def tests():
dataSet, labels = trees.createDataSet()
print dataSet
print trees.calcShannonEnt(dataSet)
myTree = trees.createTree(dataSet, labels)
print myTree, labels
print trees.classify(myTree, labels, [1, 0])
print trees.classify(myTree, labels, [1, 1])
print trees.classify(myTree, labels, [0, 0])
print trees.classify(myTree, labels, [0, 1])
def test_shannon(self):
dataSet, labels = trees.createDataSet()
print("\n dataSet == %s" % (dataSet))
shannon = trees.calcShannonEnt(dataSet)
print("\n shannon == %s" % (shannon))
# 不确定性越大，熵越大
dataSet = [[1, 1, 'yes'], [1, 1, 'yes'], [1, 0, 'yes?no'],
[0, 1, 'no'], [0, 1, 'no']]
shannon = trees.calcShannonEnt(dataSet)
print("\n shannon == %s" % (shannon))
def main():
myDat, labels = trees.createDataSet()
print 'create data:'
print myDat
shan = trees.calcShannonEnt(myDat)
print 'calc shan:'
print shan
myDat[0][-1] = 'maybe'
shan1 = trees.calcShannonEnt(myDat)
print 'change data and calc shan1:'
print shan1
def chooseBestFeatureToSplit(dataSet):
numFeatures = len(dataSet[0]) - 1 # 特征数量
baseEntropy = tr.calcShannonEnt(dataSet) # 计算数据集的香农熵
bestInfoGain = 0.0 # 信息增益
bestFeature = -1 # 最优特征的索引值
for i in range(numFeatures): # 遍历所有特征
# 获取dataSet的第i个所有特征
featList = [example[i] for example in dataSet]
uniqueVals = set(featList) # 创建set集合{},元素不可重复
newEntropy = 0.0 # 经验条件熵
for value in uniqueVals: # 计算信息增益
subDataSet = sd.splitDataSet(dataSet, i, value) # subDataSet划分后的子集
prob = len(subDataSet) / float(len(dataSet)) # 计算子集的概率
newEntropy += prob * tr.calcShannonEnt(subDataSet) # 根据公式计算经验条件熵
infoGain = baseEntropy - newEntropy # 信息增益
print("第%d个特征的增益为%.3f" % (i, infoGain)) # 打印每个特征的信息增益
if (infoGain > bestInfoGain): # 计算信息增益
bestInfoGain = infoGain # 更新信息增益，找到最大的信息增益
bestFeature = i # 记录信息增益最大的特征的索引值
return bestFeature # 返回信息增益最大的特征的索引值
#
fr = open('lensesCN.txt')
lenses = [unicode(inst, 'utf-8').strip().strip().split('\t') for inst in fr.readlines()]
#lensesLabels = ["年龄组" , "规定", "闪光", "泪液扫除率"]
lensesLabels = ['age' , 'prescript', 'astigmatic', 'tearRate']
lensesTree = tr.createTree(lenses,lensesLabels)
print(lensesTree)
tp.createPlot(lensesTree)
dataSet, labels = tr.createDataSet()
shannonEnt = tr.calcShannonEnt(dataSet)
print(shannonEnt)
print(tp.retrieveTree(1))
myTree = tp.retrieveTree(0)
numLeafs = tp.getNumLeafs(myTree)
treeDepth = tp.getTreeDepth(myTree)
print(numLeafs)
print(treeDepth)
myTree = tp.retrieveTree(0)
tp.createPlot(myTree)
import trees mydat, labels = trees.createDataSet() a = trees.calcShannonEnt(mydat) print(mydat) print(labels) print(a)
import trees myDat, labels = trees.createDataSet() print(myDat) print(labels) print(trees.calcShannonEnt(myDat)) print(trees.splitDataSet(myDat, 0, 0)) print(trees.createTree(myDat, labels))
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')
#!/usr/bin/python # -*- coding:utf-8 -*- import os import trees 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
import trees myDat, labels = trees.createDataSet() print(trees.calcShannonEnt(myDat))
# coding=utf-8 import trees import treePlotter dateset, labels = trees.createDataSet() print dateset print labels shannon = trees.calcShannonEnt(dateset) print shannon print '--条件熵' ha = trees.calcShannonEnt(trees.splitDataSet(dateset, 0, 5)) hb = trees.calcShannonEnt(trees.splitDataSet(dateset, 0, 3)) hc = trees.calcShannonEnt(trees.splitDataSet(dateset, 0, 1)) hxy = 1.0 / 3 * ha + 1.0 / 4 * hb + 5.0 / 12 * hc print ha, hb, hc print hxy print '--信息增益' ig = shannon - hxy print ig print '--找到最佳分类特征' feature = trees.chooseBestFeatureToSplit(dateset) print labels[feature] print '--创建决策树' labelsCopy = labels[:] tree = trees.createTree(dateset, labelsCopy) print tree # print '--画图' # treePlotter.createPlot(tree) print '--用决策树测试数据' #mytree = treePlotter.retrieveTree(0) testdata = [4, 4, 1, 'cha']
import trees as t data_set, labels = t.createDataSet() data_set[0][-1] = 'test' # entropy more bigger, mix of classes more higher print(t.calcShannonEnt(data_set)) print(t.calcShannonEnt([[1,0,'yes'], [1,1,'no']]))
import trees mat, labels = trees.createDataSet() ent = trees.calcShannonEnt(mat) print(ent) mat[0][-1] = 'maybe' ent = trees.calcShannonEnt(mat) print(ent) # mat, labels = trees.createDataSet() # print(mat) # split1 = trees.splitDataSet(mat, 0, 1) # print(split1) # split2 = trees.splitDataSet(mat, 0, 0) # print(split2) # mat, labels = trees.createDataSet() # feat = trees.chooseBestFeatureToSplit(mat) # print(feat)
# coding=utf-8 #程序说明 #标题：决策树的生成和绘制 #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)
def testCalcShannonEnt(self):
myDat,labels = TreesTestCase.createDataSet()
entropy = trees.calcShannonEnt(myDat)
ent = float('%0.3f' % entropy)
self.assertEqual(ent, 0.971)
def testCalcShannonEnt(dataSet):
shannonEnt = trees.calcShannonEnt(dataSet)
print(shannonEnt)
return shannonEnt
#!/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)
# This is a sample Python script.
# Press Shift+F10 to execute it or replace it with your code.
# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
import trees
# Press the green button in the gutter to run the script.
if __name__ == '__main__':
myDat, labels = trees.createDataSet()
sh = trees.calcShannonEnt(myDat)
print(sh)
# 熵越高，说明混合的数据也越多
# 修改数据集，添加类型'maybe'
myDat[0][-1] = 'maybe'
sh = trees.calcShannonEnt(myDat)
print(sh)
# 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))
# -*- 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)
import trees a1, a2 = trees.createDataSet() a3 = trees.calcShannonEnt(a1) print(a3)
import trees
import treePlotter
fr = open('lenses.txt')
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'
# -*- coding: utf-8 -*- import trees dataSet, labels = trees.createDataSet() print dataSet print labels #计算熵 print trees.calcShannonEnt(dataSet)#0.970950594455 dataSet[0][-1] = 'maybe' print dataSet print trees.calcShannonEnt(dataSet)#1.37095059445 #熵越大，则混合的数据越多 #还原 dataSet[0][-1] = 'yes' print dataSet #[[1, 1, 'yes'], [1, 1, 'yes'], [1, 0, 'no'], [0, 1, 'no'], [0, 1, 'no']] #划分数据集 #当第0列，值为0 的实例 print trees.splitDataSet(dataSet, 0, 0) #[[1, 'no'], [1, 'no']] #当第0列，值为1 的实例 print trees.splitDataSet(dataSet, 0, 1)
# -*- coding: utf-8 -*-
import trees
dataMat, labels = trees.createDataSet2()
print(dataMat)
result = trees.calcShannonEnt(dataMat)
print("result is: %.2f" % result)
import trees as DT
myDat, labels = DT.createDataSet()
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
from imp import reload import trees myDat, labels = trees.createDataSet() trees.calcShannonEnt(myDat) myTree = trees.createTree(myDat, labels) import treePlotter treePlotter.createPlot()
#coding=utf-8 __author__ = 'baconLIN' import trees myDat,labels=trees.createDataSet() print(myDat) shannonEnt = trees.calcShannonEnt(myDat) print(shannonEnt) mySplit1 = trees.splitDataSet(myDat,0,1) print mySplit1 shannonEntSplit1 = trees.calcShannonEnt(mySplit1) print(shannonEntSplit1) mySplit2 = trees.splitDataSet(myDat,0,0) print mySplit2 shannonEntSplit2 = trees.calcShannonEnt(mySplit2) print(shannonEntSplit2) mySplit3 = trees.splitDataSet(myDat,1,1) print mySplit3 shannonEntSplit3 = trees.calcShannonEnt(mySplit3) print(shannonEntSplit3) bestFeature = trees.chooseBestFeatureToSplit(myDat) print(bestFeature) myTree = trees.createTree(myDat,labels) print(myTree) import treePlotter myTree2 = treePlotter.retrieveTree(0)