import numpy as np

import operator as op

from os import listdir

def classify0(inX, dataSet, labels, k):

    dataSetSize = dataSet.shape[0]

    diffMat = np.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=op.itemgetter(1), reverse=True)

    return sortedClassCount[0][0]

def createDataSet():

    group = np.array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])

    labels = ['A','A','B','B']

    return group, labels

data,labels = createDataSet()

print(data)

print(labels)

test = np.array([[0,0.5]])

result = classify0(test,data,labels,3)

print(result)


import numpy as np

import operator as op

from os import listdir

def classify0(inX, dataSet, labels, k):

    dataSetSize = dataSet.shape[0]

    diffMat = np.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=op.itemgetter(1), reverse=True)

    return sortedClassCount[0][0]

def file2matrix(filename):

    fr = open(filename)

    returnMat = []

    classLabelVector = []                       #prepare labels return

    for line in fr.readlines():

        line = line.strip()

        listFromLine = line.split('\t')

        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])

        classLabelVector.append(int(listFromLine[-1]))

    return np.array(returnMat),np.array(classLabelVector)

trainData,trainLabel = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet2.txt")

print(trainData[0:4])

print(trainLabel[0:4])

def autoNorm(dataSet):

    minVals = dataSet.min(0)

    maxVals = dataSet.max(0)

    ranges = maxVals - minVals

    normDataSet = np.zeros(np.shape(dataSet))

    m = dataSet.shape[0]

    normDataSet = dataSet - np.tile(minVals, (m,1))

    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide

    return normDataSet, ranges, minVals

normDataSet, ranges, minVals = autoNorm(trainData)

print(ranges)

print(minVals)

print(normDataSet[0:4])

print(trainLabel[0:4])

testData = np.array([[0.5,0.3,0.5]])

result = classify0(testData, normDataSet, trainLabel, 5)

print(result)

import numpy as np

import operator as op

from os import listdir

def classify0(inX, dataSet, labels, k):

    dataSetSize = dataSet.shape[0]

    diffMat = np.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=op.itemgetter(1), reverse=True)

    return sortedClassCount[0][0]

def file2matrix(filename):

    fr = open(filename)

    returnMat = []

    classLabelVector = []                       #prepare labels return

    for line in fr.readlines():

        line = line.strip()

        listFromLine = line.split('\t')

        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])

        classLabelVector.append(listFromLine[-1])

    return np.array(returnMat),np.array(classLabelVector)

def autoNorm(dataSet):

    minVals = dataSet.min(0)

    maxVals = dataSet.max(0)

    ranges = maxVals - minVals

    normDataSet = np.zeros(np.shape(dataSet))

    m = dataSet.shape[0]

    normDataSet = dataSet - np.tile(minVals, (m,1))

    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide

    return normDataSet, ranges, minVals

normDataSet, ranges, minVals = autoNorm(trainData)

def datingClassTest():

    hoRatio = 0.10      #hold out 10%

    datingDataMat,datingLabels = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet.txt")

    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: %s, the real answer is: %s') % (classifierResult, datingLabels[i]))

        if (classifierResult != datingLabels[i]):

            errorCount += 1.0

    print(('the total error rate is: %f') % (errorCount/float(numTestVecs)))

    print(errorCount)

datingClassTest()
import numpy as np

import operator as op

from os import listdir

def classify0(inX, dataSet, labels, k):

    dataSetSize = dataSet.shape[0]

    diffMat = np.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=op.itemgetter(1), reverse=True)

    return sortedClassCount[0][0]

def file2matrix(filename):

    fr = open(filename)

    returnMat = []

    classLabelVector = []                       #prepare labels return

    for line in fr.readlines():

        line = line.strip()

        listFromLine = line.split('\t')

        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])

        classLabelVector.append(listFromLine[-1])

    return np.array(returnMat),np.array(classLabelVector)

def autoNorm(dataSet):

    minVals = dataSet.min(0)

    maxVals = dataSet.max(0)

    ranges = maxVals - minVals

    normDataSet = np.zeros(np.shape(dataSet))

    m = dataSet.shape[0]

    normDataSet = dataSet - np.tile(minVals, (m,1))

    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide

    return normDataSet, ranges, minVals

normDataSet, ranges, minVals = autoNorm(trainData)

def datingClassTest():

    hoRatio = 0.10      #hold out 10%

    datingDataMat,datingLabels = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet.txt")

    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: %s, the real answer is: %s') % (classifierResult, datingLabels[i]))

        if (classifierResult != datingLabels[i]):

            errorCount += 1.0

    print(('the total error rate is: %f') % (errorCount/float(numTestVecs)))

    print(errorCount)

datingClassTest()

................................................

import numpy as np

import operator as op

from os import listdir

def classify0(inX, dataSet, labels, k):

    dataSetSize = dataSet.shape[0]

    diffMat = np.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=op.itemgetter(1), reverse=True)

    return sortedClassCount[0][0]

def file2matrix(filename):

    fr = open(filename)

    returnMat = []

    classLabelVector = []                       #prepare labels return

    for line in fr.readlines():

        line = line.strip()

        listFromLine = line.split('\t')

        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])

        classLabelVector.append(int(listFromLine[-1]))

    return np.array(returnMat),np.array(classLabelVector)

def autoNorm(dataSet):

    minVals = dataSet.min(0)

    maxVals = dataSet.max(0)

    ranges = maxVals - minVals

    normDataSet = np.zeros(np.shape(dataSet))

    m = dataSet.shape[0]

    normDataSet = dataSet - np.tile(minVals, (m,1))

    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide

    return normDataSet, ranges, minVals

def classifyPerson():

    resultList = ["not at all", "in samll doses", "in large doses"]

    percentTats = float(input("percentage of time spent playing video game?"))

    ffMiles = float(input("frequent flier miles earned per year?"))

    iceCream = float(input("liters of ice cream consumed per year?"))

    testData = np.array([percentTats,ffMiles,iceCream])

    trainData,trainLabel = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet2.txt")

    normDataSet, ranges, minVals = autoNorm(trainData)

    result = classify0((testData-minVals)/ranges, normDataSet, trainLabel, 3)

    print("You will probably like this person: ",resultList[result-1])

classifyPerson()
import numpy as np

import operator as op

from os import listdir

def classify0(inX, dataSet, labels, k):

    dataSetSize = dataSet.shape[0]

    diffMat = np.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=op.itemgetter(1), reverse=True)

    return sortedClassCount[0][0]

def file2matrix(filename):

    fr = open(filename)

    returnMat = []

    classLabelVector = []                       #prepare labels return

    for line in fr.readlines():

        line = line.strip()

        listFromLine = line.split('\t')

        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])

        classLabelVector.append(int(listFromLine[-1]))

    return np.array(returnMat),np.array(classLabelVector)

def autoNorm(dataSet):

    minVals = dataSet.min(0)

    maxVals = dataSet.max(0)

    ranges = maxVals - minVals

    normDataSet = np.zeros(np.shape(dataSet))

    m = dataSet.shape[0]

    normDataSet = dataSet - np.tile(minVals, (m,1))

    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide

    return normDataSet, ranges, minVals

def classifyPerson():

    resultList = ["not at all", "in samll doses", "in large doses"]

    percentTats = float(input("percentage of time spent playing video game?"))

    ffMiles = float(input("frequent flier miles earned per year?"))

    iceCream = float(input("liters of ice cream consumed per year?"))

    testData = np.array([percentTats,ffMiles,iceCream])

    trainData,trainLabel = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet2.txt")

    normDataSet, ranges, minVals = autoNorm(trainData)

    result = classify0((testData-minVals)/ranges, normDataSet, trainLabel, 3)

    print("You will probably like this person: ",resultList[result-1])

classifyPerson()

import numpy as np

import operator as op

from os import listdir

def classify0(inX, dataSet, labels, k):

    dataSetSize = dataSet.shape[0]

    diffMat = np.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=op.itemgetter(1), reverse=True)

    return sortedClassCount[0][0]

def img2vector(filename):

    returnVect = []

    fr = open(filename)

    for i in range(32):

        lineStr = fr.readline()

        for j in range(32):

            returnVect.append(int(lineStr[j]))

    return np.array([returnVect])

def handwritingClassTest():

    hwLabels = []

    trainingFileList = listdir('D:\\LearningResource\\machinelearninginaction\\Ch02\\trainingDigits')           #load the training set

    m = len(trainingFileList)

    trainingMat = np.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('D:\\LearningResource\\machinelearninginaction\\Ch02\\trainingDigits\\%s' % fileNameStr)

    testFileList = listdir('D:\\LearningResource\\machinelearninginaction\\Ch02\\testDigits')        #iterate through the test set

    mTest = len(testFileList)

    errorCount = 0.0

    for i in range(mTest):

        fileNameStr = testFileList[i]

        fileStr = fileNameStr.split('.')[0]     #take off .txt

        classNumStr = int(fileStr.split('_')[0])

        vectorUnderTest = img2vector('D:\\LearningResource\\machinelearninginaction\\Ch02\\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)))

handwritingClassTest()

.......................................

吴裕雄 python 机器学习-KNN算法（1）的更多相关文章

  1. 吴裕雄 python 机器学习——KNN回归KNeighborsRegressor模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import neighbors, datasets from skle ...

  2. 吴裕雄 python 机器学习——KNN分类KNeighborsClassifier模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import neighbors, datasets from skle ...

  3. 吴裕雄 python 机器学习-KNN（2）

    import matplotlib import numpy as np import matplotlib.pyplot as plt from matplotlib.patches import ...

  4. 吴裕雄 python 机器学习——半监督学习标准迭代式标记传播算法LabelPropagation模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import metrics from sklearn import d ...

  5. 吴裕雄 python 机器学习——集成学习AdaBoost算法回归模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets,ensemble from sklear ...

  6. 吴裕雄 python 机器学习——集成学习AdaBoost算法分类模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets,ensemble from sklear ...

  7. 吴裕雄 python 机器学习——人工神经网络感知机学习算法的应用

    import numpy as np from matplotlib import pyplot as plt from sklearn import neighbors, datasets from ...

  8. 吴裕雄 python 机器学习——半监督学习LabelSpreading模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import metrics from sklearn import d ...

  9. 吴裕雄 python 机器学习——人工神经网络与原始感知机模型

    import numpy as np from matplotlib import pyplot as plt from mpl_toolkits.mplot3d import Axes3D from ...

随机推荐

  1. MySQL高可用架构之基于MHA的搭建

    一.MySQL MHA架构介绍: MHA(Master High Availability)目前在MySQL高可用方面是一个相对成熟的解决方案,它由日本DeNA公司youshimaton(现就职于Fa ...

  2. windows下git的使用

    1.安装git 下载地址:https://git-scm.com/download/win

  3. Splunk和ElasticSearch深度对比解析(转)

    转载自:http://www.sohu.com/a/154105465_354963 随着Splunk越来越被大家熟知和认可,现在市面上也不断涌各种同类产品,作为大数据搜索界的翘楚Splunk和Ela ...

  4. 利用Python实现FGO自动战斗脚本，再也不用爆肝啦~

    Fate/Grand Order(非的肝不过欧的)作为索尼为了拯救自己不倒闭而开发的面向月厨的骗氪养成抽卡爆肝游戏,居然没有像隔壁<阴阳师>的自动战斗系统(看看别人现在都自带脚本了).毕竟 ...

  5. css3选择

    在一些项目中,我们常常需要实现选择类似于3的倍数的位数的元素,或者从第n个之后的元素,或者从第n个到第m个元素这种类型的选择,如果说在以前,想完全通过css实现,似乎是天方夜谭,根本不可能实现,CSS ...

  6. Java 时间类

    1.System 类 2.Date 类 3.SimpleDateFormate 类 4.Calendar 类 1.System 类 得到当前的时间值.System 类不能被实例化,需要通过它的静态方法 ...

  7. 重识linux-linux系统服务相关

    重识linux-linux系统服务相关 1 tcp wrappers 特殊功能  应用级防火墙 2 系统开启的服务查看 top,ps 命令 3 查看系统启动的服务 1) 找到目前系统开启的网络服务 n ...

  8. 【学习】Python解决汉诺塔问题

    参考文章:http://www.cnblogs.com/dmego/p/5965835.html   一句话:学程序不是目的,理解就好:写代码也不是必然,省事最好:拿也好,查也好,解决问题就好!   ...

  9. 使用include重用布局

    尽管Android 支持各种小部件,来提供小且可以重用的交互元素,你可能还需要更大的,要求一个专门布局的重用组件.为了高效的重用整个布局,你能使用和标签在当前的布局中嵌入别的布局. 重用布局功能特别强 ...

  10. PHP 时间相关操作

    使用函式 date() 实现 <?php echo $showtime=date("Y-m-d H:i:s");?> 显示的格式: 年-月-日 小时:分钟:秒 获得当天 ...