def reDraw(tolN, tolS):
reDraw.f.clf() #清空图像
reDraw.a = reDraw.f.add_subplot(111)
trainData = regTrees.loadDataSet(
".//machinelearninginaction//ch09//sine.txt")
if chkBtnVar.get(): #复选框被选中，求模型树
modelTree = regTrees.createTree(trainData,
leafType=regTrees.modelLeaf,
errType=regTrees.modelErr,
ops=(tolS, tolN))
y_hat = regTrees.createForeCast(modelTree,
trainData[:, 0],
modelEval=regTrees.modelTreeEval)
else: #回归树
modelTree = regTrees.createTree(trainData, ops=(tolS, tolN))
y_hat = regTrees.createForeCast(modelTree, trainData[:, 0])
data_hat = np.hstack((trainData[:, 0], y_hat))
sort_hat = sorted(data_hat.tolist(), key=lambda x: x[0])
sort_x = [x[0] for x in sort_hat]
sort_y = [x[1] for x in sort_hat]
reDraw.a.scatter(trainData[:, 0].T.tolist()[0],
trainData[:, 1].T.tolist()[0],
s=50)
reDraw.a.plot(sort_x, sort_y)
reDraw.canvas.show()
def reDraw(tolS,tolN):
# 调用 Figure 对象的 clf() 方法清理画布
reDraw.f.clf()
# 添加 Axes 对象
reDraw.a = reDraw.f.add_subplot(111)
# 检查复选框是否被选中
if chkBtnVar.get():
# 绘制模型树
# tolN至少为2
if tolN < 2: tolN = 2
# 创建模型树
myTree=regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,\
regTrees.modelErr, (tolS,tolN))
# 计算预测值向量
yHat = regTrees.createForeCast(myTree, reDraw.testDat, \
regTrees.modelTreeEval)
else:
# 创建回归树
myTree=regTrees.createTree(reDraw.rawDat, ops=(tolS,tolN))
# 计算预测值向量
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
# 调用 scatter() 方法绘制真实数据图
reDraw.a.scatter(reDraw.rawDat[:,0], reDraw.rawDat[:,1], s=5)
# 预测值采用 plot() 方法绘制
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
# 在画布上显示绘制的图形
reDraw.canvas.show()
def reDraw(tolS, tolN):
'''
画出数据点和模型拟合线
:param tolS: 用户输入的最小误差值
:param tolN: 用户输入的最少样本数
:return:
'''
# pass # 空语句, 是为了保持程序结构的完整性
reDraw.f.clf() # 清空之前的图像
reDraw.a = reDraw.f.add_subplot(111) # 添加一个新图
if chkBtnVar.get(): # 复选框被选中, 构建模型树
if tolN < 2: # 最少样本数不能少于2
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else: # 复选框未选中, 构建回归树
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0].flatten().A[0],
reDraw.rawDat[:, 1].flatten().A[0],
s=5) # 画出数据点
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) # 画出模型拟合线
reDraw.canvas.show()
def reDraw(tolS, tolN):
"""
绘制原始数据的散点图以及拟合数据的曲线图
Parameters
-----------
tolS : 允许的误差下降值
tolN : 诶分的最小样本值
Returns
------------
None
"""
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0].tolist(), reDraw.rawDat[:, 1].tolist(),
s=5)
reDraw.a.plot(reDraw.testDat, yHat, 'b', linewidth=2.0)
reDraw.canvas.show()
def reDraw(tolS, tolN): reDraw.f.clf() reDraw.a = reDraw.f.add_subplot(111) if chkBtnVar.get(): if tolN < 2: tolN = 2 myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf, regTrees.modelErr, (tolS, tolN)) yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval) else: myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN)) yHat = regTrees.createForeCast(myTree, reDraw.testDat) reDraw.a.scatter(reDraw.rawDat[:,0], reDraw.rawDat[:,1], s=5) reDraw.a.plot(reDraw.testDat, yHat, linewidth = 2.0) reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf() #清空之前的图像
reDraw.a = reDraw.f.add_subplot(111)#重新添加新图
if chkBtnVar.get():#检查选框model tree是否被选中
if tolN < 2: tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1], s=5) # 绘制真实值
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) # 绘制预测值
reDraw.canvas.show()
def reDraw(tolS,tolN):
reDraw.f.clf() # clear the figure
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get(): #see if check box has been selected
if tolN < 2: tolN = 2
myTree=regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,regTrees.modelErr, (tolS,tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,regTrees.modelTreeEval)
else:
myTree=regTrees.createTree(reDraw.rawDat, ops=(tolS,tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:,0], reDraw.rawDat[:,1], s=5) #use scatter for data set
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) #use plot for yHat
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf, regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(array(reDraw.rawDat[:, 0]), array(reDraw.rawDat[:, 1]), s=5)
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
reDraw.canvas.draw()
def reDraw(tolS, tolN):
reDraw.f.clf() # clear the figure
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf, regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1], s=5) # use scatter for data set
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) # use plot for yHat
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get(): # 复选框选中，则为模型树，否则会回归树
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawData, regTrees.modelLeaf, regTrees.modelError, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testData, regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawData, ops = (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testData)
reDraw.a.scatter(reDraw.rawData[:, 0], reDraw.rawData[:, 1], s=5)
reDraw.a.plot(reDraw.testData, yHat, linewidth=2.0)
reDraw.canvas.show()
def reDraw(tolS,tolN):
reDraw.f.clf() # clear the figure
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN < 2: tolN = 2
myTree=regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,\
regTrees.modelErr, (tolS,tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, \
regTrees.modelTreeEval)
else:
myTree=regTrees.createTree(reDraw.rawDat, ops=(tolS,tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:,0], reDraw.rawDat[:,1], s=20, alpha=.7) #use scatter for data set
reDraw.a.plot(reDraw.testDat, yHat, 'or', markersize=5.0, linewidth=2.0, alpha=.6) #use plot for yHat
reDraw.canvas.show()
def reDraw(tolS, tolN):
#清空之前的图像
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN < 2: tolN = 2
myTree = rt.createTree(reDraw.rawDat, rt.modelleaf, rt.modelErr,
(tolS, tolN))
yHat = rt.createForeCast(myTree, reDraw.testDat, rt.modelTreeEval)
else:
myTree = rt.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = rt.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1], s=5)
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf() # 清空之前的图像
reDraw.a = reDraw.f.add_subplot(111) # 重新添加子图
if chkBtnVar.get(): # 检查复选框是否选中，确定是模型树还是回归树
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf, regTrees.modelErr,
(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval)
else: # 回归树
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(array(reDraw.rawDat[:, 0]), array(reDraw.rawDat[:, 1]), s=5) # 画真实值的散点图
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) # 画预测值的直线图
reDraw.canvas.draw()
def reDraw(tolS,tolN):
reDraw.rawDat=mat(regTrees.loadDataSet("C:\Users\YAN\Desktop\Cart\sine.txt"))
reDraw.testDat=arange(min(reDraw.rawDat[:,0]),max(reDraw.rawDat[:,0]),0.01)
reDraw.f.clf()
reDraw.a=reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN<2: tolN=2
myTree=regTrees.createTree(reDraw.rawDat,regTrees.modelLeaf,regTrees.modelErr,(tolS,tolN))
yHat=regTrees.createForeCast(myTree,reDraw.testDat,regTrees.modelTreeEval)
else:
myTree=regTrees.createTree(reDraw.rawDat,ops=(tolS,tolN))
yHat=regTrees.createForeCast(myTree,reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:,0],reDraw.rawDat[:,1],s=5)
reDraw.a.plot(reDraw.testDat,yHat,linewidth=2.0)
reDraw.canvas.show()
def reDraw(tolS,tolN): #清空之前的图像，使得前后两个图像不会重叠 reDraw.f.clf() reDraw.a=reDraw.f.add_subplot(111) if chkBtnVar.get():#检查复选框是否选中，则为树模型 if tolN<2: tolN=2 myTree=regTrees.createTree(reDraw.rawDat,regTrees.modelLeaf,regTrees.modelErr,(tolS,tolN)) yHat=regTrees.createForeCast(myTree,reDraw.testDat,regTrees.modelTreeEval) else:#否则为回归模型 myTree=regTrees.createTree(reDraw.rawDat,ops=(tolS,tolN)) yHat=regTrees.createForeCast(myTree,reDraw.testDat) reDraw.a.scatter(list(reDraw.rawDat[:,0]),list(reDraw.rawDat[:,1]),s=5) reDraw.a.plot(reDraw.testDat,yHat,linewidth=2.0) reDraw.canvas.show()
def reDraw(tolS, tolN): #后边会编写函数
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get(): #如果选中模型树的话
if tolN < 2: tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr,
(tolS, tolN)) #根据指定的规则创建树
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval) #计算测试集的预测集
else: #如果选中回归树
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1], s=5) #绘制样本集的散点图
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) #绘制测试集的拟合曲线
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
# Check which is selected
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf, \
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, \
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops = (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0].A, reDraw.rawDat[:, 1].A, s = 5)
reDraw.a.plot(reDraw.testDat, yHat, linewidth = 2.0)
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
# See if check box has been selected
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1], c="black", s=5)
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
reDraw.canvas.draw()
def reDraw(tolS, tolN):
reDraw.f.clf() # 清空之前的图像
reDraw.a = reDraw.f.add_subplot(111) #重新添加一个新图
if chkBtnVar.get(): #检查复选框是否被选中，根据复选框是否被选中来确定构建模型树还是回归树
if tolN < 2: tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN)) #用真实值构建树
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval) #用测试值构建树
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.rawDat[:, 0].A
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1],
s=5) #真实值用scatter()方法绘制，因为scatter构建的是离散型散点图
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) #预测值用plot()方法构建，连续曲线
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf() # clear画布
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get(): # 判断 模型树 or 回归树
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, \
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0].A, reDraw.rawDat[:, 1].A,
s=5) # 使用散点图，描绘真实数据
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) # 使用折线图，描绘预测数据
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN < 2: tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0].A,
reDraw.rawDat[:, 1].A,
s=20,
c='g',
alpha=.4)
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0, c='r')
reDraw.canvas.show()
def reDraw(tolS, tolN):
# 清空
reDraw.f = Figure(figsize=(5,4), dpi=100)
reDraw.f.clf()
# 建新图
reDraw.a = reDraw.f.add_subplot(111)
# 确认复选框是否被选中
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf, regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1], s=5)
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
reDraw.canvas = FigureCanvasTkAgg(reDraw.f, master=root)
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
#检查复选框是否选中
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
#print shape(reDraw.rawDat[:,0])
reDraw.a.scatter(reDraw.rawDat[:, 0].flatten().A[0],
reDraw.rawDat[:, 1].flatten().A[0],
s=5)
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
reDraw.canvas.show()
def reDraw(tols, tolN):
# 清空图像，重新绘图
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
# 判断复选框是否选中
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tols, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tols, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
# 绘出真实值
reDraw.a.scatter(reDraw.rawDat[:, 0].A, reDraw.rawDat[:, 1].A, s=5)
# 会出预测值
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
reDraw.canvas.show()
def reDraw(tolS,tolN): reDraw.f.clf() reDraw.a = reDraw.f.add_subplit(111) if chkBtnVar.get(): if tolN < 2: tolN = 2 myTree = regTrees.createTree(reDraw.reDat,regTrees.modelLeaf,regTrees.modelErr(tolS,tolN)) yHat = regTrees.createForeCast(myTree,reDraw.testDat,regTrees.modelTreeEval) else: myTree = regTrees.createTree(reDraw.rawDat[:,0],reDraw.rawDat[:,1],s=5) reDraw.canvas.show()
def reDraw(tolS,tolN):
reDraw.f.clf() # clear the figure
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN < 2: tolN = 2
myTree=regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,\
regTrees.modelErr, (tolS,tolN))
print 'myTree=', myTree
yHat = regTrees.createForeCast(myTree, reDraw.testDat, \
regTrees.modelTreeEval)
else:
myTree=regTrees.createTree(reDraw.rawDat, ops=(tolS,tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
# print 'min=', min(reDraw.rawDat[:,0])
# print 'min=', min(reDraw.rawDat[:,1])
print 'srcdata=',reDraw.rawDat
# reDraw.a.scatter(reDraw.rawDat[:,0], reDraw.rawDat[:,1], s=5) #use scatter for data set
reDraw.a.plot(reDraw.rawDat[:,0], reDraw.rawDat[:,1], '.') #use plot for yHat
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) #use plot for yHat
reDraw.canvas.show()
def reDraw(tolS, tolN):
# clear the figure
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
# 检查复选框是否选中
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf, regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
# use scatter for data set
reDraw.a.scatter(reDraw.rawDat[:, 0].A, reDraw.rawDat[:, 1].A, s=5)
# use plot for yHat
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0, c='red')
reDraw.canvas.show()
def reDraw(tolS, tolN): #图形是回归树还是模型树在程序内部判断
reDraw.f.clf() # 清空图像
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get(): #检查复选框（Model Tree）是否选中,选中就是模型树（叶子节点是线性模型）
if tolN < 2: tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else: #没有选中就是回归型（叶子节点就是常数型）
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
print "\n××××××××××××reDraw.rawDat的值是：\n", type(
numpy.mat(reDraw.rawDat[:, 0]))
reDraw.a.scatter(list(reDraw.rawDat[:, 0]),
list(reDraw.rawDat[:, 1]),
c='r') # 绘制原始数据的散点图（真实值）
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) # 使用预测数据yHat绘制折线图（预测值）
# （如果叶子节点是常数绘制出的图形就是方正的，如果叶子节点的模型是线性的绘制出的图形拟合程度就比较好）
reDraw.canvas.show() #绘制图像
def reDraw(tolS, tolN): # tolS是容许的误差下降值，tolN是切分的最少样本数
# tolN=200，则不切分树，用一条直线来拟合；tolN=50，5直线拟合；10，仅需要8直线便可拟合，
# 为构建尽量大的树，将tolN设置为1，tolN设为0.此时构建模型树，过拟合严重
reDraw.f.clf() # 清空之前的图像
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get(): # 检查复选框是否选中，选中则构建模型树
if tolN < 2: tolN = 2 # tolN设置的最小值为2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else: # 否则构建回归树
myTree = regTrees.createTree(reDraw.rawDat,
ops=(tolS, tolN)) # 中间两个参数采用默认参数regLeaf
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(reDraw.rawDat[:, 0].tolist(),
reDraw.rawDat[:, 1].tolist(),
s=5)
# 注意加上 .tolist() 将matrix或array转换为list，才能使用scatter函数，否则会报错
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) # 预测值采用plot()方法绘制
reDraw.canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf() # clear the figure
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
if tolN < 2: tolN = 2
myTree=regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,\
regTrees.modelErr, (tolS,tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, \
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
#plt.scatter(dataSet[0],dataSet[1])#2改成 plt.scatter(dataSet[0].tolist(),dataSet[1].tolist())
# 或plt.scatter(array(dataSet[0]),array(dataSet[1].tolist())) 、
# type(dataSet[0])==<class 'numpy.matrixlib.defmatrix.matrix'>是矩阵对象不是一维（1-D）的
reDraw.a.scatter(array(reDraw.rawDat[:, 0]),
array(reDraw.rawDat[:, 1]).tolist(),
s=5) #use scatter for data set
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) #use plot for yHat
reDraw.canvas.show()
def reDraw(tolS, tolN):
'''
函数说明：在数据点上绘制回归或模型树
'''
reDraw.f.clf() # clear the figure
reDraw.a = reDraw.f.add_subplot(111)
# 如果复选框选中，则构建模型树
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval)
# 如果复选框未选中，则构建回归树
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS,tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
reDraw.a.scatter(list(reDraw.rawDat[:,0]), list(reDraw.rawDat[:,1]), s=5) #use scatter for data set
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) #use plot for yHat
reDraw.canvas.draw()
def reDraw(tolS, tolN):
reDraw.f.clf() # 清除图像显示
reDraw.a = reDraw.f.add_subplot(111) # 显示一个图
if chkBtnVar.get(): # 复选框选中的话 为模型树
if tolN < 2: tolN = 2 # 最小数量限制
# 生成 模型树
myTree=regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,\
regTrees.modelErr, (tolS,tolN))
# 用模型树 进行预测
yHat = regTrees.createForeCast(myTree, reDraw.testDat, \
regTrees.modelTreeEval)
else: # 不选的话 默认为 普通回归树
# 生成 普通回归树
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
# 用回归树 进行预测
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
# 散点图
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1], s=5) #大小为5
# 画出预测曲线
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0) #线宽为2
# 显示画布
reDraw.canvas.show()
def test4():
trainMat = mat(regTrees.loadDataSet('bikeSpeedVsIq_train.txt'))
testMat = mat(regTrees.loadDataSet('bikeSpeedVsIq_test.txt'))
#regTrees.plot1(testMat)
myTree = regTrees.createTree(trainMat, ops=(1, 20))
yHat = regTrees.createForeCast(myTree, testMat[:, 0])
print(corrcoef(yHat, testMat[:, 1], rowvar=0)[0, 1])
#regTrees.plot1withTree(trainMat, myTree)
myTree = regTrees.createTree(trainMat, regTrees.modelLeaf,
regTrees.modelErr, (1, 20))
yHat = regTrees.createForeCast(myTree, testMat[:, 0],
regTrees.modelTreeEval)
print(corrcoef(yHat, testMat[:, 1], rowvar=0)[0, 1])
print(myTree)
regTrees.plot1withTree_Linear(trainMat, myTree)
ws, X, Y = regTrees.linearSolve(trainMat)
print(ws)
for i in range(shape(testMat)[0]):
yHat[i] = testMat[i, 0] * ws[1, 0] + ws[0, 0]
print(corrcoef(yHat, testMat[:, 1], rowvar=0)[0, 1])
def reDraw(tolS, tolN):
# 清空之前的图像，避免重叠
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
# 检查复选框是否被选中
# 确定基于tolS和tolN参数构建模型树还是回归树
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
# reDraw.rawDat[:,0].A，需要将矩阵转换成数组, 原书错误
# 真实值散点图绘制
reDraw.a.scatter(reDraw.rawDat[:, 0].A, reDraw.rawDat[:, 1].A, s=5)
# 预测值曲线绘制
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
reDraw.canvas.show()
def reDraw(tolS, tolN):
fig.clf()
a = fig.add_subplot(111)
# if chkBtnVar.get():#勾选 check button,就画模型树
# if tolN<2:
# tolN=2
# myTree=regTrees.createTree(loadData,regTrees.modelLeaf,regTrees.modelErr,ops=(tolS,tolN))
# yHat=regTrees.createForeCast(myTree,testData,regTrees.regTreeEval)
# else:#默认，就画回归树
myTree = regTrees.createTree(loadData, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, testData)
a.scatter(loadData[:, 0], loadData[:, 1], marker="s", s=5)
a.plot(testData, yHat, linewidth=2.0)
canvas.show()
def reDraw(tolS, tolN):
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
if chkBtnVar.get():
#print('模型树')
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf,
regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat,
regTrees.modelTreeEval)
else:
#print('普通树')
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
print('myTree: \n%s' % myTree)
print('\nyHat: \n%s' % yHat)
reDraw.a.scatter(reDraw.rawDat[:, 0].tolist(),
reDraw.rawDat[:, 1].tolist(),
s=5) #这里使用tolist方法，否则出现1-D的异常
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0)
reDraw.canvas.show(
) #20190107发现新版的python中不使用这个show方法，使用的话，会出错，通过在jyputer中测试发现，这句话不能注释，注释后，图形不能更新
print(regTrees.createTree(myMat2))
myTree=regTrees.createTree(myMat2,ops=(0,1))
myDatTest=regTrees.loadDataSet('ex2test.txt')
myMat2Test=mat(myDatTest)
regTrees.prune(myTree,myMat2Test)
print(myTree)
print("分段函数表示：")
myMat2=mat(regTrees.loadDataSet('exp2.txt'))
print(regTrees.createTree(myMat2,regTrees.modelLeaf,regTrees.modelErr,(1,10)))
trainMat=mat(regTrees.loadDataSet('bikeSpeedVsIq_train.txt'))
testMat=mat(regTrees.loadDataSet('bikeSpeedVsIq_test.txt'))
myTree=regTrees.createTree(trainMat,ops=(1,20))
yHat=regTrees.createForeCast(myTree,testMat[:,0])
print(corrcoef(yHat,testMat[:,1],rowvar=0)[0,1])
ws,X,Y=regTrees.linearSolve(trainMat)
print(ws)
for i in range(shape(testMat)[0]):
yHat[i]=testMat[i,0]*ws[1,0]+ws[0,0]
print(corrcoef(yHat,testMat[:,1],rowvar=0)[0,1])
from Tkinter import *
root=Tk()
myLabel=Label(root,text="Hello World")
myLabel.grid()
root.mainloop()
#print myDat2
#print regTrees.createTree(myMat2, ops=(10000,4))
#model tree
#myMat2 = mat(regTrees.loadDataSet('exp2.txt'))
#print regTrees.createTree(myMat2, regTrees.modelLeaf, regTrees.modelErr, (1,10))
trainMat = mat(regTrees.loadDataSet('bikeSpeedVsIq_train.txt'))
testMat = mat(regTrees.loadDataSet('bikeSpeedVsIq_test.txt'))
myTree = regTrees.createTree(trainMat, ops=(1,20))
#print myTree
#___REGRES TREE___
yHat = regTrees.createForeCast(myTree, testMat[:,0])
#print yHat
print corrcoef(yHat, testMat[:,1], rowvar=0)[0,1]
#___MODEL TREE___
myTree = regTrees.createTree(trainMat, regTrees.modelLeaf, regTrees.modelErr, (1,20))
yHat = regTrees.createForeCast(myTree, testMat[:,0], regTrees.modelTreeEval)
print corrcoef(yHat, testMat[:,1], rowvar=0)[0,1]
#___STAND REGRES___
ws,X,Y = regTrees.linearSolve(trainMat)
print "ws=",ws
for i in range(shape(testMat)[0]):
yHat[i] = testMat[i,0]*ws[1,0]+ws[0,0]
print corrcoef(yHat, testMat[:,1], rowvar=0)[0,1]
myMat2 = mat(myDat2)
#print regTrees.createTree(myMat2)
print regTrees.createTree(myMat2, ops=(10000, 4))
myTree = regTrees.createTree(myMat2, ops=(0, 1))
myDatTest = regTrees.loadDataSet('ex2test.txt')
myMat2Test = mat(myDatTest)
print regTrees.prune(myTree, myMat2Test)
myMat2 = mat(regTrees.loadDataSet('exp2.txt'))
print regTrees.createTree(myMat2, regTrees.modelLeaf, regTrees.modelErr,
(1, 10))
trainMat = mat(regTrees.loadDataSet('bikeSpeedVsIq_train.txt'))
testMat = mat(regTrees.loadDataSet('bikeSpeedVsIq_test.txt'))
myTree = regTrees.createTree(trainMat, ops=(1, 20))
yHat = regTrees.createForeCast(myTree, testMat[:, 0])
print corrcoef(yHat, testMat[:, 1], rowvar=0)[0, 1]
myTree = regTrees.createTree(trainMat,
regTrees.modelLeaf,
regTrees.modelErr,
ops=(1, 20))
yHat = regTrees.createForeCast(myTree, testMat[:, 0], regTrees.modelTreeEval)
print corrcoef(yHat, testMat[:, 1], rowvar=0)[0, 1]
ws, X, Y = regTrees.linearSolve(trainMat)
print ws
for i in range(shape(testMat)[0]):
yHat[i] = testMat[i, 0] * ws[1, 0] + ws[0, 0]
print corrcoef(yHat, testMat[:, 1], rowvar=0)[0, 1]
