def test1():
dataSet, labels = trees.createDataSet()
print(dataSet)
print(labels)
# print(trees.calcShannonEnt(dataSet))
# print(trees.splitDataSet(dataSet,0,0))
print(trees.chooseBestFeatureToSplit(dataSet))
dataset = []
#labels '年龄', '处方', '散光', '眼镜材质'
labels = ['age', 'prescript', 'astigmatic', 'tearRate']
for line in fr.readlines():
d = line.strip().split('\t')
dataset.append(d)
fr.close()
print dataset
print '\n'
print '数据集类的香农熵：'
print trees.calcShannonEnt(dataset)
print '\n'
bestFeatureColumn = trees.chooseBestFeatureToSplit(dataset)
print '数据集最佳分类的属性是：'
print labels[bestFeatureColumn]
print '\n'
print '决策树：'
Tree = trees.createTree(dataset, labels)
print Tree
firstFeature = Tree.keys()[0]
print firstFeature
firstFeatureValues = Tree[firstFeature].keys()
print firstFeatureValues
print '\n'
treePlotter.createPlot(Tree)
myDat, labels = trees.createDataSet() trees.calcShannonEnt(myDat) myDat[0][-1] = 'maybe' trees.calcShannonEnt(myDat) # 测试函数splitDataSet reload(trees) myDat, labels = trees.createDataSet() trees.splitDataSet(myDat, 0, 1) trees.splitDataSet(myDat, 0, 0) # 测试chooseBestFeatureToSplit reload(trees) myDat, labels = trees.createDataSet() trees.chooseBestFeatureToSplit(myDat) # 测试创建树 reload(trees) myDat, labels = trees.createDataSet() myTree = trees.createTree(myDat, labels) myTree # 测试matplotlib import treePlotter treePlotter.createPlot() # 测试获取叶子数量及树深度的函数 reload(treePlotter) treePlotter.retrieveTree(1) myTree = treePlotter.retrieveTree(0)
def testChooseBestFeatureToSplit(self): myDat,labels = TreesTestCase.createDataSet() featureIndex = trees.chooseBestFeatureToSplit(myDat) self.assertEqual(featureIndex, 0)
# -*- coding: utf-8 -*-
# os.chdir('D:\www\IdeaProject\MLiA_SourceCode\machinelearninginaction')
# print os.getcwd()
from numpy.ma import zeros, array
if __name__ == '__main__':
print 'hello'
import trees
import treePlotter
data,lables = trees.createDataSet()
print data
print lables
shannonEnt = trees.calcShannonEnt(data)
print shannonEnt
data[0][-1] ='maybe'
print trees.calcShannonEnt(data)
print data
print trees.chooseBestFeatureToSplit(data)
mytree = trees.createTree(data,lables)
print mytree
fr = open('lenses.txt')
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lensesLables = ['age','prescript','astigmatic','tearRate']
lensesTree = trees.createTree(lenses,lensesLables)
print lensesTree
treePlotter.createPlot(lensesTree)
# createPlot(thisTree)
myData, labels = trees.createDataSet()
print(myData)
print(trees.calcShannonEnt(myData))
print('---------------------------------')
print(trees.splitDataSet(myData, 0, 1))
print(trees.splitDataSet(myData, 0, 0))
print(trees.splitDataSet(myData, 1, 1))
print(trees.splitDataSet(myData, 1, 0))
print('---------------------------------')
myData, labels = trees.createDataSet()
print(myData)
print('第', trees.chooseBestFeatureToSplit(myData), '个特征是最好的用于划分数据集的特征')
print('---------------------------------')
myData, labels = trees.createDataSet()
myTree = trees.createTree(myData, labels)
print('myTree=', myTree)
print('---------------------------------')
# createPlot()
print('---------------------------------')
print(retrieveTree(1))
myTree = retrieveTree(0)
print(myTree)
print(getNumLeafs(myTree))
print(getTreeDepth(myTree))
print('---------------------------------')
myTree = retrieveTree(0)
createPlot(myTree)
# autor: zhumenger import trees myDat, lables = trees.createDataSet() print(myDat) print(lables) print(trees.calcShannonEnt(myDat))#返回期望值, 期望值越高，则混合的数据也越多 myDat[0][-1] = 'maybe' print(trees.calcShannonEnt(myDat)) #测试splitDataSet() print(trees.splitDataSet(myDat, 0, 1)) print(trees.splitDataSet(myDat, 0, 0)) trees.chooseBestFeatureToSplit(myDat) #寻找最好的划分方式 print(trees.chooseBestFeatureToSplit(myDat)) #得到按照第 0 个特征值进行划分的结果最好 #3-4： print(trees.createTree(myDat, lables))
#! /usr/bin/env python
# -*- coding: utf-8 -*-
import trees
if __name__ == '__main__':
data = trees.createDataSet1()
# print data
dataSet = data[0]
lables = data[1]
print dataSet
feature = trees.chooseBestFeatureToSplit(dataSet)
feature1 = trees.chooseBestFeatureToSplit1(dataSet)
print feature
print feature1
mytree = trees.createTree(dataSet, lables)
print mytree
print trees.splitDataSet(dataSet, 0, 1)
featLabels = ['outlook', 'temperature', 'humidity', 'windy']
testVec = [0, 1, 0, 0]
print trees.classify(mytree, featLabels, testVec)
entropy = DT.calcShannonEnt(myDat) # 0.9709505944546686
# Let’s make the data a little messier and see how the entropy changes
# myDat[0][-1]='maybe'
# entropy = DT.calcShannonEnt(myDat)
# """
# output:
# 1.3709505944546687
# """
splittedDat = DT.splitDataSet(myDat, 0,
1) # [[1, 'yes'], [1, 'yes'], [0, 'no']]
splittedDat = DT.splitDataSet(myDat, 0, 0) # [[1, 'no'], [1, 'no']]
bestFeature = DT.chooseBestFeatureToSplit(myDat) # 0
myTree = DT.createTree(
myDat, labels
) # {'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}
import treePlotter as TP
# TP.createPlot()
myTree = TP.retrieveTree(
0) #{'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}
n = TP.getNumLeafs(myTree) # 3
d = TP.getTreeDepth(myTree) # 2
TP.createPlot(myTree)
# -*- coding: utf-8 -*-
# 求使数据集熵最大的列
import trees
ds, ls = trees.createDataSet()
trees.chooseBestFeatureToSplit(ds)
# 创建决策树
import trees
ds, ls = trees.createDataSet()
trees.createTree(ds, ls)
# 绘制树
import treePlotter
mt = treePlotter.retrieveTree(0)
treePlotter.createPlot(mt)
# 利用决策树判断分类
import trees
import treePlotter
it = treePlotter.retrieveTree(0)
ds, ls = trees.createDataSet()
trees.classify(it, ls, [0, 0])
# 序列化与反序列化决策树
import trees
import treePlotter
it = treePlotter.retrieveTree(0)
trees.storeTree(it, 'classifierStorage.txt')
ot = trees.grabTree('classifierStorage.txt')
import trees import treePlotter myDat, labels = trees.createDataSet() print myDat print trees.calcShannonEnt(myDat) print trees.splitDataSet(myDat, 0, 1) print trees.splitDataSet(myDat, 0, 0) print trees.splitDataSet(myDat, 1, 1) print trees.chooseBestFeatureToSplit(myDat) print trees.createTree(myDat, labels) treePlotter.createPlot() print 'createPlot over' print treePlotter.retrieveTree(1) myTree = treePlotter.retrieveTree(0) print treePlotter.getNumLeafs(myTree) print treePlotter.getTreeDepth(myTree)
def testChooseBestFeatureToSplit(dataSet):
# print dataSet
print(trees.chooseBestFeatureToSplit(dataSet))
#!/usr/bin/env python
# -*- coding: UTF-8 -*-
# 代码来源：http://www.cnblogs.com/hantan2008/archive/2015/07/27/4674097.html
# 该代码实现了决策树算法分类（ID3算法）
import trees
import treePlotter
if __name__ == '__main__':
pass
myDat, labels = trees.createDataSetFromTXT("dataset.txt")
shan = trees.calcShannonEnt(myDat)
print shan
col = trees.chooseBestFeatureToSplit(myDat)
print col
Tree = trees.createTree(myDat, labels)
print Tree
treePlotter.createPlot(Tree)
if classList.count(classList[0])==len(classList):
return classList[0]#stop the splitting when class are same
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
if __name__ == "__main__":
import trees
myDat,labels=trees.createDataSet()
print(myDat,'\n',labels)
print("The shannonEnt is :",trees.calcShannonEnt(myDat))
print("\nsplitDataSet(myDat,1,1):\n",trees.splitDataSet(myDat,1,1))
#print("\nsplitDataSet(myDat,0,0):\n",trees.splitDataSet(myDat,0,0))
print("\nchooseBestFeatureToSplit: ",trees.chooseBestFeatureToSplit(myDat))
myTree=createTree(myDat,labels)
print("\nmyTree:\n",myTree)
from numpy import array import trees reload(trees) myDat,labels=trees.createDataSet() print myDat print trees.calcShannonEnt(myDat) print trees.splitDataSet(myDat,0,1) print trees.splitDataSet(myDat,0,0) print trees.chooseBestFeatureToSplit(myDat) myTree = trees.createTree(myDat,labels) print myTree
import trees mydata,features = trees.createDataSet() print(mydata) print(features) print(trees.calcShannonEnt(mydata)) ''' mydata[0][-1] = 'maybe' print(trees.calcShannonEnt(mydata)) ''' #print(trees.splitDataSet(mydata,0,1)) index = trees.chooseBestFeatureToSplit(mydata) #print(index) ''' mytree = trees.createTree(mydata,features) print(mytree) ''' import treePlotter ''' mytree = treePlotter.retrieveTree(0) treePlotter.createPlot(mytree) mytree['no surfacing'][3] = 'maybe' treePlotter.createPlot(mytree) ''' mytree = treePlotter.retrieveTree(0) print(trees.classify(mytree,features,[0,0])) print(trees.classify(mytree,features,[1,1])) trees.storeTree(mytree, 'classifier.txt')
import trees a1, a2 = trees.createDataSet() b1 = trees.chooseBestFeatureToSplit(a1) #print(b1) #核心就是匹配那个香浓值最接近选哪个
import treePlotter # homedir= os.getcwd()+'/machinelearninginaction/ch03/' #绝对路径 homedir = '' #相对路径 #3.1.1 信息增益 myDat, labels = trees.createDataSet() print "计算香农熵:", trees.calcShannonEnt(myDat) myDat[0][-1] = ' maybe' print "计算香农熵:", trees.calcShannonEnt(myDat) #3.1.2 划分数据集 myDat, labels = trees.createDataSet() trees.splitDataSet(myDat, 0, 1) trees.splitDataSet(myDat, 0, 0) print "选择最好的数据集划分方式:", trees.chooseBestFeatureToSplit(myDat) #3.1.3 递归构建决策树 myDat, labels = trees.createDataSet() myTree = trees.createTree(myDat, labels) print "myTree:", myTree #3.2.1 Matplotlib注解 treePlotter.createPlot() #3.2.2 构造注解树 treePlotter.retrieveTree(1) myTree = treePlotter.retrieveTree(0) print "获取叶节点的数目:", treePlotter.getNumLeafs(myTree) print "获取树的层数:", treePlotter.getTreeDepth(myTree) treePlotter.createPlot(myTree)
def test_bestChoose(self):
dataSet, label = trees.createDataSet()
print("\n dataSet == %s" % (dataSet))
bestFeature = trees.chooseBestFeatureToSplit(dataSet)
print("\n bestFeature == %s" % (bestFeature))
#内容：1.读取文档数据生成数据集，2.利用数据集生成决策树，3.绘制决策树的图形 #时间：2018年5月30日 6月6日添加备注 import trees import treePlotter #11111111111111111111111111111111111111111111111111111 #利用手动创建的数据集生成树，绘制树的图形，测试程序过程步骤 #输出手动创建的数据集，计算香农熵 myDat,labels=trees.createDataSet() print "myDat 数据集是：",myDat print "\nlabels 标签是:",labels rawCalc =trees.calcShannonEnt(myDat) print "\ncalcShannonEnt(myDat) 数据集的原始熵是：",rawCalc print "\ntrees.splitDataSet( myDat,1,1)将数据集的按 特征[1]=1(即 flippers==1) 提取出来的矩阵是:",trees.splitDataSet(myDat,1,1) # bestLabel = trees.chooseBestFeatureToSplit(myDat) print "\nchooseBestFeatureToSplit(myDat) 数据集的bestLabel最好特征的[下标]是：",bestLabel,"\tlabels[bestLabel]最好特征是：",labels[bestLabel] # myTree = trees.createTree(myDat,labels) print "\ntrees.createTree(myDat,labels) 根据数据集创建的树是:", myTree #读取预先存储的树[0] 并绘制图形 print "\n读取预先存储的树[0] 并绘制出第一个图形:" myTree0 = treePlotter.retrieveTree(0) treePlotter.createPlot(myTree0) #读取预先存储的树[1] 并绘制图形 print "\n读取预先存储的树[1] 并绘制出第二个图形:" myTree1 = treePlotter.retrieveTree(1) treePlotter.createPlot(myTree1) #change one date in "no surfacing" #and print
