def runModel(self, kind, conf):
self.setDatasets(conf)
# Create the experiment
exp = self.iteration.experiment
name = 'AL' + str(exp.experiment_id) + '-Iter' + str(
self.iteration.iteration_number) + '-' + kind
model_exp = ClassificationExperiment(
exp.project,
exp.dataset,
exp.db,
exp.cursor,
experiment_name=name,
experiment_label=exp.experiment_label,
parent=exp.experiment_id)
model_exp.setFeaturesFilenames(exp.features_filenames)
model_exp.setClassifierConf(conf)
model_exp.createExperiment()
model_exp.export()
# Build the model
model = conf.model_class(model_exp, self.datasets, cv_monitoring=True)
model.run()
self.models[kind] = model
# Execution time monitoring
time = model.training_execution_time + model.testing_execution_time
self.times[kind] = time
def createMulticlassExperiment(self):
exp = self.supervised_exp
name = exp.experiment_name + '_alertsMulticlassClassifier'
multiclass_exp = ClassificationExperiment(
exp.project,
exp.dataset,
exp.db,
exp.cursor,
experiment_name=name,
experiment_label=exp.experiment_label,
parent=exp.experiment_id)
multiclass_exp.setFeaturesFilenames(exp.features_filenames)
params = {}
params['num_folds'] = exp.classification_conf.num_folds
params['sample_weight'] = False
params['families_supervision'] = True
params['optim_algo'] = 'sag'
params['alerts_conf'] = None
test_conf = TestConfiguration()
test_conf.setUnlabeled(labels_annotations='annotations')
params['test_conf'] = test_conf
conf = ClassifierConfFactory.getFactory().fromParam(
'LogisticRegression', params)
multiclass_exp.setClassifierConf(conf)
multiclass_exp.createExperiment()
multiclass_exp.export()
return multiclass_exp
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 createMulticlassExperiment(self):
conf = self.rare_category_detection_conf.classification_conf
exp = self.iteration.experiment
name = '-'.join(['AL' + str(exp.experiment_id),
'Iter' + str(self.iteration.iteration_number),
self.label,
'analysis'])
multiclass_exp = ClassificationExperiment(exp.project, exp.dataset, exp.session,
experiment_name = name,
labels_id = exp.labels_id,
parent = exp.experiment_id)
multiclass_exp.setFeaturesFilenames(exp.features_filenames)
multiclass_exp.setClassifierConf(conf)
multiclass_exp.createExperiment()
multiclass_exp.export()
return multiclass_exp
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
class RareCategoryDetectionAnnotationQueriesExp(
RareCategoryDetectionAnnotationQueries):
def __init__(self,
iteration,
label,
proba_min,
proba_max,
multiclass_model=None,
multiclass_exp=None):
RareCategoryDetectionAnnotationQueries.__init__(self,
iteration,
label,
proba_min,
proba_max,
multiclass_model=None)
self.multiclass_exp = multiclass_exp
self.experiment = iteration.experiment
def getMulticlassConf(self):
conf = self.rare_category_detection_conf.classification_conf
exp = self.experiment
name = '-'.join([
'AL' + str(exp.experiment_id),
'Iter' + str(self.iteration.iteration_number), self.label,
'analysis'
])
self.multiclass_exp = ClassificationExperiment(
exp.project,
exp.dataset,
exp.session,
experiment_name=name,
labels_id=exp.labels_id,
parent=exp.experiment_id)
self.multiclass_exp.setFeaturesFilenames(exp.features_filenames)
self.multiclass_exp.setClassifierConf(conf)
self.multiclass_exp.createExperiment()
self.multiclass_exp.export()
return conf
def createClusteringExperiment(self):
conf = ClusteringConfiguration(self.categories.numCategories())
exp = self.experiment
name = '-'.join([
'AL' + str(exp.experiment_id),
'Iter' + str(self.iteration.iteration_number), self.label,
'clustering'
])
clustering_exp = ClusteringExperiment(exp.project,
exp.dataset,
exp.session,
conf,
labels_id=exp.labels_id,
experiment_name=name,
parent=exp.experiment_id)
clustering_exp.setFeaturesFilenames(exp.features_filenames)
clustering_exp.createExperiment()
clustering_exp.export()
return clustering_exp
def generateClusteringVisualization(self):
if self.families_analysis:
self.clustering_exp = self.createClusteringExperiment()
clustering = Clustering(self.categories.instances,
self.categories.assigned_categories)
clustering.generateClustering(None, None)
clustering.export(self.clustering_exp.getOutputDirectory())
else:
self.clustering_exp = None
def setCategories(self, all_instances, assigned_categories,
predicted_proba):
self.categories = CategoriesExp(self.multiclass_exp, self.iteration,
all_instances, assigned_categories,
predicted_proba, self.label,
self.multiclass_model.class_labels)