from math import log import operator def createDataSet(): dataSet = [[0, 0, 0, 0, 'no'], [0, 0, 0, 1, 'no'], [0, 1, 0, 1, 'yes'], [0, 1, 1, 0, 'yes'], [0, 0, 0, 0, 'no'], [1, 0, 0, 0, 'no'], [1, 0, 0, 1, 'no'], [1, 1, 1, 1, 'yes'], [1, 0, 1, 2, 'yes'], [1, 0, 1, 2, 'yes'], [2, 0, 1, 2, 'yes'], [2, 0, 1, 1, 'yes'], [2, 1, 0, 1, 'yes'], [2, 1, 0, 2, 'yes'], [2, 0, 0, 0, 'no']] labels = ['年龄','有工作','有自己的房子','信贷情况'] return dataSet, labels def calcShannonEnt(dataSet): numEntires = len(dataSet) labelCounts = {} for featVec in dataSet: 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]) / numEntires shannonEnt -= prob * log(prob, 2) return shannonEnt def splitDataSet(dataSet, axis, value): retDataSet = [] for featVec in dataSet: if featVec[axis] == value: reducedFeatVec = featVec[:axis] reducedFeatVec.extend(featVec[axis+1:]) retDataSet.append(reducedFeatVec) return retDataSet def chooseBestFeatureToSplit(dataSet): numFeatures = len(dataSet[0]) - 1 baseEntropy = calcShannonEnt(dataSet) bestInfoGain = 0.0 bestFeature = -1 for i in range(numFeatures): featList = [example[i] for example in dataSet] uniqueVals = set(featList) 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 print("第%d个特征的增益为%.3f" % (i, infoGain)) if (infoGain > bestInfoGain): bestInfoGain = infoGain bestFeature = i return bestFeature def majorityCnt(classList): classCount = {} for vote in classList: if vote not in classCount.keys(): classCount[vote] = 0 classCount[vote] += 1 sortedClassCount = sorted(classCount.items(), key = operator. itemgetter(1), reverse = True) return sortedClassCount[0][0] def createTree(dataSet, labels, featLabels): classList = [example[-1] for example in dataSet] if classList.count(classList[0]) == len(classList): return classList[0] if len(dataSet[0]) == 1: return majorityCnt(classList) bestFeat = chooseBestFeatureToSplit(dataSet) bestFeatLabel = labels[bestFeat] featLabels.append(bestFeatLabel) 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, featLabels) return myTree def classify(inputTree, featLabels, testVec): firstStr = next(iter(inputTree)) 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__': dataSet, labels = createDataSet() featLabels = [] myTree = createTree(dataSet, labels, featLabels) print(myTree) testVec = [0, 1] result = classify(myTree, featLabels, testVec) if result == 'yes': print('放贷') if result == 'no': print('不放贷') 帮忙分析该代码