# 使用k-近邻算法改进约会网站的配对效果（kNN）

### 谷歌笔记本（可选）

from google.colab import drive
drive.mount("/content/drive")
Mounted at /content/drive

### 准备数据：从文本文件中解析数据

def file2matrix(filename):
fr = open(filename)
numberOfLines = len(arrayOfLines)
returnMat = zeros((numberOfLines, 3))
classLabelVector = []
index = 0
for line in arrayOfLines:
line = line.strip()
listFromLine = line.split('\t')
returnMat[index, :] = listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat, classLabelVector
datingDataMat, datingLabels = file2matrix('/content/drive/MyDrive/MachineLearning/机器学习/k-近邻算法/使用k-近邻算法改进约会网站的配对效果/datingTestSet2.txt')
datingDataMat
array([[4.0920000e+04, 8.3269760e+00, 9.5395200e-01], [1.4488000e+04, 7.1534690e+00, 1.6739040e+00], [2.6052000e+04, 1.4418710e+00, 8.0512400e-01], ..., [2.6575000e+04, 1.0650102e+01, 8.6662700e-01], [4.8111000e+04, 9.1345280e+00, 7.2804500e-01], [4.3757000e+04, 7.8826010e+00, 1.3324460e+00]])
datingLabels[:10]

[3, 2, 1, 1, 1, 1, 3, 3, 1, 3]

### 编写算法：编写kNN算法

from numpy import *
import operator

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]

### 分析数据：使用Matplotlib创建散点图

import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2])
plt.show()

import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2],
15.0*array(datingLabels), 15.0*array(datingLabels))
plt.show()

import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax.scatter(datingDataMat[:, 0], datingDataMat[:, 1],
15.0*array(datingLabels), 15.0*array(datingLabels))
plt.show()

### 准备数据：归一化数值

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
normMat, ranges, minVals = autoNorm(datingDataMat)
normMat
array([[0.44832535, 0.39805139, 0.56233353],
[0.15873259, 0.34195467, 0.98724416],
[0.28542943, 0.06892523, 0.47449629],
...,
[0.29115949, 0.50910294, 0.51079493],
[0.52711097, 0.43665451, 0.4290048 ],
[0.47940793, 0.3768091 , 0.78571804]])
ranges
array([9.1273000e+04, 2.0919349e+01, 1.6943610e+00])
minVals
array([0.      , 0.      , 0.001156])

### 测试算法：作为完整程序验证分类器

def datingClassTest():
hoRatio = 0.1
datingDataMat, datingLabels = file2matrix('/content/drive/MyDrive/MachineLearning/机器学习/k-近邻算法/使用k-近邻算法改进约会网站的配对效果/datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
errorCount = 0
for i in range(numTestVecs):
classifierResult = classify0(normMat[i,:], normMat[numTestVecs:m,:],
datingLabels[numTestVecs:m],3)
print("the classifierResult came back with: %d,\
the real answer is: %d" % (classifierResult, datingLabels[i]))
if (classifierResult != datingLabels[i]):
errorCount += 1
print("the total error rate is: %f" % (errorCount/float(numTestVecs)))
datingClassTest()
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 3,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 3
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 3,    the real answer is: 3
the classifierResult came back with: 2,    the real answer is: 2
the classifierResult came back with: 1,    the real answer is: 1
the classifierResult came back with: 3,    the real answer is: 1
the total error rate is: 0.050000


### 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 flier miles earned per year?"))
iceCream = float(input("liters of ice cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('/content/drive/MyDrive/MachineLearning/机器学习/k-近邻算法/使用k-近邻算法改进约会网站的配对效果/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])
classifyPerson()
percentage of time spent playing video games?10
frequent flier miles earned per year?10000
liters of ice cream consumed per year?0.5
You will probably like this person: in small doses

|
2天前
|

16 9
|
2天前
|

k-近邻算法（kNN）
k-近邻算法（kNN）
11 5
|
8天前
|

kNN算法
【6月更文挑战第6天】kNN算法。
8 1
|
13天前
|

【机器学习】K-近邻算法（KNN）全面解析
K-近邻算法（K-Nearest Neighbors, KNN）是一种基于实例的学习方法，属于监督学习范畴。它的工作原理简单直观：给定一个训练数据集，对新的输入实例，KNN算法通过计算其与训练集中每个实例的距离，找出距离最近的K个邻居，然后根据这些邻居的类别（对于分类任务）或值（对于回归任务）来预测新实例的类别或值。KNN因其简单高效和无需训练过程的特点，在众多领域中得到广泛应用，如模式识别、推荐系统、图像分类等。
173 0
|
1天前
|

16 0
|
1天前
|

YOLOv2算法应用于昆虫检测，提供实时高效的方法识别和定位图像中的昆虫，提升检测精度。核心是统一检测网络，预测边界框和类别概率。通过预测框尺寸估算昆虫大小，适用于农业监控、生态研究等领域。在matlab2022A上运行，经过关键升级，如采用更优网络结构和损失函数，保证速度与精度。持续优化可增强对不同昆虫的检测能力。![image.png](https://ucc.alicdn.com/pic/developer-ecology/3tnl7rfrqv6tw_e760ff6682a3420cb4e24d1e48b10a2e.png)
9 0
|
2天前
|

8 2
|
3天前
|

9 1
|
4天前
|

m基于PSO粒子群优化的LDPC码OMS译码算法最优偏移参数计算和误码率matlab仿真
MATLAB2022a仿真实现了Offset Min-Sum (OMS)译码算法与粒子群优化（PSO）结合，以优化偏移参数，提升LDPC码解码性能。PSO通过迭代寻找最小化误码率（BER）的最佳偏移量。核心程序运用PSO进行参数更新和适应度函数（BER）评估，最终在不同信噪比下展示OMS解码性能，并保存结果。
6 0
|
4天前
|

22 3