這裡是《機器學習實戰》中第二章KNN的代碼部分解釋。
代碼參考的是:https://www.bilibili.com/video/BV16t411Q7TM
主要是邊看這個視訊邊自己查資料學習的。
KNN最常用的是歐式距離,它沒有訓練過程,直接就是分類
常用的向量距離度量準則:
歐式距離、曼哈頓距離、切比雪夫距離、馬氏距離、巴氏距離、漢明距離、皮爾遜系數、資訊熵,部分相關公式與python代碼見:
https://blog.csdn.net/weixin_43330946/article/details/105032182
優點:精度高、對異常值不敏感、無資料輸入假定(樸素貝葉斯需要假設樣本之間獨立、高斯分布)。
缺點:計算複雜度高(每一個樣本都要計算)、空間複雜度高。
使用資料範圍:數值型和标稱型。
代碼1:
已知4個樣本的類别,再輸入一個新的樣本判斷其屬于哪一類:
import numpy as np
import operator
def creatDataSet():
group = np.array([[1,101], [5,89], [100,5], [115,8]])
labels = ['愛情片','愛情片','動作片','動作片']
return group, labels
def classify0(inX, dataSet, labels, k):
dataSetSize = dataSet.shape[0]#0表示行數
#np.tile表示複制:在列方向上重複inX共1次,行方向上重複inX共dataSetSize次
diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet
sqDiffMat = diffMat ** 2#特征相減後平方
sqDistances = sqDiffMat.sum(axis=1)#sum(0)列相加,sum(1)行相加
distances = sqDistances ** 0.5
sortedDistIndices = distances.argsort()#傳回distance中元素從小到大排序後的索引值
#定義一個記錄類别次數的字典
classCount = {}
for i in range(k):
#取出前k個樣本的相關索引
voteIlable = labels[sortedDistIndices[i]]#取出第i個樣本的類别
#計算類别次數
classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
#對擷取的類别數量進行排序
sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
#key=operator.itemgetter(1)根據字典的值進行排序,
#key=operator.itemgetter(0)根據字典的鍵進行排序,
#reverse=True降序排序字典
return sortedClassCount[0][0]
if __name__ == '__main__':
group, labels = createDataSet()
test = [101, 20]
test_class = classify0(test , group, labels, 3)
print(test_class)
代碼2:
約會網站配對效果判定
import numpy as np
import matplotlib.pyplot as plt
def file2matrix(filename):
fr = open(filename)
arrayOLines = fr.readlines()
numberOfLines = len(arrayOLines)
returMat = np.zeros((numberOFLines, 3))#3個特征
classLableVector = []#傳回的分類标簽向量
index = 0#行的索引值
for line in arrayOLines:
line = line.strip()#預設删除空白符(包括\n、\r、\t、'')
listFromLine = line.split('\t')#将字元串根據'\t'分隔符進行切片
returnMat[index,:] = listFromLine[0:3]#将資料前三列提取出來放入returnMat中
#根據文本中标記的喜歡的程度進行分類
if listFromLine[-1] == 'didntlike':
classLabelVector.append(1)
elif listFromLine[-1] == 'smallDoses':
classLabelVector.append(2)
elif listFromLine[-1] == 'largeDoses':
classLabelVector.append(3)
index += 1
return returnMat, classLabelVector
def showdatas(datingDataMat, datingLabels):
font = FontProperties(fname=r'sumsun.ttc', size=14)#設定漢字格式,英語字型可以不用
fig, axs = plt.subplots(nrows=2, ncols=2, sharex=False, sharey=Flase, figsize=(13,8))
LabelsColors = []
for i in datingLabels:
if i == 1:
LabelsColors.append('black')
if i == 2:
LabelsColors.append('orange')
if i == 3:
LabelsColors.append('red')
axs[0][0].scatter(x=datingDataMat[:,0], y=datingDataMat[:,1], color=LabelsColors, s=15, alpha=.5)#根據datingDataMat的第一、二列資料畫散點資料
axs0_title_text = axs[0][0].set_title(u'每年獲得的飛行常客裡程數與玩視訊遊戲所消耗時間占比', FontProperties=font)
axs0_xlabel_text = axs[0][0].set_xlabel(u'每年獲得的飛行常客裡程數', FontProperties=font)
axs0_ylabel_text = axs[0][0].set_ylabel(u'玩視訊遊戲所消耗時間占比', FontProperties=font)
plt.setp(axs0_title_text, size=9, weight='bold', color='red')
plt.setp(axs0_xlabel_text, size=7, weight='bold', color='black')
plt.setp(axs0_ylabel_text, size=7, weight='bold', color='black')
axs[0][1].scatter(x=datingDataMat[:,0], y=datingDataMat[:,2], color=LabelsColors, s=15, alpha=.5)#根據datingDataMat的第一、三列資料畫散點資料
axs1_title_text = axs[0][1].set_title(u'每年獲得的飛行常客裡程數與每周消費的冰淇淋公升數', FontProperties=font)
axs1_xlabel_text = axs[0][1].set_xlabel(u'每年獲得的飛行常客裡程數', FontProperties=font)
axs1_ylabel_text = axs[0][1].set_ylabel(u'每周消費的冰淇淋公升數', FontProperties=font)
plt.setp(axs1_title_text, size=9, weight='bold', color='red')
plt.setp(axs1_xlabel_text, size=7, weight='bold', color='black')
plt.setp(axs1_ylabel_text, size=7, weight='bold', color='black')
axs[1][0].scatter(x=datingDataMat[:,1], y=datingDataMat[:,2], color=LabelsColors, s=15, alpha=.5)#根據datingDataMat的第二、三列資料畫散點資料
axs2_title_text = axs[1][0].set_title(u'玩視訊遊戲所消耗時間占比與每周消費的冰淇淋公升數', FontProperties=font)
axs2_xlabel_text = axs[1][0].set_xlabel(u'玩視訊遊戲所消耗時間占比', FontProperties=font)
axs2_ylabel_text = axs[1][0].set_ylabel(u'每周消費的冰淇淋公升數', FontProperties=font)
plt.setp(axs2_title_text, size=9, weight='bold', color='red')
plt.setp(axs2_xlabel_text, size=7, weight='bold', color='black')
plt.setp(axs2_ylabel_text, size=7, weight='bold', color='black')
#設定圖例
didntLike = mlines.line2D([], [], color='black', marker='.', markersize=6, label='didntLike')
smallDoses = mlines.line2D([], [], color='orange', marker='.', markersize=6, label='smallDoses')
largeDoses = mlines.line2D([], [], color='red', marker='.', markersize=6, label='largeDoses')
#添加圖例
axs[0][0].legend(handles=[didntLike, smallDoses, largeDoses])
axs[0][1].legend(handles=[didntLike, smallDoses, largeDoses])
axs[1][0].legend(handles=[didntLike, smallDoses, largeDoses])
plt.show()
def autoNorm(dataSet):
minVals = dataSet.min(0)#傳回每一列的最小數
maxVals = dataSet.max(0)
ranges = maxVals - minVals
normDataSet = np.zeros(np.shape(dataSet))
m = dataSet.shape[0]
normDataSet = dataSet - np.tile(minVals, (m,1))
normDataSet = normDataSet / np.tile(ranges, (m,1))
return normDataSet, ranges, minVals
def datingClassTest():
filename = 'datingTestSet.txt'
datingDataMat, datingLabels = file2matrix(filename)
hoRatio = 0.10#10%作為測試集
normMat, ranges, minVals = autoNorm(datingDataMat)#資料歸一化,傳回歸一化後的矩陣、資料範圍、資料最小值
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
erroeCount = 0.0
for i in range(numTestVecs):
classfierResult = classify0(normMat[i:], normMat[numTestVecs:m,:], datingLabels[numTestVecs:m], 4)
print('分類結果:%d\t真實類别:%d' % (classifierResult, datingLabels[i]))
if classifierResult != datingLabels[i]:
errorCount += 1.0
print('錯誤率:%f%%' % (errorCount / float(numTestVecs) * 100))
def classify0(inX, datsSet, labels, k):
dataSetSize = dataSet.shape[0]
diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet
sqDiffMat = diffMat ** 2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances ** 0.5
sortedDistIndices = distances.argsort()
classCount = {}
for i in range(k):
voteIlable = labels[sortedDistIndices[i]]#取出第i個樣本的類别
classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
def classifyPerson():
resultlist = ['讨厭','有些喜歡','非常喜歡']
percentTats = float(input('玩視訊遊戲所耗時間百分比:'))
ffMiles = float(input('每年獲得的飛行常客裡程數:'))
iceCream = float(input('每周消費的冰淇淋公升數'))
filename = 'datingTestSet.txt'
datingDataMat, datingLabels = file2matrix(filename)
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = np.array([percentTats, ffMiles, iceCream])
norminArr = (inArr - minVals) / ranges
classifierResult = classify0(norminArr, normMat, datingLabels, 3)
print('你可能%s這個人' % (resultlist[classifierResult]))
if __name__ == '__main__':
filename = 'datingTestSet.txt'
datingDataMat, datingLabels = file2matrix(filename)
showdatas(datingDataMat, datingLabels)
datingClassTest()
classifyPerson()
代碼3:
類似于代碼4。
代碼4:
手寫數字識别
http://archive.ocs.uci.edu/ml(加州大學歐文學院),有許多驗證機器學習算法的資料集。
from os import listdir
import numpy as np
form sklearn.neighbors import KNeighborsClassifier as KNN
def img2vextor(filename):
returnVect = np.zeros((1,1024))
#KNN不能處理二維資料,沒有位置資訊,是以隻能輸入一維資訊,也說明了CNN的強大
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 = list('traingDigits')
m = len(trainingFileList)
trainingMat = np.zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
classNumber = int(fileNameStr.split('_')[0]#獲得分類的數字
hwLabels.append(classNumber)
trainingMat[i:] = ing2vector('trainingDigits/%s' % (fileNameStr))
neigh = KNN(n_neighbors=3, algorithm='auto')
neigh.fit(trainingMat, hwLabels)
testFileList = listdir('testDigits')
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
classNumber = int(fileNameStr.split('_')[0]
vectorUnderTest = img2vector('testDigits/%s' % (fileNameStr))
classifierResult = neigh.predict(vectorUnderTest)
print('分類傳回結果為%d\t真實結果為%d' % (classifierResult, classNumber))
if (classifierResult != classNumber):
errrorCount += 1.0
print('總共錯了%d個資料\n錯誤率為%f%%' % (errorCount, erroeCount / mTest * 100))
if __name__ == '__main__':
handwritingClassTest()