决策树算法实现(python)
2014-09-15 10:55
309 查看
''' Created on Oct 12, 2010 Decision Tree Source Code for Machine Learning in Action Ch. 3 @author: cainiao ''' from math import log import operator def createDataSet(): dataSet = [[1, 1, 'yes'], [1, 1, 'yes'], [1, 0, 'no'], [0, 1, 'no'], [0, 1, 'no']] labels = ['no surfacing','flippers'] #change to discrete values return dataSet, labels def calcShannonEnt(dataSet): numEntries = len(dataSet) labelCounts = {} for featVec in dataSet: #the the number of unique elements and their occurance currentLabel = featVec[-1] if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0 labelCounts[currentLabel] += 1 shannonEnt = 0.0 for key in labelCounts: prob = float(labelCounts[key])/numEntries shannonEnt -= prob * log(prob,2) #log base 2 return shannonEnt def splitDataSet(dataSet, axis, value): retDataSet = [] for featVec in dataSet: if featVec[axis] == value: reducedFeatVec = featVec[:axis] #chop out axis used for splitting reducedFeatVec.extend(featVec[axis+1:]) retDataSet.append(reducedFeatVec) return retDataSet def chooseBestFeatureToSplit(dataSet): numFeatures = len(dataSet[0]) - 1 #the last column is used for the labels baseEntropy = calcShannonEnt(dataSet) bestInfoGain = 0.0; bestFeature = -1 for i in range(numFeatures): #iterate over all the features featList = [example[i] for example in dataSet]#create a list of all the examples of this feature uniqueVals = set(featList) #get a set of unique values newEntropy = 0.0 for value in uniqueVals: subDataSet = splitDataSet(dataSet, i, value) prob = len(subDataSet)/float(len(dataSet)) newEntropy += prob * calcShannonEnt(subDataSet) infoGain = baseEntropy - newEntropy #calculate the info gain; ie reduction in entropy if (infoGain > bestInfoGain): #compare this to the best gain so far bestInfoGain = infoGain #if better than current best, set to best bestFeature = i return bestFeature #returns an integer def majorityCnt(classList): classCount={} for vote in classList: if vote not in classCount.keys(): classCount[vote] = 0 classCount[vote] += 1 sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True) return sortedClassCount[0][0] def createTree(dataSet,labels): classList = [example[-1] for example in dataSet] if classList.count(classList[0]) == len(classList): return classList[0]#stop splitting when all of the classes are equal if len(dataSet[0]) == 1: #stop splitting when there are no more features in dataSet 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[:] #copy all of labels, so trees don't mess up existing labels myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels) return myTree def classify(inputTree,featLabels,testVec): firstStr = inputTree.keys()[0] secondDict = inputTree[firstStr] featIndex = featLabels.index(firstStr) key = testVec[featIndex] valueOfFeat = secondDict[key] if isinstance(valueOfFeat, dict): classLabel = classify(valueOfFeat, featLabels, testVec) else: classLabel = valueOfFeat return classLabel def storeTree(inputTree,filename): import pickle fw = open(filename,'w') pickle.dump(inputTree,fw) fw.close() def grabTree(filename): import pickle fr = open(filename) return pickle.load(fr)
相关文章推荐
- 机器学习实战笔记(三):决策树算法的Python实现
- 决策树算法实现应用【基于Python语言实现】
- How To Implement The Decision Tree Algorithm From Scratch In Python (从零开始在Python中实现决策树算法)
- 解读python如何实现决策树算法
- Python实现决策树算法
- 用python实现决策树算法
- python代码实现ID3决策树算法
- C4.5决策树算法(Python实现)
- Python实现决策树算法ID3
- 基于python的sklearn库的决策树算法基本实现
- Decision Tree 决策树算法Python实现
- 决策树算法 python实现
- 决策树算法Python代码实现
- 决策树算法--python实现
- python实现C4.5决策树算法
- python实现ID3决策树算法
- Python 递归实现决策树算法
- 机器学习之决策树算法python实现
- 基于ID3决策树算法的实现(Python版)
- Python实现决策树算法 C4.5和ID3算法