def regtree(par, *data):
print(par)
X_train, X_test, Y_train, Y_test = data
regTreeModel=tree.DecisionTreeRegressor\
(max_features=par[0],min_samples_split=par[1],min_samples_leaf=par[2],
min_weight_fraction_leaf=par[3],max_leaf_nodes=int(par[4]))
fitModel = linear_model.LinearRegression()
Yp,Yptrain,regTreeModel,fitModelList,predind=\
SSRS.RegressionTree(X_train,X_test,Y_train,Y_test,regTreeModel,fitModel,Field,
doFitSelection=0,doMultiBand=1)
rmse, rmse_band = SSRS.RMSECal(Yp, Y_test)
print("RMSE=%f" % rmse)
return rmse
def testModel(predListTest):
nmodel = predListTest.__len__()
nit = 50
# test 1: different size of training and test
testErr = np.ones([nmodel, 5, 50])
testsize = [0.2, 0.4, 0.5, 0.6, 0.7]
for k in range(0, nit):
print(k)
for j in range(0, nmodel):
for i in range(0, 5):
ind = range(0, nind)
X_train,X_test,Y_train,Y_test,ind_train,ind_test = \
cross_validation.train_test_split(Xn,dist,ind,test_size=testsize[i],random_state=k)
regTreeModel = tree.DecisionTreeRegressor(max_leaf_nodes=20,
min_samples_leaf=20)
fitModel = linear_model.LinearRegression()
predSel = predListTest[j]
predName = [Field[jj] for jj in predSel]
Yp,Yptrain,regTreeModel,fitModelList,predind=\
SSRS.RegressionTree(X_train[:,predSel],X_test[:,predSel],Y_train,Y_test,regTreeModel,fitModel,predName,
doFitSelection=0,doMultiBand=1)
rmse, rmse_band = SSRS.RMSECal(Yp, Y_test)
testErr[j, i, k] = rmse
# test 2: use 1 HUC2 as test
testErr1_huc2_rt = np.ones([nmodel, 18])
trainErr1_huc2_rt = np.ones([nmodel, 18])
IDhucfile = r"E:\work\SSRS\data\IDhuc_mb_4949.mat"
mat = sio.loadmat(IDhucfile)
IDhuc = mat["IDhuc"]
huc2 = IDhuc[indvalid, 1]
for k in range(0, nit):
print(k)
for i in range(0, 18):
ind = range(0, nind)
X_train,X_test,Y_train,Y_test,ind_train,ind_test = \
cross_validation.train_test_split(Xn,dist,ind,test_size=0.2,random_state=k)
ind_test = np.where(huc2 == i + 1)[0]
X_test = Xn[ind_test, :]
Y_test = dist[ind_test, :]
for j in range(0, nmodel):
regTreeModel = tree.DecisionTreeRegressor(max_leaf_nodes=20)
fitModel = linear_model.LinearRegression()
predSel = predListTest[j]
predName = [Field[jj] for jj in predSel]
Yp,Yptrain,regTreeModel,fitModelList,predind=\
SSRS.RegressionTree(X_train[:,predSel],X_test[:,predSel],Y_train,Y_test,regTreeModel,fitModel,predName,
doFitSelection=0,doMultiBand=1)
rmse, rmse_band = SSRS.RMSECal(Yptrain, Y_train)
trainErr1_huc2_rt[j, i] = rmse
rmse, rmse_band = SSRS.RMSECal(Yp, Y_test)
testErr1_huc2_rt[j, i] = rmse
# test 3: leave out 1 HUC2 one time
testErr1_huc2 = np.ones([nmodel, 18])
trainErr1_huc2 = np.ones([nmodel, 18])
IDhucfile = r"E:\work\SSRS\data\IDhuc_mb_4949.mat"
mat = sio.loadmat(IDhucfile)
IDhuc = mat["IDhuc"]
huc2 = IDhuc[indvalid, 1]
for i in range(0, 18):
ind_test = np.where(huc2 == i + 1)[0]
ind_train = np.where(huc2 != i + 1)[0]
X_train = Xn[ind_train, :]
X_test = Xn[ind_test, :]
Y_train = dist[ind_train, :]
Y_test = dist[ind_test, :]
for j in range(0, nmodel):
regTreeModel = tree.DecisionTreeRegressor(max_leaf_nodes=20)
fitModel = linear_model.LinearRegression()
predSel = predListTest[j]
predName = [Field[jj] for jj in predSel]
Yp,Yptrain,regTreeModel,fitModelList,predind=\
SSRS.RegressionTree(X_train[:,predSel],X_test[:,predSel],Y_train,Y_test,regTreeModel,fitModel,predName,
doFitSelection=0,doMultiBand=1)
rmse, rmse_band = SSRS.RMSECal(Yptrain, Y_train)
trainErr1_huc2[j, i] = rmse
rmse, rmse_band = SSRS.RMSECal(Yp, Y_test)
testErr1_huc2[j, i] = rmse
# test 4: leave out 2 HUC2 one time
testErr2_huc2 = np.ones([nmodel, 18 * 17])
trainErr2_huc2 = np.ones([nmodel, 18 * 17])
hucTab = np.ones([18 * 17, 2])
IDhucfile = r"E:\work\SSRS\data\IDhuc_mb_4949.mat"
mat = sio.loadmat(IDhucfile)
IDhuc = mat["IDhuc"]
huc2 = IDhuc[indvalid, 1]
n = -1
for i in range(0, 18):
print(i)
for j in range(0, 18):
if i == j:
continue
n = n + 1
hucTab[n, 0] = i
hucTab[n, 1] = j
ind_test = np.where((huc2 == i + 1) | (huc2 == j + 1))[0]
ind_train = np.where((huc2 != i + 1) & (huc2 != j + 1))[0]
X_train = Xn[ind_train, :]
X_test = Xn[ind_test, :]
Y_train = dist[ind_train, :]
Y_test = dist[ind_test, :]
for k in range(0, nmodel):
regTreeModel = tree.DecisionTreeRegressor(max_leaf_nodes=20)
fitModel = linear_model.LinearRegression()
predSel = predListTest[k]
predName = [Field[jj] for jj in predSel]
Yp,Yptrain,regTreeModel,fitModelList,predind=\
SSRS.RegressionTree(X_train[:,predSel],X_test[:,predSel],Y_train,Y_test,regTreeModel,fitModel,predName,
doFitSelection=0,doMultiBand=1)
rmse, rmse_band = SSRS.RMSECal(Yptrain, Y_train)
trainErr2_huc2[k, n] = rmse
rmse, rmse_band = SSRS.RMSECal(Yp, Y_test)
testErr2_huc2[k, n] = rmse
return testErr,trainErr1_huc2,testErr1_huc2,\
trainErr1_huc2_rt,testErr1_huc2_rt,\
trainErr2_huc2,testErr2_huc2,hucTab
"Y_test": Y_test
})
###
regModel = linear_model.LinearRegression()
#regModel=svm.SVC()
regModel = KNeighborsRegressor(n_neighbors=10)
regModel = tree.DecisionTreeRegressor()
regModel = GaussianNB()
regModel=tree.DecisionTreeRegressor\
(max_features=0.8,max_depth=10,min_samples_split=3,min_samples_leaf=5,
min_weight_fraction_leaf=0.5,max_leaf_nodes=10)
Yp,Yptrain,regModelList=SSRS.Regression\
(X_train,X_test,Y_train,Y_test,multiband=1,regModel=regModel,doplot=2)
rmse, rmse_band = SSRS.RMSECal(Yp, Y_test)
print(rmse)
## local regression tree
regTreeModel = tree.DecisionTreeRegressor(max_leaf_nodes=20)
fitModel = linear_model.LinearRegression()
Yp,Yptrain,regTreeModel,fitModelList,predind=\
SSRS.RegressionTree(X_train,X_test,Y_train,Y_test,regTreeModel,fitModel,Field,doMultiBand=0)
rmse, rmse_band = SSRS.RMSECal(Yptrain, Y_train)
print(rmse)
rmse, rmse_band = SSRS.RMSECal(Yp, Y_test)
print(rmse)
SSRS.Regression_plot(Yptrain, Y_train, doplot=2)
SSRS.Regression_plot(Yp, Y_test, doplot=2)
