机器学习实战笔记-k-近邻算法

# -*- coding: utf-8 -*-
from numpy import *
import operatordef createDataSet():
  """ 
    函数作用：构建一组训练数据（也就是样本),其实这里的样本是我们自己构造 
    的数据，样本容量很少，真实的情况是读取文本数据。 
    同时给出样本的标签以及labels。标签的意思就是样本四个数据的各个类别 
    比如[1.0,1.1]属于A类等。 
    """  
group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
labels = ['A','A','B','B']
return group,labels

>>> import kNN>>> group, labels = kNN.createDataSet()

def classify(inX, dataSet, labels, k): """ inX 是输入的测试样本，是一个[x, y]样式的，也就是我们需要想知道的 数据到底属于哪类A活着B，就想上面说的未知电影是爱情还是动作影片。 dataset是训练样本集 labels是训练样本标签其实就是类别A和B k是top k最相近的。说实话开始我并不理解，其实很简单就是选取离自己 最近的k个样本，具体我在上面会有介绍 """ dataSetSize = dataSet.shape[0] # 数据集大小 #dataSet.shape 结果是（4，1）返回矩阵的行数和列数。 # 那么shape[0]获取数据集的行数， # 行数就是样本的数量 这里就是4 # 计算距离 """ 下面的求距离过程就是按照欧氏距离的公式计算的。 即 根号(x2-x1）^2+(y2-y1)^2) 。比如（1，2），（2，3） 这两个点的距离就是（2-1）^2+（3-2）^2,然后开根号计算。 """ diffMat = tile(inX, (dataSetSize, 1)) - dataSet """ 由于dataset数据是一个4行1列的数据，而我们测试的数据，是一个一行一列的数据， 比如（1，0）。由于要把这个值跟测试数据每一个都进行减法。为了方便就必须是构造 一个同样结构的矩阵数据，用tile方法相当于copy inX四次沿着行。比如以前是（1，0） 那么tile（inX，（4，1））变成啦 1 0 1 0 1 0 1 0 """ sqDiffMat = diffMat**2 # 然后就是平方每个进行减法的值 sqDistances = sqDiffMat.sum(axis=1) """ sqDiffMat ＝ [[ 1. 1.21] [ 1. 1. ] [ 0. 0. ] [ 0. 0.01]] sqDiffMat.sum(axis=1) 把所有的值都加起来沿着 x轴，而都是一行行的加那么结果。四个值 ［2.21. 2. 0. 0.01］ sqDiffMat.sum(axis=0) 但是当我们把axis=0结果就发生了变化。都是一列列的加， 而只有两个值所有的x值加在一起，所有的y值加在一起 我们发现只有x值都都在一起，然后y都加在一起。 [ 2. 2.22] """ distances = sqDistances**0.5 # 按距离排序 sortedDistIndicies = distances.argsort() """ distances =[ 1.48660687 1.41421356 0. 0.1 ] distances.argsort() 这个函数就是返回从小到大的值的索引，也就是距离 值按照由近到远排列距离索引值。 比如最大就是第一个（index ＝ 0）最小值就是第三个（index＝2） 那么返回顺序就是如下。 sortedDistIndicies＝[2 3 1 0] """ # 统计前k个点所属的类别 classCount = {} for i in range(k): votaIlabel = labels[sortedDistIndicies[i]] classCount[votaIlabel] = classCount.get(votaIlabel, 0) + 1 sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True) """ sorted函数的作用就是排序，一般是从小到大，但是这里reverse=True 表示从反过来啦从大到小 classCount.iteritems()用于返回一个 iterator， 关于iteritems()方法以及其他相关函数见下面博客 我觉得研究的很好。 Python dictionary items()系列函数的使用 http://blog.csdn.net/revilwang/article/details/38686635 operator.itemgetter(1) 获取前面的classCount.iteritems()中 第二个值进行操作，按照第二个升序排列。 比如下面这个例子 >>> d = {'data1':3, 'data2':1, 'data3':2, 'data4':4} >>> sorted(d.iteritems(), key=itemgetter(1), reverse=True) >>>[('data4', 4), ('data1', 3), ('data3', 2), ('data2', 1)] """ # 返回前k个点中频率最高的类别 return sortedClassCount[0][0] """ 返回这个list或者怎么说第一个数值对中第一个值。这里是B， 比如下面例子就是data4 >>> d [('data4', 4), ('data1', 3), ('data3', 2), ('data2', 1)] >>> d[0][0] 'data4' """

>>> import kNN >>> group, labels = kNN.createDataSet() >>> kNN.classify0([0, 0], group, labels, 3) 'B'

def file2matrix(filename): fr = open(filename) numberOfLines = len(fr.readlines()) # get the number of lines in the file returnMat = zeros((numberOfLines, 3)) # prepare matrix to return classLabelVector = [] # prepare labels return fr = open(filename) index = 0 for line in fr.readlines(): line = line.strip() listFromLine = line.split('\t') returnMat[index, :] = listFromLine[0:3] classLabelVector.append(int(listFromLine[-1])) index += 1 return returnMat, classLabelVector

>>> import importlib>>> importlib.reload(kNN)>>> datingDataMat, datingLabels = kNN.file2matrix('datingTestSet.txt')>>> datingDataMat>>> datingLabels

>>> import matplotlib>>> import matplotlib.pyplot as plt>>> fig = plt.figure()>>> ax = fig.add_subplot(111)>>> ax.scatter(datingDataMat[:,1], datingDataMat[:,2])>>> plt.show()

>>> ax.scatter(datingDataMat[:,1], datingDataMat[:,2], 15.0 * array(datingLabels), 15.0 * array(datingLabels))

>>> import importlib>>> importlib.reload(kNN)>>> datingDataMat,datingLabels = kNN.file2matrix('datingTestSet2.txt')>>> import matplotlib>>> import matplotlib.pyplot as plt>>> fig = plt.figure()>>> ax = fig.add_subplot(111)>>> from numpy import *>>>ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))>>> plt.show()

import matplotlib
import numpy as np
from numpy import *
from matplotlib import pyplot as plt
from matplotlib.font_manager import FontProperties def file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines()) # get the number of lines in the file
returnMat = zeros((numberOfLines, 3)) # prepare matrix to return
classLabelVector = [] # prepare labels return
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
returnMat[index, :] = listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat, classLabelVector
zhfont = FontProperties(fname='C:/Windows/Fonts/simsun.ttc',size=12)datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
fig = plt.figure()plt.figure(figsize=(8, 5), dpi=80)
ax = plt.subplot(111)datingLabels = np.array(datingLabels)
idx_1 = np.where(datingLabels==1)
p1 = ax.scatter(datingDataMat[idx_1,0],datingDataMat[idx_1,1],marker = '*',color = 'r',label='',s=10)
idx_2 = np.where(datingLabels==2)
p2 = ax.scatter(datingDataMat[idx_2,0],datingDataMat[idx_2,1],marker = 'o',color ='g',label='',s=20)
idx_3 = np.where(datingLabels==3)
p3 = ax.scatter(datingDataMat[idx_3,0],datingDataMat[idx_3,1],marker = '+',color ='b',label='',s=30)plt.xlabel(u'每年获取的飞行里程数', fontproperties=zhfont)
plt.ylabel(u'玩视频游戏所消耗的事件百分比', fontproperties=zhfont)
ax.legend((p1, p2, p3), (u'不喜欢', u'魅力一般', u'极具魅力'), loc=2, prop=zhfont)
plt.show()

def autoNorm(dataSet): minVals = dataSet.min(0)# 分别求各个特征的最小值 maxVals = dataSet.max(0)# 分别求各个特征的最大值 ranges = maxVals - minVals# 各个特征的取值范围 normDataSet = zeros(shape(dataSet)) m = dataSet.shape[0] normDataSet = dataSet - tile(minVals, (m, 1)) normDataSet = normDataSet / tile(ranges, (m, 1)) # element wise divide return normDataSet, ranges, minVals

>>> import importlib>>> importlib.reload(kNN)>>> normMat, ranges, minVals = kNN.autoNorm(datingDataMat)>>> normMatarray([[ 0.44832535, 0.39805139, 0.56233353], [ 0.15873259, 0.34195467, 0.98724416], [ 0.28542943, 0.06892523, 0.47449629], ..., [ 0.29115949, 0.50910294, 0.51079493], [ 0.52711097, 0.43665451, 0.4290048 ], [ 0.47940793, 0.3768091 , 0.78571804]])>>> rangesarray([ 9.12730000e+04, 2.09193490e+01, 1.69436100e+00])>>> minValsarray([ 0. , 0. , 0.001156])

def datingClassTest(): hoRatio = 0.50 # hold out 10% datingDataMat, datingLabels = file2matrix('datingTestSet2.txt') # load data setfrom file normMat, ranges, minVals = autoNorm(datingDataMat) m = normMat.shape[0] numTestVecs = int(m * hoRatio) errorCount = 0.0 for i in range(numTestVecs): 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]): errorCount += 1.0 print ("the total error rate is: %f" % (errorCount / float(numTestVecs))) print(errorCount)

>>> import importlib>>> importlib.reload(kNN)>>> kNN.datingClassTest()the classifier came back with: 3, the real answer is: 3the classifier came back with: 2, the real answer is: 2the classifier came back with: 1, the real answer is: 1the classifier came back with: 1, the real answer is: 1..................................................................................the classifier came back with: 1, the real answer is: 1the classifier came back with: 1, the real answer is: 1the classifier came back with: 2, the real answer is: 2the total error rate is: 0.06400033.0

def classifyPerson(): resultList = ['not at all','in small doses','in large doses'] percentTats = float(input("percentage of time spent playing video gemaes?")) #percentTats = float(raw_input("percentage of time spent playing video gemaes?"))#raw_input改为input ffMiles = float(input("frequent flier miles earned per year?")) iceCream = float(input("liters of ice cream consumed per year?")) datingDataMat,datingLabels = file2matrix('datingTestSet2.txt') normMat,ranges,minVals = autoNorm(datingDataMat) inArr = array([ffMiles,percentTats,iceCream]) classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3) print("You will probably like this person: ",resultList [classifierResult - 1])

>>> import importlib>>> importlib.reload(kNN)>>> kNN.classifyPerson()percentage of time spent playing video gemaes?10frequent flier miles earned per year?10000liters of ice cream consumed per year?0.5You will probably like this person: in small doses

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

>>> testVector = kNN.img2vector('testDigits/0_13.txt')>>> testVector[0,0:31]array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])>>> testVector[0,32:63]array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])

def handwritingClassTest(): hwLabels = [] trainingFileList = listdir('trainingDigits') # load the training set m = len(trainingFileList) trainingMat = zeros((m, 1024)) for i in range(m): fileNameStr = trainingFileList[i] fileStr = fileNameStr.split('.')[0] # take off .txt classNumStr = int(fileStr.split('_')[0]) hwLabels.append(classNumStr) trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr) testFileList = listdir('testDigits') # iterate through the test set errorCount = 0.0 mTest = len(testFileList) for i in range(mTest): fileNameStr = testFileList[i] fileStr = fileNameStr.split('.')[0] # take off .txt classNumStr = int(fileStr.split('_')[0]) vectorUnderTest = img2vector('testDigits/%s' % fileNameStr) classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3) print( "the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr)) if (classifierResult != classNumStr): errorCount += 1.0 print("\nthe total number of errors is: %d" % errorCount) print ("\nthe total error rate is: %f" % (errorCount / float(mTest)))

>>> import importlib>>> importlib.reload(kNN)>>> kNN.handwritingClassTest()the classifier came back with: 0, the real answer is: 0the classifier came back with: 0, the real answer is: 0.the classifier came back with: 7, the real answer is: 7the classifier came back with: 7, the real answer is: 7the classifier came back with: 8, the real answer is: 8the classifier came back with: 8, the real answer is: 8.the classifier came back with: 9, the real answer is: 9the total number of errors is: 11the total error rate is: 0.011628