def test_store_classifier_data(self):
"""Test the store_classifier_data method."""
exp_id = u'1'
next_scheduled_check_time = datetime.datetime.utcnow()
state_name = 'Home'
interaction_id = 'TextInput'
job_id = self._create_classifier_training_job(
feconf.INTERACTION_CLASSIFIER_MAPPING['TextInput']['algorithm_id'],
interaction_id, exp_id, 1, next_scheduled_check_time, [],
state_name, feconf.TRAINING_JOB_STATUS_PENDING, {}, 1)
# Retrieve classifier data from GCS and ensure that content is same.
classifier_training_job = (
classifier_services.get_classifier_training_job_by_id(job_id))
classifier_data = (
self._get_classifier_data_from_classifier_training_job(
classifier_training_job))
self.assertEqual(json.loads(classifier_data.model_json), {})
classifier_data_proto = text_classifier_pb2.TextClassifierFrozenModel()
classifier_data_proto.model_json = json.dumps(
{'classifier_data': 'data'})
classifier_services.store_classifier_data(job_id,
classifier_data_proto)
classifier_training_job = (
classifier_services.get_classifier_training_job_by_id(job_id))
classifier_data = (
self._get_classifier_data_from_classifier_training_job(
classifier_training_job))
self.assertDictEqual(json.loads(classifier_data.model_json),
{'classifier_data': 'data'})
def test_save_and_get_classifier_data(self) -> None:
"""Test that classifier data is stored and retrieved correctly."""
fs_services.save_classifier_data('exp_id', 'job_id',
self.classifier_data_proto)
filepath = 'job_id-classifier-data.pb.xz'
fs = fs_services.GcsFileSystem(feconf.ENTITY_TYPE_EXPLORATION,
'exp_id')
classifier_data = utils.decompress_from_zlib(fs.get(filepath))
classifier_data_proto = text_classifier_pb2.TextClassifierFrozenModel()
classifier_data_proto.ParseFromString(classifier_data)
self.assertEqual(classifier_data_proto.model_json,
self.classifier_data_proto.model_json)
def setUp(self) -> None:
super(FileSystemClassifierDataTests, self).setUp()
self.fs = fs_services.GcsFileSystem(feconf.ENTITY_TYPE_EXPLORATION,
'exp_id')
self.classifier_data_proto = (
text_classifier_pb2.TextClassifierFrozenModel())
self.classifier_data_proto.model_json = json.dumps({
'param1':
40,
'param2': [34.2, 54.13, 95.23],
'submodel': {
'param1': 12
}
})
def _create_classifier_training_job(
self, algorithm_id, interaction_id, exp_id, exp_version,
next_scheduled_check_time, training_data, state_name, status,
classifier_data, algorithm_version):
"""Creates a new classifier training job model and stores
classfier data in a file.
"""
job_id = classifier_models.ClassifierTrainingJobModel.create(
algorithm_id, interaction_id, exp_id, exp_version,
next_scheduled_check_time, training_data, state_name, status,
algorithm_version)
classifier_data_proto = text_classifier_pb2.TextClassifierFrozenModel()
classifier_data_proto.model_json = json.dumps(classifier_data)
fs_services.save_classifier_data(exp_id, job_id, classifier_data_proto)
return job_id
def setUp(self):
super(ClassifierTrainingJobModelValidatorTests, self).setUp()
self.signup(self.OWNER_EMAIL, self.OWNER_USERNAME)
self.owner_id = self.get_user_id_from_email(self.OWNER_EMAIL)
explorations = [
exp_domain.Exploration.create_default_exploration(
'%s' % i,
title='title %d' % i,
category='category%d' % i,
) for i in python_utils.RANGE(2)
]
for exp in explorations:
exp.add_states(['StateTest%s' % exp.id])
exp_services.save_new_exploration(self.owner_id, exp)
next_scheduled_check_time = datetime.datetime.utcnow()
classifier_data_proto = text_classifier_pb2.TextClassifierFrozenModel()
classifier_data_proto.model_json = json.dumps(
{'classifier_data': 'data'})
id0 = classifier_models.ClassifierTrainingJobModel.create(
'TextClassifier', 'TextInput', '0', 1, next_scheduled_check_time,
[{
'answer_group_index': 1,
'answers': ['a1', 'a2']
}], 'StateTest0', feconf.TRAINING_JOB_STATUS_NEW, 1)
fs_services.save_classifier_data('TextClassifier', id0,
classifier_data_proto)
self.model_instance_0 = (
classifier_models.ClassifierTrainingJobModel.get_by_id(id0))
id1 = classifier_models.ClassifierTrainingJobModel.create(
'TextClassifier', 'TextInput', '1', 1, next_scheduled_check_time,
[{
'answer_group_index': 1,
'answers': ['a1', 'a2']
}], 'StateTest1', feconf.TRAINING_JOB_STATUS_NEW, 1)
fs_services.save_classifier_data('TextClassifier', id1,
classifier_data_proto)
self.model_instance_1 = (
classifier_models.ClassifierTrainingJobModel.get_by_id(id1))
self.job_class = (prod_validation_jobs_one_off.
ClassifierTrainingJobModelAuditOneOffJob)
def setUp(self):
super(NextJobHandlerTest, self).setUp()
self.exp_id = 'exp_id1'
self.title = 'Testing Classifier storing'
self.category = 'Test'
interaction_id = 'TextInput'
self.algorithm_id = feconf.INTERACTION_CLASSIFIER_MAPPING[
interaction_id]['algorithm_id']
self.algorithm_version = feconf.INTERACTION_CLASSIFIER_MAPPING[
interaction_id]['algorithm_version']
self.training_data = [
{
u'answer_group_index': 1,
u'answers': [u'a1', u'a2']
},
{
u'answer_group_index': 2,
u'answers': [u'a2', u'a3']
}
]
self.job_id = classifier_models.ClassifierTrainingJobModel.create(
self.algorithm_id, interaction_id, self.exp_id, 1,
datetime.datetime.utcnow(), self.training_data, 'Home',
feconf.TRAINING_JOB_STATUS_NEW, 1)
self.classifier_data = text_classifier_pb2.TextClassifierFrozenModel()
self.classifier_data.model_json = ''
fs_services.save_classifier_data(
self.exp_id, self.job_id, self.classifier_data)
self.expected_response = {
u'job_id': self.job_id,
u'training_data': self.training_data,
u'algorithm_id': self.algorithm_id,
u'algorithm_version': self.algorithm_version
}
self.payload = {}
self.payload['vm_id'] = feconf.DEFAULT_VM_ID
secret = feconf.DEFAULT_VM_SHARED_SECRET
self.payload['message'] = json.dumps({})
self.payload['signature'] = classifier_services.generate_signature(
python_utils.convert_to_bytes(secret),
python_utils.convert_to_bytes(self.payload['message']),
self.payload['vm_id'])
def setUp(self):
super(TrainedClassifierHandlerTests, self).setUp()
self.exp_id = 'exp_id1'
self.title = 'Testing Classifier storing'
self.category = 'Test'
yaml_path = os.path.join(feconf.TESTS_DATA_DIR,
'string_classifier_test.yaml')
with python_utils.open_file(yaml_path, 'r') as yaml_file:
self.yaml_content = yaml_file.read()
self.signup(self.CURRICULUM_ADMIN_EMAIL,
self.CURRICULUM_ADMIN_USERNAME)
self.signup('*****@*****.**', 'mod')
assets_list = []
with self.swap(feconf, 'ENABLE_ML_CLASSIFIERS', True):
exp_services.save_new_exploration_from_yaml_and_assets(
feconf.SYSTEM_COMMITTER_ID, self.yaml_content, self.exp_id,
assets_list)
self.exploration = exp_fetchers.get_exploration_by_id(self.exp_id)
self.algorithm_id = feconf.INTERACTION_CLASSIFIER_MAPPING[
self.exploration.states['Home'].interaction.id]['algorithm_id']
self.algorithm_version = feconf.INTERACTION_CLASSIFIER_MAPPING[
self.exploration.states['Home'].interaction.
id]['algorithm_version']
self.classifier_data = {
'_alpha': 0.1,
'_beta': 0.001,
'_prediction_threshold': 0.5,
'_training_iterations': 25,
'_prediction_iterations': 5,
'_num_labels': 10,
'_num_docs': 12,
'_num_words': 20,
'_label_to_id': {
'text': 1
},
'_word_to_id': {
'hello': 2
},
'_w_dp': [],
'_b_dl': [],
'_l_dp': [],
'_c_dl': [],
'_c_lw': [],
'_c_l': [],
}
classifier_training_job = (
classifier_services.get_classifier_training_job(
self.exp_id, self.exploration.version, 'Home',
self.algorithm_id))
self.assertIsNotNone(classifier_training_job)
self.job_id = classifier_training_job.job_id
# TODO(pranavsid98): Replace the three commands below with
# mark_training_job_pending after Giritheja's PR gets merged.
classifier_training_job_model = (
classifier_models.ClassifierTrainingJobModel.get(self.job_id,
strict=False))
classifier_training_job_model.status = (
feconf.TRAINING_JOB_STATUS_PENDING)
classifier_training_job_model.update_timestamps()
classifier_training_job_model.put()
self.job_result = (training_job_response_payload_pb2.
TrainingJobResponsePayload.JobResult())
self.job_result.job_id = self.job_id
classifier_frozen_model = (
text_classifier_pb2.TextClassifierFrozenModel())
classifier_frozen_model.model_json = json.dumps(self.classifier_data)
self.job_result.text_classifier.CopyFrom(classifier_frozen_model)
self.payload_proto = (
training_job_response_payload_pb2.TrainingJobResponsePayload())
self.payload_proto.job_result.CopyFrom(self.job_result)
self.payload_proto.vm_id = feconf.DEFAULT_VM_ID
self.secret = feconf.DEFAULT_VM_SHARED_SECRET
self.payload_proto.signature = classifier_services.generate_signature(
python_utils.convert_to_bytes(self.secret),
python_utils.convert_to_bytes(
self.payload_proto.job_result.SerializeToString()),
self.payload_proto.vm_id)
self.payload_for_fetching_next_job_request = {
'vm_id': feconf.DEFAULT_VM_ID,
'message': json.dumps({})
}
self.payload_for_fetching_next_job_request['signature'] = (
classifier_services.generate_signature(
python_utils.convert_to_bytes(self.secret),
python_utils.convert_to_bytes(
self.payload_for_fetching_next_job_request['message']),
self.payload_for_fetching_next_job_request['vm_id']))
