def runNaiveBayes(self):
# Create an experiment for the naive Bayes model
exp = self.iteration.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.db,
exp.cursor,
experiment_name=name,
experiment_label=exp.experiment_label,
parent=exp.experiment_id)
naive_bayes_exp.setFeaturesFilenames(exp.features_filenames)
test_conf = TestConfiguration()
test_conf.setUnlabeled(labels_annotations='annotations')
naive_bayes_conf = GaussianNaiveBayesConfiguration(
exp.conf.models_conf['multiclass'].num_folds, False, True,
test_conf)
naive_bayes_exp.setClassifierConf(naive_bayes_conf)
naive_bayes_exp.createExperiment()
naive_bayes_exp.export()
# Update training data - the naive Bayes classifier is trained on all the data
self.datasets.test_instances.families = list(self.lr_predicted_labels)
all_datasets = ClassifierDatasets(naive_bayes_exp,
naive_bayes_exp.classification_conf)
train_instances = Instances()
train_instances.union(self.datasets.train_instances,
self.datasets.test_instances)
all_datasets.train_instances = train_instances
all_datasets.test_instances = None
all_datasets.setSampleWeights()
self.evalClusteringPerf(all_datasets.train_instances)
# Train the naive Bayes detection model and predict
self.naive_bayes = GaussianNaiveBayes(naive_bayes_exp, all_datasets)
self.naive_bayes.training()
self.nb_time = self.naive_bayes.training_execution_time
self.datasets.test_instances.families = [
None
] * self.datasets.test_instances.numInstances()
self.nb_predicted_log_proba = self.naive_bayes.pipeline.predict_log_proba(
self.datasets.test_instances.getFeatures())
start_time = time.time()
self.nb_predicted_labels = self.naive_bayes.pipeline.predict(
self.datasets.test_instances.getFeatures())
self.nb_time += time.time() - start_time
self.nb_class_labels = self.naive_bayes.class_labels
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.project, exp.dataset, exp.session,
experiment_name = name,
labels_id = exp.labels_id,
parent = exp.experiment_id)
naive_bayes_exp.setFeaturesFilenames(exp.features_filenames)
test_conf = TestConfiguration()
test_conf.setUnlabeled(labels_annotations = 'annotations')
naive_bayes_conf = GaussianNaiveBayesConfiguration(exp.conf.models_conf['multiclass'].num_folds, False, True, test_conf)
naive_bayes_exp.setClassifierConf(naive_bayes_conf)
naive_bayes_exp.createExperiment()
naive_bayes_exp.export()
return naive_bayes_conf
def createNaiveBayesConf(self):
test_conf = TestConfiguration()
test_conf.setUnlabeled(labels_annotations='annotations')
naive_bayes_conf = GaussianNaiveBayesConfiguration(
4, False, True, test_conf)
return naive_bayes_conf