深度学习最邻近规则 python实现

版权声明:本文为博主原创文章,遵循 CC 4.0 by-sa 版权协议,转载请附上原文出处链接和本声明。
本文链接:https://blog.csdn.net/qq_16103331/article/details/51412420
    1.
# -*- coding: utf-8 -*- """ Created on Wed May 11 22:52:29 2016

    @author: sanmao """

    import random import math import operator

    def loadDataset(filename,split,trainingSet=[],testSet=[]):
        with open(filename,'rb') as csvfile:
            lines = csv.reader(csvfile)
            dataest = list(lines)
            for x in range(len(dataset)-1):
                for y in range(4):
                    dataset[x][y] = float(dataset[x][y])
                if random.random() < split:
                    trainingSet.append(dataset[x])
                else:
                    testSet.append(dataset[x])

    def euclideanDistance(instance1,instance2,length):
        distance = 0
        for x in range(length):
            distance += pow((instance1[x] - instance2[x]),2)
        return math.sqrt(distance)

    def getNeighbors(trainingSet,testInstance,k):
        distances = []
        length = len(testInstance)-1
        for x in range(len(trainingSet)):
            dist = euclideanDistance(testInstance,trainingSet[x],length)
            distances.append((trainingSet[x],dist))
        distances.sort(key=operator.itemgetter(1))
        neighbors = []
        for x in range(k):
            neighbors.append(distances[x][0])
        return neighbors

    def getResponse(neighbors):
        classVotes = {}
        for x in range(len(neighbors)):
            response = neighbors[x][-1]
            if response in classVotes:
                classVotes[response] += 1
            else:
                classVotes[response] = 1
        sortedVotes = sorted(classVotes.iteritems(),key=operator.itemgetter(1),reverse=True)
        return sortedVotes[0][0]
         def getAccuracy(testSet,predictions):
        corrrect = 0
        for x in range(len(testSet)):
            if testSet[x][-1] == predictions[x]:
                correct += 1
        return (corrrect/float(len(testSet))) * 100.0
         def main():
        trainingSet=[]
        testSet=[]
        split = 0.67
        loadDataset(r'D',split,trainingSet,testSet)
        print('Train set:'+repr(len(trainingSet)))
        print('Test set:'+repr(len(testSet)))
        predictions=[]
        k = 3
        for x in reange(len(testSet)):
            neighbors = getNeighbors(trainingSet,testSet[x],k)
            result = getResponse(neighbors)
            predictions.append(result)
            print('>predicted='+repr(result)+',actual='+repr(testSet[x][-1]))
            accuracy = getAccuracy(testSet,predictions)
            print('Accuracy:'+repr(accuracy)+'%')
             main()
展开阅读全文

没有更多推荐了,返回首页