1. tile的使用方法
   tile(A,n)的功能是把A數組重復n次（可以在列方向，也可以在行方向）
2. argsort()函數
   argsort()函數返回的是數組中值從大到小的索引值
3. dict.get()函數
   語法：dict.get(key, default=None)
   key----字典中要查找的鍵
   default----如果指定的簡直不存在時，返回該默認值

4. add_subplot()基礎用法

   import matplotlib.pyplot as plt
   from numpy import *
   fig = plt.figure()
   ax = fig.add_subplot(349)
   ax.plot(x,y)
    
   

   將畫布分成三行四列，在第九個分區畫圖

from numpy import *
from os import listdir
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


# 對數據進行分類
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0
 
]          #shape[0]獲取第一維的數目
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet       # tile??????
    sqDiffMat = diffMat**2
    # 求差的平方和
    sqDistance = sqDiffMat.sum(axis=1)        #axis=1？？？？？？？sum函數默認是axis=0列元素相加,axis=1是一行的元素求和
    #  求標準差
    distances = sqDistance**0.5
    # 距離排序
    sortDistIndicies =
 
 distances.argsort()    #argsort函數返回的是數組值從小到大的索引值
    # 定義元字典
    classCount = {}
    for i in range(k):
        # 獲得前k個元素的標簽
        voteIlabel = labels[sortDistIndicies[i]]
        # 計算前k個數據標簽出現的次數
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1           #dict.get()???????????
    sortedClassCount = sorted(classCount.items(),key = operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


# 讀取文本文件數據
def file2matrix(filename):
    fr = open(filename)
    lines = fr.readlines()
    num_lines = len(lines)
    train_matrix = zeros((num_lines, 3))
    label_vector = []
    index = 0
    for line in lines:
        line = line.strip()
        line_list = line.split(‘\t‘)
        train_matrix[index, :] = line_list[0:3]        # 獲取列表的前0,1,2列
        label_vector.append(int(line_list[-1]))       # 獲取列表的最後一列
        index += 1
    return train_matrix, label_vector                 # add_subplot????????????????


#歸一化函數
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))      # minVals在列上重復一次（本身），在行上重復m次，從而形成m*3的向量
    normDataSet = normDataSet/tile(ranges, (m, 1))
    return normDataSet, ranges, minVals       # 歸一化後的數據， 極差範圍， 最小值


# 分類器測試函數
def datingClassTest():
    hoRatio = 0.10      #測試集比例
    datingDataMat, datingLabels = file2matrix(‘datingTestSet2.txt‘)
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errcount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 2)
        print("the classifier came back with :%d ,the real answer is :%d" % (classifierResult, datingLabels[i]))
        if(classifierResult != datingLabels[i]):
            errcount += 1.0
        print("the total error rate is: %f" %(errcount/float(numTestVecs)))


# 手寫字符文件轉換成向量
def img2vector(filename):
    returnVect = zeros((1, 1024))
    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


# 手寫字符識別測試
def handwritingClassTest():
    hwlabels = []           # 定義手寫字符標簽
    trainingFileList = listdir(‘digits/trainingDigits‘)
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split(‘.‘)[0]
        classNumStr = fileStr.split(‘_‘)[0]
        hwlabels.append(classNumStr)
        # 把文件變成向量並賦值到trainingMat
        trainingMat[i, :] = img2vector(‘digits/trainingDigits/%s‘ % fileNameStr)
    testFileList = listdir(‘digits/testDigits‘)
    errcount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split(‘.‘)[0]
        classNumStr = int(fileStr.split(‘_‘)[0])
        vectorUnderTest = img2vector(‘digits/testDigits/%s‘ % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwlabels, 3)
        print(‘the classifier came back with : %d, the real answer is %d‘ % (int(classifierResult), classNumStr))
        if(int(classifierResult) != int(classNumStr)):
            errcount += 1
    print(‘\nthe total number of errors is %d‘ % errcount)
    print(‘\nthe total error rate is: %f‘ % float(errcount/mTest))

機器學習實戰第二章----KNN