#!/usr/bin/env Rscript             
#########################################################
# TASK: formatting data that will be used for various plots

# useful links
#https://stackoverflow.com/questions/38851592/r-append-column-in-a-dataframe-with-frequency-count-based-on-two-columns
#########################################################
# working dir and loading libraries
getwd()
setwd("~/git/LSHTM_analysis/scripts/plotting")
getwd()

#source("Header_TT.R")
library(ggplot2)
library(data.table)
library(dplyr)

require("getopt", quietly = TRUE) #cmd parse arguments
#========================================================
# command line args
#spec = matrix(c(
#  "drug"   , "d", 1, "character",
#  "gene"   , "g", 1, "character"
#), byrow = TRUE, ncol = 4)

#opt = getopt(spec)

#drug = opt$druggene = opt$gene

#if(is.null(drug)|is.null(gene)) {
#  stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
#}
#========================================================
# FIXME: change to cmd
#%% variable assignment: input and output paths & filenames
drug = "pyrazinamide"
gene = "pncA"
gene_match = paste0(gene,"_p.")
cat(gene_match)

#=============
# directories and variables
#=============
datadir = paste0("~/git/Data")
indir = paste0(datadir, "/", drug, "/input")
outdir = paste0("~/git/Data", "/", drug, "/output")
plotdir = paste0("~/git/Data", "/", drug, "/output/plots")

dr_muts_col = paste0('dr_mutations_', drug)
other_muts_col  = paste0('other_mutations_', drug)
resistance_col = "drtype"

cat('columns based on variables:\n'
      , drug
      , '\n'
      , dr_muts_col
      , '\n'
      , other_muts_col
      , "\n"
      , resistance_col
      , '\n===============================================================')

#%%===============================================================