def kfold(mleft, mright, nmleft, nmright, numtree, biniter, seed):
"""
Defines a kfold cross-validation method where T is the dataset
to train the RandomForest algorithm and k is a subelement of T which
then is tested on training-set T
"""
matchesleft = mleft
matchesright = mright
nonmatchesleft = nmleft
nonmatchesright = nmright
matchresult=[]
nonmatchresult=[]
oob=0
for ids in range(0, len(treeIDsleft)):
biniter=biniter
matchlistleft=[]
matchlistright=[]
nonmatchlistleft=[]
nonmatchlistright=[]
for ID in range(0, len(matchesleft)):
if matchesleft[ID] == matchesleft[ids]:
continue
else:
matchlistleft.append(matchesleft[ID])
for ID in range(0, len(matchesleft)):
if matchesright[ID] == matchesright[ids]:
continue
else:
matchlistright.append(matchesright[ID])
for ID in range(0, len(matchesleft)):
if nonmatchesleft[ID] == nonmatchesleft[ids]:
continue
else:
nonmatchlistleft.append(nonmatchesleft[ID])
for ID in range(0, len(matchesleft)):
if nonmatchesright[ID] == nonmatchesright[ids]:
continue
else:
nonmatchlistright.append(nonmatchesright[ID])
kmatch =[matchesleft[ids], matchesright[ids]]
knonmatch= [nonmatchesleft[ids], nonmatchesright[ids]]
matching = featureList(matchlistleft, matchlistright, biniter)
nonmatching = featureList(nonmatchlistleft, nonmatchlistright, biniter)
numTrees = numtree
numFeatures = len(matching.values()[0])
classifier = createClassifier(numTrees, numFeatures + 1, seed) # +1 to include the class
outofbag = trainClassifier(classifier, matching.values(), nonmatching.values())
oob+=float(outofbag)
print "oob =", outofbag
print "match vs raining set:", classify(classifier, [featureList([kmatch[0]], [kmatch[1]], biniter).values()[0]])
print "nonmatch vs training set:", classify(classifier, [featureList([knonmatch[0]], [knonmatch[1]], biniter).values()[0]])
matchresult.append(classify(classifier, [featureList([kmatch[0]], [kmatch[1]], biniter).values()[0]]))
nonmatchresult.append(classify(classifier, [featureList([knonmatch[0]], [knonmatch[1]], biniter).values()[0]]))
#print matchresult
#print nonmatchresult
counter=0
for m in matchresult:
if m[0] == 1.0:
counter+=1
for m in nonmatchresult:
if m[0] == 0.0:
counter +=1
elements = 2 * len(matchresult)
performance = (float(counter) / float(elements))
moob = oob / float(elements / 2)
return "The performance is:", performance, "and the mean oob is:", moob