#-*-coding:utf-8-*-
from?numpy?import?*
import?math
import?copy
import?cPickle?as?pickle

class?C45DTree（object）:

????def?__init__（self）:
????????self.tree={}
????????self.dataSet=[]
????????self.labels=[]
????#數據導入函數
????def?loadDataSet（selfpathlabels）:
????????recordlist=[]
????????fp=open（path“rb“）
????????content=fp.read（）
????????fp.close（）
????????rowlist=content.splitlines（）
????????recordlist=[row.split（“\t“）?for?row?in?rowlist?if?row.strip（）]
????????self.dataSet=recordlist
????????self.labels=labels
????#執行決策樹函數
????def?train（self）:
????????????labels=copy.deepcopy（self.labels）
????????????self.tree=self.buildTree（self.dataSetlabels）

????#構建決策樹1111111111111111111111111111111111111111
????def?buildTree（selfdataSetlabels）:
????????cateList=[data[-1]?for?data?in?dataSet]
????????if?cateList.count（cateList[0]）==len（cateList）:
????????????return?cateList[0]
????????if?len（dataSet[0]）==1:
????????????return?self.maxCate（cateList）
????????#算法核心

????????bestFeatfeatValueList=self.getBestFeat（dataSet）
????????bestFeatLabel=labels[bestFeat]
????????tree={bestFeatLabel:{}}
????????del（labels[bestFeat]）
????????for?value?in?featValueList:
????????????sublabels=labels[:]
????????????#按最優特征列和值分割數據集
????????????splitDataset=self.splitDataSet（dataSetbestFeatvalue）
????????????subTree=self.buildTree（splitDatasetsublabels）
????????????tree[bestFeatLabel][value]=subTree
????????return?tree
????#計算出現次數最多的類別標簽
????def?maxCate（selfcatelist）:
????????items=dict（[（catelist.count（i）i）?for?i?in?catelist]）
????????return?items[max（items.keys（））]
????#計算最優特征11111111111111111111111111
????def?getBestFeat（selfdataSet）:
????????Num_Feats=len（dataSet[0][:-1]）
????????totality=len（dataSet）
????????baseEntropy=self.computeEntropy（dataSet）
????????ConditionEntroy=[]
????????slpitInfo=[]
????????allFeatVList=[]
????????for?f?in?xrange（Num_Feats）:
????????????featList=[example[f]?for?example?in?dataSet]
????????????[splitIfeatureValueList]=self.computeSplitInfo（featList）
????????????allFeatVList.append（featureValueList）
????????????slpitInfo.append（splitI）
????????????resultGain=0.0
????????????for?value?in?featureValueList:
????????????????subSet=self.splitDataSet（dataSetfvalue）
????????????????appearNum=float（len（subSet））
????????????????subEntropy=self.computeEntropy（subSet）
????????????????resultGain+=（appearNum/totality）*subEntropy
????????????ConditionEntroy.append（resultGain）
????????infoGainArray=baseEntropy*ones（Num_Feats）-array（ConditionEntroy）
????????infoGainRatio=infoGainArray/array（slpitInfo）
????????bestFeatureIndex=argsort（-infoGainRatio）[0]
????????return?bestFeatureIndexallFeatVList[bestFeatureIndex]

????#計算劃分信息
????def?computeSplitInfo（selffeatureVList）:
????????numEntries=len（featureVList）
????????featureVauleSetList=list（set（featureVList））
????????valueCounts=[featureVList.count（featVec）?for?featVec?in?featureVauleSetList]
????????pList=[float（item）/n

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件????????398??2018-04-22?20:45??決策樹（ID3和C45）\C45DTree\.idea\C4.5DTree.iml

?????文件????????213??2018-04-22?20:45??決策樹（ID3和C45）\C45DTree\.idea\misc.xml

?????文件????????782??2018-04-23?09:02??決策樹（ID3和C45）\C45DTree\.idea\modules.xml

?????文件??????30492??2018-04-23?10:05??決策樹（ID3和C45）\C45DTree\.idea\workspace.xml

?????文件???????5446??2018-04-23?09:21??決策樹（ID3和C45）\C45DTree\C45DTree.py

?????文件???????4963??2018-04-23?09:21??決策樹（ID3和C45）\C45DTree\C45DTree.pyc

?????文件????????807??2018-04-25?18:12??決策樹（ID3和C45）\C45DTree\C45Test.py

?????文件????????303??2018-04-22?21:22??決策樹（ID3和C45）\C45DTree\C45Train.py

?????文件????????195??2018-04-25?18:19??決策樹（ID3和C45）\C45DTree\data.tree

?????文件???????5066??2018-04-25?18:05??決策樹（ID3和C45）\C45DTree\dataset.dat

?????文件?????????54??2018-04-23?09:26??決策樹（ID3和C45）\C45DTree\test_data.dat

?????文件????????455??2018-04-25?18:05??決策樹（ID3和C45）\ID3DTree\.idea\ID3DTree.iml

?????文件????????213??2018-04-22?19:58??決策樹（ID3和C45）\ID3DTree\.idea\misc.xml

?????文件????????405??2018-04-25?18:05??決策樹（ID3和C45）\ID3DTree\.idea\modules.xml

?????文件??????26132??2018-04-25?19:31??決策樹（ID3和C45）\ID3DTree\.idea\workspace.xml

?????文件????????195??2018-04-25?18:16??決策樹（ID3和C45）\ID3DTree\data.tree

?????文件???????5066??2018-04-25?18:04??決策樹（ID3和C45）\ID3DTree\dataset.dat

?????文件???????3887??2018-04-22?20:43??決策樹（ID3和C45）\ID3DTree\ID3DTree.py

?????文件???????4232??2018-04-22?20:43??決策樹（ID3和C45）\ID3DTree\ID3DTree.pyc

?????文件????????806??2018-04-25?18:16??決策樹（ID3和C45）\ID3DTree\ID3Test.py

?????文件????????304??2018-04-25?17:59??決策樹（ID3和C45）\ID3DTree\ID3Train.py

?????目錄??????????0??2018-05-01?21:36??決策樹（ID3和C45）\C45DTree\.idea

?????目錄??????????0??2018-05-01?21:36??決策樹（ID3和C45）\ID3DTree\.idea

?????目錄??????????0??2018-05-01?21:36??決策樹（ID3和C45）\C45DTree

?????目錄??????????0??2018-05-01?21:36??決策樹（ID3和C45）\ID3DTree

?????目錄??????????0??2018-05-01?21:36??決策樹（ID3和C45）

-----------?---------??----------?-----??----

????????????????90414????????????????????26