机器学习实战 第2章 k-近邻算法

版权声明：转载请注明出处。 https://blog.csdn.net/u014427196/article/details/50372072

原理：
选取k个最近的样本，样本中比例最大的种类即是新数据的分类。

简单的分类器：

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

g,la = createDataSet()

def classify0(inx,dataSet,labels,k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inx,(dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis = 1)
    distances = sqDistances**0.5;
    sortedDis = distances.argsort()
    classCount = {}
    for i in range (k):
        votelabel = labels[sortedDis[i]]
        classCount[votelabel] = classCount.get(votelabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(),
                              key = operator.itemgetter(1),reverse = True)
    return sortedClassCount[0][0]

print classify0([0,0],g,la,3)