added combining funct & combining_mcsm_foldx script

scripts/combining_mcsm_foldx.py

@@ -0,0 +1,112 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+'''
+Created on Tue Aug  6 12:56:03 2019
+
+@author: tanu
+'''
+# FIXME: change filename  2(mcsm normalised data)
+# to be consistent like (pnca_complex_mcsm_norm.csv) : changed manually, but ensure this is done in the mcsm pipeline
+#=======================================================================
+# Task: combine 2 dfs with aa position as linking column
+
+# Input: 2 dfs
+#   <gene.lower()>_complex_mcsm_norm.csv
+#   <gene.lower()>_foldx.csv
+
+# Output: .csv of all 2 dfs combined
+
+# useful link
+# https://stackoverflow.com/questions/23668427/pandas-three-way-joining-multiple-dataframes-on-columns
+#=======================================================================
+#%% load packages
+import sys, os
+import pandas as pd
+import numpy as np
+#from varname import nameof
+import argparse
+from combining import combine_stability_dfs
+#=======================================================================
+#%% specify input and curr dir
+homedir = os.path.expanduser('~')
+
+# set working dir
+os.getcwd()
+os.chdir(homedir + '/git/LSHTM_analysis/scripts')
+os.getcwd()
+#=======================================================================
+#%% 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
+args = arg_parser.parse_args()
+#=======================================================================
+#%% variable assignment: input and output 
+#drug = 'pyrazinamide'
+#gene = 'pncA'
+#gene_match = gene + '_p.'
+
+drug = args.drug
+gene = args.gene
+#======
+# dirs
+#======
+datadir = homedir + '/' + 'git/Data'
+indir = datadir + '/' + drug + '/' + 'output'
+outdir =   datadir + '/' + drug + '/' + 'output'
+
+#=======
+# input
+#=======
+in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv'
+in_filename_foldx = gene.lower() + '_foldx.csv'
+
+infile_mcsm = indir + '/' + in_filename_mcsm
+infile_foldx = indir + '/' + in_filename_foldx
+
+print('\nInput path:', indir
+      , '\nInput filename1:', in_filename_mcsm
+      , '\nInput filename2:', in_filename_foldx
+      , '\n============================================================')
+
+#=======
+# output 
+#=======
+out_filename_comb = gene.lower() + '_mcsm_foldx.csv'
+outfile_comb =  outdir + '/' + out_filename_comb
+print('Output filename:', outfile_comb
+      , '\n============================================================')
+
+my_join_type = 'outer'
+#my_join_type = 'left'
+#my_join_type = 'right'
+#my_join_type = 'inner'
+
+# end of variable assignment for input and output files
+#%% call function
+#=======================================================================
+#combine_stability_dfs(mcsm_df, foldx_df, outfile)
+#=======================================================================
+def main():
+
+    combined_df = combine_stability_dfs(infile_mcsm, infile_foldx, my_join = my_join_type)
+    print('Combining 2 dfs...'
+          , '\nArguments to function combine_stability_dfs:'
+          , '\ndf1:', in_filename_mcsm
+          , '\ndf2:', in_filename_foldx
+          , '\njoin_type:', my_join_type
+          , '\ncombined df sneak peak:\n'
+          , combined_df.head())
+    
+    print('Writing output...')
+        
+    combined_df.to_csv(outfile_comb, index = False)
+
+    print('Finished writing output file'
+          , '\nOutput file:', outfile_comb
+          , '\nDimensions:', combined_df.shape) 
+    
+if __name__ == '__main__':
+    main()
+#======================================================================= 
+#%% end of script