Python实现k-近邻算法

1、分类器实现

import numpy as np
import operator

def KNN(inx, dataset, labels, k):
    '''inx:待测元素;dataset:已知数据集(Numpy格式);labels:已知数据集元素对应的类别;
    k:与待测点距离最近的点的个数'''
    
    '''距离计算(欧几里德距离)'''
    datasetsize = dataset.shape(0) 
    diffmat = np.tile(inx, (datasetsize, 1)) - dataset
    sqdiffmat = diffmat**2
    sqdistances = sqdiffmat.sum(axis=1)
    distances = sqdistances**0.5
    
    '''选择距离最小的k个点'''
    sortlist = distances.argsort()
    classcount = {}
    for i in range(k):
        votelabel = labels[sortlist[i]]
        classcount[votelabel] = classcount.get(votelabel,0) + 1 #生成各个标签的直方图

    '''降序排序'''    
    sortclasscount = sorted(classcount.iteritems(),
                      key=operator.itemgetter(1), reverse=True)
    
    return sortclasscount[0][0]

2、文档处理，将tidy data（数据清洗部分本文不做说明）：

def file2matrix(filename):
    fr = open(filename)
    alines = fr.readlines()
    lines_num = len(alines)
    
    returnmat = np.zeros((lines_num, 3))
    labelsvector = []
    index = 0
    for line in alines:
        line_list = line.strip().split('\t')
        returnmat[index] = line_list[0:3]
        labelsvector.append(int(line_list[-1]))
        index += 1
    return returnmat, labelsvector

3、数据归一化，将不同取值范围的特征值转化为0到1的范围，也可以根据不同权重进行分配，以下为统一转化为0到1范围的代码：

def newvalue(dataset):
    minval = dataset.min(0)
    maxval = dataset.max(0)
    ranges = maxval - minval
    newdataset = np.zeros(np.shape(dataset))
    m = dataset.shape[0]
    newdataset = dataset - np.tile(minval, (m,1))
    newdataset = newdataset/np.tile(ranges, (m,1))
    
    return newdataset, ranges, minval
    
newdataset, ranges, minval = newvalue(returnmat)

4、分类器检测，kNN算法是机器学习中最简单的，对训练样本的预处理要求较高，错误率也通常较高，需要进行检测后才能使用分类器中的训练样本：

def datingClassTest():
    hoRatio = 0.10      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    newdataset, ranges, minval = newvalue(datingDataMat)
    m = newdataset.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = KNN(newdataset[i,:],newdataset[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
        print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i])
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print "the total error rate is: %f" % (errorCount/float(numTestVecs))
    print errorCount