handling missing dir for data_extraction.py

scripts/data_extraction.py

@@ -59,14 +59,14 @@ import pandas as pd
 import numpy as np
 import argparse
 #=======================================================================
-#%% homdir and curr dir and local imports
+#%% dir and local imports
 homedir = os.path.expanduser('~') 
 # set working dir
 os.getcwd()
 os.chdir(homedir + '/git/LSHTM_analysis/scripts')
 os.getcwd()
 
-# import aa dict
+# Requires
 from reference_dict import my_aa_dict # CHECK DIR STRUC THERE!
 from tidy_split import tidy_split
 #=======================================================================
@@ -74,16 +74,52 @@ from tidy_split import tidy_split
 arg_parser = argparse.ArgumentParser()
 arg_parser.add_argument('-d', '--drug', help='drug name (case sensitive)', default = None)
 arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = None)
+arg_parser.add_argument('--datadir', help = 'Data Directory. By default, it assmumes homedir + git/Data')
+arg_parser.add_argument('-i', '--input_dir', help = 'Input dir containing pdb files. By default, it assmumes homedir + <drug> + input')
+arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + <drug> + output')
+
+arg_parser.add_argument('--debug', action ='store_true', help = 'Debug Mode')
+
 
 args = arg_parser.parse_args()
 #=======================================================================
 #%% variable assignment: input and output paths & filenames
 drug = args.drug
 gene = args.gene
+datadir = args.datadir
+indir   = args.input_dir
+outdir  = args.output_dir
 
 #drug = 'pyrazinamide'
 #gene = 'pncA'
 
+#%% input and output dirs and files
+#=======
+# dirs
+#=======
+if not datadir:
+    datadir = homedir + '/' + 'git/Data'
+    
+if not indir:
+    indir = datadir + '/' + drug + '/input'
+    
+if not outdir:
+    outdir = datadir + '/' + drug + '/output'
+
+# handle missing dirs here
+if not os.path.isdir(datadir):
+    print('ERROR: Data directory does not exist:', datadir
+    , '\nPlease create and ensure gwas data is present and then rerun')
+    sys.exit()
+if not os.path.isdir(indir):
+    print('ERROR: Input directory does not exist:', indir
+    , '\nPlease either create or specify indir and rerun')
+    sys.exit()
+if not os.path.isdir(outdir):
+    print('ERROR: Output directory does not exist:', outdir
+    , '\nPlease create or specify outdir and rerun')
+    sys.exit()
+#=======================================================================    
 gene_match = gene + '_p.'
 print('mut pattern for gene', gene, ':',  gene_match)
 
@@ -114,13 +150,6 @@ print('Extracting columns based on variables:\n'
     , resistance_col
 	, '\n===============================================================')
 #=======================================================================
-#%% input and output dirs and files
-#=======
-# dirs
-#=======
-datadir = homedir + '/' + 'git/Data'
-indir = datadir + '/' + drug + '/' + 'input'
-outdir = datadir + '/' + drug + '/' + 'output'
 
 #=======
 # input

scripts/reference_dict.py

@@ -41,9 +41,9 @@ datadir = homedir + '/' + 'git/Data'
 #=======
 in_filename = 'aa_codes.csv'
 infile = datadir + '/' + in_filename 
-print('Input filename:', in_filename
-      , '\nInput path:', datadir
-      , '\n============================================================')
+#print('Input filename:', in_filename
+#      , '\nInput path:', datadir
+#      , '\n============================================================')
 
 #%% Read input file
 aa_table = pd.read_csv(infile) #20, 6
@@ -67,11 +67,11 @@ my_aa.index
 # using 'index' creates a dict of dicts
 # using 'records' creates a list of dicts
 my_aa_dict = my_aa.to_dict('index') #20, with 5 subkeys
-print('Printing my_aa_dict:', my_aa_dict.keys())
+#print('Printing my_aa_dict:', my_aa_dict.keys())
 
 #FIXME : use the below in all code
 low_3letter_dict = my_aa.to_dict('index') #20, with 5 subkeys
-print('Printing lower-case 3 letter aa dict:',low_3letter_dict.keys())
+#print('Printing lower-case 3 letter aa dict:',low_3letter_dict.keys())
 
 #------------------------
 #2) 1-letter code as key
@@ -81,7 +81,7 @@ aa_1let.columns
 aa_1let.index
 
 oneletter_aa_dict = aa_1let.to_dict('index') #20, with 5 subkeys
-print('Printing one letter aa dict:', oneletter_aa_dict.keys())
+#print('Printing one letter aa dict:', oneletter_aa_dict.keys())
 
 #------------------------
 #3) amino acid name as key
@@ -91,7 +91,7 @@ aa_name.columns
 aa_name.index
 
 aa_name_dict = aa_name.to_dict('index') #20, with 5 subkeys
-print('Printing amino acid names aa dict:', aa_name_dict.keys())
+#print('Printing amino acid names aa dict:', aa_name_dict.keys())
 
 #------------------------
 #3) 3 letter uppercase as key
@@ -101,7 +101,7 @@ aa_up3let.columns
 aa_up3let.index
 
 up_3letter_aa_dict = aa_up3let.to_dict('index') #20, with 5 subkeys
-print('Printing upper case 3 letter aa dict:', up_3letter_aa_dict.keys())
+#print('Printing upper case 3 letter aa dict:', up_3letter_aa_dict.keys())
 
 #================================================
 # dict of aa with their corresponding properties

scripts/running_scripts

@@ -1,3 +1,8 @@
+#========
+# data extraction: Must be run first to extract mutations for each drug-gene combination
+#========
+./data_extraction.py -d pyrazinamide -g pncA 
+
 #========
 # foldx
 #========