機器學習_K近鄰Python程式碼詳解

反正不想起名發表於2018-10-03
機器學習Python
k近鄰優點：精度高、對異常值不敏感、無資料輸入假定；
k近鄰缺點：計算複雜度高、空間複雜度高


import numpy as np
import operator
from os import listdir

# k近鄰分類器
def classify0(inx, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]   # 返回dataset第一維的長度，也就是行數
    diffMat = np.tile(inx, (dataSetSize, 1))-dataSet   # tile表示把inx行向量按列方向重複datasetsize次
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)  # 按列求和
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()  # 返回的是陣列從小到大的索引值
    classCount = {}    # 定義一個空字典
    for i in range(k):
        voteLabel = labels[sortedDistIndicies[i]]  # 返回前k個距離最小的樣本的標籤值
        classCount[voteLabel] = classCount.get(voteLabel, 0)+1   # get 表示返回指定鍵的值
        # lambda表示輸入classCount返回冒號右邊的值，reverse=True表示按照降序排列
        sortedClassCount=sorted(classCount.items(), key=lambda classCount: classCount[1], reverse=True)
    return sortedClassCount[0][0]

# 把.txt檔案轉換成矩陣形式
def file2matrix(file):
    file = open(file) # 返回檔案物件
    arr = file.readlines()  # 返回全部行，是list形式，每一行為list的一個元素
    number = len(arr)  # 返回物件長度
    returnMat = np.zeros((number,3))
    index = 0
    labelMat = []
    for line in arr:
        #line = line.strip(`
`)
        #newline = line.split(` `)
        newline = line.strip(`
`).split(` `) # 處理逐行資料，strip表示把頭尾的`
`去掉，split表示以空格來分割行資料
                                              #  然後把處理後的行資料返回到newline列表中
        returnMat[index,:] = newline[0:3] #表示列表的0,1,2列資料放到index行中
        labelMat.append(int(newline[-1]))
        index+=1
    return returnMat,labelMat

# 歸一化
def autoNorm(dataSet):
    minVals = dataSet.min(0)

    maxVals = dataSet.max(0)
    ranges = maxVals-minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = normDataSet.shape[0]
    A = normDataSet
    A = np.tile(minVals, (m,1))
    normDataSet = dataSet-A
    normDataSet = normDataSet/np.tile(ranges,(m,1))
    return normDataSet

# 把影像轉化成向量的形式
def img2vector(filename):
    returnVect = np.zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline() # readline()表示從首行開始，每次讀取一行
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j]) #int()函式用於將一個字串或數字轉換成整型
    return returnVect   # 一張圖片轉化成一行後的陣列

# 手寫數字識別系統的測試程式碼
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir(`E:/workspace/digits/trainingDigits`)
    m=len(trainingFileList)
    trainingMat = np.zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]  # 例如9_45.txt
        fileStr = fileNameStr.split(`.`)[0]  # split(`.`)通過.分隔符對字串進行切片
        classNumStr = int(fileStr.split(`_`)[0]) # split(`_`)通過_分隔符對字串進行切片
        hwLabels.append(classNumStr)
        trainingMat[i,:] =img2vector(`E:/workspace/digits/trainingDigits/%s` % fileNameStr)
    testFileList = listdir(`E:/workspace/digits/testDigits`)
    mTest = len(testFileList)
    errorCount = 0
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split(`.`)[0]
        classNumStr = int(fileStr.split(`_`)[0])
        vectorUnderTest = img2vector(`E:/workspace/digits/testDigits/%s` % fileNameStr)
        classResult = classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print(`the classifier came back with: %d, the real answer is: %d` % (classResult,classNumStr))
        if (classResult != classNumStr):
            errorCount += 1.0
    print(`
 the total number of errors is: %d` % (errorCount))
    print(`
 the total error rate is: %f` % (errorCount/float(mTest)))

handwritingClassTest()



相關文章