朴素贝叶斯分类技术算法

Question

我在网上找到了Naive bayes分类代码，用于我正在进行的一项小型研究。我正在使用的代码显示一些错误，无法找到它们的解决方案。非常感谢你的帮助。

代码如下：

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


def loadCsv(filename):
    lines = csv.reader(open(filename, "rt"))
    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))))
    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]
            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 = 'E:\iris.data.csv'
    splitRatio = 0.67
    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)))
    # prepare model
    summaries = summarizeByClass(trainingSet)
    # test model
    predictions = getPredictions(summaries, testSet)
    accuracy = getAccuracy(testSet, predictions)
    print(('Accuracy: {0}%').format(accuracy))


main()

相同的追溯如下：

  File "<ipython-input-18-4397d9969e66>", line 1, in <module>
    runfile('C:/Users/Lenovo/Desktop/EE Codes/Knn with prima.py', wdir='C:/Users/Lenovo/Desktop/EE Codes')
  File "C:\Users\Lenovo\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile
    execfile(filename, namespace)
  File "C:\Users\Lenovo\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)
  File "C:/Users/Lenovo/Desktop/EE Codes/Knn with prima.py", line 76, in <module>
    main()
  File "C:/Users/Lenovo/Desktop/EE Codes/Knn with prima.py", line 69, in main
    neighbors = getNeighbors(trainingSet, testSet[x], k)
  File "C:/Users/Lenovo/Desktop/EE Codes/Knn with prima.py", line 31, in getNeighbors
    dist = euclideanDistance(testInstance, trainingSet[x], length)
  File "C:/Users/Lenovo/Desktop/EE Codes/Knn with prima.py", line 24, in euclideanDistance
    distance += pow((instance1[x] - instance2[x]), 2)
TypeError: unsupported operand type(s) for -: 'str' and 'str'

我会请求大家为如何解决相应代码的错误提供解决方案。如果您需要数据集，那么请询问。我也可以为你提供链接。

提前致谢