【python】kNN基础算法--推荐系统

虽然把text转成全部量化是可以的，但是还是需要把text转成numpy的形式（这个是必须掌握的）

在将数据输入到分类器之前，必须将待处理数据的格式改变为分类器可以接受的格式。

数据规范化、数据归一化、数据算法化、输出误差分析

代码：

# -*- coding:utf-8 -*-
from numpy import *

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
#结果全部量化，把喜欢不喜欢排名1、2、3
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')

import matplotlib
import matplotlib.pyplot as plt
# matplotlib 是python最著名的绘图库，它提供了一整套和matlab相似的命令API，十分适合交互式地行制图。而且也可以方便地将它作为绘图控件，嵌入GUI应用程序中。
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
plt.show()

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))  #创建新的返回矩阵
    m = dataSet.shape[0]   #得到数据集的行数  shape方法用来得到矩阵或数组的维数
    normDataSet = dataSet - tile(minVals,(m,1))  #tile:numpy中的函数。tile将原来的一个数组minVals，扩充成了m行1列的数组
    normDataSet = normDataSet/tile(ranges,(m,1))
    return normDataSet,ranges,minVals

normMat,ranges,minVals = autoNorm((datingDataMat))

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.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

    def datingClassTest():
        hoRatio = 0.10
        ErrorCount = 0.0
        datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
        normMat, ranges, minVals = autoNorm(datingDataMat)
        m = normMat.shape[0]
        count = int(m*hoRatio)    #这里需要整型化
        for i in range(count):
            #算法里使用的数据是count（总数）还是i（当前数）,
            #逐渐被测试的数据inX使用[i,:],但是数据集使用count
            # 输入参数:normMat[i,:]为测试样例，表示归一化后的第i行数据
            #       normMat[numTestVecs:m,:]为训练样本数据，样本数量为(m-numTestVecs)个
            #       datingLabels[numTestVecs:m]为训练样本对应的类型标签
            #       k为k-近邻的取值
            classifierResult = classify0(normMat[i,:],normMat[count:m,:],datingLabels[count:m],4)
            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(count))

def classifyPerson():
    resultList = ['not at all','in small doses','in large doses']
    #float定义了输入的类型
    percentTats = float(raw_input(
        "percentage of time spent playing video games?"))
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    iceCream = float(raw_input("liters of ice cream consumed per year?"))
    datingDataMat,datingLabels = file2matrix(("datingTestSet2.txt"))
    normMat,ranges,minVals = autoNorm(datingDataMat)
    #将输入的数据数组化
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print "You will probably like this person:",resultList[classifierResult - 1]