Question

以下Python朴素贝叶斯代码需要一些建议。我的csv（NB.csv）不断出现“ ZeroDivisionError：浮点除以零”错误，但另一个csv（data.csv）则运行良好... 我正在运行python 3.6（也尝试过2.7）。

# Example of Naive Bayes implemented from Scratch in Python
import csv
import random
import math

def loadCsv(filename):
    lines = csv.reader(open(filename, "r"))
    dataset = list(lines)
    for i in range(len(dataset)):
        dataset[i] = [float(x) for x in dataset[i]]
    return dataset


def splitDataset(dataset, splitRatio):
    trainSize = int(len(dataset) * splitRatio)
    trainSet = []
    copy = list(dataset)
    while len(trainSet) < trainSize:
        index = random.randrange(len(copy))
        trainSet.append(copy.pop(index))
    return [trainSet, copy]


def separateByClass(dataset):
    separated = {}
    for i in range(len(dataset)):
        vector = dataset[i]
        if (vector[-1] not in separated):
            separated[vector[-1]] = []
        separated[vector[-1]].append(vector)
    return separated


def mean(numbers):
    return sum(numbers) / float(len(numbers))


def stdev(numbers):
    avg = mean(numbers)
    variance = sum([pow(x - avg, 2) for x in numbers]) / float(len(numbers) - 1)
    return math.sqrt(variance)


def summarize(dataset):
    summaries = [(mean(attribute), stdev(attribute)) for attribute in zip(*dataset)]
    del summaries[-1]
    return summaries


def summarizeByClass(dataset):
    separated = separateByClass(dataset)
    summaries = {}
    for classValue, instances in separated.items():
        summaries[classValue] = summarize(instances)
    return summaries


def calculateProbability(x, mean, stdev):
    exponent = math.exp(-(math.pow(x - mean, 2) / (2 * math.pow(stdev, 2))))
    print (stdev,"||",exponent)
    print (2 * math.pow(stdev, 2))
    return (1 / (math.sqrt(2 * math.pi) * stdev)) * exponent


def calculateClassProbabilities(summaries, inputVector):
    probabilities = {}
    for classValue, classSummaries in summaries.items():
        probabilities[classValue] = 1
        for i in range(len(classSummaries)):
            mean, stdev = classSummaries[i]
            x = inputVector[i]
            print ("x: ",x,"mean: ", mean,"stdev: ", stdev," || ","summaries: " ,summaries,"inputVector: ",inputVector,"i:",[i])
            probabilities[classValue] *= calculateProbability(x, mean, stdev)
    return probabilities


def predict(summaries, inputVector):
    probabilities = calculateClassProbabilities(summaries, inputVector)
    bestLabel, bestProb = None, -1
    for classValue, probability in probabilities.items():
        if bestLabel is None or probability > bestProb:
            bestProb = probability
            bestLabel = classValue
    return bestLabel


def getPredictions(summaries, testSet):
    predictions = []
    for i in range(len(testSet)):
        result = predict(summaries, testSet[i])
        predictions.append(result)
    return predictions


def getAccuracy(testSet, predictions):
    correct = 0
    for i in range(len(testSet)):
        if testSet[i][-1] == predictions[i]:
            correct += 1
    return (correct / float(len(testSet))) * 100.0

def main():
    filename = 'C:\\Users\\common\\Dropbox\\Project\\NB.csv'
    splitRatio = 0.67
    dataset = loadCsv(filename)
    print ("Load csv")
    trainingSet, testSet = splitDataset(dataset, splitRatio)
    print('Split ' + str(len(dataset)) + ' rows into train=' + str(len(trainingSet)) + ' and test= '+ str(len(testSet)) +' rows')
    # prepare model
    summaries = summarizeByClass(trainingSet)
    predictions = getPredictions(summaries, testSet)
    accuracy = getAccuracy(testSet, predictions)
    print('Accuracy: ' + str(accuracy))

main()

但是代码不断提示此错误”

回溯（最近通话最近）：文件 “ C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第123行，在 main（）main中的文件“ C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第117行预测= getPredictions（摘要，测试集）文件“ C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第92行，在 getPredictions 结果=预测（预测，testSet [i]）文件“ C：/Users/common/PycharmProjects/Lab/NB_raw.py”，预测中的第79行概率=计算类概率（摘要，inputVector）文件“ C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第74行，在calculateClassProbabilities中 probabilities [classValue] * = calculateProbability（x，平均值，stdev）文件“ C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第60行，在计算概率 exponent = math.exp（-（math.pow（x-mean，2）/（2 * math.pow（stdev，2））））ZeroDivisionError：浮点除以零“

Answer 1

您的代码中有一个def calculateProbability，应该是：

def calculateProbability(x, mean, stdev):
    try:
        exponent = math.exp(-(math.pow(x - mean, 2) / (2 * math.pow(stdev, 2))))
    except ZeroDivisionError:
        exponent = 0 #or whatever
    print (stdev,"||",exponent)
    print (2 * math.pow(stdev, 2))
    return (1 / (math.sqrt(2 * math.pi) * stdev)) * exponent

Answer 2

之所以这样做，是因为您试图在calculateProbability函数中将其除以0。

因此，您可以在try-catch语句中进行检查。尝试将calculateProbability函数编辑到下面，然后查看它是否运行：

def calculateProbability(x, mean, stdev):
    exponent = math.exp(-(math.pow(x - mean, 2) / (2 * math.pow(stdev, 2))))
    print (stdev,"||",exponent)
    print (2 * math.pow(stdev, 2))

    try:
        return (1 / (math.sqrt(2 * math.pi) * stdev)) * exponent

    except ZeroDivisionError:
        return 0

朴素贝叶斯Python 3：除以零错误

2 个答案: