K-近邻算法(Python)
def classify0(inx, dataSet, labels, k):
"""
:param inx: 测试样本集合
:param dataSet: 训练样本集合
:param labels: 标签集合
:param k: 选取k个相似度最高
:return: 返回测试样本标签
"""
#距离计算
dataSetSize = dataSet.shape[0] #返回数组大小 group为4*2 shape=(4,2)
diffMax = np.tile(inx, (dataSetSize,1)) -dataSet #tile 根据训练数据大小生成 矩阵减法
sqDiffMax = diffMax**2 #平方
sqDistances = sqDiffMax.sum(axis=1) #行坐标累加
distances = sqDistances**0.5 #开根号
#排序
sortedDisIndicies = distances.argsort() #排序从小到大 返回索引
#获取距离最小的K个点
classCount = {}
for i in range(k):
voteIlabel = labels[sortedDisIndicies[i]] #根据下标获取标签
classCount[voteIlabel] = classCount.get(voteIlabel,0)+1 #累计标签集合次数
#集合K根据次数排序
sortedClassCount = sorted(classCount.items(), key = operator.itemgetter(1), reverse = True)
return sortedClassCount[0][0]
构造训练样本集合 标签集合
def createDataSet():
group = np.array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
labels = ['A', 'A', 'B','B']
return group, labels
测试调用
group,labels = knn.createDataSet()
res = knn.classify0([0,0],group,labels,3)
文件读取:1000行数据 前三列表示训练样本 最后一列为标签
def file2maxtrix(filename):
fr = open(filename)
arrayOLines = fr.readlines()
numberOfLines = len(arrayOLines) #获取文本行数
returnMax = np.zeros((numberOfLines, 3))#生成1000*3 的 零矩阵
classLabelVector = []
index = 0
for line in arrayOLines:
line = line.strip()
listFromLine = line.split('\t')
returnMax[index,:] = listFromLine[0:3] #前三列是训练样本数据
classLabelVector.append(int(listFromLine[-1])) #最后一列是标签集合
index += 1
return returnMax, classLabelVector
读取文件画图,在数据处理之前,通过图形化分析数据特征 数据通过https://www.manning.com/books/machine-learning-in-action sourcecode下载
filname = 'C:/javacode/machinelearninginaction/Ch02/datingTestSet2.txt'
datingDateMat, datingLabels = knn.file2maxtrix(filname)
print('datingDateMat: {}'.format(datingDateMat))
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDateMat[:,0], datingDateMat[:,1], c=datingLabels)#c这个参数是表示颜色 根据标签分不同颜色展示 datingLabels数组
plt.show()
如图
计算样本数据之前,需要对特征值做归一化
def autoNorm (dataSet):
"""
归一化数据
"""
minVals = dataSet.min(0)
maxVals = dataSet.max(0)
ranges = maxVals - minVals
normDataSet = np.zeros(np.shape(dataSet))
m = dataSet.shape[0] #1000 读取矩阵长度
normDataSet = dataSet - np.tile(minVals, (m,1)) #tile 生成最小值矩阵 根据训练数据大小生成 矩阵减法 减去最小值
#print(np.tile(minVals, (m,1)))
normDataSet = normDataSet/np.tile(ranges, (m,1)) #除以(最大值-最小值)
return normDataSet, ranges, minVals
测试代码
def datingClassTest(filname):
hoRatio = 0.10
datingDateMat, datingLabels = knn.file2maxtrix(filname)#读取训练数据
normMat, ranges, minVals = knn.autoNorm(datingDateMat)#归一化训练数据
m = normMat.shape[0] #返回矩阵行数
numTestVecs = int (m*hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
#前100作为验证样本 后900作为训练样本
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] :#计算错误率
errorCount += 1.0
print("the total error rate is:%f"%(errorCount/float(numTestVecs)))
return
输出:
the classifier came back with:3, the real answer is : 3
the classifier came back with:2, the real answer is : 2
the classifier came back with:1, the real answer is : 1
the classifier came back with:1, the real answer is : 1
the classifier came back with:1, the real answer is : 1
the classifier came back with:1, the real answer is : 1
……
the classifier came back with:3, the real answer is : 1
the total error rate is:0.050000
100个样本错了5个 错误率为0.05
根据用户输入返回分类结果
def classifyPerson(filname):
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?'))
datingDateMat, datingLabels = knn.file2maxtrix(filname)#读取训练数据
normMat, ranges, minVals = knn.autoNorm(datingDateMat)#归一化训练数据
inArr = np.array([percentTats, ffMiles, iceCream])
inArrNorm = inArr-minVals/ranges #对测试数据归一化
classifierResult = knn.classify0(inArrNorm,normMat,datingLabels,3)
print("you will probably like this person:",resultList[classifierResult-1])
return
输入输出内容
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: not at all