inlcuded the revised master file for 35k isolates

scripts/data_extraction.py

@@ -47,15 +47,13 @@ from reference_dict import my_aa_dict # CHECK DIR STRUC THERE!
 #=======================================================================
 #%% command line args
 arg_parser = argparse.ArgumentParser()
-#arg_parser.add_argument('-d', '--drug', help='drug name', default = 'pyrazinamide')
-#arg_parser.add_argument('-g', '--gene', help='gene name', default = 'pncA') # case sensitive
-arg_parser.add_argument('-d', '--drug', help='drug name', default = 'TESTDRUG')
-arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = 'testGene') # case sensitive
+arg_parser.add_argument('-d', '--drug', help='drug name', default = None)
+arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = None) # case sensitive
 args = arg_parser.parse_args()
 #=======================================================================
 #%% variable assignment: input and output paths & filenames
-#drug = 
-#gene = '
+#drug = 'pyrazinamide'
+#gene = 'pncA'
 
 drug = args.drug
 gene = args.gene
@@ -82,7 +80,8 @@ datadir = homedir + '/' + 'git/Data'
 #=======
 # input
 #=======
-in_filename  = 'original_tanushree_data_v2.csv'
+#in_filename  = 'original_tanushree_data_v2.csv'
+in_filename  = 'mtb_gwas_v3.csv'
 infile = datadir + '/' + in_filename
 print('Input file: ', infile
       , '\n============================================================')

scripts/pipeline.ini

@@ -1,6 +1,7 @@
 [extractor]
 data_dir = /home/tanu/git/Data
-master_file = original_tanushree_data_v2.csv
+#master_file = original_tanushree_data_v2.csv
+master_file = mtb_gwas_v3.csv
 
 # Relative Paths. Per-drug paths will be created like:
 #