[ML-IA] K-近邻算法-classify0

kNN.py

#!/usr/bin/python
# -*- coding:utf8 -*-

from numpy import *
import operator

#创造数据集
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

"""
#将inX扩展到和训练样本集dataSet一样的行数
diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    tile(inX, n):拓展长度
    tile(inX, (m, n):m-拓展个数,拓展长度
    
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
以排出的每组数据的第一个元素的大小为准，按降序排列。
e.g:[('A', 2), ('B', 1)]
"""
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]  #训练样本行数（矩阵第一维度的长度）
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5 #欧氏距离计算
    sortedDistIndicies = distances.argsort()#按元素大小升序,将无数对应的索引(index)输出
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]  #输出上面相应索引(index)对应的label
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  #统计label个数
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

kNN_test.py

import kNN

group, labels = kNN.createDataSet()
print (group)
print (labels)

inX = [2, 1]
testResult = kNN.classify0(inX, group, labels, 3)
print (testResult)

result:

[[ 1.   1.1]
 [ 1.   1. ]
 [ 0.   0. ]
 [ 0.   0.1]]
['A', 'A', 'B', 'B']
A