update createOptSplit.py

src/createOptimumSplit.py

@@ -2,8 +2,10 @@ import sys
 import operator
 
 cov = open(sys.argv[1],'r')
-genomes = open(sys.argv[2],'r')
-nrToSplit = int(sys.argv[3])
+perc = open(sys.argv[2],'r')
+genomes = open(sys.argv[3],'r')
+nrToSplit = int(sys.argv[4])
+outf = sys.argv[5]
 
 genomeDict = dict()
 contigDict = dict()
@@ -35,15 +37,33 @@ for line in cov:
 
 print 'Found %d genomes again. Hope they match'%(len(covDict))
 
+
+perc.readline()
+perc.readline()
+
+percDict = dict()
+
+for line in perc:
+    #Get the sum coverage
+    s = 0.0
+    l = line.rstrip().split('\t')
+    for i in range(1,len(l)):
+        s += float(l[i])
+    percDict[l[0]] = s
+
+print 'Found %d genomes again. Hope they match'%(len(percDict))
+
+
 table = []
 #Get an approximation of how many reads hit each genome. This is as close as you will get to figuring out how long running it is going to take
 for k in genomeDict.keys():
-    read = genomeDict[k]*covDict[k]/100
+    read = genomeDict[k]*covDict[k]/100 #*percDict[k]/100
     table.append((k,read))
 
-#Now, sort the table
-t = sorted(table,key=operator.itemgetter(1),reverse=True)
 
+#Now, sort the table
+t = sorted(table,key=operator.itemgetter(1),reverse=True)#must be True
+#print(head(t))
 #Great, now get these into X bins
 
 res = [0]*nrToSplit
@@ -55,7 +75,7 @@ for k in range(len(t)):
     res[pos] += table[k][1]
     names[t[k][0]] = pos
 
-outf = sys.argv[4]
+#outf = sys.argv[5]
 #Open as many files as bins
 fileDict = dict()
 for i in xrange(nrToSplit):