import csv
import random
import operator
import math

random.seed(47)

def viewDataset(file):
    with open(file) as csvfile:
        lines = csv.reader(csvfile)
        for row in lines:
            print(', '.join(row))

dataset = r'../datasets/iris.data'
# viewDataset(dataset)

def handleDataset(filename, split):
    trainingSet = []
    testSet = []
    with open(filename, 'r') 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])
    return trainingSet, testSet

def euclideanDistance(instance1, instance2, length):
    distance = 0
    for x in range(length):
        distance += pow((instance1[x] - instance2[x]), 2)
    return math.sqrt(distance)

def getKNeighbors(trainingSet, testInstance, k):
    distances = []
    length = len(testInstance) - 1
    for x in range(len(trainingSet)):
        dist = euclideanDistance(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
#     print(classVotes)
    sortedVotes = sorted(classVotes.items(),
                         key=operator.itemgetter(1), reverse=True)
#     print(sortedVotes)
    return sortedVotes[0][0]

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

from sklearn.metrics import accuracy_score

def main():
    # prepare data
    split = 0.8
    trainingSet, testSet = handleDataset(dataset, split)
    print('Train: ' + repr(len(trainingSet)))
    print('Test: ' + repr(len(testSet)))
    # generate predictions
    predictions = []
    k = 3
    for x in range(len(testSet)):
        neighbors = getKNeighbors(trainingSet, testSet[x], k)
        result = getResponse(neighbors)    
        predictions.append(result)
        print(f'> predicted = {result}, actual = {testSet[x][-1]}')
                                            
    accuracy = getAccuracy(testSet, predictions)
    print(f'k: {k}, Accuracy: {round(accuracy,3)}%')