决策树挑出好西瓜

一、决策树

1.介绍

决策树是在已知各种情况发生概率的基础上，通过构成决策树来求取净现值的期望值大于等于零的概率，评价项目风险，判断其可行性的决策分析方法，是直观运用概率分析的一种图解法

主要算法有：ID3、C4.5、CART
2.决策事件处理流程
（1）构建策略
随着树的增加，结点的熵迅速降低。熵降低的速度越快越好，可以得到高度最矮的决策树

（2）决策树
决策树的基本流程遵循分而治之的策略
（3）伪代码

3.原理
对于一个分支结点，如果该结点所包含的样本都属于同一类，那么它的纯度为1，而纯度越高越好，尽可能多的样本属于同一类，样本集合D中第k类样本所占比例为pk，D的信息熵定义为

基于信息增益的最优属性划分原则——信息增益准则，对可取值数据较多的属性有所偏好

二、ID3决策树

（1）建立决策树
导入包

import pandas as pd
import numpy as np
from collections import Counter
from math import log2

获取数据

#数据获取与处理
def getData(filePath):
    data = pd.read_excel(filePath)
    return data

def dataDeal(data):
    dataList = np.array(data).tolist()
    dataSet = [element[1:] for element in dataList]
    return dataSet

获取属性

#获取属性名称
def getLabels(data):
    labels = list(data.columns)[1:-1]
    return labels

获取类别

#获取类别标记
def targetClass(dataSet):
    classification = set([element[-1] for element in dataSet])
    return classification

叶节点

#将分支结点标记为叶结点，选择样本数最多的类作为类标记
def majorityRule(dataSet):
    mostKind = Counter([element[-1] for element in dataSet]).most_common(1)
    majorityKind = mostKind[0][0]
    return majorityKind

计算信息熵

#计算信息熵
def infoEntropy(dataSet):
    classColumnCnt = Counter([element[-1] for element in dataSet])
    Ent = 0
    for symbol in classColumnCnt:
        p_k = classColumnCnt[symbol]/len(dataSet)
        Ent = Ent-p_k*log2(p_k)
    return Ent

子数据集构建

#子数据集构建
def makeAttributeData(dataSet,value,iColumn):
    attributeData = []
    for element in dataSet:
        if element[iColumn]==value:
            row = element[:iColumn]
            row.extend(element[iColumn+1:])
            attributeData.append(row)
    return attributeData

计算信息增益

#计算信息增益
def infoGain(dataSet,iColumn):
    Ent = infoEntropy(dataSet)
    tempGain = 0.0
    attribute = set([element[iColumn] for element in dataSet])
    for value in attribute:
        attributeData = makeAttributeData(dataSet,value,iColumn)
        tempGain = tempGain+len(attributeData)/len(dataSet)*infoEntropy(attributeData)
        Gain = Ent-tempGain
    return Gain

选择最优属性

#选择最优属性                
def selectOptimalAttribute(dataSet,labels):
    bestGain = 0
    sequence = 0
    for iColumn in range(0,len(labels)):#不计最后的类别列
        Gain = infoGain(dataSet,iColumn)
        if Gain>bestGain:
            bestGain = Gain
            sequence = iColumn
        print(labels[iColumn],Gain)
    return sequence#

建立决策树

#建立决策树
def createTree(dataSet,labels):
    classification = targetClass(dataSet) #获取类别种类（集合去重）
    if len(classification) == 1:
        return list(classification)[0]
    if len(labels) == 1:
        return majorityRule(dataSet)#返回样本种类较多的类别
    sequence = selectOptimalAttribute(dataSet,labels)
    print(labels)
    optimalAttribute = labels[sequence]
    del(labels[sequence])
    myTree = {optimalAttribute:{}}
    attribute = set([element[sequence] for element in dataSet])
    for value in attribute:
        
        print(myTree)
        print(value)
        subLabels = labels[:]
        myTree[optimalAttribute][value] =  \
                createTree(makeAttributeData(dataSet,value,sequence),subLabels)
    return myTree

主函数

def main():
    filePath = 'watermalon.xls'
    data = getData(filePath)
    dataSet = dataDeal(data)
    labels = getLabels(data)
    myTree = createTree(dataSet,labels)
    return myTree

生成

if __name__ == '__main__':
    myTree = main()

结果

二、绘制决策树

#使用Matlotlib绘制决策树
import matplotlib.pyplot as plt

#设置文本框和箭头格式
decisionNode = dict(boxstyle = "sawtooth", fc = "0.8")
leafNode = dict(boxstyle = "round4", fc = "0.8")
arrow_args = dict(arrowstyle = "<-")
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['font.family'] = 'sans-serif'

#画节点
def plotNode(nodeTxt, centerPt, parentPt, nodeType):
    createPlot.ax1.annotate(nodeTxt, xy = parentPt,\
    xycoords = "axes fraction", xytext = centerPt, textcoords = 'axes fraction',\
    va = "center", ha = "center", bbox = nodeType, arrowprops = arrow_args)
    
#获取决策树的叶子节点数
def getNumLeafs(myTree):
    leafNumber = 0
    firstStr = list(myTree.keys())[0]
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        if(type(secondDict[key]).__name__ == 'dict'):
            leafNumber = leafNumber + getNumLeafs(secondDict[key])
        else:
            leafNumber += 1
    return leafNumber

#获取决策树的高度（递归）
def getTreeDepth(myTree):
    maxDepth = 0
    firstStr = list(myTree.keys())[0]
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        #test to see if the nodes are dictonaires, if not they are leaf nodes
        if type(secondDict[key]).__name__=='dict':
            thisDepth = 1 + getTreeDepth(secondDict[key])
        else:   thisDepth = 1
        if thisDepth > maxDepth: maxDepth = thisDepth
    return maxDepth

#在父子节点添加信息
def plotMidText(cntrPt, parentPt, txtString):
    xMid = (parentPt[0]-cntrPt[0])/2.0 + cntrPt[0]
    yMid = (parentPt[1]-cntrPt[1])/2.0 + cntrPt[1]
    createPlot.ax1.text(xMid, yMid, txtString, va="center", ha="center", rotation=30)

#画树
def plotTree(myTree, parentPt, nodeTxt):#if the first key tells you what feat was split on
    numLeafs = getNumLeafs(myTree)  #this determines the x width of this tree
    depth = getTreeDepth(myTree)
    firstStr = list(myTree.keys())[0]     #the text label for this node should be this
    cntrPt = (plotTree.xOff + (1.0 + float(numLeafs))/2.0/plotTree.totalW, plotTree.yOff)
    plotMidText(cntrPt, parentPt, nodeTxt)
    plotNode(firstStr, cntrPt, parentPt, decisionNode)
    secondDict = myTree[firstStr]
    plotTree.yOff = plotTree.yOff - 1.0/plotTree.totalD
    for key in secondDict.keys():
        if type(secondDict[key]).__name__=='dict':
            plotTree(secondDict[key],cntrPt,str(key))        #recursion
        else:   #it's a leaf node print the leaf node
            plotTree.xOff = plotTree.xOff + 1.0/plotTree.totalW
            plotNode(secondDict[key], (plotTree.xOff, plotTree.yOff), cntrPt, leafNode)
            plotMidText((plotTree.xOff, plotTree.yOff), cntrPt, str(key))
    plotTree.yOff = plotTree.yOff + 1.0/plotTree.totalD


#画布初始化
def createPlot(inTree):
    fig = plt.figure(1, facecolor='white')
    fig.clf()
    axprops = dict(xticks=[], yticks=[])
    createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)    #no ticks
    #createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
    plotTree.totalW = float(getNumLeafs(inTree))
    plotTree.totalD = float(getTreeDepth(inTree))
    plotTree.xOff = -0.5/plotTree.totalW; plotTree.yOff = 1.0;
    plotTree(inTree, (0.5,1.0), '')
    plt.show()

```cpp
在这里插入代码片def main():
    #createPlot()
    print(getTreeDepth(myTree)) #输出数的深度
    print(getNumLeafs(myTree))  #输出数的叶子个数
    createPlot(myTree)

main()

三、sk-learn实现决策树

#导入相关库
import pandas as pd
import graphviz 
from sklearn.model_selection import train_test_split
from sklearn import tree

f = open('watermalon.csv','r',encoding='utf-8')
data = pd.read_csv(f)

x = data[["色泽","根蒂","敲声","纹理","脐部","触感"]].copy()
y = data['好瓜'].copy()
print(data)

数据转换

#将特征值数值化
x = x.copy()
for i in ["色泽","根蒂","敲声","纹理","脐部","触感"]:
    for j in range(len(x)):
        if(x[i][j] == "青绿" or x[i][j] == "蜷缩" or data[i][j] == "浊响" \
           or x[i][j] == "清晰" or x[i][j] == "凹陷" or x[i][j] == "硬滑"):
            x[i][j] = 1
        elif(x[i][j] == "乌黑" or x[i][j] == "稍蜷" or data[i][j] == "沉闷" \
           or x[i][j] == "稍糊" or x[i][j] == "稍凹" or x[i][j] == "软粘"):
            x[i][j] = 2
        else:
            x[i][j] = 3
            
y = y.copy()
for i in range(len(y)):
    if(y[i] == "是"):
        y[i] = int(1)
    else:
        y[i] = int(-1) 
#需要将数据x，y转化好格式，数据框dataframe，否则格式报错
x = pd.DataFrame(x).astype(int)
y = pd.DataFrame(y).astype(int)
print(x)
print(y)

x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.2)
print(x_train)

绘制决策树，需要先配置graphviz
https://link.csdn.net/?target=https%3A%2F%2Fzhuanlan.zhihu.com%2Fp%2F268532582

# 加上Graphviz2.38绝对路径
import os
os.environ["PATH"] += os.pathsep + 'C:\Program Files\Graphviz\bin'
    
feature_name = ["色泽","根蒂","敲声","纹理","脐部","触感"]
dot_data = tree.export_graphviz(clf ,feature_names= feature_name,class_names=["好瓜","坏瓜"],filled=True,rounded=True,out_file =None) 
graph = graphviz.Source(dot_data) 
graph

四、cart算法

clf = tree.DecisionTreeClassifier(criterion="gini")  #实例化 
clf = clf.fit(x_train, y_train) 
score = clf.score(x_test, y_test)
print(score)

# 加上Graphviz2.38绝对路径
import os
os.environ["PATH"] += os.pathsep + r'C:\Program Files\Graphviz\bin'
    
feature_name = ["色泽","根蒂","敲声","纹理","脐部","触感"]
dot_data = tree.export_graphviz(clf ,feature_names= feature_name,class_names=["好瓜","坏瓜"],filled=True,rounded=True,out_file =None) 
graph = graphviz.Source(dot_data) 
graph