kNN.py

改进约会网站配对效果：

k-近邻算法

  1. def classify0(inX, dataSet, labels, k):
  2.     dataSetSize = dataSet.shape[0]
  3.     diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet
  4.     sqDiffMat = diffMat**2
  5.     sqDistances = sqDiffMat.sum(axis=1)
  6.     distances = sqDistances**0.5
  7.     sortedDistIndicies = distances.argsort()
  8.     classCount = {}
  9.     for i in range(k):
  10.         voteIlabel = labels[sortedDistIndicies[i]]
  11.         classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
  12.     sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
  13.     return sortedClassCount[0][0]

Tile函数：

tile函数位于python模块 numpy.lib.shape_base中，他的功能是重复某个数组。比如tile(A,n)，功能是将数组A重复n次，构成一个新的数组

  1. >>> import numpy
  2. >>> numpy.tile([0,0],5)#在列方向上重复[0,0]5次，默认行1次
  3. array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
  4. >>> numpy.tile([0,0],(1,1))#在列方向上重复[0,0]1次，行1次
  5. array([[0, 0]])
  6. >>> numpy.tile([0,0],(2,1))#在列方向上重复[0,0]1次，行2次
  7. array([[0, 0],
  8.        [0, 0]])
  9. >>> numpy.tile([0,0],(3,1))
  10. array([[0, 0],
  11.        [0, 0],
  12.        [0, 0]])
  13. >>> numpy.tile([0,0],(1,3))#在列方向上重复[0,0]3次，行1次
  14. array([[0, 0, 0, 0, 0, 0]])
  15. >>> numpy.tile([0,0],(2,3))<span style="font-family: Arial, Helvetica, sans-serif;">#在列方向上重复[0,0]3次，行2次</span>
  16. array([[0, 0, 0, 0, 0, 0],
  17.        [0, 0, 0, 0, 0, 0]])

python中的sum函数.sum(axis=1)

浅述python中argsort()函数的用法

operator模块提供的itemgetter函数主要用于获取某一对象 特定维度的数据，其中的参数为特定维度的序号，看下面的例子吧：

  1. >>> a=[1,2,3,4]
  2. >>> b=operator.itemgetter(1) #获取下标为1的元素
  3. >>> b(a)
  4. 2
  5. >>> b=operator.itemgetter(1,0) #获取下标为1和0的元素
  6. >>> b(a)
  7. (2,1)

python更改当前工作路径

将文本记录转为Numpy的解析程序：

  1. def file2matrix(filename):
  2.     love_dictionary = {'largeDoses':3, 'smallDoses':2, 'didntLike':1}
  3.     fr = open(filename)
  4.     arrayOLines = fr.readlines()
  5.     numberOfLines = len(arrayOLines)            #get the number of lines in the file
  6.     returnMat = np.zeros((numberOfLines, 3))        #prepare matrix to return
  7.     classLabelVector = []                       #prepare labels return
  8.     index = 0
  9.     for line in arrayOLines:
  10.         line = line.strip()
  11.         listFromLine = line.split('\t')
  12.         returnMat[index, :] = listFromLine[0:3]
  13.         if(listFromLine[-1].isdigit()):
  14.             classLabelVector.append(int(listFromLine[-1]))
  15.         else:
  16.             classLabelVector.append(love_dictionary.get(listFromLine[-1]))
  17.         index += 1
  18.     return returnMat, classLabelVector

python numpy.zeros()函数的用法

在 Python 中字符串处理函数里有三个去空格（包括 ‘\n’, ‘\r’, ‘\t’, ’ ‘) 的函数：

  • strip 同时去掉左右两边的空格
  • lstrip 去掉左边的空格
  • rstrip 去掉右边的空格

matplotlib.pyplot中add_subplot方法参数111的含义

归一化特征值:

newValue = (oldValue - min)/(max - min)

  1. def autoNorm(dataSet):
  2.     minVals = dataSet.min(0)
  3.     maxVals = dataSet.max(0)
  4.     ranges = maxVals - minVals
  5.     normDataSet = np.zeros(np.shape(dataSet))
  6.     m = dataSet.shape[0]
  7.     normDataSet = dataSet - np.tile(minVals, (m, 1))
  8.     normDataSet = normDataSet/np.tile(ranges, (m, 1))   #element wise divide
  9.     return normDataSet, ranges, minVals

分类器针对约会网站的测试代码：

  1. def datingClassTest():
  2.     hoRatio = 0.50      #hold out 10%
  3.     datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
  4.     normMat, ranges, minVals = autoNorm(datingDataMat)
  5.     m = normMat.shape[0]
  6.     numTestVecs = int(m*hoRatio)
  7.     errorCount = 0.0
  8.     for i in range(numTestVecs):
  9.         classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 3)
  10.         print("the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i]))
  11.         if (classifierResult != datingLabels[i]): errorCount += 1.0
  12.     print("the total error rate is: %f" % (errorCount / float(numTestVecs)))
  13.     print(errorCount)

image.png

约会网站预测函数：

  1. def classifyPerson():
  2.     resultList = ['not at all', 'in small doses', 'in large doses']
  3.     percentTats = float(input(\
  4.                                   "percentage of time spent playing video games?"))
  5.     ffMiles = float(input("frequent flier miles earned per year?"))
  6.     iceCream = float(input("liters of ice cream consumed per year?"))
  7.     datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
  8.     normMat, ranges, minVals = autoNorm(datingDataMat)
  9.     inArr = np.array([ffMiles, percentTats, iceCream, ])
  10.     classifierResult = classify0((inArr - \
  11.                                   minVals)/ranges, normMat, datingLabels, 3)
  12.     print("You will probably like this person: %s" % resultList[classifierResult - 1])

image.png

手写识别系统：

  1. def img2vector(filename):
  2.     returnVect = np.zeros((1, 1024))
  3.     fr = open(filename)
  4.     for i in range(32):
  5.         lineStr = fr.readline()
  6.         for j in range(32):
  7.             returnVect[0, 32*i+j] = int(lineStr[j])
  8.     return returnVect

自包含函数？

手写数字识别系统的测试代码：

  1. def handwritingClassTest():
  2.     hwLabels = []
  3.     trainingFileList = listdir('trainingDigits')           #load the training set
  4.     m = len(trainingFileList)
  5.     trainingMat = np.zeros((m, 1024))
  6.     for i in range(m):
  7.         fileNameStr = trainingFileList[i]
  8.         fileStr = fileNameStr.split('.')[0]     #take off .txt
  9.         classNumStr = int(fileStr.split('_')[0])
  10.         hwLabels.append(classNumStr)
  11.         trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
  12.     testFileList = listdir('testDigits')        #iterate through the test set
  13.     errorCount = 0.0
  14.     mTest = len(testFileList)
  15.     for i in range(mTest):
  16.         fileNameStr = testFileList[i]
  17.         fileStr = fileNameStr.split('.')[0]     #take off .txt
  18.         classNumStr = int(fileStr.split('_')[0])
  19.         vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
  20.         classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
  21.         print("the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr))
  22.         if (classifierResult != classNumStr): errorCount += 1.0
  23.     print("\nthe total number of errors is: %d" % errorCount)
  24.     print("\nthe total error rate is: %f" % (errorCount/float(mTest)))

image.png