python程序运行报错
from numpy import *
def loadDateSet():
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:
returnVec[vocabList.index(word)] = 1
else:
print("the word: %s is not in my vocabulary!" % word)
return returnVec
def trainNBO(trainMatrix, trainCategory):
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory) / float(numTrainDocs)
p0Num = zeros(numWords);
p1Num = zeros(numWords)
p0Demon = 0.0;
p1Demon = 0.0
for i in range(numTrainDocs):
if trainCategory[i] == 1:
p1Num += trainMatrix[i]
p1Demon += sum(trainMatrix[i])
else:
p0Num += trainMatrix[i]
p0Demon += sum(trainMatrix[i])
p1Vect = log(p1Num * p1Demon)
p0Vect = log(p0Num * p0Demon)
return p0Vect, p1Vect, pAbusive
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
p1 = sum(vec2Classify * p1Vec) + log(pClass1)
p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
if p1 > p0:
return 1
else:
return 0
def testingNB():
listOPosts, listClasses = loadDateSet()
myVocabList = createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
p0V, p1V, pAb = trainNBO(trainMat, listClasses)
test = ['love', 'my', 'dalmation']
this = setOfWords2Vec(myVocabList, test)
print(test, 'classified as:', classifyNB(this, pAb, p1V, p0V))
test = ['stupid', 'garbage']
this = setOfWords2Vec(myVocabList, test)
print(test, 'classified as:', classifyNB(this, pAb, p1V, p0V))
修改代码
p1Vect = log(p1Num/p1Demon)
p0Vect = log(p0Num/p0Demon)
部分回答整理自GPT：（我已经验证过了，可以正常运行）
在您提供的代码中，有几个地方存在错误：
在
trainNBO函数中，计算p1Vect和p0Vect的方式不正确。应该将它们放在循环之外，以便在计算完所有的词向量和词频后再进行计算。另外，计算概率时应使用除法而不是乘法。在
classifyNB函数中，计算p1和p0的方式也不正确。应该将两个向量的元素相乘后再求和，而不是直接使用乘法运算符*。
下面是修正后的代码：
from numpy import *
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 trainNBO(trainMatrix, trainCategory):
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory) / float(numTrainDocs)
p0Num = ones(numWords)
p1Num = 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 = log(p1Num / p1Denom)
p0Vect = log(p0Num / p0Denom)
return p0Vect, p1Vect, pAbusive
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
p1 = sum(vec2Classify * p1Vec) + log(pClass1)
p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
if p1 > p0:
return 1
else:
return 0
def testingNB():
listOPosts, listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
p0V, p1V, pAb = trainNBO(trainMat, listClasses)
testEntry = ['love', 'my', 'dalmation']
thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
print(testEntry, 'classified as:', classifyNB(thisDoc, p0V, p1V, pAb))
testEntry = ['stupid', 'garbage']
thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
print(testEntry, 'classified as:', classifyNB(thisDoc, p0V, p1V, pAb))
testingNB()
最后添加了一个调用testingNB方法，以便可以运行。
错误截图放一下，还有你代码里没有main方法啊
- 这有个类似的问题, 你可以参考下: https://ask.csdn.net/questions/7743033
- 你也可以参考下这篇文章：用python进行模拟
- 除此之外, 这篇博客: Python 汇总中的 成员运算符 部分也许能够解决你的问题, 你可以仔细阅读以下内容或跳转源博客中阅读:
运算符 描述 in 如果在指定的序列中找到值返回 True，否则返回 False not in 如果在指定的序列中没有找到值返回 True，否则返回 False """ @dauthor : cpucode @date : 2022/3/1 9:06 @github : https://github.com/CPU-Code @csdn : https://blog.csdn.net/qq_44226094 """ a = 22 b = 11 list = [11, 22, 33, 44, 55] if (a in list): print("a 在列表 list 中") else: print("a 不在列表 list 中") if(b not in list): print("b 不在列表 list 中") else: print("b 在列表 list 中") print("/*****************************************/") # 修改变量 a 的值 a = 2 if (a in list): print("a 在列表 list 中") else: print("a 不在列表 list 中")
- 您还可以看一下 唐宇迪老师的Python数据挖掘实战课程中的 行为特征小节, 巩固相关知识点
报什么错，运行过后输出打印都没有