《机器学习实战》之K-近邻算法

k-近邻算法采用测量不同特征值之间的距离方法进行归类，它属于机器学习算法中的监督学习内容，用于线性回归！

优点：精度高、对异常值不敏感，无数据输入假定。

缺点：计算复杂度高、空间复杂度高

适用数据范围：数值型和标称型。

python实现代码加注释：

#encoding:utf8
from numpy import *
import operator

def createDataSet():
    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels = ['A','A','B','B']
    return group, labels

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]      #dataSet的行数,等于labels向量的元素数目
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    #print diffMat
    sqDiffMat = diffMat**2
    #print sqDiffMat
    sqDistances = sqDiffMat.sum(axis=1) #计算每行的和
    #print sqDistances
    distances = sqDistances**0.5        #计算欧式距离
    #print distances
    sortedDistIndicies = distances.argsort()#返回矩阵中每个元素的排序序号->来自原矩阵的序号:升序排列!!!
    #print sortedDistIndicies
    
    classCount = {}#建立一个空字典/哈希表/映射:键值为label;值为每个label出现的频率
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1#统计每个label出现的频率
        #D.get(k[,d]) -> D[k] if k in D, else d.  d defaults to None.
    sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse = True)
    #D.iteritems() -> an iterator over the (key, value) items of D
    #key = operator.itemgetter(1)->获取函数key第一个域的值
    
#reverse = True->逆序排序
    #将字典分解为列表,
    return sortedClassCount[0][0]

group, labels = createDataSet()
print classify0([0,0], group, labels, 3)

运行结果：

Python 2.7.6 (default, Nov 10 2013, 19:24:18) [MSC v.1500 32 bit (Intel)] on win32
Type "copyright", "credits" or "license()" for more information.
>>> ================================ RESTART ================================
>>> 
B
>>>