv"
dsl_df <- read.csv(dsl_csv, header = TRUE) 


power_model <- power_dsl(
  labeled_size = c(100, 200, 300, 600, 1000),
  model = "logit", 
  formula = dsl_score ~ human_SOL_prop_adac + 
    median_gerrit_loc_delta + median_gerrit_reviewers + 
    as.factor(isAuthorWMF) + 
    as.factor(source) +
    median_PC3_adac +
    week_index,
  predicted_var = "human_SOL_prop_adac",
  prediction = "olmo_SOL_prop_adac",
  sample_prob = "sampling_prob",
  data=dsl_df
)
summary(power_model)
plot(power_model, coef_name = "human_SOL_prop_adac")

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

trial_model <- dsl(
  model = "logit", 
  formula = dsl_score ~ human_BI_prop_adac + 
    median_gerrit_loc_delta + median_gerrit_reviewers + 
    as.factor(isAuthorWMF) + 
    as.factor(author_closer) + 
    median_PC4_adac +
    week_index,
  predicted_var = "human_BI_prop_adac",
  prediction = "olmo_BI_prop_adac",
  sample_prob = "sampling_prob",
  data=dsl_df
)
summary(trial_model)

style_model <- dsl(
  model = "lm", 
  formula = human_BE_prop ~ 
    median_PC1 + median_PC4 + 
    as.factor(isAuthorWMF) + 
    as.factor(author_closer) + 
    median_PC3 +
    week_index,
  predicted_var = "human_BE_prop",
  prediction = "olmo_BE_prop",
  sample_prob = "sampling_prob",
  data=dsl_df
)
summary(style_model)