《机器学习实战》Python3实现代码（第二章节）

本文是针对《机器学习实战》（第二章）内所需要的程序代码进行修改（书中使用的是py2），现已py3呈现。

 

本文中不同之处可以通过《机器学习实战》中函数详细解析（持续更新）这篇文章进行寻找，并且也可以根据页数进行函数的查看用法等。

 

程序清单2-1：

from numpy import *
import operator

def createDataSet():
    """
    funct:建立数据集和特征值
    :return:
    group:建立好的数据集
    labels:建立好的特征值
   """
    #建立数据集
    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    #建立特征值
    labels = ['A','A','B','B']
    return group,labels

def classify(inX,dataSet,labels,k):
    """
    funct:使用k-邻近算法将每组数据划分到某个类中
    :param inX:
    :param dataSet:训练样本集
    :param labels:标签向量
    :param k:用于选择最近邻居的数量
    :return:
    """
    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.items(),key=operator.itemgetter(1),reverse = True)
    return sortedClassCount[0][0]
group,labels = createDataSet()
print(classify([0,0],group,labels,k=3))

#运行结果：B

程序清单2-2：

from numpy import *
import operator
from numpy.ma import zeros, array
import matplotlib
import matplotlib.pyplot as plt


def file2matrix(fileName):
    #数据格式如下
    # 40920   8.326976    0.953952    3
    # 14488   7.153469    1.673904    2
    file = open(fileName)
    #读取行数
    arrayOLines = file.readlines()
    numberOfLines = len(arrayOLines)
    returnMatrix = ma.zeros((numberOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMatrix[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMatrix,classLabelVector
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter((datingDataMat[:,1]).tolist(),(datingDataMat[:,2]).tolist())
plt.show()

运行结果：

程序难点：在书上内部的代码是直接将datingDataMat[:,1]直接传给了ax.scatter()但是会报错，查看报错信息，发现由于版本的差异我们只能传入list，所以我们使用了array.tolist()函数。

修改代码ax.scatter((datingDataMat[:,1]).tolist(),(datingDataMat[:,2]).tolist(),15.0*array(datingLabels)

           ,15.0*array(datingLabels))生成的图像如下：

 

程序清单2-3：

def autoNorm(dataSet):
    #寻找列中的最小值
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    #读取第一维的矩阵
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals,(m,1))
    normDataSet = normDataSet/tile(ranges,(m,1))
    #normDataSet = linalg.solve(normDataSet,tile(range,(m,1)))
    return normDataSet,range,minVals

编码时犯的错：pycharm补齐的时候，不小心漏掉了ranges里面的s，浪费了很多时间。

 

程序清单2-4：

def classifyPerson():
    resultList = ['not at all','in small doses','in large doses']
    percentTats = float(input("1"))
    ffMiles = float(input("2"))
    iceCream = float(input("3"))
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat,ranges1,minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify((inArr - minVals)/ranges1,normMat,datingLabels,3)
    print("you will probably like the person:",resultList[classifierResult-1])

 

程序清单2-5：

def img2vector(fileName):
    returnVect = zeros((1,1024))
    file = open(fileName)
    for i in range(32):
        lineStr = file.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect

def handWritingClassTest():
    hwLabels = []
    trainingFileList = 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 = 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 = classify(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier is:%d,real answer is:%d"%(classifierResult,classNumStr))
        if(classifierResult != classNumStr):errorCount+=1.0
    print("\nthe total number of error is:%d"%errorCount)
    print("\nthe total error rate id:%f"%(errorCount/float(mTest)))