最近邻算法

def file2matrix(filename):
    """
    Desc:
        导入训练数据
    parameters:
        filename: 数据文件路径
    return: 
        数据矩阵 returnMat 和对应的类别 classLabelVector
    """
    fr = open(filename)
    # 获得文件中的数据行的行数
    numberOfLines = len(fr.readlines())
    # 生成对应的空矩阵
    # 例如：zeros(2，3)就是生成一个 2*3的矩阵，各个位置上全是 0 
    returnMat = zeros((numberOfLines, 3))  # prepare matrix to return
    classLabelVector = []  # prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        # str.strip([chars]) --返回已移除字符串头尾指定字符所生成的新字符串
        line = line.strip()
        # 以 '\t' 切割字符串
        listFromLine = line.split('\t')
        # 每列的属性数据
        returnMat[index, :] = listFromLine[0:3]
        # 每列的类别数据，就是 label 标签数据
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    # 返回数据矩阵returnMat和对应的类别classLabelVector
    return returnMat, classLabelVector

import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 0], datingDataMat[:, 1], 15.0*array(datingLabels), 15.0*array(datingLabels))
plt.show()

def autoNorm(dataSet):
    """
    Desc:
        归一化特征值，消除特征之间量级不同导致的影响
    parameter:
        dataSet: 数据集
    return:
        归一化后的数据集 normDataSet. ranges和minVals即最小值与范围，并没有用到

    归一化公式：
        Y = (X-Xmin)/(Xmax-Xmin)
        其中的 min 和 max 分别是数据集中的最小特征值和最大特征值。该函数可以自动将数字特征值转化为0到1的区间。
    """
    # 计算每种属性的最大值、最小值、范围
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    # 极差
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    # 生成与最小值之差组成的矩阵
    normDataSet = dataSet - tile(minVals, (m, 1))
    # 将最小值之差除以范围组成矩阵
    normDataSet = normDataSet / tile(ranges, (m, 1))  # element wise divide
    return normDataSet, ranges, minVals

def datingClassTest():
    """
    Desc:
        对约会网站的测试方法
    parameters:
        none
    return:
        错误数
    """
    # 设置测试数据的的一个比例（训练数据集比例=1-hoRatio）
    hoRatio = 0.1  # 测试范围,一部分测试一部分作为样本
    # 从文件中加载数据
    datingDataMat, datingLabels = file2matrix('input/2.KNN/datingTestSet2.txt')  # load data setfrom file
    # 归一化数据
    normMat, ranges, minVals = autoNorm(datingDataMat)
    # m 表示数据的行数，即矩阵的第一维
    m = normMat.shape[0]
    # 设置测试的样本数量， numTestVecs:m表示训练样本的数量
    numTestVecs = int(m * hoRatio)
    print 'numTestVecs=', numTestVecs
    errorCount = 0.0
    for i in range(numTestVecs):
        # 对数据测试
        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 classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(raw_input("percentage of time spent playing video games ?"))
    ffMiles = float(raw_input("frequent filer 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)
    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

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

>>> testVector = kNN.img2vector('testDigits/0_13.txt')
>>> testVector[0,0:32]
array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])
>>> testVector[0,32:64]
array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])

def handwritingClassTest():
    # 1. 导入训练数据
    hwLabels = []
    trainingFileList = listdir('input/2.KNN/trainingDigits')  # load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    # hwLabels存储0～9对应的index位置， trainingMat存放的每个位置对应的图片向量
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]  # take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        # 将 32*32的矩阵->1*1024的矩阵
        trainingMat[i, :] = img2vector('input/2.KNN/trainingDigits/%s' % fileNameStr)

    # 2. 导入测试数据
    testFileList = listdir('input/2.KNN/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('input/2.KNN/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))

from numpy import *
import operate

#准备导入数据  
def createDataSet()
    group=arry([[1.0,1.1),[1.0,1.0],[0,0],[0,0.1]])
    labels=['A','A','B','B']
    return group,labels
#分类算法
    #inX:分类的输入向量
    #dataSet、labels：训练样本集及对应的标签
    #k:选择最近相邻的数目

def classfiy(inX,dataSet,labels,k)
    #欧式距离计算 
    dataSetSize=dataSet.shape()
    diffMath=tile(inX,(dataSetSize,1)) -dataSet
    sqDiffMat=diffMat**2
    sqDistances=sqDiffMath.sum(axis=1)
    distances=sqlDistances**0.5
    sortedDistIndicies=distances.argsort()
    classCount={}
    
    #选择距离最小的k个点
    for i in range(k):
        votelabel=labels[sortedDistIndicies[i]]
        classCount[voteIlbel]=classCount.get(voteIlabel,0)+1
    #排序
    sortedClassCount=soted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]

#Import Library
from sklearn.neighbors import KNeighborsClassifier
 
#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset
# Create KNeighbors classifier object model 
KNeighborsClassifier(n_neighbors=6) # default value for n_neighbors is 5
 
# Train the model using the training sets and check score
model.fit(X, y)
 
#Predict Output
predicted= model.predict(x_test)