with open(filename, 'rb') as csvfile:

lines = csv.reader(csvfile)

dataset = list(lines)[1:]

for x in range(len(dataset)-1):

for y in range(len(dataset[x])):

dataset[x][y] = float(dataset[x][y])

if random.random() < split:

trainingSet.append(dataset[x])

else:

distance = 0.0

for x in range(len(instance1)):

distance = pow((instance1[x] - instance2[x]), 2)

distances = []

for x in range(len(trainingSet)):

dist = euclideanDistance(testInstance, trainingSet[x])

distances.append((trainingSet[x], dist))

distances.sort(key=operator.itemgetter(1))

neighbors = []

for x in range(k):

neighbors.append(distances[x][0])

classVotes = {}

for x in range(len(neighbors)):

response = neighbors[x][-1]

if response in classVotes:

classVotes[response] = 1

else:

classVotes[response] = 1

sortedVotes = sorted(classVotes.iteritems(), key=operator.itemgetter(1), reverse=True)

correct = 0

for x in range(len(testSet)):

if testSet[x][-1] == predictions[x]:

correct = 1

# prepare data

trainingSet=[]

testSet=[]

split = 0.67

loadDataset('data\\colonData.csv', split, trainingSet, testSet)

print 'Train set: ' repr(len(trainingSet))

print 'Test set: ' repr(len(testSet))

# generate predictions

predictions=[]

k = 2

for x in range(len(testSet)):

neighbors = getNeighbors(trainingSet, testSet[x], k)

result = getResponse(neighbors)

predictions.append(result)

print('> predicted=' repr(result) ', actual=' repr(testSet[x][-1]))

accuracy = getAccuracy(testSet, predictions)