Machine Learning in action –kNN(已勘误)

Machine Learning in action –kNN

最近在自学机器学习，应导师要求，先把《Machine Learning with R》动手刷了一遍，感觉R真不能算是一门计算机语言，感觉也就是一个功能复杂的计算器。所以这次就决定使用经典教材《Machine Learning in action》。因为开学得换work station ，怕到时候代码又丢了，所以就索性开个博客，把代码上传上来。

talk is cheap show me the code

函数定义代码

#coding=utf-8
from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt
import os

def classify0(inX, dataset, lables, k):
    #shape返回矩阵的[行数， 列数]
    #shape[0]就是行数
    dataSetSize = dataset.shape[0]
    #将 输入的inX转换为和dataSet一样的矩阵形式
    matri_temp = tile(inX, (dataSetSize, 1))
    #求 inX 到各个 train_data的距离
    diffMat = matri_temp - dataset
    sqDiffMat = diffMat**2
    #平方和
    sqDistance = sqDiffMat.sum(axis = 1)#按行累加 ，axis = 1 表示行
    #对平方和开根号
    distance = sqDistance**0.5
    #按照升序排序，返回的是原数组的下标
    sortedDistIndicies = distance.argsort()
    #创建一个空字典
    classCount = {}
    #统计前k个最近的样本所属类别包含的样本个数
    for i in range(k):
        index = sortedDistIndicies[i]
        votelable = lables[index]
        #classCount.get(votelabel, 0 )返回voteIlabel的值，如果不存在，则返回0
        classCount[votelable] = classCount.get(votelable, 0) + 1
    #按照类别计数结果降序
    sortedClassCount = sorted(classCount.items(), key = operator.itemgetter(1), reverse = True )
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    arrayOlines = fr.readlines()
    numOfLines = len(arrayOlines) #文件的行数
    returnMat = zeros((numOfLines, 3)) #创建一个0的矩阵
    #returnMat = [[] * 3] * numOfLines
    classLabelVector = []
    index = 0
    for line in arrayOlines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        #returnMat[index,i] = float(listFromLine[i])
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector

#归一化特征
def autoNorm(dataset):
    #每列的最小值
    minVals = dataset.min(0)
    #每列的最大值
    maxVals = dataset.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataset))
    m = dataset.shape[0] #行数
    normDataSet = dataset - tile(minVals, (m,1))
    normDataSet = normDataSet / tile(ranges, (m,1))
    return normDataSet, ranges, minVals

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

def handwritingClassTest():
    hwlabels = []
    trainingFileList = os.listdir('trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwlabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' %fileNameStr)
    testFileList = os.listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('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
    print("\n the total number of error is %d"%errorCount)
    print("\n the total number rate is :%f"%(errorCount/float(mTest)))

在撸代码的时候，犯了一个subtle and deadly 的错误，在 file2matrix中，误将 readlines() 写成了readline() ,虽然两者只相差一个 s ，但是确实天壤之别的含义。前者是读入所有的数据，后者是只读入一行数据，就这一点差别，让我debug了好几个小时，以后还得细心啊。

上面代码块只是定义了主要的函数，离运行还差一点。由于书原文中，采用了使用 iPython 命令行的运行方式，但是博主比较懒，所以干脆舍弃掉原来的方式，直接在代码最后添加

代码块

if __name__ == "__main__":

废话不多少，直接上代码

实验1 -分类

if __name__=="__main__":
    #导入数据
    dataset, lables = createDataSet()
    inX = [0.1, 0.01]
    #分类
    className = classify0(inX, dataset, lables, 3)
    print("the class of test sample is %s" %className)

实验2 ：file2matrix

if __name__ == "__main__":
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normData , ranges, minVals = autoNorm(datingDataMat)
    print(normData)
    print('/n')
    print(ranges)
    print('/n')
    print(minVals)

实验3 ：使用Matplotlib创建散点图

if __name__ == "__main__":
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(datingDataMat[:,1], datingDataMat[:,2],
               15.0 * array(datingLabels),
               15.0 * array(datingLabels))
    plt.show()

实验4 ：归一化特征值

if __name__ == "__main__":
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normData , ranges, minVals = autoNorm(datingDataMat)
    print(normData)
    print('\n')
    print(ranges)
    print('\n')
    print(minVals)

实验5 ：手写识别系统

if __name__ == "__main__":
    handwritingClassTest()

更多请戳github
https://github.com/Edgis/Machine-learning-in-action/blob/master/kNN.py