GIS

最新推荐文章于 2024-07-30 10:16:33 发布

weixin_33924770

最新推荐文章于 2024-07-30 10:16:33 发布

阅读量58

点赞数

def GIS():
    global C
    global FeaWeights
    for wid in WordDic.keys():
        FeaWeights[wid] = {}
        for classid in ClassList:
            FeaWeights[wid][classid] = 0.0
    n = 0
    prelogllh = -1000000.0
    logllh = -10000.0
    while logllh - prelogllh >= LogLLDiff and n < MaxIteration:
        n += 1
        prelogllh = logllh
        logllh = 0.0
        print "Iteration", n
        for wid in WordDic.keys():
            for classid in ClassList:
                FeaClassTable[wid][1][classid] = 0.0
        #compute expected values of features subject to the model p(y|x)
        for doc in DocList:
            classProbs = [0.0] * len(ClassList)
            sum = 0.0
            for i in range(len(ClassList)):
                classid = ClassList[i]
                pyx = 0.0
                for wid in doc[0].keys():
                    pyx += FeaWeights[wid][classid]
                pyx = math.exp(pyx)
                classProbs[i] = pyx
                sum += pyx
            for i in range(len(ClassList)):
                classProbs[i] = classProbs[i] / sum
            for i in range(len(ClassList)):
                classid = ClassList[i]
                if classid == doc[1]:
                    logllh += math.log(classProbs[i])
                for wid in doc[0].keys():
                    FeaClassTable[wid][1][classid] += classProbs[i] * doc[0][wid]
        #update feature weights
        for wid in WordDic.keys():
            for classid in ClassList:
                empValue = 0.0
                if classid in FeaClassTable[wid][0]:
                    empValue = FeaClassTable[wid][0][classid]
                modelValue = 0.0
                if classid in FeaClassTable[wid][1]:
                    modelValue = FeaClassTable[wid][1][classid]
                if empValue == 0.0 or modelValue == 0.0:
                    continue
                FeaWeights[wid][classid] += math.log(
                    FeaClassTable[wid][0][classid] / FeaClassTable[wid][1][classid]) / C
        print "Loglikelihood:", logllh
    return