数据挖掘算法笔记：knn算法

#前几篇的总结居然格式错误，找时间重新整理。

一调包

import numpy as np

from sklearn.neighbors import KNeighborsClassifier

knn=KNeighborsClassifier()

data = np.array([[3,104],[2,100],[1,81],[101,10],[99,5],[98,2]])   #打斗和接吻次数

labels = np.array([1,1,1,2,2,2])  #结果

knn.fit(data,labels)

knn.predict([18,90]) 

二.根据原理编写

import numpy as np
from numpy import *
import operator

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]  #shape[0]是行数，shape[1]是列数
    diffMat = tile(inX, (dataSetSize,1)) - dataSet #tile是把数组进行重复
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5 
    sortedDistIndicies = distances.argsort()  #索引从小到大排列
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1   #对出出现的label进行计数
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True) #对label出现次数进行排序
    return sortedClassCount[0][0]  #[0][0]是label出现频率最多的label

调用

classify0([2,0], group, labels, 3)

对for循环的解释：

import numpy as np
from numpy import *
import operator

data = np.array([[3,104],[2,100],[1,81],[101,10],[99,5],[98,2]])   #打斗和接吻次数

labels = np.array([1,1,1,2,2,2])  #结果

inX=[8,10]

dataSetSize = data.shape[0]
diffMat = tile(inX, (dataSetSize,1)) -data 
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5

distances 

array([ 94.1328848 ,  90.19977827,  71.34423593,  93.        ,
        91.13725912,  90.35485598])
sortedDistIndicies
 = distances.argsort()  


sortedDistIndicies #索引序列有小到大排序
array([2, 1, 5, 4, 3, 0], dtype=int32)
for i in range(6):

        voteIlabel = labels[sortedDistIndicies[i]]

        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1

sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)


classCount
{1: 3, 2: 3}
sortedClassCount


[(1, 3), (2, 3)]


cc={}
cc[1] = cc.get(1,0) + 1
cc
{1: 1}

cc[1] = cc.get(1,0) + 1
cc
{1: 2}
cc[1] = cc.get(1,0) + 1


cc
{1: 3}
#累加