樸素貝葉斯python代碼實現(xiàn)

樸素貝葉斯優(yōu)點：在數(shù)據(jù)較少的狀況下仍然有效，能夠解決多類別問題缺點：對于輸入數(shù)據(jù)的準(zhǔn)備方式較為敏感合用數(shù)據(jù)類型：標(biāo)稱型數(shù)據(jù)貝葉斯準(zhǔn)則：使用樸素貝葉斯進行文檔分類樸素貝葉斯的普通過程（1）收集數(shù)據(jù)：能夠使用任何辦法。本文使用RSS源（2）準(zhǔn)備數(shù)據(jù)：需要數(shù)值型或者布爾型數(shù)據(jù)（3）分析數(shù)據(jù)：有大量特性時，繪制特性作用不大，此時使用直方圖效果更加好（4）訓(xùn)練算法：計算不同的獨立特性的條件概率（5）測試算法：計算錯誤率（6）使用算法：一種常見的樸素貝葉斯應(yīng)用是文檔分類。能夠在任意的分類場景中使用樸素貝葉斯分類器，不一定非要是文本。準(zhǔn)備數(shù)據(jù)：從文本中構(gòu)建詞向量摘自機器學(xué)習(xí)實戰(zhàn)。[['my','dog','has','flea','problems','help','please'],0['maybe','not','take','him','to','dog','park','stupid'],1['my','dalmation','is','so','cute','I','love','him'],0['stop','posting','stupid','worthless','garbage'],1['mr','licks','ate','my','steak','how','to','stop','him'],0['quit','buying','worthless','dog','food','stupid']]1以上是六句話，標(biāo)記是0句子的表達正常句，標(biāo)記是1句子的表達為粗口。我們通過分析每個句子中的每個詞，在粗口句或是正常句出現(xiàn)的概率，能夠找出那些詞是粗口。在bayes.py文獻中添加以下代碼：[python]

\o"viewplain"viewplain\o"copy"copy#

coding=utf-8

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]

#

1代表侮辱性文字，0代表正常言論

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

運行成果：訓(xùn)練算法：從詞向量計算概率[python]

\o"viewplain"viewplain\o"copy"copy#

樸素貝葉斯分類器訓(xùn)練函數(shù)

#

trainMatrix:

文檔矩陣，

trainCategory:

由每篇文檔類別標(biāo)簽所構(gòu)成的向量

def

trainNB0(trainMatrix,

trainCategory):

numTrainDocs

=

len(trainMatrix)

numWords

=

len(trainMatrix[0])

pAbusive

=

sum(trainCategory)

/

float(numTrainDocs)

p0Num

=

zeros(numWords);

p1Num

=

zeros(numWords);

p0Denom

=

0.0;

p1Denom

=

0.0;

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

=

p1Num

/

p1Denom

p0Vect

=

p0Num

/

p1Denom

return

p0Vect,

p1Vect,

pAbusive

運行成果：測試算法：根據(jù)現(xiàn)狀修改分類器上一節(jié)中的trainNB0函數(shù)中修改幾處：p0Num

=

ones(numWords);p1Num

=

ones(numWords);p0Denom

=

2.0;p1Denom

=

2.0;p1Vect

=

log(p1Num

/

p1Denom)p0Vect

=

log(p0Num

/

p1Denom)[python]

\o"viewplain"viewplain\o"copy"copy#

樸素貝葉斯分類器訓(xùn)練函數(shù)

#

trainMatrix:

文檔矩陣，

trainCategory:

由每篇文檔類別標(biāo)簽所構(gòu)成的向量

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

/

p1Denom)

return

p0Vect,

p1Vect,

pAbusive

#

樸素貝葉斯分類函數(shù)

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

=

trainNB0(array(trainMat),

array(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)

運行成果：準(zhǔn)備數(shù)據(jù)：文檔詞袋模型詞集模型（set-of-words

model）：每個詞與否出現(xiàn)，每個詞只能出現(xiàn)一次詞袋模型（bag-of-words

model）：一種詞能夠出現(xiàn)不止一次[python]

\o"viewplain"viewplain\o"copy"copy#

樸素貝葉斯詞袋模型

def

bagOfWords2VecMN(vocabList,

inputSet):

returnVec

=

[0]

*

len(vocabList)

for

word

in

inputSet:

if

word

in

vocabList:

returnVec[vocabList.index(word)]

+=

1

return

returnVec

示例：使用樸素貝葉斯過濾垃圾郵件（1）收集數(shù)據(jù)：提供文本文獻（2）準(zhǔn)備數(shù)據(jù)：將文本文獻解析成詞條向量（3）分析數(shù)據(jù)：檢查詞條確保解析的對的性（4）訓(xùn)練算法：使用我們之前建立的trainNB0()函數(shù)（5）測試算法：使用classifyNB()，并且構(gòu)建一種新的測試函數(shù)來計算文檔集的錯誤率（6）使用算法：構(gòu)建一種完整的程序?qū)σ唤M文檔進行分類，將錯分的文檔輸出到屏幕上準(zhǔn)備數(shù)據(jù)：切分文本使用正則體現(xiàn)式切分句子測試算法：使用樸素貝葉斯進行交叉驗證[python]

\o"viewplain"viewplain\o"copy"copy#

該函數(shù)接受一種大寫字符的字串，將其解析為字符串列表

#

該函數(shù)去掉少于兩個字符的字符串，并將全部字符串轉(zhuǎn)換為小寫

def

textParse(bigString):

import

re

listOfTokens

=

re.split(r'\W*',

bigString)

return

[tok.lower()

for

tok

in

listOfTokens

if

len(tok)

>

2]

#

完整的垃圾郵件測試函數(shù)

def

spamTest():

docList

=

[]

classList

=

[]

fullText

=

[]

#

導(dǎo)入并解析文本文獻

for

i

in

range(1,

26):

wordList

=

textParse(open('email/spam/%d.txt'

%

i).read())

docList.append(wordList)

fullText.extend(wordList)

classList.append(1)

wordList

=

textParse(open('email/ham/%d.txt'

%

i).read())

docList.append(wordList)

fullText.extend(wordList)

classList.append(0)

vocabList

=

createVocabList(docList)

trainingSet

=

range(50)

testSet

=

[]

#

隨機構(gòu)建訓(xùn)練集

for

i

in

range(10):

randIndex

=

int(random.uniform(0,

len(trainingSet)))

testSet.append(trainingSet[randIndex])

del(trainingSet[randIndex