Machine Learning in Action

最新推荐文章于 2024-10-11 21:24:38 发布

哈伊亚湖

最新推荐文章于 2024-10-11 21:24:38 发布

阅读量171

点赞数

分类专栏： Machine Learning 文章标签：机器学习 python

本文链接：https://blog.csdn.net/sinat_31182281/article/details/78487224

版权

Machine Learning 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

Classification

Chapter 2 KNN Python code

实现环境：

Python3.5
Numpy
Operator

代码块

实现的python代码：
KNN.py

from numpy import *
import operator

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



def classify0(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
    sortedClassCount = sorted(classCount.items(),key = operator.itemgetter(1), reverse= True)

    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())
    returnMat = zeros((numberOfLines, 3))
    classLabelVector = []
    index = 0
    fr.seek(0)
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    fr.close()
    return returnMat, classLabelVector


def autoNorm(dataSet):
    minVals = dataSet.min(0)
    print(minVals)
    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

# test classifier
def datingClassTest():
    hoRatio =0.10
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0

    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:], normMat[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)))