def main(): # createPlot() dataSet,labels = trees.createDataSet() labelsTmp = copy.deepcopy(labels) mytree = trees.createTree(dataSet,labelsTmp) print mytree print dataSet print labels print getNumLeafs(mytree) print getTreeDepth(mytree) # createPlot(mytree) print trees.classify(mytree,labels,[1,0])
sys.setdefaultencoding('utf8')
print(sys.getdefaultencoding())
#
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)
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':#test to see if the nodes are dictonaires, if not they are leaf nodes
plotTree(secondDict[key],cntrPt,str(key)) #recursion
else: #it's a leaf node print the leaf node
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
#if you do get a dictonary you know it's a tree, and the first element will be another dict
def createPlot(inTree):
fig = plt.figure(1, facecolor='white')
fig.clf()
axprops = dict(xticks=[], yticks=[])
createPlot.ax1 = plt.subplot(111, frameon=False, **axprops) #no ticks
#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()
# collect data
myDat, labels = trees.createDataSet()
mytree = trees.createTree(myDat, labels)
#visualize decision tree
createPlot(mytree)
import trees
myDat, lables = trees.createDataSet()
print("------ shannon ------")
print(myDat)
print(trees.calcShannonEnt(myDat))
# print("------ shannon after changed ------")
# myDat[0][-1] = 'maybe'
# print(myDat)
# print(trees.calcShannonEnt(myDat))
print("------ split data set ------")
print(trees.splitDataSet(myDat, 0, 1))
print(trees.splitDataSet(myDat, 0, 0))
print("------ choose best feature to split ------")
print(trees.chooseBestFeatureToSplit(myDat))
print("------ create tree ------")
tree = trees.createTree(myDat, lables)
print(tree)
print("------ test tree classify ------")
print(trees.classify(tree, ['no surfacing', 'flippers'], [1, 0]))
# -*- coding:utf-8 -*-
import trees
myData,myLabels = trees.createDataSet()
testLabels = myLabels.copy()
print ('myData is ' , myData)
#计算无序数据集的香农熵
#myShannonEnt = trees.calcShannonEnt(myData)
#print ('myShannonEnt is ' , myShannonEnt )
###测试划分数据集函数
#mySplitDat = trees.splitDataSet(myData, 1, 0)
#print ('mySplitDat is ' , mySplitDat )
#myBestData = trees.chooseBestFeatureToSplit(myData)
#print ('myBestData is ' , myBestData )
myTree = trees.createTree(myData, myLabels)
print ('myTree is ' ,myTree)
#测试训练集
print ('testLabels is ' ,testLabels)
testResult = trees.classify(myTree, testLabels, [1,1])
print ('testResult is ' ,testResult)
#trees.storeTree(myTree, 'classifierStorage.txt')
fromFileTree = trees.grabTree('classifierStorage.txt')
print ('fromFileTree is' , fromFileTree)
# 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()
# 划分数据集
retDataSet = trees.splitDataSet(myDat, 0, 5)
print(retDataSet)
bestFeature = trees.chooseBestFeatureToSplit(myDat)
print("best feature: %d" % bestFeature)
# -*- 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')
''' 决策树测试类 ''' import trees ''' dataSet,lables = trees.createDataSet() print(dataSet) print(lables) shannonEnt = trees.calcShannonEnt(dataSet) print(shannonEnt) ''' dataSet,labels = trees.createDataSet() tree = trees.createTree(dataSet,labels) d,l = trees.createDataSet() result = trees.classify(tree,l,[1,0]) print(result)
def testCreateDataSet():
myData, labels = trees.createDataSet()
# print myData
# print labels
return myData, labels
import trees as tr
"""
函数说明:按照给定特征划分数据集
Parameters:
dataSet - 待划分的数据集
axis - 划分数据集的特征
value - 需要返回的特征的值
Returns:
无
Modify:
2020-04-11
"""
def splitDataSet(dataSet, axis, value):
retDataSet = [] # 创建返回的数据集列表
for featVec in dataSet: # 遍历数据集
if featVec[axis] == value:
reducedFeatVec = featVec[:axis] # 去掉axis特征
reducedFeatVec.extend(featVec[axis + 1:]) # 将符合条件的添加到返回的数据集
retDataSet.append(reducedFeatVec)
return retDataSet # 返回划分后的数据集
if __name__ == '__main__':
dataSet, features = tr.createDataSet()
print(splitDataSet(dataSet, 0, 1))
print(splitDataSet(dataSet, 0, 0))
def main():
import trees
myDat, labels = trees.createDataSet()
myTree = trees.createTree(myDat, labels)
print(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))
inputTree - 已经生成的决策树
featLabels - 存储选择的最优特征标签
testVec - 测试数据列表，顺序对应最优特征标签
Returns:
classLabel - 分类结果
Modify:
2020-04-11
"""
def classify(inputTree, featLabels, testVec):
firstStr = next(iter(inputTree)) # 获取决策树结点
secondDict = inputTree[firstStr] # 下一个字典
featIndex = featLabels.index(firstStr)
for key in secondDict.keys():
if testVec[featIndex] == key:
if type(secondDict[key]).__name__ == 'dict':
classLabel = classify(secondDict[key], featLabels, testVec)
else:
classLabel = secondDict[key]
return classLabel
if __name__ == '__main__':
dataSet, labels = tr.createDataSet()
print(labels)
myTree = at.retriveTree(0)
print(myTree)
print(classify(myTree, labels, [1, 0]))
print(classify(myTree, labels, [1, 1]))
# -*- coding: utf-8 -*-
"""
Created on Wed May 23 11:35:31 2018
@author: lijie
"""
import trees
import treePlotter
def classify(inputTree, featLabels, testVec):
firstSide = list(inputTree.keys())
firstStr = firstSide[0]
secondDict = inputTree[firstStr]
featIndex = featLabels.index(firstStr)
for key in secondDict.keys():
if testVec[featIndex] == key:
if type(secondDict[key]).__name__ == 'dict':
classLabel = classify(secondDict[key], featLabels, testVec)
else:
classLabel = secondDict[key]
return classLabel
if __name__ == '__main__':
#test
tree = treePlotter.retrieveTree(0)
dataset, labels = trees.createDataSet()
a = classify(tree, labels, [1, 0])
print(a)
