Migrate codebase from Python 2 to Python 3

.gitignore

@@ -0,0 +1,21 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg

BBChop/source/BBChop.py

@@ -49,7 +49,7 @@ def greedyStrat(counts,locPrior,likelihoodsObj,dag,skipProbs):
     # test where expected entropy is smallest
 
     expectedGain = [(currEntropy-entropyResults[i])*(numberType.one-skipProbs[i]) for
-                    i in xrange(len(entropyResults))]
+                    i in range(len(entropyResults))]
     (next,nextp)=findMax(expectedGain)
 
     return next
@@ -58,7 +58,7 @@ def greedyStrat(counts,locPrior,likelihoodsObj,dag,skipProbs):
 # would be expected to improve next gain in entropy.
 
 def nearlyGreedyStrat(counts,locPrior,likelihoodsObj,dag,skipProbs):
-    dlocs=[i for i in xrange(len(counts)) if counts[i][1]]
+    dlocs=[i for i in range(len(counts)) if counts[i][1]]
     (currEntropy,entropyResults,findProbs)=entropiesFast(counts,locPrior,likelihoodsObj,dag)
     (next,nextE)=findMin(entropyResults)
     if len(dlocs):
@@ -140,16 +140,16 @@ def addResult(self,location,observation):
             self.counts[location]=(t+1,d)
 
         if debug:
-            print "ct",self.counts
+            print("ct",self.counts)
 
 
     def search(self):
         (locProbs,evProb)=self.likelihoodsObj.probs(self.counts,self.locPrior,self.dag)
 
         (whereabouts,maxp) = findMax(locProbs)
         if debug:
-            print "lp",map(float,locProbs)
-            print "ct",self.counts
+            print("lp",list(map(float,locProbs)))
+            print("ct",self.counts)
         while(maxp<self.certainty):
             #decide where to seach next
 
@@ -174,9 +174,9 @@ def search(self):
 
 
             if debug:
-                print "lp",map(float,locProbs)
-                print "e",float(entropy(locProbs)),map(float,entropyResults)
-                print "fp",map(float,findProbs)
+                print("lp",list(map(float,locProbs)))
+                print("e",float(entropy(locProbs)),list(map(float,entropyResults)))
+                print("fp",list(map(float,findProbs)))
 
             (whereabouts,maxp) = findMax(locProbs)
 

BBChop/source/bbchop

@@ -46,7 +46,7 @@ options_long  = [
 ]
 
 def usage():
-    print """
+    print("""
 bbchop is a binary search program that works in the presense of false negatives. 
 
 bbchop -l <locations> -c <certainty> [<options>]
@@ -90,7 +90,7 @@ bbchop -i <file>      -c <certainty> [<options>]
                                            it is an arithmetic decay factor.
 
 
-"""
+""")
 
 
 def checkarg(arg,checkfunc):
@@ -108,7 +108,7 @@ likelihoodSet={"singlerate": likelihoods.singleRateCalc,
 
 def getIdentifiers(fname):
     try:
-        f=file(fname,"r")
+        f=open(fname,"r")
 
         res=[l.strip() for l in f]
         if len(res)==0:
@@ -119,10 +119,10 @@ def getIdentifiers(fname):
         return None   # caller must deal with error
 
 def getPrior(fname,N):
-    f=file(fname,"r")
+    f=open(fname,"r")
     prior=[float(l) for l in f]
     if len(prior)!=N:
-        raise "Wrong number of entries in prior file"
+        raise Exception("Wrong number of entries in prior file")
     return prior
 
 
@@ -203,17 +203,17 @@ class Args:
 
         if identifiersFilename is not None:
             if ancestryFilename is not None:
-                print "specification of ancestry and indentifiers are incompatible"
-                print "(identifiers are in ancestry file anyway)"
+                print("specification of ancestry and indentifiers are incompatible")
+                print("(identifiers are in ancestry file anyway)")
                 sys.exit(1)
             self.identifiers=getIdentifiers(identifiersFilename)
             if self.identifiers is None:
-                print "failed to read identifiers\n"
+                print("failed to read identifiers\n")
                 usage()
                 sys.exit()
 
         if ancestryFilename is not None:
-            f=file(ancestryFilename,"r")
+            f=open(ancestryFilename,"r")
             (self.identifiers,parents)=dagRead.read(f)
             f.close()
             self.thisDag=dag.dag(parents,len(parents))
@@ -223,27 +223,27 @@ class Args:
 
 
 
-        if likelihoodSet.has_key(self.likelihoodCalc.lower()):
+        if self.likelihoodCalc.lower() in likelihoodSet:
             self.likelihoodCalc=likelihoodSet[self.likelihoodCalc.lower()]
         else:
-            print "Argument error: Unknown likelihood function\n"
+            print("Argument error: Unknown likelihood function\n")
             usage()
             sys.exit()
 
 
         if self.logFileName is None and self.resume:
-            print "cannot resume: no logfile specified\n"
+            print("cannot resume: no logfile specified\n")
             usage()
-            sys.exit
+            sys.exit()
 
         if self.locations is None and self.identifiers is None:
-            print "Argument error: Must specify number of locations or file of identifiers\n"
+            print("Argument error: Must specify number of locations or file of identifiers\n")
             usage()
             sys.exit(1)
         elif self.locations is None:
             self.locations=len(self.identifiers)
         elif self.identifiers is None:
-            self.identifiers=[repr(i) for i in range(self.locations)]
+            self.identifiers=[repr(i) for i in list(range(self.locations))]
 
         if distPriorFilename is not None:
             self.prior=getPrior(distPriorFilename,len(self.identifiers))
@@ -252,7 +252,7 @@ class Args:
 
 
         if self.certainty is None:
-            print "Argument error: Must specify termination certainty\n"
+            print("Argument error: Must specify termination certainty\n")
             usage()
             sys.exit(1)
 
@@ -275,7 +275,7 @@ class Args:
     def getPrior(self):
         #if specified, prior is loaded in parseArgs(). Otherwise, uniform default is set here.
         if self.prior is None:
-            return [ 1/float(self.locations) for i in range(self.locations)]
+            return [ 1/float(self.locations) for i in list(range(self.locations))]
         else:
             return self.prior
 
@@ -312,16 +312,16 @@ class runClass:
             if os.WIFEXITED(retval):
                 code=os.WEXITSTATUS(retval)
                 if code!=0:
-                    raise "switch script (%s) exited with code %d \n" % (cmd,code)
+                    raise Exception("switch script (%s) exited with code %d \n" % (cmd,code))
             else:
-                raise "switch script (%s) did not exit normally\n" % (cmd)
+                raise Exception("switch script (%s) did not exit normally\n" % (cmd))
 
 
 
     def statusCallback(self,ended,mostLikely,mostLikelyProb,probs,counts):
         if ended:
-            print "\nSearch complete. ",
-        print "Most likely location is %s (probability %f)." % (self.identifiers[mostLikely],mostLikelyProb)
+            print("\nSearch complete. ", end=' ')
+        print("Most likely location is %s (probability %f)." % (self.identifiers[mostLikely],mostLikelyProb))
 
 
 # assumes unix return code from script
@@ -346,9 +346,9 @@ class scriptTest(runClass):
             elif code>0 and code<=127:
                 ret= True
             else:
-                raise "unknown exit code from (%s) = %d\n" % (cmd,code)
+                raise Exception("unknown exit code from (%s) = %d\n" % (cmd,code))
         else:
-            raise "test script (%s) did not exit normally\n" % (cmd)
+            raise Exception("test script (%s) did not exit normally\n" % (cmd))
 
         self.logger.log(where,ret)
         return ret
@@ -358,11 +358,11 @@ class scriptTest(runClass):
 class manualTest(runClass):
     def test(self,where):
         self.switch(where)
-        print "Please test at location %s." % self.identifiers[where]
+        print("Please test at location %s." % self.identifiers[where])
         prompt="Target detected at %s? Y/N/S(kip) " % self.identifiers[where]
 
         while True:
-            instr=raw_input(prompt)
+            instr=input(prompt)
             if instr in ['Y','y']:
                 ret= True
                 break
@@ -415,12 +415,12 @@ if args.doResume():
 where=finder.search()
 logger.close()
 
-print "Number of tests at %s: %d of which %d detected" %(identifiers[where],sum(finder.counts[where]),finder.counts[where][1])
+print("Number of tests at %s: %d of which %d detected" %(identifiers[where],sum(finder.counts[where]),finder.counts[where][1]))
 
 if len(thisDag.getParents(where))>0:
-    print "Number of tests at parents of %s:" % (identifiers[where])
+    print("Number of tests at parents of %s:" % (identifiers[where]))
     for p in thisDag.getParents(where):
-        print "\t At %s, %d of which %d detected" %(identifiers[p],sum(finder.counts[p]),finder.counts[p][1])
+        print("\t At %s, %d of which %d detected" %(identifiers[p],sum(finder.counts[p]),finder.counts[p][1]))
 else:
-    print "Location %s has no parents" %(identifiers[where])
+    print("Location %s has no parents" %(identifiers[where]))
 

BBChop/source/cse.py

@@ -42,10 +42,10 @@ def doCalc(self,values,comb,nil):
 
         temp=copy.copy(values)
 
-        for i in xrange(self.numVals,len(self.subExps)):
+        for i in range(self.numVals,len(self.subExps)):
             if self.subExps[i] is None:
                 temp.append(values[i])
-            elif self.subExps[i] is -1:
+            elif self.subExps[i] == -1:
                 temp.append(nil)
             else:
                 (a,b)=self.subExps[i]
@@ -110,15 +110,15 @@ def getExp(self,l):
                 a=nl[0]
                 b=nl[1]
                 if  (a[virt]+1) == b[virt] and not (a[virt]&1):
-                    next.append((a[virt]/2,self.getBinaryExp(a[loc],b[loc])))
+                    next.append((a[virt]//2,self.getBinaryExp(a[loc],b[loc])))
                     nl.popleft()
                     nl.popleft()
                 else:
-                    next.append((a[virt]/2,a[loc]))
+                    next.append((a[virt]//2,a[loc]))
                     nl.popleft()
             while len(nl)>0:
                 a=nl[0]
-                next.append((a[virt]/2,a[loc]))
+                next.append((a[virt]//2,a[loc]))
                 nl.popleft()
 
 
@@ -130,7 +130,7 @@ def getExp(self,l):
     # given a list of expressions, return an object which can calculate them
 
     def getExpList(self,expList):
-        return expListCalc([ self.getExp(toSortedList(expList[i])) for i in xrange(len(expList))],self)
+        return expListCalc([ self.getExp(toSortedList(expList[i])) for i in range(len(expList))],self)
 
 
 # This object holds the locations of the wanted expressions in the temporary
@@ -149,7 +149,7 @@ def __init__(self,expList,cse):
 
     def doCalc(self,values,comb,nil):
         temp=self.cse.doCalc(values,comb,nil)
-        res = [temp[self.expList[i]] for i in xrange(len(self.expList))]
+        res = [temp[self.expList[i]] for i in range(len(self.expList))]
         return res
 
 

BBChop/source/dag.py

@@ -96,26 +96,26 @@ def findCover(soFar,covered,node,parents):
 
 class dagX(absDag):
     def __init__(self,parents,N):
-        print "Analysing DAG structure...",
+        print("Analysing DAG structure...", end=' ')
         sys.stdout.flush()
         self.parents=parents
 
-        children=[[] for i in xrange(N)]
+        children=[[] for i in range(N)]
 
 
-        for i in xrange(N):
+        for i in range(N):
             for p in parents[i]:
                 children[p].append(i)
 
         self.children=children
 
         # a linear stretch ends if a node has multiple children or its child has multiple parents
-        self.linearEnd=  [len(children[i])!=1 or len(parents[children[i][0]])!=1 for i in xrange(N)] 
+        self.linearEnd=  [len(children[i])!=1 or len(parents[children[i][0]])!=1 for i in range(N)] 
         # a linear stretch starts if a node has multiple parents or its parent has multiple children
-        self.linearStart=[len(parents[i])!=1 or len(children[parents[i][0]])!=1 for i in xrange(N)]
+        self.linearStart=[len(parents[i])!=1 or len(children[parents[i][0]])!=1 for i in range(N)]
 
-        loc=[set([i]) for i in xrange(N)]
-        empty=[set() for i in xrange(N)]
+        loc=[set([i]) for i in range(N)]
+        empty=[set() for i in range(N)]
         locE=listCond(self.linearEnd,loc,empty)
         locS=listCond(self.linearStart,loc,empty)
 
@@ -134,7 +134,7 @@ def __init__(self,parents,N):
         self.AfterExpr = self.cseAfter.getExpList(self.multiAfter)
 
 
-        print "done"
+        print("done")
     # The 'unique' versions of the methods do not assume that the combination function is idempotent. 
 
     def combUptoUnique(self,values,comb):
@@ -158,7 +158,7 @@ def combAfterUnique(self,values,comb):
     def combUptoLinear(self,values,comb):
         res=[comb([])]*len(values)
 
-        for i in xrange(len(values)):
+        for i in range(len(values)):
             if not self.linearStart[i]:
                 res[i]=comb([comb([values[j],res[j]]) for j in self.parents[i]])
         return res
@@ -167,7 +167,7 @@ def combUptoLinear(self,values,comb):
     def combAfterLinear(self,values,comb):
         res=[comb([])]*len(values)
 
-        for i in reversed(xrange(len(values))):
+        for i in reversed(range(len(values))):
             if not self.linearEnd[i]:
                 res[i]=comb([comb([values[j],res[j]]) for j in self.children[i]])
         return res
@@ -198,7 +198,7 @@ def getParents(self,loc):
     def combUpto(self,values,comb):
         res=[comb([])]*len(values)
 
-        for i in xrange(len(values)):
+        for i in range(len(values)):
             res[i]=comb([comb([values[j],res[j]]) for j in self.parents[i]])
         return res
 
@@ -207,7 +207,7 @@ def combUpto(self,values,comb):
     def combAfter(self,values,comb):
         res=[comb([])]*len(values)
 
-        for i in reversed(xrange(len(values))):
+        for i in reversed(range(len(values))):
             res[i]=comb([comb([values[j],res[j]]) for j in self.children[i]])
         return res
 
@@ -278,7 +278,7 @@ def sumOther(self,values):
 
 
 def linearTestDag(N):
-    parents=['%d %d' %(a+1,a) for a in xrange(N-1)]
+    parents=['%d %d' %(a+1,a) for a in range(N-1)]
     parents[:0]='0'
     return dag(parents,N)
 

BBChop/source/dagRead.py

@@ -102,7 +102,7 @@ def read(inputFile):
 
     # which node id is where
     dagLocs={}
-    for i in xrange(len(identifiers)):
+    for i in range(len(identifiers)):
         dagLocs[identifiers[i]]=i