决策树(Decision Tree)算法 python简单实现

""

"""

import numpy as np

from math import log

import operator

import json

#生成海洋生物数据

def createData():

data = [[1,1,'yes'],

[1,1,'yes'],

[1,0,'no'],

[0,1,'no'],

[0,1,'no']]

labels=['不浮出水面可生存','脚蹼']

return data, labels

#生产西瓜数据

# =============================================================================

# 色泽： 浅白 青绿 乌黑

# 根蒂： 蜷缩 稍蜷 硬挺

# 敲声： 浊响 沉闷 清脆

# 纹理： 清晰 稍糊 模糊

# 脐部： 凹陷 稍凹 平坦

# 触感： 硬滑 软粘

# =============================================================================

def createWatermelonData():

data = [['青绿','蜷缩','浊响','清晰','凹陷','硬滑','好'],

['乌黑','蜷缩','沉闷','清晰','凹陷','硬滑','好'],

['乌黑','蜷缩','浊响','清晰','凹陷','硬滑','好'],

['青绿','蜷缩','沉闷','清晰','凹陷','硬滑','好'],

['浅白','蜷缩','浊响','清晰','凹陷','硬滑','好'],

['青绿','稍蜷','浊响','清晰','稍凹','软粘','好'],

['乌黑','稍蜷','浊响','稍糊','稍凹','软粘','好'],

['乌黑','稍蜷','浊响','清晰','稍凹','硬滑','好'],

['乌黑','稍蜷','沉闷','稍糊','稍凹','硬滑','坏'],

['青绿','硬挺','清脆','清晰','平坦','软粘','坏'],

['浅白','硬挺','清脆','模糊','平坦','硬滑','坏'],

['浅白','蜷缩','浊响','模糊','平坦','软粘','坏'],

['青绿','稍蜷','浊响','稍糊','凹陷','硬滑','坏'],

['浅白','稍蜷','沉闷','稍糊','凹陷','硬滑','坏'],

['乌黑','稍蜷','浊响','清晰','稍凹','软粘','坏'],

['浅白','蜷缩','浊响','模糊','平坦','硬滑','坏'],

['青绿','蜷缩','沉闷','模糊','稍凹','硬滑','坏']]

labels=['色泽','根蒂','敲声','纹理','脐部','触感']

return data, labels

#计算熵

def calcEnt(data):

num = len(data)

labelCounts = {}

for item in data:

label = item[-1]

if label not in labelCounts.keys():labelCounts[label] = 0

labelCounts[label] += 1

ent = 0

for key in labelCounts:

prob = labelCounts[key]*1.0/num

ent -= prob * log(prob,2)

return ent

#划分数据 根据某一特征axis 取出该特征某一特定值value的数据

def splitData(dataSet,axis,value):

retData=[]

for item in dataSet:

if item[axis]==value:

newItem = item[:axis]

newItem.extend(item[axis+1:])

retData.append(newItem)

return retData

#从特种中选择最好的方式 增益最高

def chooseBestFeature(dataSet):

numFeat = len(dataSet[0]) - 1

## 初始化 信息熵 最佳信息增益 最佳特征

baseEnt = calcEnt(dataSet)

bestGain = 0

bestFeat = -1

for i in range(numFeat):

##获取第i个特征的所有取值

uniFeats = set([item[i] for item in dataSet])

newEnt = 0

##计算按第i个特征分类的熵

for value in uniFeats:

##第i个特征值 外汇常见问题的概率

subData = splitData(dataSet,i,value)

prob = float(len(subData))/len(dataSet)

newEnt += prob * calcEnt(subData)

gain = baseEnt - newEnt

if gain>bestGain:

bestGain = gain

bestFeat = i

return bestFeat

## 返回类别最高的分类

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]

#建立表

def createTree(dataSet,labels):

classList = [item[-1] for item in dataSet]

##只包含一种分类 返回该分类

if len(set(classList))==1:

return classList[0]

if len(dataSet[0])==1:

return majorityCnt(classList)

bestFeat = chooseBestFeature(dataSet)

bestFeatLabel = labels[bestFeat]

##以最佳分类标签为节点 以字典形式保存

myTree={bestFeatLabel:{}}

del(labels[bestFeat])

uniFeats = set([item[bestFeat] for item in dataSet])

for value in uniFeats:

subLabels = labels[:]

##根据不同的value 继续建立子分支

myTree[bestFeatLabel][value] = createTree(splitData(dataSet,bestFeat,value),subLabels)

return myTree

data,labels = createWatermelonData()

ret=createTree(data,labels)

print(json.dumps(ret,sort_keys=True, indent=2,ensure_ascii=False))

{

"纹理": {

"模糊": "坏",

"清晰": {

"根蒂": {

"硬挺": "坏",

"稍蜷": {

"色泽": {

"乌黑": {

"触感": {

"硬滑": "好",

"软粘": "坏"

}

},

"青绿": "好"

}

},

"蜷缩": "好"

}

},

"稍糊": {

"触感": {

"硬滑": "坏",

"软粘": "好"

}

}

}

}

原文链接：https://blog.csdn.net/zkt286468541/article/details/103372686