python之k近邻的约会网站配对

1.准备数据：

# downloadDatas.py
import numpy as np
def loadDatas(txtName):
    f = open(txtName)
    datasLines = f.readlines()
    sizeDatas = len(datasLines)
    sizeLine = datasLines[0].split()
    sizeColumnNumber = len(sizeLine)
    dataZeros = np.zeros((sizeDatas,sizeColumnNumber - 1))
    labels = []
    index = 0
    for line in datasLines[0 : ]:
        line = line.split()
        dataZeros[index ,:] = line[0 : sizeColumnNumber - 1]
        labels.append(int(line[-1]))
        index += 1
    datas = dataZeros
    labels = np.array(labels)
    return datas,labels

2.绘制散点图：

# scatter.py
import numpy as np
import matplotlib.pyplot as plt
from downloadDatas import loadDatas
txtName = 'datingTestSet2.txt'
datas,labels = loadDatas(txtName)
datas1 = []
datas2 = []
datas3 = []
n = len(labels)
for i in range(n):
    if labels[i] == 1:
        datas1.append(datas[i])
    elif labels[i] == 2:
        datas2.append(datas[i])
    elif labels[i] == 3:
        datas3.append(datas[i])

datas1 = np.array(datas1)
datas2 = np.array(datas2)
datas3 = np.array(datas3)
plt.figure(1,figsize=(8,8))
plt.subplot(111)
plt.scatter(datas1[:,1],datas1[:,2],marker='o',color='r',s=40,label='不喜欢')
plt.scatter(datas2[:,1],datas2[:,2],marker='+',color='b',s=40,label='魅力一般')
plt.scatter(datas3[:,1],datas3[:,2],marker='^',color='black',s=40,label='极具魅力')
plt.legend((u'不喜欢',u'魅力一般',u'极具魅力'),loc='best',prop={'family':'SimHei','size':14})
plt.xlabel(u'玩视频游戏所耗时间百分比',fontproperties='SimHei',fontsize=14)
plt.ylabel(u'每周消费的冰淇淋公升数',fontproperties='SimHei',fontsize=14)
plt.show()

3.数据归一化处理：

# minmaxNorm.py
import numpy as np
def minmaxNorm(datas):
    minDatas = datas.min(0)
    maxDatas = datas.max(0)
    max_min = maxDatas - minDatas
    m = datas.shape[0]
    datasMin = datas - np.tile(minDatas,(m,1))
    datasNorm = datasMin / np.tile(max_min,(m,1))
    return datasNorm,minDatas,max_min

# a = [[1,2,3],
#      [4,5,6],
#      [9,8,7],
#      [2,2,2]]
# a = np.array(a)
# b,c,d = minmaxNorm(a)
# print(b)

4.k-近邻算法：

# knn.py
import numpy as np
import operator
def knn(test,trains,labels,k):
    trainsSizeHang = trains.shape[0]
    values = np.tile(test,(trainsSizeHang,1)) - trains
    sqValues = values ** 2
    sqDistances = sqValues.sum(axis = 1)
    distances = sqDistances ** 0.5
    sortedDists = np.argsort(distances)
    classCount = {}
    for i in range(k):
        voteLabel = labels[sortedDists[i]]
        classCount[voteLabel] = classCount.get(voteLabel,0) + 1
    classCount = classCount.items()
    sortClassCount = sorted(classCount,key=operator.itemgetter(1),reverse=True)
    return sortClassCount[0][0]

# trains = [[3 ,104],
#           [2 ,100],
#           [1 ,81],
#           [101 ,10],
#           [99 ,5],
#           [98 ,2]]
# # ‘1’表示爱情片，‘2’表示动作片
# labels = [1 , 1 , 1 , 2 , 2 ,2]
# test = [18 ,90]
# k = 3
#
# trains = np.array(trains)
# labels = np.array(labels)
# test = np.array(test)
# print('测试样本的类别：' + str(knn(test , trains , labels , k)))

5.测试算法：

# checkKnn.py
import numpy as np
from downloadDatas import loadDatas
from minmaxNorm import minmaxNorm
from knn import knn
txtName = 'datingTestSet2.txt'
datas,labels = loadDatas(txtName)
datasNorm,minDatas,max_min = minmaxNorm(datas)
testRate = 0.1
m = datasNorm.shape[0]
testNum = int(m*testRate)
errorNum = 0
for i in range(testNum):
    knnResult = knn(datasNorm[i,:],datasNorm[testNum:m,:],labels[testNum:m],3)
    print('识别结果：' + str(knnResult) + ',正确结果：' + str(labels[i]))
    if knnResult != labels[i]:
        errorNum += 1
error = errorNum/testNum
print('测试结果的错误率：' + '%.2f%%' % (error*100))

6.使用算法：

# uesKnn.py
import numpy as np
from downloadDatas import loadDatas
from minmaxNorm import minmaxNorm
from knn import knn
txtName = 'datingTestSet2.txt'
datas,labels = loadDatas(txtName)
datasNorm,minDatas,max_min = minmaxNorm(datas)
feature1 = float(input('每年获得的飞行常客里程数：'))
feature2 = float(input('玩视频游戏所耗时间百分比：'))
feature3 = float(input('每周消费的冰淇淋公升数：'))
newData = np.array([feature1,feature2,feature3])
newDataNorm = (newData-minDatas) / max_min
newDataResult = knn(newDataNorm,datasNorm,labels,3)
resultList = ['不喜欢','魅力一般','极具魅力']
print('对方类型的判断结果为：' + str(resultList[newDataResult-1]))

# 输入数据：10000、10、0.5，结果：魅力一般