- 决策树(Decision tree) 是一种特殊的树结构,由一个决策图和可能的结果(例如成本和风险)组成,用来辅助决策。决策树仅有单一输出,通常该算法用于解决回归和分类问题。
机器学习中,决策树是一个预测模型,树中每个节点表示某个对象,而每个分叉路径则代表某个可能的属性值,而每个叶节点则对应从根节点到该叶节点所经历的路径所表示的对象的值。在每个节点上,我们根据可用的特征询问有关数据的问题。左右分支代表可能的答案。最终节点(即叶节点)对应于一个预测值。每个特征的重要性是通过自顶向下方法确定的。节点越高,其属性就越重要。
python实现代码如下:
#coding=utf-8
import operator
from math import log
import time
def createDataSet():
dataSet=[[1,1,'yes'],
[1,1,'yes'],
[1,0,'no'],
[0,1,'no'],
[0,1,'no']]
labels = ['no surfaceing','flippers']
return dataSet, labels
#计算香农熵,分两步,第一步计算频率,第二部根据公式计算香农熵
def calcShannonEnt(dataSet):
numEntries = len(dataSet)
labelCounts = {}
for feaVec in dataSet:
currentLabel = feaVec[-1]
if currentLabel not in labelCounts:
labelCounts[currentLabel] = 0
labelCounts[currentLabel] += 1
shannonEnt = 0.0
for key in labelCounts:
prob = float(labelCounts[key])/numEntries
shannonEnt -= prob * log(prob, 2)
return shannonEnt
#划分数据集,将满足X[aixs]==value的值都划分到一起,返回一个划分好的集合(不包括用来划分的aixs属性,因为不需要)
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
#选择最好的属性进行划分,思路很简单就是对每个属性都划分下,看哪个好。这里使用到了一个set来选取列表中唯一的元素,这是一中很快的方法
def chooseBestFeatureToSplit(dataSet):
numFeatures = len(dataSet[0]) - 1#因为数据集的最后一项是标签
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
if infoGain > bestInfoGain:
bestInfoGain = infoGain
bestFeature = i
return bestFeature
#因为我们递归构建决策树是根据属性的消耗进行计算的,所以可能会存在最后属性用完了,但是分类
#还是没有算完,这时候就会采用多数表决的方式计算节点分类
def majorityCnt(classList):
classCount = {}
for vote in classList:
if vote not in classCount.keys():
classCount[vote] = 0
classCount[vote] += 1
return max(classCount)
#基于递归构建决策树。这里的label更多是对于分类特征的名字,为了更好看和后面的理解。
def createTree(dataSet, labels):
classList = [example[-1] for example in dataSet]
if classList.count(classList[0]) ==len(classList):#类别相同则停止划分
return classList[0]
if len(dataSet[0]) == 1:#所有特征已经用完
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[:]#为了不改变原始列表的内容复制了一下
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,
bestFeat, value),subLabels)
return myTree
def main():
data,label = createDataSet()
#t1 = time.clock()
myTree = createTree(data,label)
#t2 = time.clock()
print(myTree)
#print('execute for ',t2-t1)
if __name__=='__main__':
main()
这里的数据比较简单。运行后在控制台输出:
{‘no surfaceing’: {0: ‘no’, 1: {‘flippers’: {0: ‘no’, 1: ‘yes’}}}}