K最近邻结点算法(k-Nearest Neighbor algorithm)KNN——python简单实现

最新推荐文章于 2022-08-27 09:32:26 发布

dangzhileiqaz

最新推荐文章于 2022-08-27 09:32:26 发布

阅读量1.3k

点赞数

分类专栏：机器学习 python

本文链接：https://blog.csdn.net/dangzhileiqaz/article/details/15338461

版权

机器学习同时被 2 个专栏收录

7 篇文章 0 订阅

订阅专栏

python

6 篇文章 0 订阅

订阅专栏

代码实现：

# -*- coding: utf-8 -*-

import numpy
#from numpy  import *
import operator

#函数功能：将数据文件转换为矩阵形式
def FileToMartix(filename):
    f = open(filename)
    arrayLines = f.readlines()
    numberOfLines = len(arrayLines)
    returnMat = numpy.zeros((numberOfLines , 3))

    classLabeVector = []
    index = 0

    for line in arrayLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:-1]
        classLabeVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat , classLabeVector



#数据归一化处理
#newvalue = (oldvalue - min)/(max - min)
def normlized(dataset):
    #n维数组的最大值，最小值
    minval = dataset.min(0)
    maxval = dataset.max(0)
    ranges = maxval - minval

    norDataSet = numpy.zeros(numpy.shape(dataset))
    m = dataset.shape[0]

    norDataSet = dataset - numpy.tile(minval , (m , 1))
    norDataSet = norDataSet / numpy.tile(ranges , (m , 1))

    return norDataSet , ranges , minval


#KNN分类器
#输入参数：目标测试样本vect ，训练集：dataset ， 样本标签：lables , 近邻数：k 
def classified(vect , dataSet , lables , k):
    dataSize = dataSet.shape[0]
    diffMat = numpy.tile(vect , (dataSize , 1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistance = sqDiffMat.sum(axis = 1)
    distances = sqDistance**0.5
    sortedIndicies = distances.argsort()
    classCount = {}

    for i in range(k):
        voteLable = lables[sortedIndicies[i]]
        classCount[voteLable] = classCount.get(voteLable , 0) + 1
    sortedClassCount = sorted(classCount.iteritems() ,
                              key = operator.itemgetter(1) , reverse = True)

    return sortedClassCount[0][0]