机器学习---K-Nearest Neighbor算法应用二(手动实现KNN算法)

原始数据

测试数据集irisdata.txt
格式如下,
其中，Iris-setosa/Iris-versicolor/Iris-virginica表示类别

5.1,3.5,1.4,0.2,Iris-setosa4.9,3.0,1.4,0.2,Iris-setosa4.7,3.2,1.3,0.2,Iris-setosa4.6,3.1,1.5,0.2,Iris-setosa5.0,3.6,1.4,0.2,Iris-setosa5.4,3.9,1.7,0.4,Iris-setosa4.6,3.4,1.4,0.3,Iris-setosa5.0,3.4,1.5,0.2,Iris-setosa4.4,2.9,1.4,0.2,Iris-setosa4.9,3.1,1.5,0.1,Iris-setosa5.4,3.7,1.5,0.2,Iris-setosa4.8,3.4,1.6,0.2,Iris-setosa4.8,3.0,1.4,0.1,Iris-setosa4.3,3.0,1.1,0.1,Iris-setosa5.8,4.0,1.2,0.2,Iris-setosa5.7,4.4,1.5,0.4,Iris-setosa5.4,3.9,1.3,0.4,Iris-setosa5.1,3.5,1.4,0.3,Iris-setosa5.7,3.8,1.7,0.3,Iris-setosa5.1,3.8,1.5,0.3,Iris-setosa5.4,3.4,1.7,0.2,Iris-setosa5.1,3.7,1.5,0.4,Iris-setosa4.6,3.6,1.0,0.2,Iris-setosa5.1,3.3,1.7,0.5,Iris-setosa4.8,3.4,1.9,0.2,Iris-setosa5.0,3.0,1.6,0.2,Iris-setosa5.0,3.4,1.6,0.4,Iris-setosa5.2,3.5,1.5,0.2,Iris-setosa5.2,3.4,1.4,0.2,Iris-setosa4.7,3.2,1.6,0.2,Iris-setosa4.8,3.1,1.6,0.2,Iris-setosa5.4,3.4,1.5,0.4,Iris-setosa5.2,4.1,1.5,0.1,Iris-setosa5.5,4.2,1.4,0.2,Iris-setosa4.9,3.1,1.5,0.1,Iris-setosa5.0,3.2,1.2,0.2,Iris-setosa5.5,3.5,1.3,0.2,Iris-setosa4.9,3.1,1.5,0.1,Iris-setosa4.4,3.0,1.3,0.2,Iris-setosa5.1,3.4,1.5,0.2,Iris-setosa5.0,3.5,1.3,0.3,Iris-setosa4.5,2.3,1.3,0.3,Iris-setosa4.4,3.2,1.3,0.2,Iris-setosa5.0,3.5,1.6,0.6,Iris-setosa5.1,3.8,1.9,0.4,Iris-setosa4.8,3.0,1.4,0.3,Iris-setosa5.1,3.8,1.6,0.2,Iris-setosa4.6,3.2,1.4,0.2,Iris-setosa5.3,3.7,1.5,0.2,Iris-setosa5.0,3.3,1.4,0.2,Iris-setosa7.0,3.2,4.7,1.4,Iris-versicolor6.4,3.2,4.5,1.5,Iris-versicolor6.9,3.1,4.9,1.5,Iris-versicolor5.5,2.3,4.0,1.3,Iris-versicolor6.5,2.8,4.6,1.5,Iris-versicolor5.7,2.8,4.5,1.3,Iris-versicolor6.3,3.3,4.7,1.6,Iris-versicolor4.9,2.4,3.3,1.0,Iris-versicolor6.6,2.9,4.6,1.3,Iris-versicolor5.2,2.7,3.9,1.4,Iris-versicolor5.0,2.0,3.5,1.0,Iris-versicolor5.9,3.0,4.2,1.5,Iris-versicolor6.0,2.2,4.0,1.0,Iris-versicolor6.1,2.9,4.7,1.4,Iris-versicolor5.6,2.9,3.6,1.3,Iris-versicolor6.7,3.1,4.4,1.4,Iris-versicolor5.6,3.0,4.5,1.5,Iris-versicolor5.8,2.7,4.1,1.0,Iris-versicolor6.2,2.2,4.5,1.5,Iris-versicolor5.6,2.5,3.9,1.1,Iris-versicolor5.9,3.2,4.8,1.8,Iris-versicolor6.1,2.8,4.0,1.3,Iris-versicolor6.3,2.5,4.9,1.5,Iris-versicolor6.1,2.8,4.7,1.2,Iris-versicolor6.4,2.9,4.3,1.3,Iris-versicolor6.6,3.0,4.4,1.4,Iris-versicolor6.8,2.8,4.8,1.4,Iris-versicolor6.7,3.0,5.0,1.7,Iris-versicolor6.0,2.9,4.5,1.5,Iris-versicolor5.7,2.6,3.5,1.0,Iris-versicolor5.5,2.4,3.8,1.1,Iris-versicolor5.5,2.4,3.7,1.0,Iris-versicolor5.8,2.7,3.9,1.2,Iris-versicolor6.0,2.7,5.1,1.6,Iris-versicolor5.4,3.0,4.5,1.5,Iris-versicolor6.0,3.4,4.5,1.6,Iris-versicolor6.7,3.1,4.7,1.5,Iris-versicolor6.3,2.3,4.4,1.3,Iris-versicolor5.6,3.0,4.1,1.3,Iris-versicolor5.5,2.5,4.0,1.3,Iris-versicolor5.5,2.6,4.4,1.2,Iris-versicolor6.1,3.0,4.6,1.4,Iris-versicolor5.8,2.6,4.0,1.2,Iris-versicolor5.0,2.3,3.3,1.0,Iris-versicolor5.6,2.7,4.2,1.3,Iris-versicolor5.7,3.0,4.2,1.2,Iris-versicolor5.7,2.9,4.2,1.3,Iris-versicolor6.2,2.9,4.3,1.3,Iris-versicolor5.1,2.5,3.0,1.1,Iris-versicolor5.7,2.8,4.1,1.3,Iris-versicolor6.3,3.3,6.0,2.5,Iris-virginica5.8,2.7,5.1,1.9,Iris-virginica7.1,3.0,5.9,2.1,Iris-virginica6.3,2.9,5.6,1.8,Iris-virginica6.5,3.0,5.8,2.2,Iris-virginica7.6,3.0,6.6,2.1,Iris-virginica4.9,2.5,4.5,1.7,Iris-virginica7.3,2.9,6.3,1.8,Iris-virginica6.7,2.5,5.8,1.8,Iris-virginica7.2,3.6,6.1,2.5,Iris-virginica6.5,3.2,5.1,2.0,Iris-virginica6.4,2.7,5.3,1.9,Iris-virginica6.8,3.0,5.5,2.1,Iris-virginica5.7,2.5,5.0,2.0,Iris-virginica5.8,2.8,5.1,2.4,Iris-virginica6.4,3.2,5.3,2.3,Iris-virginica6.5,3.0,5.5,1.8,Iris-virginica7.7,3.8,6.7,2.2,Iris-virginica7.7,2.6,6.9,2.3,Iris-virginica6.0,2.2,5.0,1.5,Iris-virginica6.9,3.2,5.7,2.3,Iris-virginica5.6,2.8,4.9,2.0,Iris-virginica7.7,2.8,6.7,2.0,Iris-virginica6.3,2.7,4.9,1.8,Iris-virginica6.7,3.3,5.7,2.1,Iris-virginica7.2,3.2,6.0,1.8,Iris-virginica6.2,2.8,4.8,1.8,Iris-virginica6.1,3.0,4.9,1.8,Iris-virginica6.4,2.8,5.6,2.1,Iris-virginica7.2,3.0,5.8,1.6,Iris-virginica7.4,2.8,6.1,1.9,Iris-virginica7.9,3.8,6.4,2.0,Iris-virginica6.4,2.8,5.6,2.2,Iris-virginica6.3,2.8,5.1,1.5,Iris-virginica6.1,2.6,5.6,1.4,Iris-virginica7.7,3.0,6.1,2.3,Iris-virginica6.3,3.4,5.6,2.4,Iris-virginica6.4,3.1,5.5,1.8,Iris-virginica6.0,3.0,4.8,1.8,Iris-virginica6.9,3.1,5.4,2.1,Iris-virginica6.7,3.1,5.6,2.4,Iris-virginica6.9,3.1,5.1,2.3,Iris-virginica5.8,2.7,5.1,1.9,Iris-virginica6.8,3.2,5.9,2.3,Iris-virginica6.7,3.3,5.7,2.5,Iris-virginica6.7,3.0,5.2,2.3,Iris-virginica6.3,2.5,5.0,1.9,Iris-virginica6.5,3.0,5.2,2.0,Iris-virginica6.2,3.4,5.4,2.3,Iris-virginica5.9,3.0,5.1,1.8,Iris-virginica

源码

# !/usr/bin/env python# -*- coding: utf-8 -*-# Author: Justin Chanimport csvimport randomimport mathimport operator#装载数据集函数#filename数据集文件#filename数据集分为两部分，一个是训练集trainingSet,一个是测试集testSet.#split用来将原始数据集分为训练集和测试集的界限。def loadDataset(filename, split, trainingSet = [], testSet = []):    with open(filename,'rb') as csvfile:        lines = csv.reader(csvfile)#读取所有行        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:#随机一个数与split比较，大的装载到测试集，小的装载的数据集。                trainingSet.append(dataset[x])            else:                testSet.append(dataset[x])#计算坐标两个实例的直线距离,length表示维度def euclideanDistance(instance1,instance2,length):    distance = 0    for x in range(length):        distance += pow((instance1[x] - instance2[x]),2)#计算两个点所有维度的平方和    return math.sqrt(distance)#返回最近的k个邻居def getNeighbors(trainingSet,testInstance,k):    distances = []    length = len(testInstance)-1 #测试实例的维度    for x in range(len(trainingSet)):        dist = euclideanDistance(testInstance,trainingSet[x],length)        distances.append((trainingSet[x],dist))    distances.sort(key=operator.itemgetter(1))#把距离从小到大排序    neighbors = []    for x in range(k):        neighbors.append(distances[x][0])    return neighbors#在邻居中取得最近的那个邻居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)#每个类进行降序排列    return sortedVotes[0][0]#计算测试集的准确率def getAccuracy(testSet,predictions):    correct = 0#预测对的个数    for x in range(len(testSet)):        if testSet[x][-1] == predictions[x]:#下标-1即表示最后一个值,这里就是label            correct += 1    return (correct/float(len(testSet)))*100.0def main():    #prepare data    trainingSet = []    testSet = []    split = 0.67    loadDataset(r'/home/justin18chan/PycharmProjects/tensorflowProj/KNearestNeighbor/irisdata.txt', split, trainingSet, testSet)#在传路径时，加r表示后面传的是原始字符串，忽略特殊字符    print('Train set:' + repr(len(trainingSet)))    print('Test set:' + repr(len(testSet)))    #gengrate prediction    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()

遇到的问题

1.在读取csv文件时，打开文件格式错误，要用‘rt’打开。

    with open(filename,'rb') as csvfile:        lines = csv.reader(csvfile)#读取所有行        dataset = list(lines)

_csv.Error: iterator should return strings, not bytes (did you open the file in text mode?
原因是csv文件是文本文件，不是二进制文件，不能用‘rb’格式打开。文本文件打开要用rt。

2.在python3.X中是classVotes.items()，在2.X是iteritems().

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

运算结果

/usr/bin/python3.5 xxxxx/KNearestNeighbor/KnnImplementation.pyTrain set:92Test set:57> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-setosa',actual'Iris-setosa'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-virginica',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-versicolor',actual'Iris-versicolor'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-versicolor',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-versicolor',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'> predicted'Iris-virginica',actual'Iris-virginica'Accuracy:94.73684210526315%