首先导包:
from matplotlib.font_manager import FontProperties
import matplotlib.pyplot as plt
from math import log
import operator
import pickle
from _functools import reduce
然后开始实现具体的函数功能:
"""
函数说明:创建测试数据集
Parameters:无
Returns:
dataSet:数据集
labels:分类属性
"""
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 = ['F1-AGE','F2-WORK','F3-HOME','F4-LOAN']
return dataSet, labels
"""
函数说明:创建决策树
Parameters:
dataSet:训练数据集
labels:分类属性标签
featLabels:存储选择的最优特征标签
Returns:
myTree:决策树
"""
# 递归函数,递归地创建树模型
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: {}}
# 关键部分:创建labels的副本
subLabels = labels[:]
del subLabels[bestFeat]
featValues = [example[bestFeat] for example in dataSet]
uniqueVals = set(featValues)
for value in uniqueVals:
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels, featLabels)
return myTree
"""
函数说明:统计classList中出现次数最多的元素(类标签)
Parameters:
classList:类标签列表
Returns:
sortedClassCount[0][0]:出现次数最多的元素(类标签)
"""
# 计算哪一个类是最多的
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]
"""
函数说明:计算给定数据集的经验熵(香农熵)
Parameters:
dataSet:数据集
Returns:
shannonEnt:信息增益最大特征的索引值
"""
# 选择最好的一个特征
def chooseBestFeatureToSplit(dataSet):
# 首先计算当前的特征数量
numFeatures = len(dataSet[0]) - 1
baseEntropy = calcShannonEnt(dataSet)
bestInfoGain = 0
bestFeature = -1
for i in range(numFeatures):
featList = [example[i] for example in dataSet]
uniqueVals = set(featList)
newEntropy = 0
for val in uniqueVals:
subDataSet = splitDataSet(dataSet,i,val)
prob = len(subDataSet)/float(len(dataSet))
newEntropy += prob * calcShannonEnt(subDataSet)
infoGain = baseEntropy - newEntropy
if infoGain > bestInfoGain:
bestInfoGain = infoGain
bestFeature = i
# 返回特征索引
return bestFeature
"""
函数说明:按照给定特征划分数据集
Parameters:
dataSet:待划分的数据集
axis:划分数据集的特征
value:需要返回的特征值
Returns:
无
"""
def splitDataSet(dataSet,axis,val):
retDataSet = []
for featVec in dataSet:
if featVec[axis] == val:
reducedFeatVec = featVec[:axis]
reducedFeatVec.extend(featVec[axis+1:])
retDataSet.append(reducedFeatVec)
return retDataSet
"""
函数说明:计算给定数据集的经验熵(香农熵)
Parameters:
dataSet:数据集
Returns:
shannonEnt:经验熵
"""
def calcShannonEnt(dataSet):
numexamples = len(dataSet)
labelCounts = {}
for featVec in dataSet:
currentLabel = featVec[-1]
if currentLabel not in labelCounts.keys():
labelCounts[currentLabel] = 0
labelCounts[currentLabel] += 1
shannonEnt = 0
for key in labelCounts:
# 计算概率值
prop = float(labelCounts[key]) / numexamples
# 计算熵值
shannonEnt -= prop * log(prop, 2)
return shannonEnt
"""
函数说明:获取决策树叶子节点的数目
Parameters:
myTree:决策树
Returns:
numLeafs:决策树的叶子节点的数目
"""
def getNumLeafs(myTree):
numLeafs = 0
firstStr = next(iter(myTree))
secondDict = myTree[firstStr]
for key in secondDict.keys():
if type(secondDict[key]).__name__ == 'dict':
numLeafs += getNumLeafs(secondDict[key])
else:
numLeafs += 1
return numLeafs
然后后开始编写绘制树结构需要的函数:
"""
函数说明:获取决策树的层数
Parameters:
myTree:决策树
Returns:
maxDepth:决策树的层数
"""
def getTreeDepth(myTree):
maxDepth = 0 # 初始化决策树深度
firstStr = next(iter(
myTree)) # python3中myTree.keys()返回的是dict_keys,不在是list,所以不能使用myTree.keys()[0]的方法获取结点属性,可以使用list(myTree.keys())[0]
secondDict = myTree[firstStr] # 获取下一个字典
for key in secondDict.keys():
if type(secondDict[key]).__name__ == 'dict': # 测试该结点是否为字典,如果不是字典,代表此结点为叶子结点
thisDepth = 1 + getTreeDepth(secondDict[key])
else:
thisDepth = 1
if thisDepth > maxDepth: maxDepth = thisDepth # 更新层数
return maxDepth
"""
函数说明:绘制结点
Parameters:
nodeTxt - 结点名
centerPt - 文本位置
parentPt - 标注的箭头位置
nodeType - 结点格式
Returns:
无
"""
def plotNode(nodeTxt, centerPt, parentPt, nodeType):
arrow_args = dict(arrowstyle="<-") # 定义箭头格式
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14) # 设置中文字体
createPlot.ax1.annotate(nodeTxt, xy=parentPt, xycoords='axes fraction', # 绘制结点
xytext=centerPt, textcoords='axes fraction',
va="center", ha="center", bbox=nodeType, arrowprops=arrow_args, fontproperties=font)
"""
函数说明:标注有向边属性值
Parameters:
cntrPt、parentPt - 用于计算标注位置
txtString - 标注的内容
Returns:
无
"""
def plotMidText(cntrPt, parentPt, txtString):
xMid = (parentPt[0] - cntrPt[0]) / 2.0 + cntrPt[0] # 计算标注位置
yMid = (parentPt[1] - cntrPt[1]) / 2.0 + cntrPt[1]
createPlot.ax1.text(xMid, yMid, txtString, va="center", ha="center", rotation=30)
"""
函数说明:绘制决策树
Parameters:
myTree - 决策树(字典)
parentPt - 标注的内容
nodeTxt - 结点名
Returns:
无
"""
def plotTree(myTree, parentPt, nodeTxt):
decisionNode = dict(boxstyle="sawtooth", fc="0.8") # 设置结点格式
leafNode = dict(boxstyle="round4", fc="0.8") # 设置叶结点格式
numLeafs = getNumLeafs(myTree) # 获取决策树叶结点数目,决定了树的宽度
depth = getTreeDepth(myTree) # 获取决策树层数
firstStr = next(iter(myTree)) # 下个字典
cntrPt = (plotTree.xOff + (1.0 + float(numLeafs)) / 2.0 / plotTree.totalW, plotTree.yOff) # 中心位置
plotMidText(cntrPt, parentPt, nodeTxt) # 标注有向边属性值
plotNode(firstStr, cntrPt, parentPt, decisionNode) # 绘制结点
secondDict = myTree[firstStr] # 下一个字典,也就是继续绘制子结点
plotTree.yOff = plotTree.yOff - 1.0 / plotTree.totalD # y偏移
for key in secondDict.keys():
if type(secondDict[key]).__name__ == 'dict': # 测试该结点是否为字典,如果不是字典,代表此结点为叶子结点
plotTree(secondDict[key], cntrPt, str(key)) # 不是叶结点,递归调用继续绘制
else: # 如果是叶结点,绘制叶结点,并标注有向边属性值
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
"""
函数说明:创建绘制面板
Parameters:
inTree - 决策树(字典)
Returns:
无
"""
def createPlot(inTree):
fig = plt.figure(1, facecolor='white') # 创建fig
fig.clf() # 清空fig
axprops = dict(xticks=[], yticks=[])
createPlot.ax1 = plt.subplot(111, frameon=False, **axprops) # 去掉x、y轴
plotTree.totalW = float(getNumLeafs(inTree)) # 获取决策树叶结点数目
plotTree.totalD = float(getTreeDepth(inTree)) # 获取决策树层数
plotTree.xOff = -0.5 / plotTree.totalW;
plotTree.yOff = 1.0 # x偏移
plotTree(inTree, (0.5, 1.0), '') # 绘制决策树
plt.show() # 显示绘制结果
最后是main函数:
if __name__ == '__main__':
dataSet, labels = createDataSet()
featLabels = []
myTree = createTree(dataSet, labels, featLabels)
# print(myTree)
createPlot(myTree)
运行结果: