import csv
def loadCsv(filename):
lines = csv.reader(open(filename, "rb"))
dataset = list(lines)
for i in range(len(dataset)):
dataset[i] = [float(x) for x in dataset[i]]
return dataset
Nach dem Login kopieren
我们可以通过加载皮马印第安人数据集，然后打印出数据样本的个数，以此测试这个函数。
filename = 'pima-indians-diabetes.data.csv'
dataset = loadCsv(filename)
print('Loaded data file {0} with {1} rows').format(filename, len(dataset))
dataset = [[1], [2], [3], [4], [5]]
splitRatio = 0.67
train, test = splitDataset(dataset, splitRatio)
print('Split {0} rows into train with {1} and test with {2}').format(len(dataset), train, test)
Nach dem Login kopieren
运行测试，你会看到如下结果：
Split 5 rows into train with [[4], [3], [5]] and test with [[1], [2]]
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)
Nach dem Login kopieren
通过计算从1到5这5个数的均值来测试函数。
numbers = [1,2,3,4,5]
print('Summary of {0}: mean={1}, stdev={2}').format(numbers, mean(numbers), stdev(numbers))
Nach dem Login kopieren
运行测试，你会看到如下结果：
Summary of [1, 2, 3, 4, 5]: mean=3.0, stdev=1.58113883008
x = 71.5
mean = 73
stdev = 6.2
probability = calculateProbability(x, mean, stdev)
print('Probability of belonging to this class: {0}').format(probability)
Nach dem Login kopieren
运行测试，你会看到如下结果：
Probability of belonging to this class: 0.0624896575937
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
Nach dem Login kopieren
测试calculateClassProbabilities()函数。
summaries = {0:[(1, 0.5)], 1:[(20, 5.0)]}
inputVector = [1.1, '?']
probabilities = calculateClassProbabilities(summaries, inputVector)
print('Probabilities for each class: {0}').format(probabilities)
Nach dem Login kopieren
运行测试，你会看到如下结果：
Probabilities for each class: {0: 0.7820853879509118, 1: 6.298736258150442e-05}
Nach dem Login kopieren
单一预测
既然可以计算一个数据样本属于每个类的概率，那么我们可以找到最大的概率值，并返回关联的类。
下面的predict()函数可以完成以上任务。
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
Der Inhalt dieses Artikels wird freiwillig von Internetnutzern beigesteuert und das Urheberrecht liegt beim ursprünglichen Autor. Diese Website übernimmt keine entsprechende rechtliche Verantwortung. Wenn Sie Inhalte finden, bei denen der Verdacht eines Plagiats oder einer Rechtsverletzung besteht, wenden Sie sich bitte an admin@php.cn
朴素贝叶斯分类器，Matt Buck保留部分版权
