trainer = TrainerClass.__dict__[classname](options.parameters, C=options.C)
else:
trainer = TrainerClass.__dict__[classname](options.parameters)
trainer.set_null_flag("NULL")
modulepath = "pica.classifiers.%s"%(options.classification_algorithm)
classname = options.classification_algorithm.split(".")[-1]
ClassifierClass = __import__(modulepath, fromlist=(classname,))
classifier = ClassifierClass.__dict__[classname](options.parameters)
classifier.set_null_flag("NULL")
test_configurations = [TestConfiguration("A",None,trainer,classifier)]
#RVF changed (added the last 3 parameters)
if ( options.crossval_files ):
crossvalidator = CrossValidation(samples,options.parameters,options.folds,options.replicates,test_configurations,False,None,options.target_class,options.output_filename)
else:
crossvalidator = CrossValidation(samples,options.parameters,options.folds,options.replicates,test_configurations)
crossvalidator.crossvalidate()
classifications,misclassifications = crossvalidator.get_classification_vector()
metadata = None
if options.metadata:
metadata = fileio.load_metadata(options.metadata)
fout = open(options.output_filename,"w")
fout.write("who\t%s\tFalse Classifications\tTrue Classifications\tTotal"%(options.target_class))
if metadata:
for key in metadata.get_key_list():
fout.write("\t%s"%(key))
fout.write("\n")
for who in misclassifications.keys():
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()