目录
基于贝叶斯决策理论的分类方法
优点：在数据较少的情况下仍然有效，可以处理多类别问题。
缺点：对于输入数据的准备方式较为敏感。
适用数据：标称型数据。
使用Python进行文本分类
准备数据：从文本中构建词向量
python
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
python
def createVocabList(dataSet):
vocabSet = set([])
for document in dataSet:
vocabSet = vocabSet | set(document)
return list(vocabSet)
python
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
python
listOPosts, listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
myVocabListoutput
['quit',
'him',
'is',
'food',
'to',
'so',
'please',
'maybe',
'love',
'problems',
'flea',
'park',
'stop',
'not',
'how',
'take',
'dog',
'has',
'i',
'my',
'dalmation',
'garbage',
'ate',
'buying',
'steak',
'mr',
'worthless',
'stupid',
'cute',
'help',
'licks',
'posting']
python
setOfWords2Vec(myVocabList, listOPosts[0])output
[0,
0,
0,
0,
0,
0,
1,
0,
0,
1,
1,
0,
0,
0,
0,
0,
1,
1,
0,
1,
0,
0,
0,
0,
0,
0,
0,
0,
0,
1,
0,
0]训练算法：从词向量计算概率
python
from numpy import *
def trainNB0(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
python
listOPosts, listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
python
listOPostsoutput
[['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']]
python
trainMat
python
len(trainMat[0])output
32
python
trainMatrix = trainMat
trainCategory = listClasses
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]
print(p1Num)
p1Denom += sum(trainMatrix[i])
print(p1Denom)
else:
p0Num += trainMatrix[i]
print(p0Num)
p0Denom += sum(trainMatrix[i])
print(p0Denom)
p1Vect = log(p1Num / p1Denom)
p0Vect = log(p0Num / p0Denom)output
[1. 1. 1. 1. 1. 1. 2. 1. 1. 2. 2. 1. 1. 1. 1. 1. 2. 2. 1. 2. 1. 1. 1. 1.
1. 1. 1. 1. 1. 2. 1. 1.]
9.0
[1. 2. 1. 1. 2. 1. 1. 2. 1. 1. 1. 2. 1. 2. 1. 2. 2. 1. 1. 1. 1. 1. 1. 1.
1. 1. 1. 2. 1. 1. 1. 1.]
10.0
[1. 2. 2. 1. 1. 2. 2. 1. 2. 2. 2. 1. 1. 1. 1. 1. 2. 2. 2. 3. 2. 1. 1. 1.
1. 1. 1. 1. 2. 2. 1. 1.]
17.0
[1. 2. 1. 1. 2. 1. 1. 2. 1. 1. 1. 2. 2. 2. 1. 2. 2. 1. 1. 1. 1. 2. 1. 1.
1. 1. 2. 3. 1. 1. 1. 2.]
15.0
[1. 3. 2. 1. 2. 2. 2. 1. 2. 2. 2. 1. 2. 1. 2. 1. 2. 2. 2. 4. 2. 1. 2. 1.
2. 2. 1. 1. 2. 2. 2. 1.]
26.0
[2. 2. 1. 2. 2. 1. 1. 2. 1. 1. 1. 2. 2. 2. 1. 2. 3. 1. 1. 1. 1. 2. 1. 2.
1. 1. 3. 4. 1. 1. 1. 2.]
21.0
python
p0V, p1V, pAb = trainNB0(trainMat, listClasses)
python
pAboutput
0.5
python
p0Voutput
array([-3.25809654, -2.15948425, -2.56494936, -3.25809654, -2.56494936,
-2.56494936, -2.56494936, -3.25809654, -2.56494936, -2.56494936,
-2.56494936, -3.25809654, -2.56494936, -3.25809654, -2.56494936,
-3.25809654, -2.56494936, -2.56494936, -2.56494936, -1.87180218,
-2.56494936, -3.25809654, -2.56494936, -3.25809654, -2.56494936,
-2.56494936, -3.25809654, -3.25809654, -2.56494936, -2.56494936,
-2.56494936, -3.25809654])
python
p1Voutput
array([-2.35137526, -2.35137526, -3.04452244, -2.35137526, -2.35137526,
-3.04452244, -3.04452244, -2.35137526, -3.04452244, -3.04452244,
-3.04452244, -2.35137526, -2.35137526, -2.35137526, -3.04452244,
-2.35137526, -1.94591015, -3.04452244, -3.04452244, -3.04452244,
-3.04452244, -2.35137526, -3.04452244, -2.35137526, -3.04452244,
-3.04452244, -1.94591015, -1.65822808, -3.04452244, -3.04452244,
-3.04452244, -2.35137526])测试算法：根据现实情况修改分类器
python
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
python
def testingNB():
listOPosts, listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
p0V, p1V, pAb = trainNB0(trainMat, listClasses)
testEntry = ['love', 'my', 'dalmation']
thisDoc = setOfWords2Vec(myVocabList, testEntry)
print(testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb))
testEntry = ['stupid', 'garbage']
thisDoc = setOfWords2Vec(myVocabList, testEntry)
print(testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb))
testEntry = ['stupid']
thisDoc = setOfWords2Vec(myVocabList, testEntry)
print(testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb))
python
testingNB()output
['love', 'my', 'dalmation'] classified as: 0
['stupid', 'garbage'] classified as: 1
['stupid'] classified as: 1