def BuildModel(self, data, labels, options):
cart = CARTree()
cart.set_feature_types(np.array([False] * data.get_num_features()))
cart.set_labels(labels)
cart.train(data)
return cart
def regression_cartree_modular(num_train=500,num_test=50,x_range=15,noise_var=0.2,ft=feattypes):
try:
from modshogun import RealFeatures, RegressionLabels, CSVFile, CARTree, PT_REGRESSION
from numpy import random
except ImportError:
print("Could not import Shogun and/or numpy modules")
return
random.seed(1)
# form training dataset : y=x with noise
X_train=random.rand(1,num_train)*x_range;
Y_train=X_train+random.randn(num_train)*noise_var
# form test dataset
X_test=array([[float(i)/num_test*x_range for i in range(num_test)]])
# wrap features and labels into Shogun objects
feats_train=RealFeatures(X_train)
feats_test=RealFeatures(X_test)
train_labels=RegressionLabels(Y_train[0])
# CART Tree formation
c=CARTree(ft,PT_REGRESSION,5,True)
c.set_labels(train_labels)
c.train(feats_train)
# Classify test data
output=c.apply_regression(feats_test).get_labels()
return c,output
def BuildModel(self, data, labels, options):
cart = CARTree()
cart.set_feature_types(np.array([False] * data.get_num_features()))
cart.set_labels(labels)
cart.train(data)
return cart
def stochasticgbmachine_modular(train=traindat,train_labels=label_traindat,ft=feat_types):
try:
from modshogun import RealFeatures, RegressionLabels, CSVFile, CARTree, StochasticGBMachine, SquaredLoss
except ImportError:
print("Could not import Shogun modules")
return
# wrap features and labels into Shogun objects
feats=RealFeatures(CSVFile(train))
labels=RegressionLabels(CSVFile(train_labels))
# divide into training (90%) and test dataset (10%)
p=np.random.permutation(labels.get_num_labels())
num=labels.get_num_labels()*0.9
cart=CARTree()
cart.set_feature_types(ft)
cart.set_max_depth(1)
loss=SquaredLoss()
s=StochasticGBMachine(cart,loss,500,0.01,0.6)
# train
feats.add_subset(np.int32(p[0:num]))
labels.add_subset(np.int32(p[0:num]))
s.set_labels(labels)
s.train(feats)
feats.remove_subset()
labels.remove_subset()
# apply
feats.add_subset(np.int32(p[num:len(p)]))
labels.add_subset(np.int32(p[num:len(p)]))
output=s.apply_regression(feats)
feats.remove_subset()
labels.remove_subset()
return s,output
def multiclass_cartree_modular(train=traindat,
test=testdat,
labels=label_traindat,
ft=feattypes):
try:
from modshogun import RealFeatures, MulticlassLabels, CSVFile, CARTree, PT_MULTICLASS
except ImportError:
print("Could not import Shogun modules")
return
# wrap features and labels into Shogun objects
feats_train = RealFeatures(CSVFile(train))
feats_test = RealFeatures(CSVFile(test))
train_labels = MulticlassLabels(CSVFile(labels))
# CART Tree formation with 5 fold cross-validation pruning
c = CARTree(ft, PT_MULTICLASS, 5, True)
c.set_labels(train_labels)
c.train(feats_train)
# Classify test data
output = c.apply_multiclass(feats_test).get_labels()
return c, output
def multiclass_cartree_modular(train=traindat,test=testdat,labels=label_traindat,ft=feattypes):
try:
from modshogun import RealFeatures, MulticlassLabels, CSVFile, CARTree, PT_MULTICLASS
except ImportError:
print("Could not import Shogun modules")
return
# wrap features and labels into Shogun objects
feats_train=RealFeatures(CSVFile(train))
feats_test=RealFeatures(CSVFile(test))
train_labels=MulticlassLabels(CSVFile(labels))
# CART Tree formation with 5 fold cross-validation pruning
c=CARTree(ft,PT_MULTICLASS,5,True)
c.set_labels(train_labels)
c.train(feats_train)
# Classify test data
output=c.apply_multiclass(feats_test).get_labels()
return c,output
def stochasticgbmachine_modular(train=traindat,
train_labels=label_traindat,
ft=feat_types):
try:
from modshogun import RealFeatures, RegressionLabels, CSVFile, CARTree, StochasticGBMachine, SquaredLoss
except ImportError:
print("Could not import Shogun modules")
return
# wrap features and labels into Shogun objects
feats = RealFeatures(CSVFile(train))
labels = RegressionLabels(CSVFile(train_labels))
# divide into training (90%) and test dataset (10%)
p = np.random.permutation(labels.get_num_labels())
num = labels.get_num_labels() * 0.9
cart = CARTree()
cart.set_feature_types(ft)
cart.set_max_depth(1)
loss = SquaredLoss()
s = StochasticGBMachine(cart, loss, 500, 0.01, 0.6)
# train
feats.add_subset(np.int32(p[0:num]))
labels.add_subset(np.int32(p[0:num]))
s.set_labels(labels)
s.train(feats)
feats.remove_subset()
labels.remove_subset()
# apply
feats.add_subset(np.int32(p[num:len(p)]))
labels.add_subset(np.int32(p[num:len(p)]))
output = s.apply_regression(feats)
feats.remove_subset()
labels.remove_subset()
return s, output
