二、Python实现
对于机器学习而已，Python需要额外安装三件宝，分别是Numpy，scipy和Matplotlib。前两者用于数值计算，后者用于画图。安装很简单，直接到各自的官网下载回来安装即可。安装程序会自动搜索我们的python版本和目录，然后安装到python支持的搜索路径下。反正就python和这三个插件都默认安装就没问题了。
另外，如果我们需要添加我们的脚本目录进Python的目录(这样Python的命令行就可以直接import)，可以在系统环境变量中添加：PYTHONPATH环境变量，值为我们的路径，例如：E:\Python\Machine Learning in Action
2.1、kNN基础实践
一般实现一个算法后，我们需要先用一个很小的数据库来测试它的正确性，否则一下子给个大数据给它，它也很难消化，而且还不利于我们分析代码的有效性。
首先，我们新建一个kNN.py脚本文件，文件里面包含两个函数，一个用来生成小数据库，一个实现kNN分类算法。代码如下：
#########################################
# kNN: k Nearest Neighbors
# Input: newInput: vector to compare to existing dataset (1xN)
# dataSet: size m data set of known vectors (NxM)
# labels: data set labels (1xM vector)
# k: number of neighbors to use for comparison
# Output: the most popular class label
#########################################
from numpy import *
import operator
# create a dataset which contains 4 samples with 2 classes
def createDataSet():
# create a matrix: each row as a sample
group = array([[1.0, 0.9], [1.0, 1.0], [0.1, 0.2], [0.0, 0.1]])
labels = ['A', 'A', 'B', 'B'] # four samples and two classes
return group, labels
# classify using kNN
def kNNClassify(newInput, dataSet, labels, k):
numSamples = dataSet.shape[0] # shape[0] stands for the num of row
## step 1: calculate Euclidean distance
# tile(A, reps): Construct an array by repeating A reps times
# the following copy numSamples rows for dataSet
diff = tile(newInput, (numSamples, 1)) - dataSet # Subtract element-wise
squaredDiff = diff ** 2 # squared for the subtract
squaredDist = sum(squaredDiff, axis = 1) # sum is performed by row
distance = squaredDist ** 0.5
## step 2: sort the distance
# argsort() returns the indices that would sort an array in a ascending order
sortedDistIndices = argsort(distance)
classCount = {} # define a dictionary (can be append element)
for i in xrange(k):
## step 3: choose the min k distance
voteLabel = labels[sortedDistIndices[i]]
## step 4: count the times labels occur
# when the key voteLabel is not in dictionary classCount, get()
# will return 0
classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
## step 5: the max voted class will return
maxCount = 0
for key, value in classCount.items():
if value > maxCount:
maxCount = value
maxIndex = key
return maxIndex
然后我们在命令行中这样测试即可：
import kNN
from numpy import *
dataSet, labels = kNN.createDataSet()
testX = array([1.2, 1.0])
k = 3
outputLabel = kNN.kNNClassify(testX, dataSet, labels, 3)
print "Your input is:", testX, "and classified to class: ", outputLabel
testX = array([0.1, 0.3])
outputLabel = kNN.kNNClassify(testX, dataSet, labels, 3)
print "Your input is:", testX, "and classified to class: ", outputLabel
这时候会输出：
Your input is: [ 1.2 1.0] and classified to class: A
Your input is: [ 0.1 0.3] and classified to class: B2.2、kNN进阶
这里我们用kNN来分类一个大点的数据库，包括数据维度比较大和样本数比较多的数据库。这里我们用到一个手写数字的数据库，可以到这里下载。这个数据库包括数字0-9的手写体。每个数字大约有200个样本。每个样本保持在一个txt文件中。手写体图像本身的大小是32x32的二值图，转换到txt文件保存后，内容也是32x32个数字，0或者1，如下：
数据库解压后有两个目录：目录trainingDigits存放的是大约2000个训练数据，testDigits存放大约900个测试数据。
这里我们还是新建一个kNN.py脚本文件，文件里面包含四个函数，一个用来生成将每个样本的txt文件转换为对应的一个向量，一个用来加载整个数据库，一个实现kNN分类算法。最后就是实现这个加载，测试的函数。
#########################################
# kNN: k Nearest Neighbors
# Input: inX: vector to compare to existing dataset (1xN)
# dataSet: size m data set of known vectors (NxM)
# labels: data set labels (1xM vector)
# k: number of neighbors to use for comparison
# Output: the most popular class label
#########################################
from numpy import *
import operator
import os
# classify using kNN
def kNNClassify(newInput, dataSet, labels, k):
numSamples = dataSet.shape[0] # shape[0] stands for the num of row
## step 1: calculate Euclidean distance
# tile(A, reps): Construct an array by repeating A reps times
# the following copy numSamples rows for dataSet
diff = tile(newInput, (numSamples, 1)) - dataSet # Subtract element-wise
squaredDiff = diff ** 2 # squared for the subtract
squaredDist = sum(squaredDiff, axis = 1) # sum is performed by row
distance = squaredDist ** 0.5
## step 2: sort the distance
# argsort() returns the indices that would sort an array in a ascending order
sortedDistIndices = argsort(distance)
classCount = {} # define a dictionary (can be append element)
for i in xrange(k):
## step 3: choose the min k distance
voteLabel = labels[sortedDistIndices[i]]
## step 4: count the times labels occur
# when the key voteLabel is not in dictionary classCount, get()
# will return 0
classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
## step 5: the max voted class will return
maxCount = 0
for key, value in classCount.items():
if value > maxCount:
maxCount = value
maxIndex = key
return maxIndex
# convert image to vector
def img2vector(filename):
rows = 32
cols = 32
imgVector = zeros((1, rows * cols))
fileIn = open(filename)
for row in xrange(rows):
lineStr = fileIn.readline()
for col in xrange(cols):
imgVector[0, row * 32 + col] = int(lineStr[col])
return imgVector
# load dataSet
def loadDataSet():
## step 1: Getting training set
print "---Getting training set..."
dataSetDir = 'E:/Python/Machine Learning in Action/'
trainingFileList = os.listdir(dataSetDir + 'trainingDigits') # load the training set
numSamples = len(trainingFileList)
train_x = zeros((numSamples, 1024))
train_y = []
for i in xrange(numSamples):
filename = trainingFileList[i]
# get train_x
train_x[i, :] = img2vector(dataSetDir + 'trainingDigits/%s' % filename)
# get label from file name such as "1_18.txt"
label = int(filename.split('_')[0]) # return 1
train_y.append(label)
## step 2: Getting testing set
print "---Getting testing set..."
testingFileList = os.listdir(dataSetDir + 'testDigits') # load the testing set
numSamples = len(testingFileList)
test_x = zeros((numSamples, 1024))
test_y = []
for i in xrange(numSamples):
filename = testingFileList[i]
# get train_x
test_x[i, :] = img2vector(dataSetDir + 'testDigits/%s' % filename)
# get label from file name such as "1_18.txt"
label = int(filename.split('_')[0]) # return 1
test_y.append(label)
return train_x, train_y, test_x, test_y
# test hand writing class
def testHandWritingClass():
## step 1: load data
print "step 1: load data..."
train_x, train_y, test_x, test_y = loadDataSet()
## step 2: training...
print "step 2: training..."
pass
## step 3: testing
print "step 3: testing..."
numTestSamples = test_x.shape[0]
matchCount = 0
for i in xrange(numTestSamples):
predict = kNNClassify(test_x[i], train_x, train_y, 3)
if predict == test_y[i]:
matchCount += 1
accuracy = float(matchCount) / numTestSamples
## step 4: show the result
print "step 4: show the result..."
print 'The classify accuracy is: %.2f%%' % (accuracy * 100)
测试非常简单，只需要在命令行中输入：
import kNN
kNN.testHandWritingClass()输出结果如下：
step 1: load data...
---Getting training set...
---Getting testing set...
step 2: training...
step 3: testing...
step 4: show the result...
The classify accuracy is: 98.84%
个人修改一些注释：
# -*- coding: utf-8 -*-
"""KNN: K Nearest Neighbors
Input: newInput:vector to compare to existing dataset(1xN)
dataSet:size m data set of known vectors(NxM)
labels:data set labels(1xM vector)
k:number of neighbors to use for comparison
Output: the most popular class labels
N为数据的维度
M为数据个数"""
from numpy import *
importoperator#create a dataset which contains 4 samples with 2 classes
defcreateDataSet():#create a matrix:each row as a sample
group = array([[1.0,0.9],[1.0,1.0],[0.1,0.2],[0.0,0.1]])#four samples and two classes
labels = ['A','A','B','B']returngroup,labels#classify using KNN
defKNNClassify(newInput, dataSet, labels, k):
numSamples= dataSet.shape[0] #shape[0] stands for the num of row 即是m
##step 1:calculate Euclidean distance
#tile(A,reps):Construct an array by repeating A reps times
#the following copy numSamples rows for dataSet
diff = tile(newInput,(numSamples,1)) - dataSet #Subtract element-wise
squaredDiff = diff ** 2 #squared for the subtract
squaredDist = sum(squaredDiff, axis = 1) #sum is performed by row
distance = squaredDist ** 0.5
##step 2:sort the distance
#argsort() return the indices that would sort an array in a ascending order
sortedDistIndices =argsort(distance)
classCount= {} #define a dictionary (can be append element)
for i inxrange(k):##step 3:choose the min k diatance
voteLabel =labels[sortedDistIndices[i]]##step 4:count the times labels occur
#when the key voteLabel is not in dictionary classCount,get()
#will return 0
#按classCount字典的第2个元素(即类别出现的次数)从大到小排序
#即classCount是一个字典，key是类型，value是该类型出现的次数，通过for循环遍历来计算
classCount[voteLabel] = classCount.get(voteLabel,0) + 1
##step 5:the max voted class will return
#eg:假设classCount={'A':3,'B':2}
maxCount =0for key,value inclassCount.items():if value >maxCount:
maxCount=value
maxIndex=keyreturn maxIndex本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
