《機器學習實戰》之樸素貝葉斯

基于機率論的分類方法：樸素貝葉斯

優點：在資料較少的情況下仍然有效，可以處理多類别問題。

缺點：對于輸入資料的準備方式較為敏感。

适用資料類型：标稱型資料。

适用條件機率進行分類。

# -*- coding: utf-8 -*-
from numpy import *

# --Step1--
# 1> loadDataSet(): 加載實驗樣本
def loadDataSet():
    postingList = [['my','dog','has','flea','problems','help','please'],     # 7
                   ['maybe','not','take','him','to','dog','park','stupid'],  # 8
                   ['my','dalmation','is','so','cute','I','love','him'],     # 8
                   ['stop','posting','stupid','worthless','garbage'],        # 5
                   ['mr','licks','ate','my','steak','how','to','stop','him'],# 9
                   ['quit','buying','worthless','dog','food','stupid']]      # 6
    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
    
# 2> createVocabList(dataSet): 建立詞彙表(每個單詞唯一),包含所有文檔中出現的不重複清單   
def createVocabList(dataSet):
    vocabSet = set([])                      #建立一個空集
    for document in dataSet:
        vocabSet = vocabSet | set(document) #建立兩個集合的并集
    return list(vocabSet)

# 3> setOfWords2Vec(vocabList, inputSet): 輸出文檔向量,向量的每個元素為1或0, 1出現, 0未出現
# 詞集模型(set-of-words model), 每個詞隻能出現一次!
def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0] * len(vocabList)       #建立一個所有元素值為0的向量
    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
 
 # 4> bagOfWords2Vec(vocabList, inputSet): 輸出文檔向量
 # 詞袋模型(bag-of-words model),每個詞可以出現不止一次
def bagOfWords2Vec(vocabList, inputSet):
    returnVec = [0] * len(vocabList)       #建立一個所有元素值為0的向量
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1 # 唯一不同與setOfWords2Vec代碼
        else:
            print "the word: %s is not in my Vocabulary!" % word
    return returnVec
    
          
# --Step2--
# trainMatrix : 文檔矩陣,由文檔向量構成!!!
# trainCategory : 由每篇文檔類别标簽所構成的向量(0: 正常言論  1: 侮辱言論)
#
def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)                  # trainMatrix矩陣行數 numTrainDocs
    numWords = len(trainMatrix[0])                   # trainMatrix矩陣列數 numWords
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = ones(numWords);                         # numWords長的機關向量, 防止出現條件機率為0時，所求機率值為0
    p1Num = ones(numWords); 
    p0Denom = 2.0;                                  # 分母初始化2.0
    p1Denom = 2.0;
    for i in range(numTrainDocs):# 
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]                  # 向量相加
            p1Denom += sum(trainMatrix[i])           # p1Denom總和
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect = log(p1Num/p1Denom) #change to log() 防止很多小數相乘導緻下溢出
    p0Vect = log(p0Num/p0Denom) #change to log()
    return p0Vect,p1Vect,pAbusive

# --Step3--

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1) # 元素相乘
    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)