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
- 30 个 OpenStack 经典面试问题和解答
现在,大多数公司都试图将它们的 IT 基础设施和电信设施迁移到私有云, 如 OpenStack.如果你打算面试 OpenStack 管理员这个岗位,那么下面列出的这些面试问题可能会帮助你通过面试.-- ...
- es6(11)--Proxy,Reflect
//Proxy,Reflect { let obj={ time:'2018-06-25', name:'net', _r:123 }; let monitor = new Proxy(obj,{ / ...
- ELK集群部署实例（转）
转载自:http://blog.51cto.com/ckl893/1772287,感谢原博. 一.ELK说明 二.架构图 三.规划说明 四.安装部署nginx+logstash 五.安装部署redis ...
- mysql查询当前时间，一天内，一周，一个月内的sql语句
查询一天:select * from 表名 where to_days(时间字段名) = to_days(now()); 昨天 SELECT * FROM 表名 WHERE TO_DAYS( NOW( ...
- 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 ...
- postgresql copy的使用方式
方法一: 将数据库表复制到磁盘文件: copy "Test" to 'G:/Test.csv' delimiter ',' csv header encoding 'GBK'; 从 ...
- angularjs探秘<二>表达式、指令、数据绑定
距离第一篇笔记好久了,抽空把angular的笔记梳理梳理. ng-init:初始化指令,这里可以声明变量,且变量不用指定数据类型(类似js中的var用法). 数值变量与字符串相加默认做字符串拼接运算. ...
- [转]asp＋oracle分页
PageSize:每页显示的记录数.PageCount:根据用户设定好的PageSize和表中的总记录数,系统自动算出总页数.RecordCount:表中的总记录数.AbsolutePage:表示当前 ...
- 快速了解CSS3当中的HSLA 颜色值怎么算
CSS3文档中提到:(HSLA) H是色度,取值在0度~360度之间,0度是红色,120度是绿色,240度是蓝色.360度也是红色. S是饱和度,是色彩的纯度,是一个百分比的值,取值在0%~100%, ...
- 4.安装mitmproxy问题处理
上次进行到安装 证书出现问题: 1.主要原因是:对应python版本不一致 需要3.6以上的版本 才能在cmd黑窗口执行 mitmdump命令 生成证书 如图: windows 版本 双击安装 mit ...