wrapper script basic_barplots_PS.R now takes cmd and calls functions to generate plots.Tested and verfiied.

scripts/plotting/plotting_data.R

@@ -6,13 +6,12 @@
 library(data.table)
 library(dplyr)
 #########################################################
-# FIXME (not urgent!): Dirty function return nothing, but creates global dfs
+
 # plotting_data(): formatting data for plots
 # input args: 
  ## input csv file
  ## lig cut off dist, default = 10 Ang
-# output: None
-# Side effects: global dfs (formatted and added columns)
+# output: list of 4 dfs, that need to be decompressed
   ## my_df
   ## my_df_u
   ## my_df_u_lig
@@ -24,18 +23,7 @@ my_df_u     = data.frame()
 my_df_u_lig = data.frame()
 dup_muts    = data.frame()
   
-cat(paste0("Input file 1:", infile_params, '\n') )
-
-# These globals are created by import_dirs()
-#cat('columns based on variables:\n'
-#    , drug
-#    , '\n'
-#    , dr_muts_col
-#    , '\n'
-#    , other_muts_col
-#    , "\n"
-#    , resistance_col
-#    , '\n===============================================================')
+cat(paste0("\nInput file to prepare for plotting:", infile_params, "\n") )
 
 #===========================
 # Read file: struct params
@@ -73,7 +61,7 @@ if (my_min == -1 && my_max == 1){
       , "\nProceeding with assigning foldx outcome category")
 }else{
   cat("\nFAIL: could not scale foldx ddg values"
-      , "Aborting!")
+      , "Aborting!\n")
 }
 
 #------------------------------
@@ -87,7 +75,7 @@ c2 = table(my_df$ddg < 0)
 if ( all(c1 == c2) ){
   cat("\nPASS: foldx outcome successfully created")
 }else{
-  cat("\nFAIL: foldx outcome could not be created. Aborting!")
+  cat("\nFAIL: foldx outcome could not be created. Aborting!\n")
   exit()
 }
 
@@ -98,21 +86,21 @@ if ( all(c1 == c2) ){
 # check for duplicate mutations
 if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformation)){
   cat(paste0("\nCAUTION:", " Duplicate mutations identified"
-             , "\nExtracting these..."))
+             , "\nExtracting these...\n"))
   #cat(my_df[duplicated(my_df$mutationinformation),])
   dup_muts = my_df[duplicated(my_df$mutationinformation),]
   dup_muts_nu = length(unique(dup_muts$mutationinformation))
   cat(paste0("\nDim of duplicate mutation df:", nrow(dup_muts)
              , "\nNo. of unique duplicate mutations:", dup_muts_nu
-             , "\n\nExtracting df with unique mutations only"))
+             , "\n\nExtracting df with unique mutations only\n"))
   my_df_u = my_df[!duplicated(my_df$mutationinformation),]
 }else{
-  cat(paste0("\nNo duplicate mutations detected"))
+  cat(paste0("\nNo duplicate mutations detected\n"))
   my_df_u = my_df
 }
 
 upos = unique(my_df_u$position)
-cat("\nDim of clean df:"); cat(dim(my_df_u))
+cat("\nDim of clean df:"); cat(dim(my_df_u), "\n")
 cat("\nNo. of unique mutational positions:"); cat(length(upos), "\n")
   
 #===============================================