Python分类技术天真的贝叶斯

Question

我正在研究分类技术。我在python中找到了Naive Bayes Classification的在线代码。我已经分享了下面的代码。但是我收到了错误。请帮助解决错误。我使用的软件是带有Python 3.6的Anaconda。 代码如下：

import csv

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


import random
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


import math
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.iteritems():
        summaries[classValue] = summarize(instances)
    return summaries


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


def calculateClassProbabilities(summaries, inputVector):
    probabilities = {}
    for classValue, classSummaries in summaries.iteritems():
        probabilities[classValue] = 1
        for i in range(len(classSummaries)):
            mean, stdev = classSummaries[i]
            x = inputVector[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.iteritems():
        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 x in range(len(testSet)):
        if testSet[x][-1] == predictions[x]:
            correct += 1
    return (correct/float(len(testSet))) * 100.0


def main():
    splitRatio = 0.67
    filename = 'E:\iris.data.csv'
    dataset = loadCsv(filename)
    trainingSet, testSet = splitDataset(dataset, splitRatio)
    print('Split {0} rows into train = {1} and test = {2} rows'). format(len(dataset), len(trainingSet), len(testSet))
    summaries = summarizeByClass(trainingSet)
    predictions = getPredictions(summaries, testSet)
    accuracy = getAccuracy(testSet, predictions)
    print('Accuracy: {0}%').format(accuracy)

main()

我将这作为我的追溯：

  

runfile（＆＃39; C：/ Users / Lenovo / Desktop / Naive .py＆＃39;，wdir =＆＃39; C：/ Users / Lenovo / Desktop＆＃39;）
  追溯（最近的呼叫最后）：
    文件＆＃34;＆lt; ipython-input-11-c6b2508abccc＆gt;＆＃34;，第1行，＆lt; module＆gt;       runfile（＆＃39; C：/ Users / Lenovo / Desktop / Naive .py＆＃39;，wdir =＆＃39; C：/ Users / Lenovo / Desktop＆＃39;）
    文件＆＃34; C：\ Users \ Lenovo \ Anaconda3 \ lib \ site-packages \ spyder \ utils \ site \ sitecustomize.py＆＃34;，第710行，在runfile中       execfile（filename，namespace）
    文件＆＃34; C：\ Users \ Lenovo \ Anaconda3 \ lib \ site-packages \ spyder \ utils \ site \ sitecustomize.py＆＃34;，第101行，在execfile中       exec（compile（f.read（），filename，＆＃39; exec＆＃39;），命名空间）
    文件＆＃34; C：/ Users / Lenovo / Desktop / Naive .py＆＃34;，第109行，＆lt; module＆gt;       主（）
    文件＆＃34; C：/ Users / Lenovo / Desktop / Naive .py＆＃34;，第101行，主要       dataset = loadCsv（filename）
    文件＆＃34; C：/ Users / Lenovo / Desktop / Naive .py＆＃34;，第7行，在loadCsv中       dataset [i] = [float（x）for x in dataset [i]]
    文件＆＃34; C：/ Users / Lenovo / Desktop / Naive .py＆＃34;，第7行，＆lt; listcomp＆gt;       dataset [i] = [float（x）for x in dataset [i]]
    ValueError：无法将字符串转换为float：＆＃39; Iris-setosa＆＃39;

请帮我解决问题。提前谢谢