ID3決策樹(shù)是以信息增益作為決策標(biāo)準(zhǔn)的一種貪心決策樹(shù)算法
# -*- coding: utf-8 -*- from numpy import * import math import copy import cPickle as pickle class ID3DTree(object): def __init__(self): # 構(gòu)造方法 self.tree = {} # 生成樹(shù) self.dataSet = [] # 數(shù)據(jù)集 self.labels = [] # 標(biāo)簽集 # 數(shù)據(jù)導(dǎo)入函數(shù) def loadDataSet(self, path, labels): recordList = [] fp = open(path, "rb") # 讀取文件內(nèi)容 content = fp.read() fp.close() rowList = content.splitlines() # 按行轉(zhuǎn)換為一維表 recordList = [row.split("\t") for row in rowList if row.strip()] # strip()函數(shù)刪除空格、Tab等 self.dataSet = recordList self.labels = labels # 執(zhí)行決策樹(shù)函數(shù) def train(self): labels = copy.deepcopy(self.labels) self.tree = self.buildTree(self.dataSet, labels) # 構(gòu)件決策樹(shù):穿件決策樹(shù)主程序 def buildTree(self, dataSet, lables): cateList = [data[-1] for data in dataSet] # 抽取源數(shù)據(jù)集中的決策標(biāo)簽列 # 程序終止條件1:如果classList只有一種決策標(biāo)簽,停止劃分,返回這個(gè)決策標(biāo)簽 if cateList.count(cateList[0]) == len(cateList): return cateList[0] # 程序終止條件2:如果數(shù)據(jù)集的第一個(gè)決策標(biāo)簽只有一個(gè),返回這個(gè)標(biāo)簽 if len(dataSet[0]) == 1: return self.maxCate(cateList) # 核心部分 bestFeat = self.getBestFeat(dataSet) # 返回?cái)?shù)據(jù)集的最優(yōu)特征軸 bestFeatLabel = lables[bestFeat] tree = {bestFeatLabel: {}} del (lables[bestFeat]) # 抽取最優(yōu)特征軸的列向量 uniqueVals = set([data[bestFeat] for data in dataSet]) # 去重 for value in uniqueVals: # 決策樹(shù)遞歸生長(zhǎng) subLables = lables[:] # 將刪除后的特征類(lèi)別集建立子類(lèi)別集 # 按最優(yōu)特征列和值分隔數(shù)據(jù)集 splitDataset = self.splitDataSet(dataSet, bestFeat, value) subTree = self.buildTree(splitDataset, subLables) # 構(gòu)建子樹(shù) tree[bestFeatLabel][value] = subTree return tree # 計(jì)算出現(xiàn)次數(shù)最多的類(lèi)別標(biāo)簽 def maxCate(self, cateList): items = dict([(cateList.count(i), i) for i in cateList]) return items[max(items.keys())] # 計(jì)算最優(yōu)特征 def getBestFeat(self, dataSet): # 計(jì)算特征向量維,其中最后一列用于類(lèi)別標(biāo)簽 numFeatures = len(dataSet[0]) - 1 # 特征向量維數(shù)=行向量維數(shù)-1 baseEntropy = self.computeEntropy(dataSet) # 基礎(chǔ)熵 bestInfoGain = 0.0 # 初始化最優(yōu)的信息增益 bestFeature = -1 # 初始化最優(yōu)的特征軸 # 外循環(huán):遍歷數(shù)據(jù)集各列,計(jì)算最優(yōu)特征軸 # i為數(shù)據(jù)集列索引:取值范圍0~(numFeatures-1) for i in xrange(numFeatures): uniqueVals = set([data[i] for data in dataSet]) # 去重 newEntropy = 0.0 for value in uniqueVals: subDataSet = self.splitDataSet(dataSet, i, value) prob = len(subDataSet) / float(len(dataSet)) newEntropy += prob * self.computeEntropy(subDataSet) infoGain = baseEntropy - newEntropy if (infoGain > bestInfoGain): # 信息增益大于0 bestInfoGain = infoGain # 用當(dāng)前信息增益值替代之前的最優(yōu)增益值 bestFeature = i # 重置最優(yōu)特征為當(dāng)前列 return bestFeature # 計(jì)算信息熵 # @staticmethod def computeEntropy(self, dataSet): dataLen = float(len(dataSet)) cateList = [data[-1] for data in dataSet] # 從數(shù)據(jù)集中得到類(lèi)別標(biāo)簽 # 得到類(lèi)別為key、 出現(xiàn)次數(shù)value的字典 items = dict([(i, cateList.count(i)) for i in cateList]) infoEntropy = 0.0 for key in items: # 香農(nóng)熵: = -p*log2(p) --infoEntropy = -prob * log(prob, 2) prob = float(items[key]) / dataLen infoEntropy -= prob * math.log(prob, 2) return infoEntropy # 劃分?jǐn)?shù)據(jù)集: 分割數(shù)據(jù)集; 刪除特征軸所在的數(shù)據(jù)列,返回剩余的數(shù)據(jù)集 # dataSet : 數(shù)據(jù)集; axis: 特征軸; value: 特征軸的取值 def splitDataSet(self, dataSet, axis, value): rtnList = [] for featVec in dataSet: if featVec[axis] == value: rFeatVec = featVec[:axis] # list操作:提取0~(axis-1)的元素 rFeatVec.extend(featVec[axis + 1:]) rtnList.append(rFeatVec) return rtnList # 存取樹(shù)到文件 def storetree(self, inputTree, filename): fw = open(filename,'w') pickle.dump(inputTree, fw) fw.close() # 從文件抓取樹(shù) def grabTree(self, filename): fr = open(filename) return pickle.load(fr)
分享題目:python實(shí)現(xiàn)ID3決策樹(shù)算法-創(chuàng)新互聯(lián)
文章源于:http://vcdvsql.cn/article44/jehee.html
成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián),為您提供企業(yè)建站、全網(wǎng)營(yíng)銷(xiāo)推廣、域名注冊(cè)、關(guān)鍵詞優(yōu)化、網(wǎng)頁(yè)設(shè)計(jì)公司、網(wǎng)站改版
聲明:本網(wǎng)站發(fā)布的內(nèi)容(圖片、視頻和文字)以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主,如果涉及侵權(quán)請(qǐng)盡快告知,我們將會(huì)在第一時(shí)間刪除。文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如需處理請(qǐng)聯(lián)系客服。電話:028-86922220;郵箱:631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載,或轉(zhuǎn)載時(shí)需注明來(lái)源: 創(chuàng)新互聯(lián)
猜你還喜歡下面的內(nèi)容