def test_get_training_data(self):
"""Test retrieval of training data."""
exploration_id = 'eid'
test_exp_filepath = os.path.join(feconf.SAMPLE_EXPLORATIONS_DIR,
'classifier_demo_exploration.yaml')
yaml_content = utils.get_file_contents(test_exp_filepath)
assets_list = []
exp_services.save_new_exploration_from_yaml_and_assets(
feconf.SYSTEM_COMMITTER_ID, yaml_content, exploration_id,
assets_list)
exploration = exp_services.get_exploration_by_id(exploration_id)
state = exploration.states['text']
expected_training_data = [{
'answer_group_index':
1,
'answers': [
u'cheerful', u'merry', u'ecstatic', u'glad', u'overjoyed',
u'pleased', u'thrilled', u'smile'
]
}]
observed_training_data = state.get_training_data()
self.assertEqual(observed_training_data, expected_training_data)
def _init_classify_inputs(self, exploration_id):
test_exp_filepath = os.path.join(feconf.TESTS_DATA_DIR, "string_classifier_test.yaml")
yaml_content = utils.get_file_contents(test_exp_filepath)
assets_list = []
exp_services.save_new_exploration_from_yaml_and_assets(
feconf.SYSTEM_COMMITTER_ID, yaml_content, exploration_id, assets_list
)
self.exp_id = exploration_id
self.exp_state = exp_services.get_exploration_by_id(exploration_id).states["Home"]
def _init_classify_inputs(self, exploration_id):
test_exp_filepath = os.path.join(feconf.TESTS_DATA_DIR,
'string_classifier_test.yaml')
yaml_content = utils.get_file_contents(test_exp_filepath)
assets_list = []
exp_services.save_new_exploration_from_yaml_and_assets(
feconf.SYSTEM_COMMITTER_ID, yaml_content,
'Testing String Classifier', 'Test', exploration_id, assets_list)
self.exp_id = exploration_id
self.exp_state = (
exp_services.get_exploration_by_id(exploration_id).states['Home'])
def post(self):
"""Handles POST requests."""
yaml_content = self.request.get('yaml_file')
new_exploration_id = exp_services.get_new_exploration_id()
if feconf.ALLOW_YAML_FILE_UPLOAD:
exp_services.save_new_exploration_from_yaml_and_assets(
self.user_id, yaml_content, new_exploration_id, [])
self.render_json({EXPLORATION_ID_KEY: new_exploration_id})
else:
raise self.InvalidInputException(
'This server does not allow file uploads.')
def _init_classify_inputs(self, exploration_id):
test_exp_filepath = os.path.join(
feconf.TESTS_DATA_DIR, 'string_classifier_test.yaml')
yaml_content = utils.get_file_contents(test_exp_filepath)
assets_list = []
exp_services.save_new_exploration_from_yaml_and_assets(
feconf.SYSTEM_COMMITTER_ID, yaml_content,
'Testing String Classifier', 'Test',
exploration_id, assets_list)
self.EXP_ID = exploration_id
self.EXP_STATE = (
exp_services.get_exploration_by_id(exploration_id).states['Home'])
def _init_classify_inputs(self, exploration_id):
test_exp_filepath = os.path.join(feconf.TESTS_DATA_DIR,
'string_classifier_test.yaml')
yaml_content = utils.get_file_contents(test_exp_filepath)
assets_list = []
with self.swap(feconf, 'ENABLE_ML_CLASSIFIERS', True):
exp_services.save_new_exploration_from_yaml_and_assets(
feconf.SYSTEM_COMMITTER_ID, yaml_content, exploration_id,
assets_list)
self.exp_id = exploration_id
self.exp_state = (
exp_services.get_exploration_by_id(exploration_id).states['Home'])
def post(self):
"""Handles POST requests."""
yaml_content = self.request.get('yaml_file')
new_exploration_id = exp_services.get_new_exploration_id()
if feconf.ALLOW_YAML_FILE_UPLOAD:
exp_services.save_new_exploration_from_yaml_and_assets(
self.user_id, yaml_content, new_exploration_id, [])
self.render_json({
EXPLORATION_ID_KEY: new_exploration_id
})
else:
raise self.InvalidInputException(
'This server does not allow file uploads.')
def post(self):
"""Handles POST requests."""
yaml_content = self.normalized_payload.get('yaml_file')
new_exploration_id = exp_fetchers.get_new_exploration_id()
if constants.ALLOW_YAML_FILE_UPLOAD:
exp_services.save_new_exploration_from_yaml_and_assets(
self.user_id,
yaml_content,
new_exploration_id, [],
strip_voiceovers=True)
self.render_json({EXPLORATION_ID_KEY: new_exploration_id})
else:
raise self.InvalidInputException(
'This server does not allow file uploads.')
def _init_classify_inputs(self, exploration_id: str) -> None:
"""Initializes all the classification inputs of the exploration
corresponding to the given exploration id.
"""
test_exp_filepath = os.path.join(feconf.TESTS_DATA_DIR,
'string_classifier_test.yaml')
yaml_content = utils.get_file_contents(test_exp_filepath)
assets_list: List[str] = []
with self.swap(feconf, 'ENABLE_ML_CLASSIFIERS', True):
exp_services.save_new_exploration_from_yaml_and_assets( # type: ignore[no-untyped-call]
feconf.SYSTEM_COMMITTER_ID, yaml_content, exploration_id,
assets_list)
self.exp_id = exploration_id
self.exp_state = (
exp_fetchers.get_exploration_by_id(exploration_id).states['Home'])
def setUp(self):
super(GenerateV1StatisticsJobTest, self).setUp()
self.exp_id = 'exp_id'
test_exp_filepath = os.path.join(feconf.TESTS_DATA_DIR,
'string_classifier_test.yaml')
yaml_content = utils.get_file_contents(test_exp_filepath)
assets_list = []
exp_services.save_new_exploration_from_yaml_and_assets(
feconf.SYSTEM_COMMITTER_ID, yaml_content, self.exp_id, assets_list)
self.exploration = exp_services.get_exploration_by_id(self.exp_id)
# Create event models for version 1 of the exploration.
stats_models.StartExplorationEventLogEntryModel.create(
self.exp_id, self.exploration.version, 'Home', 'session_id1', {},
feconf.PLAY_TYPE_NORMAL)
stats_models.StartExplorationEventLogEntryModel.create(
self.exp_id, self.exploration.version, 'Home', 'session_id2', {},
feconf.PLAY_TYPE_NORMAL)
stats_models.StateHitEventLogEntryModel.create(
self.exp_id, self.exploration.version, 'Home', 'session_id1', {},
feconf.PLAY_TYPE_NORMAL)
stats_models.StateHitEventLogEntryModel.create(
self.exp_id, self.exploration.version, 'Home', 'session_id2', {},
feconf.PLAY_TYPE_NORMAL)
stats_models.StateHitEventLogEntryModel.create(
self.exp_id, self.exploration.version, 'Home', 'session_id2', {},
feconf.PLAY_TYPE_NORMAL)
stats_models.StateHitEventLogEntryModel.create(
self.exp_id, self.exploration.version, 'End', 'session_id2', {},
feconf.PLAY_TYPE_NORMAL)
stats_models.CompleteExplorationEventLogEntryModel.create(
self.exp_id, self.exploration.version, 'End', 'session_id2', 10,
{}, feconf.PLAY_TYPE_NORMAL)
event_services.AnswerSubmissionEventHandler.record(
self.exp_id, self.exploration.version, 'Home', 'TextInput', 0, 0,
exp_domain.EXPLICIT_CLASSIFICATION, 'session_id2', 0, {},
'answer1')
event_services.AnswerSubmissionEventHandler.record(
self.exp_id, self.exploration.version, 'Home', 'TextInput', 0, 0,
exp_domain.DEFAULT_OUTCOME_CLASSIFICATION, 'session_id2', 0, {},
'answer2')
def post(self):
"""Handles POST requests."""
title = self.payload.get('title')
category = self.payload.get('category')
yaml_content = self.request.get('yaml_file')
if not title:
raise self.InvalidInputException('No title supplied.')
if not category:
raise self.InvalidInputException('No category chosen.')
new_exploration_id = exp_services.get_new_exploration_id()
if ALLOW_YAML_FILE_UPLOAD.value:
exp_services.save_new_exploration_from_yaml_and_assets(
self.user_id, yaml_content, title, category,
new_exploration_id, [])
self.render_json({EXPLORATION_ID_KEY: new_exploration_id})
else:
raise self.InvalidInputException(
'This server does not allow file uploads.')
def post(self):
"""Handles POST requests."""
title = self.payload.get('title')
category = self.payload.get('category')
yaml_content = self.request.get('yaml_file')
if not title:
raise self.InvalidInputException('No title supplied.')
if not category:
raise self.InvalidInputException('No category chosen.')
new_exploration_id = exp_services.get_new_exploration_id()
if ALLOW_YAML_FILE_UPLOAD.value:
exp_services.save_new_exploration_from_yaml_and_assets(
self.user_id, yaml_content, title, category,
new_exploration_id, [])
self.render_json({EXPLORATION_ID_KEY: new_exploration_id})
else:
raise self.InvalidInputException(
'This server does not allow file uploads.')
def test_can_undergo_classification(self):
"""Test the can_undergo_classification() function."""
exploration_id = 'eid'
test_exp_filepath = os.path.join(feconf.TESTS_DATA_DIR,
'string_classifier_test.yaml')
yaml_content = utils.get_file_contents(test_exp_filepath)
assets_list = []
exp_services.save_new_exploration_from_yaml_and_assets(
feconf.SYSTEM_COMMITTER_ID, yaml_content, exploration_id,
assets_list)
exploration = exp_services.get_exploration_by_id(exploration_id)
state_with_training_data = exploration.states['Home']
state_without_training_data = exploration.states['End']
# A state with 786 training examples.
self.assertTrue(state_with_training_data.can_undergo_classification())
# A state with no training examples.
self.assertFalse(
state_without_training_data.can_undergo_classification())
def setUp(self):
super(TrainedClassifierHandlerTest, 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 open(yaml_path, 'r') as yaml_file:
self.yaml_content = yaml_file.read()
self.signup(self.ADMIN_EMAIL, self.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_services.get_exploration_by_id(self.exp_id)
self.classifier_data_with_floats_stringified = {
'_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_jobs = (
classifier_services.get_classifier_training_jobs(
self.exp_id, self.exploration.version, ['Home']))
self.assertEqual(len(classifier_training_jobs), 1)
classifier_training_job = classifier_training_jobs[0]
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.put()
self.job_result_dict = {
'job_id': self.job_id,
'classifier_data_with_floats_stringified': (
self.classifier_data_with_floats_stringified)
}
self.payload = {}
self.payload['vm_id'] = feconf.DEFAULT_VM_ID
self.payload['message'] = self.job_result_dict
secret = feconf.DEFAULT_VM_SHARED_SECRET
self.payload['signature'] = classifier.generate_signature(
secret, self.payload['message'])
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']))
