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

  1. 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 = [ ...

  2. 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 ...

  3. 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 ...

  4. 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 ...

  5. 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 ...

  6. 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 ...

  7. 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 ...

  8. 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 ...

  9. 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

  1. Java并发知识整理

    整理了一下前段时间学习Java并发的笔记,大约有40篇. 1. Java并发基础知识 并发基础(一) 线程介绍 并发基础(二) Thread类的API总结 并发基础(三) java线程优先级 并发基础 ...

  2. kafka 消息系统

    一.为什么需要消息系统 1.解耦: 允许你独立的扩展或修改两边的处理过程,只要确保它们遵守同样的接口约束. 2.冗余: 消息队列把数据进行持久化直到它们已经被完全处理,通过这一方式规避了数据丢失风险. ...

  3. JVM总结-虚拟机加载类

    从 class 文件到内存中的类,按先后顺序需要经过加载.链接以及初始化三大步骤.其中,链接过程中同样需要验证:而内存中的类没有经过初始化,同样不能使用.那么,是否所有的 Java 类都需要经过这几步 ...

  4. etree和Beautiful Soup的使用

    1.lxml 是一种使用 Python 编写的库,可以迅速.灵活地处理 XML ,支持 XPath (XML Path Language),使用 lxml 的 etree 库来进行爬取网站信息 2.B ...

  5. python库myqr生成二维码

    python中有一个好玩的库,不仅可以生成各种花色的二维码,还可以生成动态二维码. MyQR是一个能够生成自定义二维码的第三方库,可以根据需要生成普通二维码.带图片的艺术二维码,也可以生成动态二维码 ...

  6. Python笔记:字典的fromkeys方法创建的初始value同内存地址问题

    dict中的fromkeys()函数可以通过一个list来创建一个用同一初始value的dict. d = dict.fromkeys(["苹果", "菠萝"] ...

  7. 微信小程序笔记<六>模块化 —— module.exports

    微信小程序中所有 js 文件作用域皆为独立的,每一个 js 文件即为一个模块.模块与模块之间的引用通过 module.exports 或 exports 对外暴露接口. 注意: exports 是 m ...

  8. android开发 RecyclerView 列表布局

    创建一个一行的自定义布局 <?xml version="1.0" encoding="utf-8"?> <LinearLayout xmlns ...

  9. Thinkphp时间转换与统计的问题

    1.thinkphp一般存入的都是时间戳,如果希望输入时直接显示格式化的时间呢: a. sql语句: SELECT DATE_FORMAT(create_time,'%Y%u') weeks,COUN ...

  10. [Unity工具]批量修改字体

    效果图: using System.IO; using System.Text; using UnityEditor; using UnityEngine; using UnityEngine.UI; ...