def classifier_featureblock_logistic_regression(fm_train=traindat,
fm_test=testdat,
label_train=label_traindat):
from shogun import BinaryLabels, RealFeatures, IndexBlock, IndexBlockGroup
try:
from shogun import FeatureBlockLogisticRegression
except ImportError:
print("FeatureBlockLogisticRegression not available")
exit(0)
features = RealFeatures(hstack((traindat, traindat)))
labels = BinaryLabels(hstack((label_train, label_train)))
n_features = features.get_num_features()
block_one = IndexBlock(0, n_features // 2)
block_two = IndexBlock(n_features // 2, n_features)
block_group = IndexBlockGroup()
block_group.add_block(block_one)
block_group.add_block(block_two)
mtlr = FeatureBlockLogisticRegression(0.1, features, labels, block_group)
mtlr.set_regularization(1) # use regularization ratio
mtlr.set_tolerance(1e-2) # use 1e-2 tolerance
mtlr.train()
out = mtlr.apply().get_labels()
return out
def classifier_featureblock_logistic_regression (fm_train=traindat,fm_test=testdat,label_train=label_traindat):
from shogun import BinaryLabels, RealFeatures, IndexBlock, IndexBlockGroup
try:
from shogun import FeatureBlockLogisticRegression
except ImportError:
print("FeatureBlockLogisticRegression not available")
exit(0)
features = RealFeatures(hstack((traindat,traindat)))
labels = BinaryLabels(hstack((label_train,label_train)))
n_features = features.get_num_features()
block_one = IndexBlock(0,n_features//2)
block_two = IndexBlock(n_features//2,n_features)
block_group = IndexBlockGroup()
block_group.add_block(block_one)
block_group.add_block(block_two)
mtlr = FeatureBlockLogisticRegression(0.1,features,labels,block_group)
mtlr.set_regularization(1) # use regularization ratio
mtlr.set_tolerance(1e-2) # use 1e-2 tolerance
mtlr.train()
out = mtlr.apply().get_labels()
return out
class SHOGUN_DTR(object):
'''
Create the CART Tree Regression benchmark instance.
@type method_param - dict
@param method_paramm - Extra options for the benchmarking method.
@type run_param - dict
@param run_param - Path option for executing the benchmark. Not used for
Shogun.
'''
def __init__(self, method_param, run_param):
self.info = "SHOGUN_DTR (" + str(method_param) + ")"
# Assemble run model parameter.
self.data = load_dataset(method_param["datasets"], ["csv"])
self.data_split = split_dataset(self.data[0])
self.train_feat = RealFeatures(self.data_split[0].T)
self.train_labels = RegressionLabels(self.data_split[1])
if len(self.data) >= 2:
self.test_feat = RealFeatures(self.data[1].T)
# Flag for Cross Validation Pruning
self.cv_prune = False
if "pruning" in method_param:
self.cv_prune = bool(method_param["pruning"])
self.num_folds = 2
if "k" in method_param:
# Making sure that the value is of the right type
self.num_folds = int(method_param["k"])
'''
Return information about the benchmarking isntance.
@rtype - str
@returns - Information as a single string
'''
def __str__(self):
return self.info
'''
Calculate metrics to be used for benckmarking.
@rtype - dict
@returns - Evaluated metrics.
'''
def metric(self):
totalTimer = Timer()
with totalTimer:
model = CARTree(np.array([False] * self.train_feat.get_num_features()),
PT_REGRESSION, self.num_folds, self.cv_prune)
model.set_labels(self.train_labels)
model.train(self.train_feat)
if len(self.data) >= 2:
predictions = model.apply_regression(self.test_feat).get_labels()
metric = {}
metric["runtime"] = totalTimer.ElapsedTime()
if len(self.data) >= 3:
confusionMatrix = Metrics.ConfusionMatrix(self.data[2], predictions)
metric['ACC'] = Metrics.AverageAccuracy(confusionMatrix)
metric['MCC'] = Metrics.MCCMultiClass(confusionMatrix)
metric['Precision'] = Metrics.AvgPrecision(confusionMatrix)
metric['Recall'] = Metrics.AvgRecall(confusionMatrix)
metric['MSE'] = Metrics.SimpleMeanSquaredError(self.data[2], predictions)
return metric
