MachineLearning Practice：K-NN

1.存在一个样本数据集，作为样本数据集，该样本集的每一条数据都存在标签也就是说每条样本集的类别已知。输入一个没有标签的新数据集，将新数据的特征和样本集的数据特征进行比较，然后提取与新数据最相似的样本数据的标签作为新数据的标签。一般来说，选择样本集中前K个出现次数最多的标签作为新数据的标签。

2.一般步骤：收集数据（文本/其他程序收集）–>准备数据（归一化，格式化数据，是数据使用于距离计算）–>分析数据（散点图分布，可以探究数据是否存意义）–>训练算法（K-NN算法中无需此步骤）–>测试算法（计算错误率，错误率为1毫无意义，0最为完美，力求分类器获得最低错误率）–>使用算法进行预测

3.K-NN算法的优点：精度高，对异常数据不敏感，无数据输入要求。缺点：计算复杂度高、空间复杂度高。适用数据范围：数值型和标称型。

4.数据准备预处理
+++++++++++++++++++++++++++++++++++
f1 f2 f3 labels
40920 8.326976 0.953952 largeDoses
14488 7.153469 1.673904 smallDoses
26052 1.441871 0.805124 didntLike
:
:
:
61364 7.516754 1.269164 didntLike
69673 14.239195 0.261333 didntLike
15669 0.000000 1.250185 smallDoses
28488 10.528555 1.304844 largeDoses
6487 3.540265 0.822483 smallDoses
37708 2.991551 0.833920 didntLike
++++++++++++++++++++++++++++++++
转换为：（以下表标称转为数值，后面数值的归一化去除不同特征的数值相对偏大或偏小的影响）
f1 f2 f3 labels
40920 8.326976 0.953952 3
14488 7.153469 1.673904 2
：
：
：
50242 3.723498 0.831917 1
63275 8.385879 1.669485 1
5569 4.875435 0.728658 2
51052 4.680098 0.625224 1
+++++++++++++++++++++++++++++++++

5.使用散点图进行数据特征与类别分析

import matplotlib
import matplotlib.pyplot as plt
fig=plt.figure()
ax=fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datinglabels)##大小,90*array(datinglabels)##颜色)
plt.show()

##########################################################
#matplotlib.pyplot.scatter(x, y, s=20, c=None, marker='o', cmap=None, norm=None, vmin=None, vmax=None, alpha=None, linewidths=None, verts=None, edgecolors=None, hold=None, data=None, **kwargs)
#x, y : array_like, shape (n, )
Input data
s : scalar or array_like, shape (n, ), optional,default: 20
size in points^2.
c : color or sequence of color, optional, default

from numpy import *
import operator
from os import listdir

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 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 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

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

def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('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

def img2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect

def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr)
        if (classifierResult != classNumStr): errorCount += 1.0
    print "\nthe total number of errors is: %d" % errorCount
    print "\nthe total error rate is: %f" % (errorCount/float(mTest))


group,labels=createDataSet()    
patten = classify0([0,0],group,labels,3)  
print patten
datingDataMat,datinglabels=file2matrix('C:\Users\Administrator\Desktop\MLiA_SourceCode\machinelearninginaction\Ch02\datingTestSet2.txt')
print datingDataMat
import matplotlib
import matplotlib.pyplot as plt
fig=plt.figure()
ax=fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datinglabels),90*array(datinglabels))
print datingDataMat.min(0)
print datingDataMat.m
# plt.show()