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
- Linux下Mysql自启动
如果你都是按照默认配置安装的那么只要按照如下步骤就可以了 1.cp /usr/local/mysql/support-files/mysql.server /etc/init.d/mysql 将服 ...
- CS229 6.7 Neurons Networks whitening
PCA的过程结束后,还有一个与之相关的预处理步骤,白化(whitening) 对于输入数据之间有很强的相关性,所以用于训练数据是有很大冗余的,白化的作用就是降低输入数据的冗余,通过白化可以达到(1)降 ...
- TP5实现邮件发送（PHP 利用QQ邮箱发送邮件「PHPMailer」）
在 PHP 应用开发中,往往需要验证用户邮箱.发送消息通知,而使用 PHP 内置的 mail() 函数,则需要邮件系统的支持. 如果熟悉 IMAP/SMTP 协议,结合 Socket 功能就可以编写邮 ...
- ECharts学习记录
一.ECharts在GitHub的地址以及需要引入文件地址: 1.Github地址:https://github.com/ecomfe/echarts 2.官网下载文件地址:http://echart ...
- angularjs的cache
首先要引入angular-cookies.js插件 angular.module('app').service('cache', ['$cookies', function($cookies){ th ...
- LeetCode 771 宝石和石头
Input: J = "aA", S = "aAAbbbb" Output: 3 解:J为宝石字符串,S为包含宝石的字符串,J中的字母如果在S中出现数字就➕1 ...
- js提高篇
1定义一个方法 function aa(){alert(this)} 对于浏览器 这只是一个方法,那么this是什么的,this理所当然是document对象了..也就是说 打页面定义的方法 都是do ...
- 9. 一个list拆分成多个list返回
/** * @Title: splitList * @Description: 1个list分割成多个list * @param targe 原list * @para ...
- Android编程权威指南(第三版)- 2.8 挑战练习：添加后退按钮
package com.example.geoquiz; import android.support.v7.app.AppCompatActivity; import android.os.Bund ...
- 机器学习进阶-图像基本操作-数值计算 1.cv2.add(将图片进行加和) 2.cv2.resize（图片的维度变换） 3.cv2.addWeighted(将图片按照公式进行重叠操作)
1.cv2.add(dog_img, cat_img) # 进行图片的加和 参数说明: cv2.add将两个图片进行加和,大于255的使用255计数 2.cv2.resize(img, (500, ...