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
- hbase启动后子节点的regionserver不能启动
启动hbase后,主节点的进程正常,但是子节点的regionserver进程会自动挂掉 然后我们看看子节点的情况 可以看到挂掉了 我们这样解决问题,先把hadoop目录下的这个两个文件放到hbase的 ...
- RecyclerView中设置match_parent无效;
在RecyclerView中宽度设置了match_parent,但是效果和wrap_content一样: 说下解决方法: 1.这样子写,match_parent没有效果: View v = View. ...
- SQL with(unlock)与with(readpast)
所有Select加 With (NoLock)解决阻塞死锁,在查询语句中使用 NOLOCK 和 READPAST 处理一个数据库死锁的异常时候,其中一个建议就是使用 NOLOCK 或者 READPAS ...
- three.js学习:点光源+动画的实现
与前几个教程类似,场景和相机等设置就不再重复声明了.这里只列出新学的内容. 1.圆柱体(圆锥体)的初始化 function initObject() { var geometry = new THRE ...
- springmvc接收前台(如ajax)传来的数组list,set等图文详解
ref:https://blog.csdn.net/wabiaozia/article/details/50803581 前言: 相信很人都被springmvc接收数组问题折磨过,查过几个解决 ...
- jQuery插件——下拉选择框
其实,之前也写过jQuery插件,今天写的是一个模拟select选择的下拉插件. 既然是jQuery插件,那么必然是依赖jQuery的了. 老规矩,直接上代码吧! ;(function () { $. ...
- Redis实现分布式锁原理与实现分析
一.关于分布式锁 关于分布式锁,可能绝大部分人都会或多或少涉及到. 我举二个例子: 场景一:从前端界面发起一笔支付请求,如果前端没有做防重处理,那么可能在某一个时刻会有二笔一样的单子同时到达系统后台. ...
- Maintenance Planner calculate SPs by manual
note Are you unable to view your system or updated system information? Apply the latest version of t ...
- <转载> MySQL 性能优化的最佳20多条经验分享 http://www.jb51.net/article/24392.htm
当我们去设计数据库表结构,对操作数据库时(尤其是查表时的SQL语句),我们都需要注意数据操作的性能.这里,我们不会讲过多的SQL语句的优化,而只是针对MySQL这一Web应用最多的数据库.希望下面的这 ...
- tomcat中项目后有括号
引入他人项目时,由于报错,copy本地workspace下其他项目的 .settings和.project到该项目路径下 结果Eclipse 的 Server 中出现了 aaa(bbb)的情况 并且 ...