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. vs code编辑器格式化react jsx插件

    vs code格式化jsx比较适合的插件是react-beautify: 格式化中遇到的问题是indent几格,这个问题的解决是你在space里设置几格这个插件就会自动格式化出几格.

  2. python装饰器(二)

    有参装饰器 def outer(flag): def timer(func): def inner(*args,**kwargs): if flag: print('''执行函数之前要做的''') r ...

  3. Spark Streaming实时数据分析

    [kfk@bigdata-pro01 softwares]$ sudo rpm -ivh nc-.el6.x86_64.rpm Preparing... ####################### ...

  4. [TJOI2015]弦论(后缀自动机)

    /* 一道在树上乱搞的题目 建立出parent树来, 然后就能搞出每个节点往后能扩展出几个串, 至于位置不同算同一个的话就强制让right集合大小为1即可 然后在树上类比权值线段树找第k大26分统计一 ...

  5. 小数据池 id

    1. 小数据池, id() 小数据池针对的是: int, str, bool 在py文件中几乎所有的字符串都会缓存. id() 查看变量的内存地址 # id()函数可以帮我们查看一个变量的内存地址 # ...

  6. 安全测试3_Web后端知识学习

    其实中间还应该学习下web服务和数据库的基础,对于web服务大家可以回家玩下tomcat或者wamp等东西,数据库的话大家掌握基本的增删该查就好了,另外最好掌握下数据库的内置函数,如:concat() ...

  7. [Unity动画]02.动画播放

    参考链接: http://www.cnblogs.com/hont/p/5100472.html 上一篇是直接通过界面来控制动作的播放,这篇将使用脚本去管理对象的动作 API解析: Animator. ...

  8. 2014最新 iOS App 提交上架store 详细流程

    http://blog.csdn.net/tt5267621/article/details/39430659

  9. leetcode329

    public class Solution { bool[,] tags;//用于标记是否已经访问过,false未访问,true已访问 int[,] records;//用于标记以当前为起点的最长升序 ...

  10. HTML 圆心节点

    <!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8&quo ...