吴裕雄 python 机器学习-NBYS(1)
import numpy as np def loadDataSet():
postingList=[['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
['stop', 'posting', 'stupid', 'worthless', 'garbage'],
['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
classVec = [0,1,0,1,0,1]
return postingList,classVec def createVocabList(dataSet):
vocabSet = set([])
for document in dataSet:
vocabSet = vocabSet | set(document)
return list(vocabSet) def setOfWords2Vec(vocabList, inputSet):
returnVec = [0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] = 1
else:
print("the word: %s is not in my Vocabulary!" % word)
return returnVec def trainNB0(trainMatrix,trainCategory):
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory)/float(numTrainDocs)
p0Num = np.ones(numWords)
p1Num = np.ones(numWords)
p0Denom = 2.0
p1Denom = 2.0
for i in range(numTrainDocs):
if(trainCategory[i] == 1):
p1Num += trainMatrix[i]
p1Denom += sum(trainMatrix[i])
else:
p0Num += trainMatrix[i]
p0Denom += sum(trainMatrix[i])
p1Vect = np.log(p1Num/p1Denom)
p0Vect = np.log(p0Num/p0Denom)
return p0Vect,p1Vect,pAbusive def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
p1 = sum(vec2Classify * p1Vec) + np.log(pClass1)
p0 = sum(vec2Classify * p0Vec) + np.log(1.0 - pClass1)
if p1 > p0:
return 1
else:
return 0 def bagOfWords2VecMN(vocabList, inputSet):
returnVec = [0]*len(vocabList)
for word in inputSet:
if(word in vocabList):
returnVec[vocabList.index(word)] += 1
return returnVec def testingNB():
listOPosts,listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat=[]
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
p0V,p1V,pAb = trainNB0(np.array(trainMat),np.array(listClasses))
testEntry = ['love', 'my', 'dalmation']
thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))
testEntry = ['stupid', 'garbage']
thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)) testingNB()
import re
import numpy as np def createVocabList(dataSet):
vocabSet = set([])
for document in dataSet:
vocabSet = vocabSet | set(document)
return list(vocabSet) def bagOfWords2VecMN(vocabList, inputSet):
returnVec = [0]*len(vocabList)
for word in inputSet:
if(word in vocabList):
returnVec[vocabList.index(word)] += 1
return returnVec def trainNB0(trainMatrix,trainCategory):
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory)/float(numTrainDocs)
p0Num = np.ones(numWords)
p1Num = np.ones(numWords)
p0Denom = 2.0
p1Denom = 2.0
for i in range(numTrainDocs):
if(trainCategory[i] == 1):
p1Num += trainMatrix[i]
p1Denom += sum(trainMatrix[i])
else:
p0Num += trainMatrix[i]
p0Denom += sum(trainMatrix[i])
p1Vect = np.log(p1Num/p1Denom)
p0Vect = np.log(p0Num/p0Denom)
return p0Vect,p1Vect,pAbusive def textParse(bigString):
listOfTokens = re.split(r'\W*', bigString)
return [tok.lower() for tok in listOfTokens if len(tok) > 2] def spamTest():
docList=[]
classList = []
fullText =[]
for i in range(1,26):
wordList = textParse(open('D:\\LearningResource\\machinelearninginaction\\Ch04\\email\\spam\\%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('D:\\LearningResource\\machinelearninginaction\\Ch04\\email\\ham\\%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = createVocabList(docList)
trainingSet = list(np.arange(50))
testSet=[]
for i in range(10):
randIndex = int(np.random.uniform(0,len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat=[]
trainClasses = []
for docIndex in trainingSet:
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V,p1V,pSpam = trainNB0(np.array(trainMat),np.array(trainClasses))
errorCount = 0
for docIndex in testSet:
wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
if(classifyNB(np.array(wordVector),p0V,p1V,pSpam) != classList[docIndex]):
errorCount += 1
print("classification error",docList[docIndex])
print('the error rate is: ',float(errorCount)/len(testSet)) spamTest()
吴裕雄 python 机器学习-NBYS(1)的更多相关文章
- 吴裕雄 python 机器学习-NBYS(2)
import matplotlib import numpy as np import matplotlib.pyplot as plt n = 1000 xcord0 = [] ycord0 = [ ...
- 吴裕雄 python 机器学习——分类决策树模型
import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...
- 吴裕雄 python 机器学习——回归决策树模型
import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...
- 吴裕雄 python 机器学习——线性判断分析LinearDiscriminantAnalysis
import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...
- 吴裕雄 python 机器学习——逻辑回归
import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...
- 吴裕雄 python 机器学习——ElasticNet回归
import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...
- 吴裕雄 python 机器学习——Lasso回归
import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, linear_model from s ...
- 吴裕雄 python 机器学习——岭回归
import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, linear_model from s ...
- 吴裕雄 python 机器学习——线性回归模型
import numpy as np from sklearn import datasets,linear_model from sklearn.model_selection import tra ...
随机推荐
- ngModel缺省是by reference,
1) 缺省是 by reference, not value, ngModel, ngOptions等都一样 2) 如果要 track value 用 "track by", ...
- Android Notification通知栏的使用,通知栏在Android8.0系统不显示的问题;
1.正常使用通知栏: /** * 创建通知栏管理工具 */ NotificationManager notificationManager = (NotificationManager) getSys ...
- 使用Redis数据库(String类型)
一 String类型 首先使用启动服务器进程 : redis-server.exe 1. Set 设置Key对应的值为String 类型的value. 例子:向 Redis数据库中插入一条数据类型为S ...
- webstorm命令行无法使用node-gyp进行编译
换成cmd命令即可:
- “javac”不是内部或外部命令的解决办法(JDK1.5 ~ JDK10)
配置环境变量:计算机 -> 属性 -> 高级系统设置 -> 环境变量 JDK9以后版本(9-10): JAVA_HOME D:\Java\jdk-10 //jdk所在目录 JRE_H ...
- SQL各种语(持续更新)
--通过分组查询,并查询各个组下面的数据数量 SELECT cord,COUNT(*) AS s FROM View_QualityPolicy GROUP BY cord ORDER BY s DE ...
- java的list遍历
for(String str : list) {//增强for循环,其内部实质上还是调用了迭代器遍历方式,这种循环方式还有其他限制,不建议使用. System.out.println(str); } ...
- (转)微信小程序开发—弹出框
原文地址 <span style="font-family:Comic Sans MS;font-size:18px;color:#333333;"><view ...
- layer.js关闭子窗口及刷新父窗口
在需要layer.js弹窗口时,当编辑完窗口内容,需要关闭及刷新父窗口时: $("#senddata").click(function(){var id = $('input[na ...
- oracle数据库tns配置方法详解
TNS简要介绍与应用 Oracle中TNS的完整定义:transparence Network Substrate透明网络底层,监听服务是它重要的一部分,不是全部,不要把TNS当作只是监听器. TNS ...