knn算法实例（python）

参考地址（里面有解释和原数据）

import csv
import random
import math
import operator

def loadDataset(filename,split,trainingSet=[],testSet=[]):
    # 注意这儿加上'b'模式会出错，因为csv文件与普通文件不一样
    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])


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


# test for function euclideanDistance
# data1 = [2, 2, 2, 'a']
# data2 = [4, 4, 4, 'b']
# distance = euclideanDistance(data1, data2, 3)
# print(distance)


def getNeighbors(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))
    # print(distances)
    distances.sort(key=operator.itemgetter(1))
    # print(distances)
    neighbors = []
    for x in range(k):
        neighbors.append(distances[x][0])
    return neighbors


# test for function getNeighbors
# trainSet = [[2, 2, 2, 'a'], [4, 4, 4, 'b'],[4.5, 4.5, 4.5, 'c']]
# testInstance = [5, 5, 5]
# k = 1
# neighbors = getNeighbors(trainSet, testInstance, 1)
# print(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
    # py3.+使用 items() 与2.+的 iteritems()  不同
    sortedVotes = sorted(classVotes.items(), key=operator.itemgetter(1), reverse=True)
    return sortedVotes[0][0]


# test for function getResponse
# neighbors = [[1, 1, 1, 'a'], [2, 2, 2, 'a'], [3, 3, 3, 'b']]
# response = getResponse(neighbors)
# print(response)


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 = []
    loadDataset('f:/iris.csv', 0.66, trainingSet, testSet)
    print("Train" + repr(len(trainingSet)))
    print("Test" + repr(len(testSet)))
    # print(trainingSet)

    # generate predictions
    predictions = []
    k = 3
    for x in range(len(testSet)):
        neighbors = getNeighbors(trainingSet, testSet[x], k)
        # print(neighbors)
        result = getResponse(neighbors)
        predictions.append(result)
        print('> predicted=' + repr(result) + ', actual=' + repr(testSet[x][-1]))
    accuraty = getAccuracy(testSet, predictions)
    print('Accuracy: ' + repr(accuraty) + '%')


main()