机器学习----KNN（Python实现）（三）

#导入csv，读取数据
import csv
#导入random，进行随机变量的运算
import random
#导入math，进行数学运算
import math
import operator

#下载算法所需的数据集，并将数据集分为训练集和测试集
#参数：filename文件路径名；以split为界限将数据集分为训练集（产生模型）和测试集；
def loadDataset(filename,split,trainingSet=[],testSet=[]):
    with open(filename,"r") as csvfile:
        #读取所有的行
        lines = csv.reader(csvfile)
        #将所有行的数据转换成list格式        
        dataset = list(lines)
        #数据集为len行5列（0-4）
        for x in range(len(dataset)-1):
            for y in range(4):
                dataset[x][y] = float(dataset[x][y])
            #训练集
            if random.random() < split:
                trainingSet.append(dataset[x])
            #测试集
            else:
                testSet.append(dataset[x])

#计算任意两个实例的距离
#距离的衡量：欧氏距离（实例可以是任意维度的）
def euclideanDistance(instance1,instance2,length):
    distance = 0
    #length为维度
    for x in range(length):
        #相对应求差的平方，再累加
        distance += pow((instance1[x]-instance2[x]),2)
        #开平方math.sqrt
        return math.sqrt(distance)

#返回测试实例最近的K个邻居
#给定训练集和测试实例以及邻居个数K
#计算测试实例到训练集中每个实例的距离，距离值按从小到大排列选出K个
def getNeighbors(trainingSet,testInstance,k):
    #distances装所有的距离
    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])
    #返回K个邻居
    return neighbors
        

#少数服从多数法则
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
    sorteVotes = sorted(classVotes.items(),key = operator.itemgetter(1),reverse =True)
    return sorteVotes[0][0]
            
            
#算法的准确率 
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():
    trainingSet = []
    testSet = []
    split = 0.67
    loadDataset(r'F:\iris.txt',split,trainingSet,testSet)
    print('Train Set:' + repr(len(trainingSet)))
    print('Test Set:' + repr(len(testSet)))   
    predictions = []
    k = 3
    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)   
    print('Accuracy:'+ repr(accuracy)+'%')
    
main()