def testwine():
wqred = dataifywine('wine/winequality-red.csv') + dataifywine('wine/winequality-white.csv')
leftoutperc = 0.1
leftout = int(len(wqred)*leftoutperc)
testing = wqred[:leftout]
training = wqred[leftout:]
print "Training:",len(training)
print "Testing:",len(testing)
foo = FastKNN(10)
foo.addEvidence(numpy.array([thing[:-1] for thing in training]), [thing[-1] for thing in training])
knn.addEvidence(numpy.array(training))
total = 0
correct = 0
for x in xrange(len(testing)):
thing = testing[x]
guess = foo.query(numpy.array(thing[:-1]),3)
#realknn = knn.query(numpy.array([thing[:-1],]),3,method='mean')
#guess = realknn[0]
#print realknn
#print guess, thing[-1]
if guess == thing[-1]:
correct += 1
total += 1
if total % 50 == 0:
print total,'/',len(testing)
print correct,"/",total,":",float(correct)/float(total)
print "Average checks per query:", float(foo.num_checks)/float(total)
def testwine():
wqred = dataifywine('wine/winequality-red.csv') + dataifywine(
'wine/winequality-white.csv')
leftoutperc = 0.1
leftout = int(len(wqred) * leftoutperc)
testing = wqred[:leftout]
training = wqred[leftout:]
print "Training:", len(training)
print "Testing:", len(testing)
foo = FastKNN(10)
foo.addEvidence(numpy.array([thing[:-1] for thing in training]),
[thing[-1] for thing in training])
knn.addEvidence(numpy.array(training))
total = 0
correct = 0
for x in xrange(len(testing)):
thing = testing[x]
guess = foo.query(numpy.array(thing[:-1]), 3)
#realknn = knn.query(numpy.array([thing[:-1],]),3,method='mean')
#guess = realknn[0]
#print realknn
#print guess, thing[-1]
if guess == thing[-1]:
correct += 1
total += 1
if total % 50 == 0:
print total, '/', len(testing)
print correct, "/", total, ":", float(correct) / float(total)
print "Average checks per query:", float(foo.num_checks) / float(total)
def _knnResult(naData):
''' Split up data into training/testing '''
lSplit = naData.shape[0] * .7
naTrain = naData[:lSplit, :]
naTest = naData[lSplit:, :]
knn.addEvidence(naTrain.astype(float), 1)
''' Query with last column omitted and 5 nearest neighbors '''
naResults = knn.query(naTest[:, :-1], 5, 'mode')
''' Count returns which are correct '''
lCount = 0
for i, dVal in enumerate(naResults):
if dVal == naTest[i, -1]:
lCount = lCount + 1
dResult = float(lCount) / naResults.size
return dResult
def _knnResult(naData):
''' Split up data into training/testing '''
lSplit = naData.shape[0] * .7
naTrain = naData[:lSplit, :]
naTest = naData[lSplit:, :]
knn.addEvidence(naTrain.astype(float), 1)
''' Query with last column omitted and 5 nearest neighbors '''
naResults = knn.query(naTest[:, :-1], 5, 'mode')
''' Count returns which are correct '''
lCount = 0
for i, dVal in enumerate(naResults):
if dVal == naTest[i, -1]:
lCount = lCount + 1
dResult = float(lCount) / naResults.size
return dResult
