getopt and commandArgs examples, and AF/OR update to use getopt()

scripts/AF_and_OR_calcs.R

@@ -1,19 +1,37 @@
+#!/usr/bin/env Rscript                                                  
+#require('compare')
+require('getopt', quietly=TRUE) # We need to be able to parse arguments
 #########################################################
 # TASK: To calculate Allele Frequency and
 # Odds Ratio from master data
 # and add the calculated params to meta_data extracted from
 # data_extraction.py
 #########################################################
-getwd()
+#getwd()
 setwd('~/git/LSHTM_analysis/scripts')
-getwd()
+cat(c(getwd(),'\n'))
 
-options(scipen = 999) #disabling scientific notation in R.
+# Command line args
+spec = matrix(c(
+  "drug"   , "d", 1, "character",
+  "gene"   , "g", 1, "character"
+), byrow = TRUE, ncol = 4)
+
+opt = getopt(spec);
+
+drug = opt$drug
+gene = opt$gene
+
+if(is.null(drug)|is.null(gene)) {
+    stop('--drug and --gene must both be specified (case-sensitive)')
+    }
+
+#options(scipen = 999) #disabling scientific notation in R.
 #options(scipen = 4)  
 
 #%% variable assignment: input and output paths & filenames
-drug = 'pyrazinamide'
-gene = 'pncA'
+#drug = 'pyrazinamide'
+#gene = 'pncA'
 gene_match = paste0(gene,'_p.')
 cat(gene_match)
 
@@ -41,7 +59,8 @@ cat(paste0('Reading infile2: gene associated metadata:', infile_metadata))
 # outdir = 'git/Data/pyrazinamide/output'
 outdir = paste0('~/git/Data', '/', drug, '/', 'output')
 #out_filename = paste0(tolower(gene), '_meta_data_with_AF_OR.csv')
-out_filename = paste0(tolower(gene), '_AF_OR.csv')
+#out_filename = paste0(tolower(gene), '_AF_OR.csv')
+out_filename = paste0(tolower(gene), '_XXXXX_AF_OR.csv')
 outfile = paste0(outdir, '/', out_filename)
 cat(paste0('Output file with full path:', outfile))
 #%% end of variable assignment for input and output files
@@ -380,14 +399,14 @@ head(pvals_logistic)
 #=============================================
 
 # check ..(hmmm) perhaps separate script)
-afs['pnca_p.trp68gly']
-afs['pnca_p.gln10pro'] 
-afs['pnca_p.leu4ser'] 
-
-plot(density(log(ors_logistic)))
-plot(-log10(pvals))
-hist(log(ors)
-     , breaks = 100)
+#afs['pnca_p.trp68gly']
+#afs['pnca_p.gln10pro'] 
+#afs['pnca_p.leu4ser'] 
+#
+#plot(density(log(ors_logistic)))
+#plot(-log10(pvals))
+#hist(log(ors)
+#     , breaks = 100)
 
 # sanity check: if names are equal (just for 3 vars)
 all(sapply(list(names(afs)
@@ -395,11 +414,11 @@ all(sapply(list(names(afs)
                 , names(statistic_chi) # should return False
                 , names(ors_chi_cus)), function (x) x == names(ors_logistic)))
 
-compare(names(afs)
-        , names(pvals_chi)
-        , names(statistic_chi) #TEST: should return False, but DOESN'T 
-        , names(ors_chi_cus)
-        , names(stat_chi))$result
+#compare(names(afs)
+#        , names(pvals_chi)
+#        , names(statistic_chi) #TEST: should return False, but DOESN'T 
+#        , names(ors_chi_cus)
+#        , names(stat_chi))$result
 
 #=============== Now with all vars
 
@@ -484,4 +503,7 @@ cat('End of script: calculated AF, OR, pvalues and saved file')
 #df1 = gene_metadata
 #df2 = comb_AF_and_OR
 
+
+
+
 # COMMENT: will do the combining with the other OR and AF (in python)

scripts/commandArgs-example.r

@@ -0,0 +1,9 @@
+#!/usr/bin/env Rscript
+print('R Argument Test')
+
+cmd <- paste(commandArgs(), collapse=" ")
+cat("How R was invoked:\n");
+cat(cmd, "\n")
+
+args <- commandArgs(trailingOnly = TRUE)
+cat(c('Command Line Arguments supplied: ', args))

scripts/getopt-example.r

@@ -0,0 +1,14 @@
+#!/usr/bin/env Rscript
+require('getopt', quietly=TRUE)
+
+spec = matrix(c(
+  "drug"   , "d", 1, "character",
+  "gene"   , "g", 1, "character"
+), byrow=TRUE, ncol=4)
+
+opt = getopt(spec);
+
+drug = opt$drug
+gene = opt$gene
+
+cat(c('\nDrug:', drug, '\nGene:', gene, '\n'))