How To Implement Naive Bayes From Scratch in Python

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

1. # Example of Naive Bayes implemented from Scratch in Python
   
2. import csv
   
3. import random
   
4. import math
   
5. 
   
6. def loadCsv(filename):
   
7.         lines = csv.reader(open(filename, "rb"))
   
8.         dataset = list(lines)
   
9.         for i in range(len(dataset)):
   
10.                 dataset[i] = [float(x) for x in dataset[i]]
    
11.         return dataset
    
12. 
    
13. def splitDataset(dataset, splitRatio):
    
14.         trainSize = int(len(dataset) * splitRatio)
    
15.         trainSet = []
    
16.         copy = list(dataset)
    
17.         while len(trainSet) < trainSize:
    
18.                 index = random.randrange(len(copy))
    
19.                 trainSet.append(copy.pop(index))
    
20.         return [trainSet, copy]
    
21. 
    
22. def separateByClass(dataset):
    
23.         separated = {}
    
24.         for i in range(len(dataset)):
    
25.                 vector = dataset[i]
    
26.                 if (vector[-1] not in separated):
    
27.                         separated[vector[-1]] = []
    
28.                 separated[vector[-1]].append(vector)
    
29.         return separated
    
30. 
    
31. def mean(numbers):
    
32.         return sum(numbers)/float(len(numbers))
    
33. 
    
34. def stdev(numbers):
    
35.         avg = mean(numbers)
    
36.         variance = sum([pow(x-avg,2) for x in numbers])/float(len(numbers)-1)
    
37.         return math.sqrt(variance)
    
38. 
    
39. def summarize(dataset):
    
40.         summaries = [(mean(attribute), stdev(attribute)) for attribute in zip(*dataset)]
    
41.         del summaries[-1]
    
42.         return summaries
    
43. 
    
44. def summarizeByClass(dataset):
    
45.         separated = separateByClass(dataset)
    
46.         summaries = {}
    
47.         for classValue, instances in separated.iteritems():
    
48.                 summaries[classValue] = summarize(instances)
    
49.         return summaries
    
50. 
    
51. def calculateProbability(x, mean, stdev):
    
52.         exponent = math.exp(-(math.pow(x-mean,2)/(2*math.pow(stdev,2))))
    
53.         return (1 / (math.sqrt(2*math.pi) * stdev)) * exponent
    
54. 
    
55. def calculateClassProbabilities(summaries, inputVector):
    
56.         probabilities = {}
    
57.         for classValue, classSummaries in summaries.iteritems():
    
58.                 probabilities[classValue] = 1
    
59.                 for i in range(len(classSummaries)):
    
60.                         mean, stdev = classSummaries[i]
    
61.                         x = inputVector[i]
    
62.                         probabilities[classValue] *= calculateProbability(x, mean, stdev)
    
63.         return probabilities
    
64.                        
    
65. def predict(summaries, inputVector):
    
66.         probabilities = calculateClassProbabilities(summaries, inputVector)
    
67.         bestLabel, bestProb = None, -1
    
68.         for classValue, probability in probabilities.iteritems():
    
69.                 if bestLabel is None or probability > bestProb:
    
70.                         bestProb = probability
    
71.                         bestLabel = classValue
    
72.         return bestLabel
    
73. 
    
74. def getPredictions(summaries, testSet):
    
75.         predictions = []
    
76.         for i in range(len(testSet)):
    
77.                 result = predict(summaries, testSet[i])
    
78.                 predictions.append(result)
    
79.         return predictions
    
80. 
    
81. def getAccuracy(testSet, predictions):
    
82.         correct = 0
    
83.         for i in range(len(testSet)):
    
84.                 if testSet[i][-1] == predictions[i]:
    
85.                         correct += 1
    
86.         return (correct/float(len(testSet))) * 100.0
    
87. 
    
88. def main():
    
89.         filename = 'pima-indians-diabetes.data.csv'
    
90.         splitRatio = 0.67
    
91.         dataset = loadCsv(filename)
    
92.         trainingSet, testSet = splitDataset(dataset, splitRatio)
    
93.         print('Split {0} rows into train={1} and test={2} rows').format(len(dataset), len(trainingSet), len(testSet))
    
94.         # prepare model
    
95.         summaries = summarizeByClass(trainingSet)
    
96.         # test model
    
97.         predictions = getPredictions(summaries, testSet)
    
98.         accuracy = getAccuracy(testSet, predictions)
    
99.         print('Accuracy: {0}%').format(accuracy)
    
100. 
     
101. main()

复制代码

http://machinelearningmastery.com/naive-bayes-classifier-scratch-python/

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：implement scratch python Bayes naive 文山

1. >>> from sklearn import datasets
   
2. >>> iris = datasets.load_iris()
   
3. >>> from sklearn.naive_bayes import GaussianNB
   
4. >>> gnb = GaussianNB()
   
5. >>> y_pred = gnb.fit(iris.data, iris.target).predict(iris.data)
   
6. >>> print("Number of mislabeled points out of a total %d points : %d"
   
7. ...       % (iris.data.shape[0],(iris.target != y_pred).sum()))

复制代码

http://scikit-learn.org/stable/modules/naive_bayes.html