def regression_chaidtree_modular(num_train=500,
num_test=50,
x_range=15,
noise_var=0.2,
ft=feattypes):
try:
from modshogun import RealFeatures, RegressionLabels, CSVFile, CHAIDTree, 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])
# CHAID Tree formation
c = CHAIDTree(2, feattypes, 50)
c.set_labels(train_labels)
c.train(feats_train)
# Regress on test data
output = c.apply_regression(feats_test).get_labels()
return c, output
def multiclass_chaidtree_modular(train=traindat,
test=testdat,
labels=label_traindat,
ft=feattypes):
try:
from modshogun import RealFeatures, MulticlassLabels, CSVFile, CHAIDTree
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))
# CHAID Tree formation with nominal dependent variable
c = CHAIDTree(0, feattypes, 10)
c.set_labels(train_labels)
c.train(feats_train)
# Classify test data
output = c.apply_multiclass(feats_test).get_labels()
return c, output
