吴裕雄 python 机器学习-KNN算法（1）

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

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

es6基础(5)--数值扩展
{ //Number.isFinite数字是有尽的 console.log(Number.isFinite(15));//true console.log(Number.isFinite(NaN)); ...
Java之ConcurrentHashMap
由于工作中使用到了ConcurrentHashMap,然后查了一波资料,最后整理如下: 1. 描述: ConcurrentHashMap是在Java1.5作为HashTable的替代选择新引入的,是c ...
[work]Spring_Jdbc
封装Spring-RowMapper,使得使用更加灵活 import java.sql.ResultSet; import java.sql.SQLException; import java.uti ...
nodejs运行的两种方式<小记>
在mac上: 1.方式一:使用IDE运行配置需要运行的js文件: 配置并运行 ①配置运行的js文件和运行的文件不一致时会导致报错.如图备注 ②当运行另一个文件提示端口8080被占用 ,需要改为其他端 ...
网易云音乐mp3外链、真实地址下载方法
一个网易音乐外链地址长期有效,很简单的方法: 第一步打开网易云音乐,随便找到一首歌,播放,复制网址的ID, 例如:杨钰莹的心雨,网址是: http://music.163.com/#/song?id= ...
Java 文件类 File
1.File 类 1.File 类 1.1.构造方法文件的抽象路径名(操作系统无关) 构造方法格式说明 File(String filename) 把文件路径名字符串转换为“抽象路径名”,用来 ...
[Lua]弱引用table
参考链接: http://www.benmutou.com/archives/1808 一.强引用table lua中的table是引用类型,更准确地说,是强引用类型.如下第二段代码,在内存中有一个{ ...
1. @ModelAttribute注解
添加@ModelAttribute修饰的方法,在每个目标方法调用前都会执行该方法. 一般情况下,在form表单修改的时,某项字段规定为不可更改,就需要使用该注解标注的方法,根据id的获取与否,来从数据 ...
HTML+CSS盒模型
一.Padding 1.padding用来调整内容在容器中的位置关系:padding的属性要添加到父元素上. padding值是额外加在元素原有的大小之上的,若想保证元素大小不变,需从元素宽或高上 ...
leetcode970
public class Solution { public IList<int> PowerfulIntegers(int x, int y, int bound) { var list ...

吴裕雄 python 机器学习-KNN算法（1）

吴裕雄 python 机器学习-KNN算法（1）的更多相关文章

随机推荐

热门专题