吴裕雄--天生自然python机器学习：使用K-近邻算法改进约会网站的配对效果

在约会网站使用K-近邻算法

import operator
from numpy import *
from os import listdir

def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    fr = open(filename)
    index = 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
    return returnMat,classLabelVector

returnMat,classLabelVector = file2matrix('F:\\machinelearninginaction\\Ch02\\datingTestSet2.txt')
print(returnMat)
print(classLabelVector)

import matplotlib
import matplotlib.pyplot as plt

from numpy import *

fig = plt.figure()
ax = fig.add_subplot(111)
datingDataMat,datingLabels = file2matrix('F:\\machinelearninginaction\\Ch02\\datingTestSet2.txt')
#ax.scatter(datingDataMat[:,1], datingDataMat[:,2])
ax.scatter(datingDataMat[:,1], datingDataMat[:,2], 15.0*array(datingLabels), 15.0*array(datingLabels))
ax.axis([-2,25,-0.2,2.0])
plt.xlabel('Percentage of Time Spent Playing Video Games')
plt.ylabel('Liters of Ice Cream Consumed Per Week')
plt.show()

import matplotlib
import matplotlib.pyplot as plt

from numpy import *
from matplotlib.patches import Rectangle


n = 1000 #number of points to create
xcord1 = []; ycord1 = []
xcord2 = []; ycord2 = []
xcord3 = []; ycord3 = []
markers =[]
colors =[]
fw = open('E:\\testSet.txt','w')
for i in range(n):
    [r0,r1] = random.standard_normal(2)
    myClass = random.uniform(0,1)
    if (myClass <= 0.16):
        fFlyer = random.uniform(22000, 60000)
        tats = 3 + 1.6*r1
        markers.append(20)
        colors.append(2.1)
        classLabel = 1 #'didntLike'
        xcord1.append(fFlyer); ycord1.append(tats)
    elif ((myClass > 0.16) and (myClass <= 0.33)):
        fFlyer = 6000*r0 + 70000
        tats = 10 + 3*r1 + 2*r0
        markers.append(20)
        colors.append(1.1)
        classLabel = 1 #'didntLike'
        if (tats < 0): tats =0
        if (fFlyer < 0): fFlyer =0
        xcord1.append(fFlyer); ycord1.append(tats)
    elif ((myClass > 0.33) and (myClass <= 0.66)):
        fFlyer = 5000*r0 + 10000
        tats = 3 + 2.8*r1
        markers.append(30)
        colors.append(1.1)
        classLabel = 2 #'smallDoses'
        if (tats < 0): tats =0
        if (fFlyer < 0): fFlyer =0
        xcord2.append(fFlyer); ycord2.append(tats)
    else:
        fFlyer = 10000*r0 + 35000
        tats = 10 + 2.0*r1
        markers.append(50)
        colors.append(0.1)
        classLabel = 3 #'largeDoses'
        if (tats < 0): tats =0
        if (fFlyer < 0): fFlyer =0
        xcord3.append(fFlyer); ycord3.append(tats)    

fw.close()
fig = plt.figure()
ax = fig.add_subplot(111)
#ax.scatter(xcord,ycord, c=colors, s=markers)
type1 = ax.scatter(xcord1, ycord1, s=20, c='red')
type2 = ax.scatter(xcord2, ycord2, s=30, c='green')
type3 = ax.scatter(xcord3, ycord3, s=50, c='blue')
ax.legend([type1, type2, type3], ["Did Not Like", "Liked in Small Doses", "Liked in Large Doses"], loc=2)
ax.axis([-5000,100000,-2,25])
plt.xlabel('Frequent Flyier Miles Earned Per Year')
plt.ylabel('Percentage of Time Spent Playing Video Games')
plt.show()

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))   #element wise divide
    return normDataSet, ranges, minVals

normDataSet, ranges, minVals = autoNorm(returnMat)
print(normDataSet)

def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('F:\\machinelearninginaction\\Ch02\\datingTestSet2.txt')       #load data setfrom file
    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)))
    print(errorCount)
    
datingClassTest()

def classifyPerson():
    resultList = ['not at all','in small doses1','in large doses'] 
    percentTats = float(input("percentage of time spent playing video games?"))
    ffMiles = float(input("freguent flier miles earned per year?"))
    iceCream = float(input('liters of ice cream consumed per year?')) 
    datingDataMat,datingLabels = file2matrix('F:\\machinelearninginaction\\Ch02\\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()