1 准备数据：从文本文件中解析数据
datingTestSet.txt:
每列分别代表每年获得的飞行常客里程数、玩游戏视频所耗时间百分比、每周消费的冰淇淋公升数、不喜欢/魅力一般/极具魅力（即标签）
datingTestSet2.txt:
使用file2matrix函数处理输入格式问题，使分类器可以接受：
输入为文件名字符串，输出为训练样本矩阵和类标签向量。代码如下：
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
命令行中运行：
2 分析数据：使用matplotlib创建散点图
涉及的一些函数：
add_subplot(abc):将画布分割成a行b列，图象画在从左到右从上到下的第c块
scatter(x,y) 在向量 x 和 y 指定的位置创建一个包含圆形的散点图。该类型的图形也称为气泡图
绘制出散点图如图：
该散点图使用datingDataMat矩阵的第二列、第三列数据，分别表示特征值”玩视频所耗时间百分比”和”每周所消费冰淇淋公升书”
此时没有使用样本分类的特征值，不能获得有效信息。
一般会采用色彩或其他记号来标记不同样本分类，以更好理解数据信息
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2], 15.0 * array(datingLabels), 15.0 * array(datingLabels))
注：*15用于放大散点的尺寸，便于观察
; 3 准备数据：归一化数值
常用方法：将取值范围处理为0到1或-1到1之间
如转化为0-1区间内的值可用公式：
newValue=(oldValue-min)/(max-min)
min、max分别为数据集中的最小特征值和最大特征值。
下面使用autoNorm()函数自动将数字特征值转化为0到1的区间
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
在命令行中执行：
normMat,ranges,minVals=kNN.autoNorm(datingDataMat)
注：返回ranges,minVals是为了后序测试数据
4 测试算法：作为完整程序验证分类器
此处使用错误率来检测分类器的性能：分类器给出错误结果的次数除以测试数据的总数
def datingClassTest():
hoRatio = 0.20
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)))
kNN.datingClassTest()
5 使用算法：构建完整可用系统
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(input("percentage of time spent playing video games?"))
ffMiles = float(input("frequent filter miles earned per year?"))
iceCream = float(input("liters of ice cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = array([ffMiles, percentTats, iceCream])
classifierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3)
print("You will probably like this person:", resultList[classifierResult - 1])
kNN.classifyPerson()
附：完整代码
kNN.py
from numpy import *
import numpy as np
import operator
import matplotlib
import matplotlib.pyplot as plt
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)
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 = 0.20
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)))
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(input("percentage of time spent playing video games?"))
ffMiles = float(input("frequent filter miles earned per year?"))
iceCream = float(input("liters of ice cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = array([ffMiles, percentTats, iceCream])
classifierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3)
print("You will probably like this person:", resultList[classifierResult - 1])
main.py
import kNN
if __name__ == '__main__':
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
kNN.classifyPerson()
Original: https://blog.csdn.net/weixin_43340821/article/details/122043911
Author: 不要秃头、
Title: 机器学习实战|使用K-临近算法改进约会网站的配对效果
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/768260/
转载文章受原作者版权保护。转载请注明原作者出处！