diff cmpb2016/compare_repertoire_V.py @ 0:8be019b173e6 draft

Uploaded included tools

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cmpb2016/compare_repertoire_V.py	Sun Mar 18 05:54:20 2018 -0400
@@ -0,0 +1,65 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Sep 16 12:50:43 2014
+
+@author: chmaramis
+"""
+
+from __future__ import division
+import numpy as np
+from pandas import *
+from numpy import nan as NA
+import sys
+import time
+
+sw_reads = lambda x: x.startswith('Reads')
+sw_freq = lambda x: x.startswith('Freq')
+sw_gene = lambda x: x.startswith('V')
+
+def freqtoall(inputs):
+
+    mer=DataFrame()
+    
+    for x in range(0,len(inputs),2):
+        
+            ini = read_csv(inputs[x] , sep = '\t' , index_col = 0)
+            
+            ini.drop(ini.columns[np.where(ini.columns.map(sw_reads))[0]], axis=1, inplace=True)
+            
+            x1 = inputs[x+1].split('_')
+            ini.rename(columns={ini.columns[np.where(ini.columns.map(sw_freq))[0][0]]: x1[0]}, inplace=True)
+            
+            if mer.empty:
+                mer = DataFrame(ini)
+            else:
+                mer = merge(mer,ini, on=ini.columns[np.where(ini.columns.map(sw_gene))[0][0]] , how='outer')
+            
+    mer=mer.fillna(0)
+    mer['mean'] = mer.sum(axis=1)/(len(mer.columns)-1)
+    fr = 'mean'
+
+    mer=mer.sort_values(by = fr,ascending=False)
+    mer[fr] = mer[fr].map('{:.4f}'.format)
+    mer.index = range(1,len(mer)+1)
+    
+    return mer
+
+
+if __name__ == '__main__':   
+
+    start=time.time()
+
+    # Parse input arguments    
+    inputs = sys.argv[2:]
+    output = sys.argv[1]
+            
+    # Execute basic function
+    mer = freqtoall(inputs)
+    
+    # Save output to CSV files
+    if not mer.empty: 
+        mer.to_csv(output , sep = '\t')  
+        
+    # Print execution time
+    stop=time.time()
+    print('Runtime:' + str(stop-start))