import random
import math
import csv
import operator
def loadDataset(filename,split,trainingset=[],testset=[]):
    with open(filename) as csvfile:
        lines=csv.reader(csvfile)
        dataset=list(lines)
        for x in range(len(dataset)-1):
            for y in range(4):
                dataset[x][y]=float(dataset[x][y])
            if random.random()<split:
                trainingset.append(dataset[x])
            else:
                testset.append(dataset[x])
def euclidiandistance(instance1,instance2,length):
    distance=0
    for x in range(length):
        distance+=pow((instance1[x]-instance2[x]),2)
    return math.sqrt(distance)

def getneighbours(trainingset,testInstance,k):
    distances=[]
    length=len(testInstance)-1
    for x in range(len(trainingset)):
        dist=euclidiandistance(testInstance,trainingset[x],length)
        distances.append((trainingset[x],dist))
    distances.sort(key=operator.itemgetter(1))
    neighbors=[]
    for x in range(k):
        neighbors.append(distances[x][0])
    return neighbors

def getresponse(neighbors):
    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.items(),key=operator.itemgetter(1),reverse=True)
    return sortedvotes[0][0]

def getaccuracy(testset,predictions):
    correct=0
    for x in range(len(testset)):
        if testset[x][-1]==predictions[x]:
            correct+=1
    return (correct / float(len(testset))) * (100.0)

def main():
    #prepare data
    trainingset=[]
    testset=[]
    split=0.67
    loadDataset('iris_data.csv',split,trainingset,testset)
    print('\n Number of training data :'+(repr(len(trainingset))))
    print('\n Number of test data : '+(repr(len(testset))))
    #generate predictions
    predictions=[]
    k=3
    print('\n The predictions are: ')
    for x in range(len(testset)):
        neighbors=getneighbours(trainingset,testset[x],k)
        result=getresponse(neighbors)
        predictions.append(result)
        print('predicted = '+repr(result) +' ,actual ='+repr(testset[x][-1]))
    accuracy=getaccuracy(testset,predictions)
    print('\n The accuracy is : '+repr(accuracy) +'%')
main()