ML in Action 02 KNN python3.6 code
2017-12-29 16:11
381 查看
机器学习实战02章KNN代码,数据为iris鸢尾花数据(已经先打乱)
from numpy import *
import operator
from os import listdir
def classify0(inX, dataSet, labels, k):
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]
def createDataSet():
group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
labels = ['A','A','B','B']
return group, labels
def file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines()) #get the number of lines in the file
returnMat = zeros((numberOfLines,4)) #prepare matrix to return
classLabelVector = [] #prepare labels return
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
returnMat[index,:] = listFromLine[0:4]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat,classLabelVector
手写数字分类器:
def img2vector(filename):
returnVect = zeros((1,1024))
fr = open(filename)
for i in range(32):
lineStr = fr.readline()
for j in range(32):
returnVect[0,32*i+j] = int(lineStr[j])
return returnVect
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('D:/ML_in_Action/machinelearninginaction/Ch02/trainingDigits') #load the training set
m = len(trainingFileList)
trainingMat = 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:/ML_in_Action/machinelearninginaction/Ch02/trainingDigits/%s' % fileNameStr)
testFileList = listdir('D:/ML_in_Action/machinelearninginaction/Ch02/testDigits') #iterate through the test set
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('D:/ML_in_Action/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)))
from numpy import *
import operator
from os import listdir
def classify0(inX, dataSet, labels, k):
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]
def createDataSet():
group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
labels = ['A','A','B','B']
return group, labels
def file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines()) #get the number of lines in the file
returnMat = zeros((numberOfLines,4)) #prepare matrix to return
classLabelVector = [] #prepare labels return
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
returnMat[index,:] = listFromLine[0:4]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat,classLabelVector
def autoNorm(dataSet): minVals = dataSet.min(0) maxVals = dataSet.max(0) ranges = maxVals - minVals normDataSet = zeros(shape(dataSet)) m = dataSet.shape[0] normDataSet = dataSet - tile(minVals, (m,1)) normDataSet = normDataSet/tile(ranges, (m,1)) #element wise divide return normDataSet, ranges, minVals def datingClassTest(): hoRatio = 0.10 #hold out 10% datingDataMat,datingLabels = file2matrix('D:/ML_in_Action/machinelearninginaction/Ch02/iris.txt') #load data setfrom file 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: %d, the real answer is: %d" % (classifierResult, datingLabels[i])) if (classifierResult != datingLabels[i]): errorCount += 1.0 print ("the total error rate is: %f" % (errorCount/float(numTestVecs))) print (errorCount)
手写数字分类器:
def img2vector(filename):
returnVect = zeros((1,1024))
fr = open(filename)
for i in range(32):
lineStr = fr.readline()
for j in range(32):
returnVect[0,32*i+j] = int(lineStr[j])
return returnVect
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('D:/ML_in_Action/machinelearninginaction/Ch02/trainingDigits') #load the training set
m = len(trainingFileList)
trainingMat = 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:/ML_in_Action/machinelearninginaction/Ch02/trainingDigits/%s' % fileNameStr)
testFileList = listdir('D:/ML_in_Action/machinelearninginaction/Ch02/testDigits') #iterate through the test set
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('D:/ML_in_Action/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)))
相关文章推荐
- ML in Action 05 Logistic Regression python3.6 code
- 常用python_ML in Action
- 【ML】【python】Machine Learning in Action
- Machine Learning In Action:KNN(Python)
- ML in action代码学习/CH02 KNN/约会网站配对效果改进
- test run time of lines code in microsecond under Python3.6
- Machine Learning In Action -- kNN的python实现
- crossplatform---Nodejs in Visual Studio Code 02.学习Nodejs
- 6 Easy Steps to Learn Naive Bayes Algorithm (with code in Python)
- Machine Learning in Action_CH2_2_使用kNN改进约会网站的配对效果
- Face Recognition with Python, in Under 25 Lines of Code
- pip安装jupyter时报错Command "python setup.py egg_info" failed with error code 1 in /tmp/pip-build-Fd4ir0/
- note of code in python
- Spring in action 02 -- 装配 Bean(JavaConfig)遇到的问题
- error:Command "python setup.py egg_info" failed with error code 1 in /private/var/folders/_r/fcrtlb8
- Code Generation in Action
- SPRING IN ACTION 第4版笔记-第九章Securing web applications-006-用LDAP比较密码(passwordCompare()、passwordAttribute("passcode")、passwordEncoder(new Md5PasswordEncoder()))
- (未解决,只是提供一种思路)安装pyspider失败:Command "python setup.py egg_info"failed with error code 10 in.....
- python错误:SyntaxError: Non-UTF-8 code starting with '\xcb' in file E:/Python/test.py on line 2
- Command "python setup.py egg_info" failed with error code 1 in /tmp/pip-build-b2PICB/unroll/