CS_ALearn/ailearning
1
0
Fork 0
mirror of https://github.com/apachecn/ailearning.git synced 2026-02-13 15:26:28 +08:00
Code Issues Projects Releases Wiki Activity

更新文件路径

Browse Source
This commit is contained in:
jiangzhonglian
2017-04-07 16:51:24 +08:00
parent afd689e5d8
commit 3c4fc66fd2
19 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/python/5.Logistic/logistic.py
View File

@@ -129,7 +129,7 @@ def plotBestFit(dataArr, labelMat, weights):
def main():
# 1.收集并准备数据
dataMat, labelMat = loadDataSet("input/05.Logistic/TestSet.txt")
dataMat, labelMat = loadDataSet("input/5.Logistic/TestSet.txt")
# print dataMat, '---\n', labelMat
# 2.训练模型， f(x)=a1*x1+b2*x2+..+nn*xn中 (a1,b2, .., nn).T的矩阵值

4
src/python/7.AdaBoost/adaboost.py
View File

@@ -290,13 +290,13 @@ if __name__ == "__main__":
# # 马疝病数据集
# # 训练集合
# dataArr, labelArr = loadDataSet("input/07.AdaBoost/horseColicTraining2.txt")
# dataArr, labelArr = loadDataSet("input/7.AdaBoost/horseColicTraining2.txt")
# weakClassArr, aggClassEst = adaBoostTrainDS(dataArr, labelArr, 40)
# print weakClassArr, '\n-----\n', aggClassEst.T
# # 计算ROC下面的AUC的面积大小
# plotROC(aggClassEst.T, labelArr)
# # 测试集合
# dataArrTest, labelArrTest = loadDataSet("input/07.AdaBoost/horseColicTest2.txt")
# dataArrTest, labelArrTest = loadDataSet("input/7.AdaBoost/horseColicTest2.txt")
# m = shape(dataArrTest)[0]
# predicting10 = adaClassify(dataArrTest, weakClassArr)
# errArr = mat(ones((m, 1)))

8
src/python/8.Predictive numerical data regression/regression.py
View File

@@ -233,7 +233,7 @@ def crossValidation(xArr,yArr,numVal=10):
#test for standRegression
def regression1():
xArr, yArr = loadDataSet("testData/Regression_data.txt")
xArr, yArr = loadDataSet("input/8.Regression/data.txt")
xMat = mat(xArr)
yMat = mat(yArr)
ws = standRegres(xArr, yArr)
@@ -251,7 +251,7 @@ def regression1():
#test for LWLR
def regression2():
xArr, yArr = loadDataSet("input/08.Regression/data.txt")
xArr, yArr = loadDataSet("input/8.Regression/data.txt")
yHat = lwlrTest(xArr, xArr, yArr, 0.003)
xMat = mat(xArr)
srtInd = xMat[:,1].argsort(0) #argsort()函数是将x中的元素从小到大排列，提取其对应的index(索引)，然后输出
@@ -265,7 +265,7 @@ def regression2():
#test for ridgeRegression
def regression3():
abX,abY = loadDataSet("input/08.Regression/abalone.txt")
abX,abY = loadDataSet("input/8.Regression/abalone.txt")
ridgeWeights = ridgeTest(abX, abY)
fig = plt.figure()
ax = fig.add_subplot(111)
@@ -275,7 +275,7 @@ def regression3():
#test for stageWise
def regression4():
xArr,yArr=loadDataSet("input/08.Regression/abalone.txt")
xArr,yArr=loadDataSet("input/8.Regression/abalone.txt")
stageWise(xArr,yArr,0.01,200)
xMat = mat(xArr)
yMat = mat(yArr).T

14
src/python/9.RegTrees/regTrees.py
View File

@@ -290,8 +290,8 @@ if __name__ == "__main__":
# print mat0, '\n-----------\n', mat1
# # 回归树
# myDat = loadDataSet('input/09.RegTrees/data1.txt')
# # myDat = loadDataSet('input/09.RegTrees/data2.txt')
# myDat = loadDataSet('input/9.RegTrees/data1.txt')
# # myDat = loadDataSet('input/9.RegTrees/data2.txt')
# # print 'myDat=', myDat
# myMat = mat(myDat)
# # print 'myMat=', myMat
@@ -299,13 +299,13 @@ if __name__ == "__main__":
# print myTree
# # 1. 预剪枝就是：提起设置最大误差数和最少元素数
# myDat = loadDataSet('input/09.RegTrees/data3.txt')
# myDat = loadDataSet('input/9.RegTrees/data3.txt')
# myMat = mat(myDat)
# myTree = createTree(myMat, ops=(0, 1))
# print myTree
# # 2. 后剪枝就是：通过测试数据，对预测模型进行合并判断
# myDatTest = loadDataSet('input/09.RegTrees/data3test.txt')
# myDatTest = loadDataSet('input/9.RegTrees/data3test.txt')
# myMat2Test = mat(myDatTest)
# myFinalTree = prune(myTree, myMat2Test)
# print '\n\n\n-------------------'
@@ -313,14 +313,14 @@ if __name__ == "__main__":
# # --------
# # 模型树求解
# myDat = loadDataSet('input/09.RegTrees/data4.txt')
# myDat = loadDataSet('input/9.RegTrees/data4.txt')
# myMat = mat(myDat)
# myTree = createTree(myMat, modelLeaf, modelErr)
# print myTree
# 回归树 VS 模型树 VS 线性回归
trainMat = mat(loadDataSet('input/09.RegTrees/bikeSpeedVsIq_train.txt'))
testMat = mat(loadDataSet('input/09.RegTrees/bikeSpeedVsIq_test.txt'))
trainMat = mat(loadDataSet('input/9.RegTrees/bikeSpeedVsIq_train.txt'))
testMat = mat(loadDataSet('input/9.RegTrees/bikeSpeedVsIq_test.txt'))
# 回归树
myTree1 = createTree(trainMat, ops=(1, 20))
print myTree1