[机器学习] 1-Knn近邻算法

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/simonyucsdy/article/details/82320639

Python实现：

新建Knn.py文件用于实现近邻算法

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# time:2018/9/2

from numpy import *
# import operator


# 给出训练数据以及对应的类别
def createDataSet():
    group = array([[1.0, 2.0], [1.2, 0.1], [0.1, 1.4], [0.3, 3.5]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels


# 通过KNN进行分类
def classify(input, dataSet, label, k):
    dataSize = dataSet.shape[0]

    # 计算欧式距离
    diff = tile(input, (dataSize, 1)) - dataSet
    sqdiff = diff ** 2
    squareDist = sum(sqdiff, axis=1)  # 行向量分别相加，从而得到新的一个行向量
    dist = squareDist ** 0.5

    # 对距离进行排序
    sortedDistIndex = argsort(dist)  # argsort()根据元素的值从大到小对元素进行排序，返回下标

    classCount = {}
    for i in range(k):
        voteLabel = label[sortedDistIndex[i]]
        # 对选取的K个样本所属的类别个数进行统计
        classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
    # 选取出现的类别次数最多的类别
    maxCount = 0
    for key, value in classCount.items():
        if value > maxCount:
            maxCount = value
            classes = key
    return classes

新建test.py测试文件

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# author:ingy time:2018/9/2

import sys
sys.path.append("...文件路径...")
import Knn
from numpy import *

dataSet, labels = Knn.createDataSet()
input = array([1.1, 0.3])
K = 3
output = Knn.classify(input, dataSet, labels, K)
print("测试数据为:", input, "分类结果为：", output)

 OpenCV实现：