def train(self,samples):
"""Train with CPAR on the sample set, returning an AssociationRuleSet."""
current_class = samples.get_current_class()
""" original. changed by RVF, see below...
print "TRAINER FOUND PARAMETERS FROM %s"%(self.parameters)
svm_trainer = libSVMTrainer(self.parameters)
cpar_trainer = CPARTrainer(self.parameters)
"""
if self.parameters == None:
print "Using standard parameters. "
elif os.path.isfile(self.parameters):
print "TRAINER FOUND PARAMETERS FROM %s"%(self.parameters)
else:
print "Trainer DID NOT find %s"%(self.parameters)
svm_trainer = libSVMTrainer(self.parameters)
cpar_trainer = CPARTrainer(self.parameters)
arset = cpar_trainer.train(samples)
print "Found %d rules!"%(len(arset))
distinct_items = {}
for rule in arset:
for item in rule.ls:
distinct_items[item] = 1
print "Found %d distinct items"%(len(distinct_items.keys()))
sample_set_feature_selected = samples.feature_select(distinct_items.keys())
sample_set_feature_selected.set_current_class(current_class)
non_zero_features = {}
class_labels = {}
for sample in sample_set_feature_selected:
for item in nonzero(sample.get_attribute_matrix())[0]:
non_zero_features[int(item)] = 1
class_labels[sample.get_class_label()] = 1
print "Using %d features with SVM classifier over %s (%d) class labels."%(len(non_zero_features.keys()),str(class_labels.keys()),len(class_labels.keys()))
model = svm_trainer.train(sample_set_feature_selected)
return model
samples.set_current_class(options.target_class)
print "Parameters from %s"%(options.parameters)
print "Compressing features...",
samples = samples.compress_features()
print "compressed to %d distinct features."%(samples.get_number_of_features())
samples.set_current_class(options.target_class)
samples.hide_nulls(options.target_class)
test_configurations = []
confounders = ("genus","family","order","class","phylum","superkingdom")
scores_list = (("cmi",),("cwmi",),("mi","cwmi"))
feature_selector = CWMIRankFeatureSelector(confounders_filename=options.parameters,scores=("mi",),features_per_class=options.features_per_class,confounder=options.confounder)
trainer = libSVMTrainer(kernel_type="LINEAR",C=5)
classifier = libSVMClassifier()
tc = TestConfiguration("mi",feature_selector,trainer,classifier)
test_configurations.append(tc)
for scores in scores_list:
feature_selector = CWMIRankFeatureSelector(features_per_class=options.features_per_class,confounder=options.confounder,scores=scores,confounders_filename=options.parameters)
tc = TestConfiguration("%s_%s"%("_".join(scores),options.confounder),feature_selector,trainer,classifier)
test_configurations.append(tc)
root = "%s_%s_p%dn%d"%(options.target_class,options.confounder,options.features_per_class,options.features_per_class)
crossvalidator = CrossValidation(samples,options.parameters,options.folds,options.replicates,test_configurations,root_output=options.output_filename)
crossvalidator.crossvalidate()
