From 5429b8fed70b52638c93b980fda36bfa93afba94 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Thu, 28 Apr 2022 13:02:30 +0100
Subject: [PATCH] saving data extraction updated script

---
 scripts/data_extraction.py | 61 +++++++++++++++++++++++++++++++++-----
 1 file changed, 54 insertions(+), 7 deletions(-)

diff --git a/scripts/data_extraction.py b/scripts/data_extraction.py
index be9fc9a..bc418d1 100755
--- a/scripts/data_extraction.py
+++ b/scripts/data_extraction.py
@@ -68,7 +68,7 @@ os.getcwd()
 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('--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('-m', '--make_dirs', help = 'Make dir for Data, input and output', action='store_true')
@@ -93,13 +93,13 @@ if not datadir:
     datadir = homedir + '/' + 'git/Data'
     
 if not indir:
-    indir = datadir + '/' + drug + '/input_v2'
+    indir = datadir + '/' + drug + '/input'
     
 if not outdir:
-    outdir = datadir + '/' + drug + '/output_v2'
+    outdir = datadir + '/' + drug + '/output'
 
 if make_dirs:
-    print('make_dirs is turned on, creating data dir:', datadir)
+    print('make_dirs is turned on, creating data dir (unless it already exists):', datadir)
     try: 
         os.makedirs(datadir, exist_ok = True) 
         print("Directory '%s' created successfully" %datadir) 
@@ -1411,7 +1411,7 @@ gene_LF3['drtype_numeric']  = gene_LF3['drtype'].map(drtype_map)
 gene_LF3['drtype'].value_counts()
 gene_LF3['drtype_numeric'].value_counts()
 
-#%% Multimode: drtype
+# Multimode: drtype
 #=============================
 # Recalculation: Revised drtype
 # max(multimode)
@@ -1520,7 +1520,7 @@ gene_LF3['dst_multimode'].value_counts()
 # Now get the max from multimode
 #gene_LF3['dst_mode']  = gene_LF3.groupby('mutationinformation')['dst_noNA'].max() # this somehow is not right!
 #gene_LF3['dst_noNA'] = gene_LF3['dst_multimode'].apply(lambda x: np.nanmax(x))
-gene_LF3['dst_mode'] = gene_LF3['dst_multimode'].apply(lambda x: np.nanmax(x))
+gene_LF3['dst_mode'] = gene_LF3['dst_multimode'].apply(lambda x: np.nanmax(x)) #ML
 
 # sanity checks
 #gene_LF3['dst_noNA'].equals(gene_LF3['dst_mode'])
@@ -1969,8 +1969,55 @@ if dr_muts.isin(other_muts).sum() & other_muts.isin(dr_muts).sum() > 0:
           , '\n============================================================='
           , '\nPost resolving ambiguity\n'
           , ambig_muts_rev_df['mutation_info_REV'].value_counts())
+    
+print('\n============================================================='
+      , '\n============================================================='
+      , '\###############################\n'
+      , '\nNumbers for ML workflows...'
+      , '\n###############################\n'
+
+      , '\ncolumn name [drug, old]:', drug, '\n'
+      , gene_LF4[drug].value_counts()
+      , '\nTotal drug samples[old]:', gene_LF4[drug].value_counts().sum()
+      , '\nPercentages:\n'
+      , gene_LF4[drug].value_counts(normalize = True)
+      , '\n-------------------------------------------------------------'
+
+      , '\ncolumn name [drug, revised]: dst_mode\n'
+      , gene_LF4['dst_mode'].value_counts()
+      , '\nTotal drug samples[revised]:', gene_LF4['dst_mode'].value_counts().sum()
+      , '\nPercentages:\n'
+      , gene_LF4['dst_mode'].value_counts(normalize = True)
+      , '\n-------------------------------------------------------------'
+          
+      , '\n-------------------------------------------------------------'
+      , '\ncolumn name: drtye_mode\n'
+      , gene_LF4['drtype_mode'].value_counts()
+      , '\nTotal drtype_mode:', gene_LF4['drtype_mode'].value_counts().sum()
+      , '\nPercentages:\n'
+      , gene_LF4['drtype_mode'].value_counts(normalize = True)
+      , '\n-------------------------------------------------------------'
+
+      , '\n-------------------------------------------------------------'    
+      , '\ncolumn name [dm_om, old]: mutation_info_orig\n'
+      , gene_LF4['mutation_info_orig'].value_counts()
+      , '\nTotal mutation_info_orig:', gene_LF4['mutation_info_orig'].value_counts().sum()
+      , '\nPercentages:\n'
+      , gene_LF4['mutation_info_orig'].value_counts(normalize = True)
+      , '\n-------------------------------------------------------------'
+            
+      , '\n-------------------------------------------------------------'
+      , '\ncolumn name [dm_om, revised]: mutation_info\n'
+      , gene_LF4['mutation_info'].value_counts()
+      , '\nTotal mutation_info:', gene_LF4['mutation_info'].value_counts().sum()
+      , '\nPercentages:\n'
+      , gene_LF4['mutation_info'].value_counts(normalize = True)
+      , '\n-------------------------------------------------------------'
+      
+      , '\n============================================================='
+      )  
 #=======================================================================
 print(u'\u2698' * 50,
       '\nEnd of script: Data extraction and writing files'
       '\n' + u'\u2698' * 50 )
-#%% end of script
\ No newline at end of file
+#%% end of script