import csv

import random

import math

def loadCsv (myfile):

lines = csv.reader(open(myfile,""))

dataset = list(lines)

for i in range(len(dataset)):

dataset[i]= [float(x) for x in dataset[i]]

return dataset

def separateByClass(dataset):

separated = {}

for i in range(len(dataset)):

vector= dataset[i]

if(vector[-1] not in separated):

separated[vector[-1]]= []

separated[vector[-1]].append(vector)

return separated

def P_root(m,p_root):

return round (decimal(m) ** decimal((1/float(p_root))),k)

def MinkowskiDistance(x,xi,p):

return P_root(sum(pow((a-b),p) for a, b in zip(x, xi)),p)

def Neighbors(train_dataSet, test_dataset, k):

distances = []

neighbor = []

L_train=len(train_dataSet)

L_test=len(test_dataset)

for x in range(L_train):

dis = MinkowskiDistance(test_dataset,train_dataSet,L_test)

distances.append((train_dataSet, dis))

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

for x in range(k):

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

return neighbor

def Response(neighbor):

classVotes = {}

for x in range(len(neighbor)):

response = neighbor[x][-1]

if response in classVotes:

classVotes[response] += 1

else:

classVotes[response] = 1

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

return sortedVotes[0][0]

def accuracy(test,predict):

correct=0

for i in test:

if test ==predict:

correct +=1

return float(corect/len(test))*100.00

def main():

myfile = ''

train_dataSet=[]

test_dataset=[]

splitRatio = 0.67

dataset = loadCsv(myfile)

train_dataSet, test_dataset = splitDataset(dataset, splitRatio)

predictions=[]

k = 3

for x in range(len(test_dataset)):

neighbor = Neighbors(train_dataSet, test_dataset[x], k)

result = Response(neighbor)

predictions.append(result)

predictions = getPredictions(summaries, testSet)

accuracy = getAccuracy(testSet, predictions)

print('Accuracy: {0}%').format(accuracy)

main()