需要一些关于python中朴素贝叶斯代码的建议 . 我一直用我的csv（NB.csv）命中“ZeroDivisionError：float division by zero”错误，但是另一个csv（data.csv）运行正常......我正在运行python 3.6（也试过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()
但是代码一直在提示这个错误“
Traceback（最近一次调用最后一次）：文件“C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第123行，在main（）文件“C：/Users/common/PycharmProjects/Lab/NB_raw.py “，第117行，主要预测= getPredictions（摘要，testSet）文件”C：/Users/common/PycharmProjects/Lab/NB_raw.py“，第92行，getPredictions结果=预测（摘要，testSet [i]）文件“C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第79行，预测概率= calculateClassProbabilities（summary，inputVector）文件“C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第74行，在calculateClassProbabilities概率[classValue] * = calculateProbability（x，mean，stdev）文件“C：/Users/common/PycharmProjects/Lab/NB_raw.py”，第60行，在calculateProbability指数= math.exp（ - （数学 . pow（x - mean，2）/（2 * math.pow（stdev，2））））ZeroDivisionError：float division by zero“