def createNaiveBayesConf(self):
exp = self.experiment
name = '-'.join([
'AL' + str(exp.experiment_id),
'Iter' + str(self.iteration.iteration_number), 'all', 'NaiveBayes'
])
naive_bayes_exp = ClassificationExperiment(exp.secuml_conf,
session=exp.session)
naive_bayes_exp.initExperiment(exp.project,
exp.dataset,
experiment_name=name,
parent=exp.experiment_id)
test_conf = UnlabeledLabeledConf(logger=exp.logger)
naive_bayes_conf = GaussianNaiveBayesConfiguration(
exp.conf.models_conf['multiclass'].n_jobs,
exp.conf.models_conf['multiclass'].num_folds,
False,
True,
test_conf,
logger=exp.logger)
naive_bayes_exp.setConf(naive_bayes_conf,
exp.features_filename,
annotations_id=exp.annotations_id)
naive_bayes_exp.export()
return naive_bayes_conf
def createNaiveBayesConf(self):
test_conf = UnlabeledLabeledConf(logger=self.conf.logger)
naive_bayes_conf = GaussianNaiveBayesConfiguration(
4,
False,
True,
test_conf,
logger=self.conf.logger)
return naive_bayes_conf
def gornitzBinaryModelConf(logger):
classifier_args = {}
classifier_args['num_folds'] = 4
classifier_args['sample_weight'] = False
classifier_args['families_supervision'] = False
test_conf = UnlabeledLabeledConf()
classifier_args['test_conf'] = test_conf
binary_model_conf = ClassifierConfFactory.getFactory().fromParam(
'Sssvdd', classifier_args, logger=logger)
return binary_model_conf
def generateParamsFromArgs(args):
supervised_args = {}
supervised_args['num_folds'] = 4
supervised_args['sample_weight'] = False
supervised_args['families_supervision'] = False
test_conf = UnlabeledLabeledConf()
supervised_args['test_conf'] = test_conf
binary_model_conf = ClassifierConfFactory.getFactory().fromParam(
'Sssvdd', supervised_args)
params = ActiveLearningConfiguration.generateParamsFromArgs(
args, binary_model_conf=binary_model_conf)
params['batch'] = args.batch
return params
def getMulticlassModel(self):
params = {}
params['num_folds'] = 4
params['sample_weight'] = False
params['families_supervision'] = True
params['optim_algo'] = 'liblinear'
params['alerts_conf'] = None
test_conf = UnlabeledLabeledConf(logger=self.alerts_conf.logger)
params['test_conf'] = test_conf
conf = ClassifierConfFactory.getFactory().fromParam(
'LogisticRegression', params, logger=self.alerts_conf.logger)
model = conf.model_class(conf)
return model
def generateParamsFromArgs(args, logger=None):
supervised_args = {}
supervised_args['num_folds'] = 4
supervised_args['sample_weight'] = False
supervised_args['families_supervision'] = False
test_conf = UnlabeledLabeledConf(logger=logger)
supervised_args['test_conf'] = test_conf
binary_model_conf = ClassifierConfFactory.getFactory().fromParam(
'LogisticRegression', supervised_args, logger=logger)
params = ActiveLearningConfiguration.generateParamsFromArgs(
args, binary_model_conf=binary_model_conf, logger=logger)
params['num_annotations'] = args.num_annotations
return params
def aladinMulticlassModelConf(logger):
classifier_args = {}
classifier_args['num_folds'] = 4
classifier_args['sample_weight'] = False
classifier_args['families_supervision'] = True
classifier_args['alerts_conf'] = None
classifier_args['optim_algo'] = 'liblinear'
test_conf = UnlabeledLabeledConf(logger=logger)
classifier_args['test_conf'] = test_conf
factory = ClassifierConfFactory.getFactory()
multiclass_model_conf = factory.fromParam('LogisticRegression',
classifier_args,
logger=logger)
return multiclass_model_conf
def generateParamsFromArgs(args):
params = ActiveLearningConfiguration.generateParamsFromArgs(args)
multiclass_classifier_args = {}
multiclass_classifier_args['num_folds'] = args.num_folds
multiclass_classifier_args['sample_weight'] = False
multiclass_classifier_args['families_supervision'] = True
multiclass_classifier_args['alerts_conf'] = None
test_conf = UnlabeledLabeledConf()
multiclass_classifier_args['test_conf'] = test_conf
multiclass_conf = ClassifierConfFactory.getFactory().fromParam(
args.model_class, multiclass_classifier_args)
rare_category_detection_conf = RareCategoryDetectionStrategy(multiclass_conf,
args.cluster_strategy, args.num_annotations, 'uniform')
params['rare_category_detection_conf'] = rare_category_detection_conf
params['num_annotations'] = args.num_annotations
params['multiclass_model_conf'] = multiclass_conf
return params
def generateParamsFromArgs(args):
params = ActiveLearningConfiguration.generateParamsFromArgs(args)
multiclass_classifier_args = {}
multiclass_classifier_args['num_folds'] = args.num_folds
multiclass_classifier_args['sample_weight'] = False
multiclass_classifier_args['families_supervision'] = True
multiclass_classifier_args['optim_algo'] = 'liblinear'
test_conf = UnlabeledLabeledConf()
multiclass_classifier_args['test_conf'] = test_conf
multiclass_conf = ClassifierConfFactory.getFactory().fromParam(
'LogisticRegression', multiclass_classifier_args)
rare_category_detection_conf = RareCategoryDetectionStrategy(multiclass_conf,
args.cluster_strategy, args.num_annotations, 'uniform')
params['rare_category_detection_conf'] = rare_category_detection_conf
params['num_uncertain'] = args.num_uncertain
params['eps'] = 0.49
return params
def getNaiveBayesConf(self):
exp = self.experiment
name = '-'.join([
'AL' + str(exp.experiment_id),
'Iter' + str(self.iteration.iteration_number), 'all', 'NaiveBayes'
])
naive_bayes_exp = ClassificationExperiment(exp.project,
exp.dataset,
exp.session,
experiment_name=name,
parent=exp.experiment_id)
test_conf = UnlabeledLabeledConf()
naive_bayes_conf = GaussianNaiveBayesConfiguration(
exp.conf.num_folds, False, True, test_conf)
naive_bayes_exp.setConf(naive_bayes_conf,
exp.features_filename,
annotations_id=exp.annotations_id)
naive_bayes_exp.export()
return naive_bayes_conf
def generateParamsFromArgs(args, binary_model_conf=None):
if binary_model_conf is None:
supervised_args = {}
supervised_args['num_folds'] = args.num_folds
supervised_args['sample_weight'] = args.sample_weight
supervised_args['families_supervision'] = False
supervised_args['test_conf'] = UnlabeledLabeledConf()
binary_model_conf = ClassifierConfFactory.getFactory().fromParam(
args.model_class, supervised_args)
active_learning_params = {}
active_learning_params['auto'] = args.auto
active_learning_params['budget'] = args.budget
active_learning_params['binary_model_conf'] = binary_model_conf
validation_conf = None
if args.validation_dataset is not None:
validation_conf = ValidationDatasetConf(args.validation_dataset)
active_learning_params['validation_conf'] = validation_conf
return active_learning_params
def getNaiveBayesConf(self):
test_conf = UnlabeledLabeledConf()
naive_bayes_conf = GaussianNaiveBayesConfiguration(
4, False, True, test_conf)
return naive_bayes_conf
