监督学习-树回归模板
来源:互联网 发布:人工智能机器2氏族战争 编辑:程序博客网 时间:2024/06/05 18:23
from numpy import *def loadDataSet(fileName): #general function to parse tab -delimited floats dataMat = [] #assume last column is target value fr = open(fileName) for line in fr.readlines(): curLine = line.strip().split('\t') fltLine = map(float,curLine) #map all elements to float() dataMat.append(fltLine) return dataMatdef binSplitDataSet(dataSet, feature, value): mat0 = dataSet[nonzero(dataSet[:,feature] > value)[0],:][0] mat1 = dataSet[nonzero(dataSet[:,feature] <= value)[0],:][0] return mat0,mat1def regLeaf(dataSet):#returns the value used for each leaf return mean(dataSet[:,-1])def regErr(dataSet): return var(dataSet[:,-1]) * shape(dataSet)[0]def linearSolve(dataSet): #helper function used in two places m,n = shape(dataSet) X = mat(ones((m,n))); Y = mat(ones((m,1)))#create a copy of data with 1 in 0th postion X[:,1:n] = dataSet[:,0:n-1]; Y = dataSet[:,-1]#and strip out Y xTx = X.T*X if linalg.det(xTx) == 0.0: raise NameError('This matrix is singular, cannot do inverse,\n\ try increasing the second value of ops') ws = xTx.I * (X.T * Y) return ws,X,Ydef modelLeaf(dataSet):#create linear model and return coeficients ws,X,Y = linearSolve(dataSet) return wsdef modelErr(dataSet): ws,X,Y = linearSolve(dataSet) yHat = X * ws return sum(power(Y - yHat,2))def chooseBestSplit(dataSet, leafType=regLeaf, errType=regErr, ops=(1,4)): tolS = ops[0]; tolN = ops[1] #if all the target variables are the same value: quit and return value if len(set(dataSet[:,-1].T.tolist()[0])) == 1: #exit cond 1 return None, leafType(dataSet) m,n = shape(dataSet) #the choice of the best feature is driven by Reduction in RSS error from mean S = errType(dataSet) bestS = inf; bestIndex = 0; bestValue = 0 for featIndex in range(n-1): for splitVal in set(dataSet[:,featIndex]): mat0, mat1 = binSplitDataSet(dataSet, featIndex, splitVal) if (shape(mat0)[0] < tolN) or (shape(mat1)[0] < tolN): continue newS = errType(mat0) + errType(mat1) if newS < bestS: bestIndex = featIndex bestValue = splitVal bestS = newS #if the decrease (S-bestS) is less than a threshold don't do the split if (S - bestS) < tolS: return None, leafType(dataSet) #exit cond 2 mat0, mat1 = binSplitDataSet(dataSet, bestIndex, bestValue) if (shape(mat0)[0] < tolN) or (shape(mat1)[0] < tolN): #exit cond 3 return None, leafType(dataSet) return bestIndex,bestValue#returns the best feature to split on #and the value used for that splitdef createTree(dataSet, leafType=regLeaf, errType=regErr, ops=(1,4)):#assume dataSet is NumPy Mat so we can array filtering feat, val = chooseBestSplit(dataSet, leafType, errType, ops)#choose the best split if feat == None: return val #if the splitting hit a stop condition return val retTree = {} retTree['spInd'] = feat retTree['spVal'] = val lSet, rSet = binSplitDataSet(dataSet, feat, val) retTree['left'] = createTree(lSet, leafType, errType, ops) retTree['right'] = createTree(rSet, leafType, errType, ops) return retTree def isTree(obj): return (type(obj).__name__=='dict')def getMean(tree): if isTree(tree['right']): tree['right'] = getMean(tree['right']) if isTree(tree['left']): tree['left'] = getMean(tree['left']) return (tree['left']+tree['right'])/2.0def prune(tree, testData): if shape(testData)[0] == 0: return getMean(tree) #if we have no test data collapse the tree if (isTree(tree['right']) or isTree(tree['left'])):#if the branches are not trees try to prune them lSet, rSet = binSplitDataSet(testData, tree['spInd'], tree['spVal']) if isTree(tree['left']): tree['left'] = prune(tree['left'], lSet) if isTree(tree['right']): tree['right'] = prune(tree['right'], rSet) #if they are now both leafs, see if we can merge them if not isTree(tree['left']) and not isTree(tree['right']): lSet, rSet = binSplitDataSet(testData, tree['spInd'], tree['spVal']) errorNoMerge = sum(power(lSet[:,-1] - tree['left'],2)) +\ sum(power(rSet[:,-1] - tree['right'],2)) treeMean = (tree['left']+tree['right'])/2.0 errorMerge = sum(power(testData[:,-1] - treeMean,2)) if errorMerge < errorNoMerge: print ("merging") return treeMean else: return tree else: return treedef regTreeEval(model, inDat): return float(model)def modelTreeEval(model, inDat): n = shape(inDat)[1] X = mat(ones((1,n+1))) X[:,1:n+1]=inDat return float(X*model)def treeForeCast(tree, inData, modelEval=regTreeEval): if not isTree(tree): return modelEval(tree, inData) if inData[tree['spInd']] > tree['spVal']: if isTree(tree['left']): return treeForeCast(tree['left'], inData, modelEval) else: return modelEval(tree['left'], inData) else: if isTree(tree['right']): return treeForeCast(tree['right'], inData, modelEval) else: return modelEval(tree['right'], inData)def createForeCast(tree, testData, modelEval=regTreeEval): m=len(testData) yHat = mat(zeros((m,1))) for i in range(m): yHat[i,0] = treeForeCast(tree, mat(testData[i]), modelEval) return yHatdef test(): import regTrees 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]) a=corrcoef(yHat,testMat[:,1],rowvar=0)[0,1] print(a) myTree=regTrees.createTree(trainMat,regTrees.modelLeaf,regTrees.modelErr,(1,20)) yHat=regTrees.createForeCast(myTree,testMat[:,0],regTrees.modelTreeEval) a=corrcoef(yHat,testMat[:,1],rowvar=0)[0,1] print(a)
0 0
- 监督学习-树回归模板
- 监督学习-logistics回归算法模板
- 监督学习-局部加权回归模板
- 监督学习&回归问题(Regression)
- 监督学习之线性回归
- 有监督回归:稀疏学习
- 监督学习之线性回归
- 机器学习有监督学习之--回归
- 机器学习-监督学习-线性回归
- 机器学习之监督学习-回归
- 监督学习-决策树算法模板
- 监督学习之线性回归(续)
- 监督学习之分类和逻辑回归
- 有监督回归:鲁棒学习
- 监督学习二 回归和分类
- 有监督学习(分类、回归)
- 监督学习之多变量线性回归
- MachineLearning-监督学习之线性回归
- 铁夫破词第二季总结(1)
- 查看远端的端口是否通畅3个简单实用案例!
- java的HMACSHA1加密算法使用方法
- 在js中=后面赋值出现||符号
- C++调用Python实例
- 监督学习-树回归模板
- 【bzoj2631】tree LCT
- 图像标注工具
- C++单例模式使用
- 格式化EXT中的 UTC 时间
- Javascript 中 apply、call、bind
- oracle数据库密码到期解决
- instanceof 运算符
- git打patch的方法