Simplify and fix summary stats

qhtcp-workflow/apps/r/calculate_interaction_zscores.R

@@ -156,7 +156,7 @@ update_gene_names <- function(df, sgd_gene_list) {
 }
 
 calculate_summary_stats <- function(df, variables, group_vars = c("OrfRep", "conc_num", "conc_num_factor")) {
-  # Summarize the variables within the grouped data
+
   summary_stats <- df %>%
     group_by(across(all_of(group_vars))) %>%
     summarise(
@@ -172,11 +172,10 @@ calculate_summary_stats <- function(df, variables, group_vars = c("OrfRep", "con
     )
 
   # Create a cleaned version of df that doesn't overlap with summary_stats
-  cols_to_exclude <- unique(c(variables, group_vars))
+  cols_to_keep <- setdiff(names(df), names(summary_stats)[-which(names(summary_stats) %in% group_vars)])
   df_cleaned <- df %>%
-    select(-any_of(cols_to_exclude))
+    select(all_of(cols_to_keep))
 
-  # Join the stats back to the original dataframe
   df_with_stats <- left_join(df_cleaned, summary_stats, by = group_vars)
 
   return(list(summary_stats = summary_stats, df_with_stats = df_with_stats))