《机器学习实战》K近邻算法

from numpy import *
import operator

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 classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis = 1)
    distance = sqDistances ** 0.5
    sortedDistIndicies = distance.argsort() 
   #argsort()函数,是numpy库中的函数，返回的是数组值从小到大的索引值
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    #字典get()方法返回指定键的值，如果键不在字典中，返回一个指定值，默认为None。
    sortedClassCount = sorted(classCount.items(),
                              key = operator.itemgetter(1), reverse = True)
    
    return sortedClassCount[0][0]

'''
sorted 语法：

sorted(iterable[, cmp[, key[, reverse]]])
参数说明：
iterable -- 可迭代对象。
cmp -- 比较的函数，这个具有两个参数，参数的值都是从可迭代对象中取出，
此函数必须遵守的规则为，大于则返回1，小于则返回-1，等于则返回0。
key -- 主要是用来进行比较的元素，只有一个参数，
具体的函数的参数就是取自于可迭代对象中，指定可迭代对象中的一个元素来进行排序。
reverse -- 排序规则，reverse = True 降序 ， reverse = False 升序（默认）。
'''


'''
operator.itemgetter函数
operator模块提供的itemgetter函数用于获取对象的哪些维的数据，参数为一些序号。看下面的例子

a = [1,2,3] 
>>> b=operator.itemgetter(1)      //定义函数b，获取对象的第1个域的值
>>> b(a) 

2
    
>>> b=operator.itemgetter(1,0)  //定义函数b，获取对象的第1个域和第0个的值
>>> b(a) 
(2, 1)

要注意，operator.itemgetter函数获取的不是值，而是定义了一个函数，通过该函数作用到对象上才能获取值。

sorted函数用来排序，sorted(iterable[, cmp[, key[, reverse]]])

其中key的参数为一个函数或者lambda函数。所以itemgetter可以用来当key的参数

a = [('john', 'A', 15), ('jane', 'B', 12), ('dave', 'B', 10)]

根据第二个域和第三个域进行排序

sorted(students, key=operator.itemgetter(1,2))
'''
    


def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('	')
        returnMat[index, :] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector


# 归一化特征值
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))
    return normDataSet, ranges, minVals


def datingClassTest():
    hoRatio = 0.1
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    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 classfier came back with: %d, the real answer is: %d" 
              % (classifierResult, datingLabels[i]))
        if classifierResult != datingLabels[i]:
            errorCount += 1
    print("the total error rate is: %f" % (errorCount/float(numTestVecs)))
    
    
    
def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(input("percentage of time spent playing video games?"))
    ffMiles = float(input("frequent flier miles earned per year?"))
    iceCream = float(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])