Absorb finite filter

qhtcp-workflow/apps/r/calculate_interaction_zscores.R

@@ -579,7 +579,7 @@ generate_interaction_plot_configs <- function(df, variables) {
     AUC = c(-6500, 6500)
   )
 
-  df_filtered <- filter_data_for_plots(df, variables, missing = TRUE, limits_map)
+  df_filtered <- filter_data(df, variables, missing = TRUE, limits_map)
 
   # Define annotation label functions
   generate_annotation_labels <- function(df, var, annotation_name) {
@@ -672,7 +672,7 @@ generate_interaction_plot_configs <- function(df, variables) {
 
 generate_rank_plot_configs <- function(df, variables, is_lm = FALSE, adjust = FALSE) {
 
-  df_filtered <- filter_data_for_plots(df, variables, missing = TRUE)
+  df_filtered <- filter_data(df, variables, missing = TRUE)
 
   for (var in variables) {
     avg_zscore_col <- paste0("Avg_Zscore_", var)
@@ -776,22 +776,20 @@ generate_correlation_plot_configs <- function(df, variables) {
   return(configs)
 }
 
-filter_and_print_non_finite <- function(df, vars_to_check, print_vars) {
-  non_finite_rows <- df %>% filter(if_any(all_of(vars_to_check), ~ !is.finite(.)))
-  
-  if (nrow(non_finite_rows) > 0) {
-    message("Filtering non-finite rows:")
-    print(non_finite_rows %>% select(all_of(print_vars)), n = 200)
-  }
-  
-  df %>% filter(if_all(all_of(vars_to_check), is.finite))
-}
-
-filter_data_for_plots <- function(df, variables, missing = FALSE, limits_map = NULL) {
+filter_data <- function(df, variables, nf = FALSE, missing = FALSE, limits_map = NULL) {
   
   # Loop through each variable to filter and print missing/out-of-range data
   for (variable in variables) {
     y_var_sym <- sym(variable)
+
+    if (nf) {
+      non_finite <- df %>% filter(!is.finite(!!y_var_sym))
+      if (nrow(non_finite) > 0) {
+        message("Non-finite rows for variable ", variable, ":")
+        print(non_finite)
+      }
+      df <- df %>% filter(is.finite(!!y_var_sym))
+    }
     
     # Filter missing data
     if (missing) {
@@ -844,7 +842,7 @@ main <- function() {
       update_gene_names(args$sgd_gene_list) %>%
       as_tibble()
 
-    # Quality Control: Filter rows above tolerance
+    # Filter rows above delta background tolerance
     df_above_tolerance <- df %>% filter(DB == 1)
     df_na <- df %>% mutate(across(all_of(summary_vars), ~ ifelse(DB == 1, NA, .)))
     df_no_zeros <- df_na %>% filter(L > 0)
@@ -857,20 +855,20 @@ main <- function() {
     message("Calculating summary statistics before quality control")
     ss <- calculate_summary_stats(df, summary_vars, group_vars = group_vars)
     df_stats <- ss$df_with_stats
-    df_filtered_stats <- filter_and_print_non_finite(df_stats, "L", print_vars)
+    message("Filtering non-finite data")
+    df_filtered_stats <- filter_data(df_stats, c("L"), nf = TRUE)
 
     message("Calculating summary statistics after quality control")
     ss <- calculate_summary_stats(df_na, summary_vars, group_vars = group_vars)
     df_na_ss <- ss$summary_stats
     df_na_stats <- ss$df_with_stats
     write.csv(df_na_ss, file = file.path(out_dir, "summary_stats_all_strains.csv"), row.names = FALSE)
-    # Filter out non-finite rows for plotting
-    df_na_filtered_stats <- filter_and_print_non_finite(df_na_stats, "L", print_vars)
+    df_na_filtered_stats <- filter_data(df_na_stats, c("L"), nf = TRUE)
 
     message("Calculating summary statistics after quality control excluding zero values")
     ss <- calculate_summary_stats(df_no_zeros, summary_vars, group_vars = group_vars)
     df_no_zeros_stats <- ss$df_with_stats
-    df_no_zeros_filtered_stats <- filter_and_print_non_finite(df_no_zeros_stats, "L", print_vars)
+    df_no_zeros_filtered_stats <- filter_data(df_no_zeros_stats, c("L"), nf = TRUE)
 
     message("Filtering by 2SD of K")
     df_na_within_2sd_k <- df_na_stats %>%