KNN分类（python）

最新推荐文章于 2023-07-17 08:38:45 发布

原创

最新推荐文章于 2023-07-17 08:38:45 发布 · 349 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#knn分类

version：python 3.6
环境：anaconda/JupyterLab 0.27.0
操作系统：Windows 10

knn分类笔记，会不断完善。

#k邻近值分类  KNN模型，选择2个邻居
from numpy import *
import operator

def get_dataset(train_x,train_y):
    group = train_x.values
    labels = train_y.values
    return (group,labels)

def knn_classify(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
    sortedDistIndicies = distances.argsort()    
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]        
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    # change itemgetter to item
    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),
                    reverse=True)
    return sortedClassCount[0][0]

def knn(trainset,train_label,test,k):
    y_p = []
    for i in range(test.shape[0]):