python常用函数示例和knn分类的一个实例之海伦约会系统

创建一个数组，并得到这个数组中的每一行中的最小值和最大值。

>>> import numpy as no
>>> dataSet = no.array([[0.8,400,0.5],[12,134000,0.9],[0,20000,1.1],[67,32000,0.1]])
>>> dataSet
array([[  8.00000000e-01,   4.00000000e+02,   5.00000000e-01],
       [  1.20000000e+01,   1.34000000e+05,   9.00000000e-01],
       [  0.00000000e+00,   2.00000000e+04,   1.10000000e+00],
       [  6.70000000e+01,   3.20000000e+04,   1.00000000e-01]])
>>> dataSet.min(0)
array([  0.00000000e+00,   4.00000000e+02,   1.00000000e-01])
>>> minVals = dataSet.min(0)
>>> maxVals = dataSet.max(0)
>>> ranges = maxVals - minVals
>>> ranges
array([  6.70000000e+01,   1.33600000e+05,   1.00000000e+00])
>>> normDataSet = no.zeros(shape(dataSet))

创建一个和上面的dataSet一样的数组，并用0填充

>>> normDataSet = no.zeros(no.shape(dataSet))
>>> normDataSet
array([[ 0.,  0.,  0.],
       [ 0.,  0.,  0.],
       [ 0.,  0.,  0.],
       [ 0.,  0.,  0.]])

取出normDataSet中的行数和列数

m = dataSet.shape[0]#行数4
n = dataSet.shape[1]#列数3

>>> dataSet.min(0)<span style="font-family: Arial, Helvetica, sans-serif;">#取出每一列中的最小值</span>
array([  0.00000000e+00,   4.00000000e+02,   1.00000000e-01])
>>> minVals = dataSet.min(0)<span style="font-family: Arial, Helvetica, sans-serif;">#取出每一列中的最小值</span>
>>> maxVals = dataSet.max(0)<span style="font-family: Arial, Helvetica, sans-serif;">#取出每一行中的最小值</span>
>>> ranges = maxVals - minVals
>>> ranges
array([  6.70000000e+01,   1.33600000e+05,   1.00000000e+00])

>>> bbbb = no.tile(minVals,(m,1))#minVals的值上面有，m的值为4，创建m行个和minVals一样的数组
>>> bbbb
array([[  0.00000000e+00,   4.00000000e+02,   1.00000000e-01],
       [  0.00000000e+00,   4.00000000e+02,   1.00000000e-01],
       [  0.00000000e+00,   4.00000000e+02,   1.00000000e-01],
       [  0.00000000e+00,   4.00000000e+02,   1.00000000e-01]])
>>> minVals
array([  0.00000000e+00,   4.00000000e+02,   1.00000000e-01])

利用库matplotlib画图，并显示

>>> import matplotlib
>>> import matplotlib.pyplot as plt
f
>>> fig = plt.figure()#创建一个图
>>> ax = fig.add_subplot(111)#前俩1是比例，后一个1是位置，可以改成222，或223查看效果，一目了然
>>> ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*no.array(datingLabels),15.0*no.array(datingLabels))
<matplotlib.collections.PathCollection object at 0x0226EEB0>
>>> plt.show()

另附：机器学习那本书上的约会代码，创建knn.py文件，放入下面代码：

下面代码的作用是，利用knn近邻算法构建一个约会网站系统

之后对这个网站系统的错误率进行计算，并给定一个人的信息，对这个网站进行测试，看看是不是当事人（这里是海伦）喜欢的类型

海伦通过三个参数判断是不是自己喜欢的类型。先通过一个datingTestSet2.txt文件中的1000个人的信息中的900个作为训练，再用剩下的100个测试

这三个参数是ffMiles、percentTats、iceCream，每年飞行的里程数、玩视频游戏所消耗的百分比、每周消费冰淇淋的公升数

# -*- coding: cp936 -*-
#构造完整的k-临近算法之前，我们先编写一些基本的通用函数
from numpy import *
import operator
#这个函数作为简单的训练数据进行简单的测试下，由于 矩阵简单，容易理解，基本上和下面没什么关系。基本上也没什么用到

#主要用到他的是

import knn

group,labels = knn.createDataSet()

knn.classify0([0,0],group,labels,3)

就可以看到结果了，就是group中的每行和[0,0]作欧式距离。找最小的。

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
#k--近邻算法
#inX:每一行和它做欧式距离。将最小的找出来
def classify0(inX,dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount = {}
    for i in range(k):  #取前k个
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(),
     key = operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]

#用来处理输入格式的问题
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
	index += 1
    return returnMat,classLabelVector

#归一化特征值
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))#dataSet中的值减去每一列中的最小值
    normDataSet = normDataSet/tile(ranges,(m,1))
    return normDataSet, ranges, minVals
      
#为了测试分类效果，该函数是自包含的，可以在任何时候在Python运行环境中使用该函数测试分类器效果
#下面用它来测试约会网站的测试代码
def datingClassTest():
    hoRatio = 0.10
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        #normMat[i,:]一行的数据，normMat[numTestVecs:m,:]100--1000行的900条数据
        #用来训练，一行和所有的行做欧式距离，取前3个
        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],\
                                     datingLabels[numTestVecs:m],3)
        print('lsp: ',classifierResult)
        print('the classifier came back with: %d ,the real answer is: %d' % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[i]):errorCount +=1.0
        print('the totle error rate is : %f' % (errorCount/float(numTestVecs)))
        
        
#约会网站预测函数，输入一个人的信息，看海伦对他的兴趣度
def classifyPerson():
    resultList = ['not at all','in a small doses','in large doses']
    percentTats = float(raw_input("percentage of time spent playing video games?"))
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    iceCream = float(raw_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])

对约会网站的测试代码，查看这个分类的错误率：

>>> knn.datingClassTest()
('lsp: ', 3)
the classifier came back with: 3 ,the real answer is: 3
the totle error rate is : 0.000000
('lsp: ', 2)
the classifier came back with: 2 ,the real answer is: 2
the totle error rate is : 0.000000
('lsp: ', 1)
the classifier came back with: 1 ,the real answer is: 1
the totle error rate is : 0.000000
.
.
.
the classifier came back with: 2 ,the real answer is: 2
the totle error rate is : 0.040000
('lsp: ', 1)
the classifier came back with: 1 ,the real answer is: 1
the totle error rate is : 0.040000
('lsp: ', 3)
the classifier came back with: 3 ,the real answer is: 1
the totle error rate is : 0.050000
>>>

错误率0.5%，还不错

现在给我们一个人，让我们来看看这个人是否是海伦喜欢的类型：

测试代码如下

>>> knn.classifyPerson()
percentage of time spent playing video games?10
frequent flier miles earned per year?10000
liters of ice cream consumed per year？0.5
('you will probably like this person:', 'in a small doses')#小兴趣
>>> knn.classifyPerson()
percentage of time spent playing video games?10
frequent flier miles earned per year?30000
liters of ice cream consumed per year？0.5
('you will probably like this person:', 'in large doses')#特别有兴趣

这这里面会用到一个datingTestSet2.txt文件，可以去官网上下载，当然也可以向我要。不知道怎么传上来，就不传了。