From e41fb78e37ba1913ec1a3228a9a7c4ad563c5e6e Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Wed, 15 Jul 2020 13:36:20 +0100
Subject: [PATCH] saved work before adding plots

---
 scripts/combining_dfs.py | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/scripts/combining_dfs.py b/scripts/combining_dfs.py
index d5253b8..fef2779 100755
--- a/scripts/combining_dfs.py
+++ b/scripts/combining_dfs.py
@@ -56,28 +56,28 @@ os.getcwd()
 from combining_FIXME import detect_common_cols
 #=======================================================================
 #%% 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 = 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('--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('--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')
+arg_parser.add_argument('--debug', action ='store_true', help = 'Debug Mode')
 
-#args = arg_parser.parse_args()
+args = arg_parser.parse_args()
 #=======================================================================
 #%% variable assignment: input and output 
-drug = 'pyrazinamide'
-gene = 'pncA'
-gene_match = gene + '_p.'
+#drug = 'pyrazinamide'
+#gene = 'pncA'
+#gene_match = gene + '_p.'
 
-#drug = args.drug
-#gene = args.gene
-#datadir      = args.datadir
-#indir        = args.input_dir
-#outdir       = args.output_dir
+drug    = args.drug
+gene    = args.gene
+datadir = args.datadir
+indir   = args.input_dir
+outdir  = args.output_dir
 #%%=======================================================================
 #==============
 # directories
@@ -385,7 +385,7 @@ print('Checking mutations in the two dfs:'
 #print('\nNo. of common muts:', np.intersect1d(combined_df['mutationinformation'], ors_df_ordered['mutationinformation']) )
 
 #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
-combined_df_all = pd.merge(combined_df, ors_df, on = merging_cols_m7, how = o_join)
+combined_df_all = pd.merge(combined_df, ors_df, on = merging_cols_m7, how = l_join)
 #combined_df_all.shape
 
 # FIXME: DIM
@@ -396,7 +396,7 @@ outdf_expected_cols = len(combined_df.columns) + len(ors_df_ordered.columns) - l
 #if combined_df_all.shape[1] == outdf_expected_cols and combined_df_all.shape[0] == outdf_expected_rows:  
 if combined_df_all.shape[1] == outdf_expected_cols and combined_df_all['mutationinformation'].nunique() == outdf_expected_rows:
     print('PASS: Df dimension match'
-          , '\nDim of combined_df_all with join type:', o_join
+          , '\nDim of combined_df_all with join type:', l_join
           , '\n', combined_df_all.shape
           , '\n===============================================================')
 else: