def save_model_manager_to_s3(model_name,
model_manager,
bucket=EMMAA_BUCKET_NAME):
logger.info(f'Saving a model manager for {model_name} model to S3.')
date_str = model_manager.date_str
save_pickle_to_s3(model_manager, bucket,
f'results/{model_name}/model_manager_{date_str}.pkl')
def save_to_s3(self, bucket=EMMAA_BUCKET_NAME):
"""Dump the model state to S3."""
date_str = make_date_str()
fname = f'models/{self.name}/model_{date_str}'
# Dump as pickle
save_pickle_to_s3(self.stmts, bucket, key=fname + '.pkl')
# Dump as json
save_json_to_s3(self.stmts, bucket, key=fname + '.json')
def save_to_s3(self, bucket=EMMAA_BUCKET_NAME):
"""Dump the model state to S3."""
fname = f'models/{self.name}/model_{self.date_str}'
# Dump as pickle
save_pickle_to_s3(self.stmts, bucket, key=fname+'.pkl')
# Save ids to stmt hashes mapping as json
id_fname = f'papers/{self.name}/paper_ids_{self.date_str}.json'
save_json_to_s3(list(self.paper_ids), bucket, key=id_fname)
def save_model_manager_to_s3(model_name, model_manager,
bucket=EMMAA_BUCKET_NAME):
logger.info(f'Saving a model manager for {model_name} model to S3.')
date_str = model_manager.date_str
model_manager.model.stmts = []
model_manager.model.assembled_stmts = []
model_manager.model.dynamic_assembled_stmts = []
save_pickle_to_s3(model_manager, bucket,
f'results/{model_name}/model_manager_{date_str}.pkl')
def save_tests_to_s3(tests, bucket, key, save_format='pkl'):
"""Save tests in pkl, json or jsonl format."""
if save_format == 'pkl':
save_pickle_to_s3(tests, bucket, key)
elif save_format in ['json', 'jsonl']:
if isinstance(tests, list):
stmts = [test.stmt for test in tests]
elif isinstance(tests, dict):
stmts = [test.stmt for test in tests['tests']]
stmts_json = stmts_to_json(stmts)
save_json_to_s3(stmts_json, bucket, key, save_format)
def model_to_tests(model_name, upload=True, bucket=EMMAA_BUCKET_NAME):
em = EmmaaModel.load_from_s3(model_name, bucket=bucket)
em.run_assembly()
tests = [
StatementCheckingTest(stmt) for stmt in em.assembled_stmts
if all(stmt.agent_list())
]
date_str = make_date_str()
test_description = (
f'These tests were generated from the {em.human_readable_name} '
f'on {date_str[:10]}')
test_dict = {
'test_data': {
'description': test_description
},
'tests': tests
}
if upload:
save_pickle_to_s3(test_dict, bucket,
f'tests/{model_name}_tests_{date_str}.pkl')
return test_dict