K-邻近均值算法

代码来自Peter Harrington《机器学习实战》
相关数据集见www.manning.com/MachineLearninginAction
kNN.py

from numpy import *
import operator

class k_algrithom:
    def __init__(self):
        self.inx = None
        self.dataset = None
        self.labels = None
        self.k = None

   # def createDataset(self):
    #     group = array([1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1])
    #     labaels = ['A', 'A', 'B', 'B']
    #     return group, labaels

    def classify0(self,inx, dataset, labels, k):
        # inx:输入向量，dataset:输入样本，labels:标签向量,k:选择最邻近的数目
        dataSetSize = dataset.shape[0]
        diffMat = tile(inx, (dataSetSize, 1)) - dataset
        sqDiffMat = diffMat ** 2
        sqDistance = sqDiffMat.sum(axis=1)
        distance = sqDistance ** 0.5
        sortedDistIndices = distance.argsort()
        classcount = {
   }
        for i in range(k):
            votelabel = labels[sortedDistIndices[i]]
            classcount[votelabel] = classcount.get(votelabel, 0) + 1
        sortedclasscount = sorted(classcount.items(), key=operator.itemgetter(1),
                                  reverse