机器学习实战：ch02-1

'''
kNN.py
'''

from numpy import *
from 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

'''
intX: 输入向量,与dataset矩阵矩阵的行数一致
k: 邻近的个数
'''
def classify0(intX,dataSet,labels,k):
    dataSetSize = dataSet.shape[0]
    # 计算欧式距离
    diffMat = tile(intX,(dataSetSize,1)) - dataSet # 矩阵减法
    # tile（A,reps） A沿各个维度重复的次数
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis = 1) # 矩阵行相加,列的参数是0
    distances = sqDistances ** 0.5
    #print("distances:")
    #print distances
    sortedDistIndicies = distances.argsort() # argsort函数返回的是数组值从小到大的索引值
    
    #print("sortedDistIndicies:")
    #print sortedDistIndicies 
    classCount ={} #dict 类型
    
    for i in range(k):
        voteIlabel = label[sortedDistIndicies[i]]
        #print ("i: %d, sortedDistIndicies[%d]: %d"%(i,i,sortedDistIndicies[i]))
        #print ("voteIlabel:%s"%(voteIlabel))
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
        #D.get(k[, d])   => D[k] if k in D else d. d defaults to none.提取标签出现的个数
        
        #print ("classCount[%s]:%d"%(voteIlabel,classCount[voteIlabel]))
        sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse = True)
        #classCount.iteritems()遍历
        #operator.itemgetter函数选取第几个维的数字，和sorted一起用可根据选出的那个维进行排序
        
    return  sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    arrayOfLines = fr.readlines()
    numberOfLines = len(arrayOfLines)
    returnMat = zeros((numberOfLines,3)) #3列矩阵
    classLabelVector = [] #list
    index = 0
    
    for line for arrayOfLines:
        line = line.strip() # 去除回车
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1])) # 使用索引-1表示列表中的最后一列
        index += 1
    return returnMax, classLabelVector

'''
 归一化
 newValue = (oldValue - minValue)/(maxValue - minValue)
'''
    
def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = normDataSet - tile(minVals,(m,1))
    normDataSet = normDataSet / tile(ranges,(m,1))
    return normDataSet, ranges, minVals
    
'''
Test
'''
def datingDataTest():
    hoRatio = 0.10 
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    normTestVecs = int (m * hoRatio)
    errorCount = 0.0
    for i in range(normTestVecs):
        classifierResult = classify0(normMat[i,:],\
                                    normMat[normTestVecs:m,:],\
                                    datingLabels[normTestVecs: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)))
    

'''
classify
'''
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 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)
    inArr = array([percentTats,ffMiles,iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,\
                                 normMat,\
                                 datingLabels,\
                                 3)
    print ("You will probably like this person: ",\
           resultList[classifierResult-1])