朴素贝叶斯代码讲解

import numpy as np
from numpy import array
import math
def loadDataSet(): #导入数据
    postingList=[['青绿', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', ],
                 ['乌黑', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑', ],
                 ['乌黑', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', ],
                 ['青绿', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑', ],
                 ['浅白', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', ],
                 ['青绿', '稍蜷', '浊响', '清晰', '稍凹', '软粘', ],
                 ['乌黑', '稍蜷', '浊响', '稍糊', '稍凹', '软粘', ],
                 ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '硬滑', ],
                 ['乌黑', '稍蜷', '沉闷', '稍糊', '稍凹', '硬滑', ],
                 ['青绿', '硬挺', '清脆', '清晰', '平坦', '软粘', ],
                 ['浅白', '硬挺', '清脆', '模糊', '平坦', '硬滑', ],
                 ['浅白', '蜷缩', '浊响', '模糊', '平坦', '软粘', ],
                 ['青绿', '稍蜷', '浊响', '稍糊', '凹陷', '硬滑', ],
                 ['浅白', '稍蜷', '沉闷', '稍糊', '凹陷', '硬滑', ],
                 ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '软粘', ],
                 ['浅白', '蜷缩', '浊响', '模糊', '平坦', '硬滑', ],
                 ['青绿', '蜷缩', '沉闷', '稍糊', '稍凹', '硬滑', ], ]
    classVec = [1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0]
    return postingList,classVec

def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    print(vocabSet)
    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.zeros(numWords)
    p1Num = np.zeros(numWords)
    p0Denom = 0.0; p1Denom = 0.0
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]
            p1Denom+=1
        else:
            p0Num += trainMatrix[i]
            p0Denom+=1
    print(p1Num)
    print(p1Denom)
    p1Vect = p1Num/p1Denom
    p0Vect = p0Num/p0Denom
    return p0Vect,p1Vect,pAbusive

def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
    p1 = sum(vec2Classify * p1Vec) + math.log2(pClass1)
    p0 = sum(vec2Classify * p0Vec) + math.log2(1-pClass1)
    if(p1>p0):
        return '好瓜'
    if(p0>p1):
        return '坏瓜'

listOPosts,listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
    trainMat.append(setOfWords2Vec(myVocabList,postinDoc))
print(trainMat)
p0V,p1V,pAb = trainNB0(trainMat,listClasses)
print (p0V,p1V,pAb)
testEntry = ['青绿', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑']
thisDoc = array(setOfWords2Vec(myVocabList,testEntry))
print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))