吴裕雄 python 机器学习-DMT（2）
import matplotlib.pyplot as plt decisionNode = dict(boxstyle="sawtooth", fc="0.8")
leafNode = dict(boxstyle="round4", fc="0.8")
arrow_args = dict(arrowstyle="<-") def getNumLeafs(myTree):
numLeafs = 0
for i in myTree.keys():
firstStr = i
break
secondDict = myTree[firstStr]
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
numLeafs += getNumLeafs(secondDict[key])
else: numLeafs +=1
return numLeafs def getTreeDepth(myTree):
maxDepth = 0
for i in myTree.keys():
firstStr = i
break
secondDict = myTree[firstStr]
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
thisDepth = 1 + getTreeDepth(secondDict[key])
else: thisDepth = 1
if thisDepth > maxDepth: maxDepth = thisDepth
return maxDepth def plotNode(nodeTxt, centerPt, parentPt, nodeType):
createPlot.ax1.annotate(nodeTxt, xy=parentPt, xycoords='axes fraction',xytext=centerPt, textcoords='axes fraction',va="center", ha="center", bbox=nodeType, arrowprops=arrow_args ) def plotMidText(cntrPt, parentPt, txtString):
xMid = (parentPt[0]-cntrPt[0])/2.0 + cntrPt[0]
yMid = (parentPt[1]-cntrPt[1])/2.0 + cntrPt[1]
createPlot.ax1.text(xMid, yMid, txtString, va="center", ha="center", rotation=30) def plotTree(myTree, parentPt, nodeTxt):
numLeafs = getNumLeafs(myTree)
depth = getTreeDepth(myTree)
for i in myTree.keys():
firstStr = i
break
cntrPt = (plotTree.xOff + (1.0 + float(numLeafs))/2.0/plotTree.totalW, plotTree.yOff)
plotMidText(cntrPt, parentPt, nodeTxt)
plotNode(firstStr, cntrPt, parentPt, decisionNode)
secondDict = myTree[firstStr]
plotTree.yOff = plotTree.yOff - 1.0/plotTree.totalD
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
plotTree(secondDict[key],cntrPt,str(key))
else:
plotTree.xOff = plotTree.xOff + 1.0/plotTree.totalW
plotNode(secondDict[key], (plotTree.xOff, plotTree.yOff), cntrPt, leafNode)
plotMidText((plotTree.xOff, plotTree.yOff), cntrPt, str(key))
plotTree.yOff = plotTree.yOff + 1.0/plotTree.totalD def createPlot(inTree):
fig = plt.figure(1, facecolor='white')
fig.clf()
axprops = dict(xticks=[], yticks=[])
createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)
#createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
plotTree.totalW = float(getNumLeafs(inTree))
plotTree.totalD = float(getTreeDepth(inTree))
plotTree.xOff = -0.5/plotTree.totalW; plotTree.yOff = 1.0;
plotTree(inTree, (0.5,1.0), '')
plt.show() def retrieveTree(i):
listOfTrees =[{'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}},
{'no surfacing': {0: 'no', 1: {'flippers': {0: {'head': {0: 'no', 1: 'yes'}}, 1: 'no'}}}}
]
return listOfTrees[i] thisTree = retrieveTree(0)
createPlot(thisTree)
thisTree = retrieveTree(1)
createPlot(thisTree)
import numpy as np
import operator as op
from math import log def calcShannonEnt(dataSet):
labelCounts = {}
for featVec in dataSet:
currentLabel = featVec[-1]
if(currentLabel not in labelCounts.keys()):
labelCounts[currentLabel] = 0
labelCounts[currentLabel] += 1
shannonEnt = 0.0
rowNum = len(dataSet)
for key in labelCounts:
prob = float(labelCounts[key])/rowNum
shannonEnt -= prob * log(prob,2)
return shannonEnt def splitDataSet(dataSet, axis, value):
retDataSet = []
for featVec in dataSet:
if(featVec[axis] == value):
reducedFeatVec = featVec[:axis]
reducedFeatVec.extend(featVec[axis+1:])
retDataSet.append(reducedFeatVec)
return retDataSet def chooseBestFeatureToSplit(dataSet):
numFeatures = np.shape(dataSet)[1]-1
baseEntropy = calcShannonEnt(dataSet)
bestInfoGain = 0.0
bestFeature = -1
for i in range(numFeatures):
featList = [example[i] for example in dataSet]
uniqueVals = set(featList)
newEntropy = 0.0
for value in uniqueVals:
subDataSet = splitDataSet(dataSet, i, value)
prob = len(subDataSet)/float(len(dataSet))
newEntropy += prob * calcShannonEnt(subDataSet)
infoGain = baseEntropy - newEntropy
if (infoGain > bestInfoGain):
bestInfoGain = infoGain
bestFeature = i
return bestFeature def majorityCnt(classList):
classCount={}
for vote in classList:
if(vote not in classCount.keys()):
classCount[vote] = 0
classCount[vote] += 1
sortedClassCount = sorted(classCount.items(), key=op.itemgetter(1), reverse=True)
return sortedClassCount[0][0] def createTree(dataSet,labels):
classList = [example[-1] for example in dataSet]
if(classList.count(classList[0]) == len(classList)):
return classList[0]
if len(dataSet[0]) == 1:
return majorityCnt(classList)
bestFeat = chooseBestFeatureToSplit(dataSet)
bestFeatLabel = labels[bestFeat]
myTree = {bestFeatLabel:{}}
del(labels[bestFeat])
featValues = [example[bestFeat] for example in dataSet]
uniqueVals = set(featValues)
for value in uniqueVals:
subLabels = labels[:]
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)
return myTree def classify(inputTree,featLabels,testVec):
for i in inputTree.keys():
firstStr = i
break
secondDict = inputTree[firstStr]
featIndex = featLabels.index(firstStr)
key = testVec[featIndex]
valueOfFeat = secondDict[key]
if isinstance(valueOfFeat, dict):
classLabel = classify(valueOfFeat, featLabels, testVec)
else:
classLabel = valueOfFeat
return classLabel data = open("D:\\LearningResource\\machinelearninginaction\\Ch03\\lenses.txt")
dataSet = [inst.strip().split("\t") for inst in data.readlines()]
print(dataSet)
print(np.shape(dataSet))
labels = ["age","prescript","astigmatic","tearRate"]
tree = createTree(dataSet,labels)
print(tree) import matplotlib.pyplot as plt decisionNode = dict(boxstyle="sawtooth", fc="0.8")
leafNode = dict(boxstyle="round4", fc="0.8")
arrow_args = dict(arrowstyle="<-") def getNumLeafs(myTree):
numLeafs = 0
for i in myTree.keys():
firstStr = i
break
secondDict = myTree[firstStr]
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
numLeafs += getNumLeafs(secondDict[key])
else: numLeafs +=1
return numLeafs def getTreeDepth(myTree):
maxDepth = 0
for i in myTree.keys():
firstStr = i
break
secondDict = myTree[firstStr]
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
thisDepth = 1 + getTreeDepth(secondDict[key])
else: thisDepth = 1
if thisDepth > maxDepth: maxDepth = thisDepth
return maxDepth def plotNode(nodeTxt, centerPt, parentPt, nodeType):
createPlot.ax1.annotate(nodeTxt, xy=parentPt, xycoords='axes fraction',xytext=centerPt, textcoords='axes fraction',va="center", ha="center", bbox=nodeType, arrowprops=arrow_args ) def plotMidText(cntrPt, parentPt, txtString):
xMid = (parentPt[0]-cntrPt[0])/2.0 + cntrPt[0]
yMid = (parentPt[1]-cntrPt[1])/2.0 + cntrPt[1]
createPlot.ax1.text(xMid, yMid, txtString, va="center", ha="center", rotation=30) def plotTree(myTree, parentPt, nodeTxt):
numLeafs = getNumLeafs(myTree)
depth = getTreeDepth(myTree)
for i in myTree.keys():
firstStr = i
break
cntrPt = (plotTree.xOff + (1.0 + float(numLeafs))/2.0/plotTree.totalW, plotTree.yOff)
plotMidText(cntrPt, parentPt, nodeTxt)
plotNode(firstStr, cntrPt, parentPt, decisionNode)
secondDict = myTree[firstStr]
plotTree.yOff = plotTree.yOff - 1.0/plotTree.totalD
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
plotTree(secondDict[key],cntrPt,str(key))
else:
plotTree.xOff = plotTree.xOff + 1.0/plotTree.totalW
plotNode(secondDict[key], (plotTree.xOff, plotTree.yOff), cntrPt, leafNode)
plotMidText((plotTree.xOff, plotTree.yOff), cntrPt, str(key))
plotTree.yOff = plotTree.yOff + 1.0/plotTree.totalD def createPlot(inTree):
fig = plt.figure(1, facecolor='white')
fig.clf()
axprops = dict(xticks=[], yticks=[])
createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)
#createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
plotTree.totalW = float(getNumLeafs(inTree))
plotTree.totalD = float(getTreeDepth(inTree))
plotTree.xOff = -0.5/plotTree.totalW; plotTree.yOff = 1.0;
plotTree(inTree, (0.5,1.0), '')
plt.show() createPlot(tree)
吴裕雄 python 机器学习-DMT（2）的更多相关文章
- 吴裕雄 python 机器学习-DMT（1）
import numpy as np import operator as op from math import log def createDataSet(): dataSet = [[1, 1, ...
- 吴裕雄 python 机器学习——分类决策树模型
import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...
- 吴裕雄 python 机器学习——回归决策树模型
import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...
- 吴裕雄 python 机器学习——线性判断分析LinearDiscriminantAnalysis
import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...
- 吴裕雄 python 机器学习——逻辑回归
import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...
- 吴裕雄 python 机器学习——ElasticNet回归
import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...
- 吴裕雄 python 机器学习——Lasso回归
import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, linear_model from s ...
- 吴裕雄 python 机器学习——岭回归
import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, linear_model from s ...
- 吴裕雄 python 机器学习——线性回归模型
import numpy as np from sklearn import datasets,linear_model from sklearn.model_selection import tra ...
随机推荐
- Centos7使用pxe安装KVM虚拟机
Centos7使用pxe安装KVM虚拟机 一.安装服务所需的软件 [root@localhost ~]yum install nginx dhcp vsftpd syslinux -y [root@l ...
- flask基础知识
关于flask框架的基础知识 相关基础知识:定义路由,定义参数,获取参数,重定向 简单易懂 ---hello.py # -*- coding: utf-8 -*- # Flask hello worl ...
- Linux RPS/RFS 实现原理浅析
本文快速解析一下RPS/RFS的基本原理. RPS-Receive Packet Steering 下面这个就是RPS的原理: 其实就是一个软件对CPU负载重分发的机制.其使能的作用点在CPU开始处 ...
- MySQL · 最佳实践 · 分区表基本类型
MySQL · 最佳实践 · 分区表基本类型 MySQL分区表概述 随着MySQL越来越流行,Mysql里面的保存的数据也越来越大.在日常的工作中,我们经常遇到一张表里面保存了上亿甚至过十亿的记录.这 ...
- JVM总结-异常处理
众所周知,异常处理的两大组成要素是抛出异常和捕获异常.这两大要素共同实现程序控制流的非正常转移. 抛出异常可分为显式和隐式两种.显式抛异常的主体是应用程序,它指的是在程序中使用“throw”关键字,手 ...
- 三种常见的Web安全问题
XSS漏洞 1.XSS简介 跨站脚本(cross site script)简称为XSS,是一种经常出现在web应用中的计算机安全漏洞,也是web中最主流的攻击方式. XSS是指恶意攻击者利用网站没有对 ...
- 微信小程序笔记<四>page.js —— 页面注册
小程序的每个页面都是独立的,每个页面都必须有 page.js 和 page.wxhl 文件,page.json 和 page.wxss 文件非必要文件,注意如果创建 page.json 则至少保证有一 ...
- 20165205 2017-2018-2 《Java程序设计》第七周学习总结
20165205 2017-2018-2 <Java程序设计>第七周学习总结 教材学习内容总结 下载XAMPP并完成配置 完成XAMPP与数据库的连接 学会创建一个数据库 学会用java语 ...
- 学习笔记：webpack
http://wiki.jikexueyuan.com/project/webpack-handbook/ Webpack 中文指南 http://www.itzjt.cc/2017/04/09/we ...
- Ubuntu系统安装
一:Ubuntu14.04 安装及使用:[1]制作安装U盘(选择USB-HDD+”并单击后, 一定要点“写入”,注意,“写入”是一个按钮) 以下是详细的连接步骤: https:// ...