def export(self):
experiment_dir = dir_tools.getExperimentOutputDirectory(self)
dir_tools.createDirectory(experiment_dir)
conf_filename = experiment_dir + 'conf.json'
with open(conf_filename, 'w') as f:
json.dump(self.toJson(), f,
indent = 2)
def removeExperimentDB(self):
experiment_id, experiment_label_id = self.isInDB()
if experiment_id is None:
return
self.experiment_id = experiment_id
self.experiment_label_id = experiment_label_id
## Remove children experiments
children = experiment_db_tools.getChildren(self.cursor, experiment_id)
for child in children:
child_exp = ExperimentFactory.getFactory().fromJson(
self.project, self.dataset, child, self.db, self.cursor)
child_exp.removeExperimentDB()
if self.parent is None:
labels_tools.removeExperimentLabels(self.cursor,
experiment_label_id)
self.cursor.execute(
'DELETE FROM Experiments \
WHERE name = %s \
AND kind = %s', (
self.experiment_name,
self.kind,
))
self.db.commit()
experiment_dir = dir_tools.getExperimentOutputDirectory(self)
dir_tools.removeDirectory(experiment_dir)
def activeLearningSuggestionsMonitoring(project, dataset, experiment_id, iteration):
experiment = ExperimentFactory.getFactory().fromJson(project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment) + str(int(iteration) - 1) + '/'
filename += 'suggestions_accuracy/'
filename += 'labels_families'
filename += '_high_confidence_suggestions.png'
return send_file(filename)
def getAnnotationsTypes(project, dataset, experiment_id, iteration):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment) + str(
iteration) + '/'
filename += 'annotations_types.json'
return send_file(filename)
def getFamiliesInstancesToAnnotate(project, dataset, experiment_id, iteration,
predicted_label):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment) + str(
iteration) + '/'
filename += 'toannotate_' + predicted_label + '.json'
return send_file(filename)
def getNumComponents(project, dataset, experiment_id):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
directory = dir_tools.getExperimentOutputDirectory(experiment)
filename = directory + 'projection_matrix.csv'
with open(filename, 'r') as f:
header = f.readline()
num_components = len(header.split(',')) - 1
return str(num_components)
def getStatsPlot(project, dataset, experiment_id, plot_type, feature):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(
experiment) + feature + '/'
if plot_type.find('histogram') >= 0:
filename += plot_type + '.json'
else:
filename += plot_type + '.png'
return send_file(filename)
def getInstancesToAnnotate(project, dataset, experiment_id, iteration,
predicted_label):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment) + str(
iteration) + '/'
filename += 'toannotate_' + predicted_label + '.csv'
df = pd.read_csv(filename)
queries = list(df.instance_id)
return jsonify({'instances': queries})
def getPredictions(project, dataset, experiment_id, train_test, index):
experiment = ExperimentFactory.getFactory().fromJson(project, dataset, experiment_id,
db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += train_test + '/predictions.csv'
index = int(index)
min_value = index * 0.1
max_value = (index+1) * 0.1
with open(filename, 'r') as f:
data = pd.read_csv(f, header = 0, index_col = 0)
data = matrix_tools.extractRowsWithThresholds(data, min_value, max_value,
'predicted_proba')
selected_instances = list(data.index.values)
proba = list(data['predicted_proba'])
return jsonify({'instances': selected_instances, 'proba': proba})
def getAlerts(project, dataset, experiment_id, analysis_type):
experiment = ExperimentFactory.getFactory().fromJson(project, dataset, experiment_id,
db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += 'alerts.csv'
with open(filename, 'r') as f:
data = pd.read_csv(f, header = 0, index_col = 0)
num_max_alerts = experiment.classification_conf.test_conf.alerts_conf.num_max_alerts
alerts = list(data[['predicted_proba']].itertuples())
if num_max_alerts < len(alerts):
if analysis_type == 'topN':
alerts = alerts[:num_max_alerts]
elif analysis_type == 'random':
alerts = random.sample(alerts, num_max_alerts)
return jsonify({'instances': [alert[0] for alert in alerts], 'proba': dict(alerts)})
def runNextIteration(project, dataset, experiment_id, iteration_number):
res = str(celeryRunNextIteration.s().apply_async())
if user_exp:
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [datetime.datetime.now(), 'nextIteration', iteration_number]
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return res
def currentAnnotations(project, dataset, experiment_id, iteration):
page = render_template('ActiveLearning/current_annotations.html',
project=project)
if user_exp:
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [datetime.datetime.now(), 'displayAnnotatedInstances']
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return page
def changeFamilyLabel(project, dataset, experiment_id, experiment_label_id,
label, family):
mysql_tools.useDatabase(cursor, project, dataset)
labels_tools.changeFamilyLabel(cursor, label, family, experiment_label_id)
if user_exp:
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [
datetime.datetime.now(), 'changeFamilyLabel', family, label
]
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return ''
def mergeFamilies(project, dataset, experiment_id, experiment_label_id, label,
families, new_family_name):
families = families.split(',')
mysql_tools.useDatabase(cursor, project, dataset)
labels_tools.mergeFamilies(cursor, label, families, new_family_name,
experiment_label_id)
if user_exp:
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [datetime.datetime.now(), 'mergeFamilies', new_family_name]
to_print += map(str, families)
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return ''
def removeLabel(project, dataset, experiment_id, inst_dataset,
inst_experiment_label_id, iteration_number, instance_id):
mysql_tools.useDatabase(cursor, project, inst_dataset)
labels_tools.removeLabel(cursor, inst_experiment_label_id, instance_id)
db.commit()
if user_exp:
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += 'user_actions.log'
file_exists = dir_tools.checkFileExists(filename)
mode = 'a' if file_exists else 'w'
to_print = [
datetime.datetime.now(), 'removeLabel', project, dataset,
instance_id
]
to_print = map(str, to_print)
to_print = ','.join(to_print)
with open(filename, mode) as f:
print >> f, to_print
return ''
def getProjectionMatrix(project, dataset, experiment_id):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
directory = dir_tools.getExperimentOutputDirectory(experiment)
filename = directory + 'projection_matrix.csv'
return send_file(filename)
def getHexBin(project, dataset, experiment_id, x, y):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
directory = dir_tools.getExperimentOutputDirectory(experiment)
filename = directory + 'c_' + x + '_' + y + '_hexbin.json'
return send_file(filename)
def getModelPipeline(self):
experiment_dir = dir_tools.getExperimentOutputDirectory(self)
pipeline = joblib.load(experiment_dir + '/model/model.out')
return pipeline
def setDirectories(self):
self.AL_directory = dir_tools.getExperimentOutputDirectory(
self.experiment)
self.iteration_dir = self.AL_directory
self.iteration_dir += str(self.iteration_number) + '/'
def getFeaturesTypes(project, dataset, experiment_id):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += 'features_types.json'
return send_file(filename)
def getLabelsMonitoring(project, dataset, experiment_id, iteration):
experiment = ExperimentFactory.getFactory().fromJson(project, dataset, experiment_id,
db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment) + str(iteration) + '/'
filename += 'labels_monitoring/labels_monitoring.json'
return send_file(filename)
def getAlertsClusteringExperimentId(project, dataset, experiment_id):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
filename = dir_tools.getExperimentOutputDirectory(experiment)
filename += 'grouping.json'
return send_file(filename)
def getDir(project, dataset, experiment_id):
exp = ExperimentFactory.getFactory().fromJson(project, dataset,
experiment_id, db, cursor)
return dir_tools.getExperimentOutputDirectory(exp)
def __init__(self, experiment):
self.experiment = experiment
self.conf = experiment.conf
self.num_components = self.conf.num_components
self.output_directory = dir_tools.getExperimentOutputDirectory(
experiment)
def __init__(self, experiment):
self.instances = Instances()
self.instances.initFromExperiment(experiment)
self.output_directory = dir_tools.getExperimentOutputDirectory(
experiment)
def getCumExplVar(project, dataset, experiment_id):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
directory = dir_tools.getExperimentOutputDirectory(experiment)
filename = directory + 'cumuled_explained_variance.csv'
return send_file(filename)
def getReconsErrors(project, dataset, experiment_id):
experiment = ExperimentFactory.getFactory().fromJson(
project, dataset, experiment_id, db, cursor)
directory = dir_tools.getExperimentOutputDirectory(experiment)
filename = directory + 'reconstruction_errors.csv'
return send_file(filename)
def setOutputDirectory(self):
self.output_directory = dir_tools.getExperimentOutputDirectory(
self.experiment)
