machine learning实践学习二：K-Nearest Neighbors

K-Nearest Neighbors算法

一、优缺点

优点：精度高、对异常值不敏感、无数据输入假定

缺点：计算复杂度高、空间复杂度高

适用数据范围：数值型和标称型。

二、步骤

(1) 收集数据Data Collections:提供文本文件
(2) 准备数据Data Preparation:使用Python解析文本文件
(3) 分析数据Data Analysis:使用Matplotlib画二维扩散图
(4) 训练数据Data Training:此步骤不适用于k-近邻算法
(5) 测试数据Data Testing:计算错误率
(6) 使用数据Utilizing Algorithm:首先需要输入样本数据和结构化的输出结果，然后运行k-近邻算法判定输入数据分别属于哪个分类，最后应用对计算出的分类执行后续的处理。

三、代码及简单解释

from numpy import *
import operator
from os import listdir


#Chapter2-1: KNN Algorithm
def createDataSet():
    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels = ['A','A','B','B']
    return group, labels

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()     
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

#Chapter2-2: Dating 案例
#Step 1: Data Collection+Data Preparation
#读取文件后形成了特征矩阵，和标签向量
def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

>>>import KNN

>>>datingDataMat, datingLabels=KNN.file2matrix('datingTestSet.txt')

#使用Matplotlib创建散点图

>>>import matplotlib

>>>import matplotlib.pyplot as plt

>>>fig=plt.figure()

>>>ax=fig.add_subplot(111)

>>>ax.scatter(datingDataMat[:,1],datingDataMat[:,2])

>>>plt.show()

#不同类别显示不同颜色

>>>ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))

#Step 2：归一化处理
def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m,1))
    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

>>>import KNN

>>>normMat, ranges, minVals = KNN.autoNorm(datingDataMat)

#Step 3:测试算法
def datingClassTest():
    hoRatio = 0.10      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
        print("the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print("the total error rate is: %f" % (errorCount/float(numTestVecs)))
    print(errorCount)

>>>KNN.datingClassTest()

#Chapter 2-3 手写识别系统
#Step 1:把32*32的二进制图像转换为1*1024的向量
def img2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect

>>>testVector=KNN.img2vector('testDigits/0_13.txt')

#Step 2: 
def handwritingClassTest():
#获取目录内容
    hwLabels = []
    trainingFileList = listdir('C:/Users/yy/Anaconda3/Test/KNN/trainingDigits')           #load the 
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('C:/Users/yy/Anaconda3/Test/KNN/trainingDigits/%s' % fileNameStr)
    testFileList = listdir('C:/Users/yy/Anaconda3/Test/KNN/testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('C:/Users/yy/Anaconda3/Test/KNN/testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print("the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr))
        if (classifierResult != classNumStr): errorCount += 1.0
    print("\nthe total number of errors is: %d" % errorCount)
    print("\nthe total error rate is: %f" % (errorCount/float(mTest)))

>>>KNN.handwritingClassTest()

四、数据集：

见附件

本文为《机器学习实战》学习笔记