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. Noi.ac #309. Mas的童年(贪心）

    /* 用所谓的加法拆分操作得到 x + y = (x ^ y) + 2 * (x & y) 那么我们这两段异或相当于前缀和 + 2 * 分段使左右两块&最大 记当前前缀异或和为S, 那 ...

  2. spring boot整合quartz实现多个定时任务

        版权声明:本文为博主原创文章,转载请注明出处. https://blog.csdn.net/liuchuanhong1/article/details/78543574 最近收到了很多封邮件, ...

  3. NoSQL学习1

    MongoDB使用C++语言编写的一个基于分布式的文件存储的开源数据库.可以在承受高负载的情况下,保证服务器的性能. MongoDB将数据存储成为一个文档,数据结构有键值对组成.类似于JSON,字段值 ...

  4. FreeMarker内建函数

    内建函数 内建函数语法格式: 变量+?+函数名称 获取集合大小 我们通常要得到某个集合的大小,如下图: 我们使用size函数来实现,代码如下: 共  ${goodsList?size}  条记录 转换 ...

  5. tkinter面板切换

  6. <转载> nginx服务器安装及配置文件详解 https://segmentfault.com/a/1190000002797601

    nginx在工作中已经有好几个环境在使用了,每次都是重新去网上扒博客,各种编译配置,今天自己也整理一份安装文档和nginx.conf配置选项的说明,留作以后参考.像负载均衡配置(包括健康检查).缓存( ...

  7. hdfs standby namenode checkpoint 的一些参数

    dfs.namenode.checkpoint.period --两次检查点创建之间的固定时间间隔,默认3600,即1小时.所以去ann snn 看到的fsimage 相隔1个小时. dfs.name ...

  8. 关于 HTTP

    HTTP是一种能够获取如 HTML 这样的网络资源的 protocol(通讯协议).它是在 Web 上进行数据交换的基础,是一种 client-server 协议,也就是说,请求通常是由像浏览器这样的 ...

  9. Redis命令操作详解

    一.key pattern 查询相应的key (1)redis允许模糊查询key 有3个通配符  *.?.[] (2)randomkey:返回随机key (3)type key:返回key存储的类型 ...

  10. PHP 使用非对称加密算法（RSA）

    解释: 非对称加密算法需要两个密钥:公开密钥(publickey)和私有密钥(privatekey).公开密钥与私有密钥是一对,如果用公开密钥对数据进行加密,只有用对应的私有密钥才能解密:如果用私有密 ...