机器学习实战 4knn（书）终章

最新推荐文章于 2023-02-16 09:43:12 发布

viold

最新推荐文章于 2023-02-16 09:43:12 发布

阅读量393

点赞数

本文链接：https://blog.csdn.net/viold/article/details/88776002

版权

本文档记录了shi2.py文件中的问题及其解决方案。主要问题在于上一行的print语句括号未闭合，通过添加缺失的右括号解决了该问题。

摘要由CSDN通过智能技术生成

1.记录

from numpy import *
import operator


def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDisttances = sqDiffMat.sum(axis=1)
    distances = sqDisttances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.items(),
                              key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]
        
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals,(m,1))
    normDataSet = normDataSet/tile(ranges,(m,1))
    return normDataSet,ranges,minVals

def datingClassTest():
     hoRatio = 0.10 
     dati