def test_dmlrunner_same_train_job_with_split_1( \
runner, mnist_filepath):
split_job = make_split_job(mnist_filepath)
split_job.hyperparams['split'] = 1
job_results = runner.run_job(split_job)
session_filepath = job_results.results['session_filepath']
datapoint_count = job_results.results['datapoint_count']
initialize_job = make_initialize_job()
initial_weights = runner.run_job(initialize_job).results['weights']
train_job = make_train_job(
initial_weights,
session_filepath,
datapoint_count
)
result = runner.run_job(train_job)
assert result.status == 'successful'
results = result.results
new_weights = results['weights']
omega = results['omega']
train_stats = results['train_stats']
assert result.job.job_type is JobTypes.JOB_TRAIN.name
assert type(new_weights) == list
assert type(new_weights[0]) == np.ndarray
assert type(omega) == int or type(omega) == float
assert type(train_stats) == dict
def split_dmlresult_obj(config_manager, mnist_filepath):
model_json = make_model_json()
runner = DMLRunner(config_manager)
split_job = make_split_job(
model_json,
mnist_filepath,
)
split_job.hyperparams['split'] = 0.75
job_results = runner.run_job(split_job)
return job_results
def split_dmlresult_obj(config_manager, mnist_uuid, dataset_manager):
model_json = make_model_json()
runner = DMLRunner(config_manager)
mnist_filepath = dataset_manager.get_mappings()[mnist_uuid]
split_job = make_split_job(
model_json,
mnist_filepath,
)
split_job.hyperparams['split'] = 0.75
job_results = runner.run_job(split_job)
print(job_results)
return job_results
def test_dmlrunner_transform_and_split( \
runner, small_filepath):
split_job = make_split_job(small_filepath)
split_job.hyperparams['split'] = 0.75
job_results = runner.run_job(split_job)
session_filepath = job_results.results['session_filepath']
assert os.path.isdir(session_filepath), \
"Session folder does not exist!"
train_filepath = os.path.join(session_filepath, 'train.csv')
test_filepath = os.path.join(session_filepath, 'test.csv')
assert os.path.isfile(train_filepath) and os.path.isfile(test_filepath), \
"Training and test set not created!"
train = pd.read_csv(train_filepath)
test = pd.read_csv(test_filepath)
assert len(train) == 6 and len(test) == 2, \
"Train test split was not performed correctly."
def test_dmlrunner_same_train_job_with_split_1( \
config_manager, mnist_filepath):
model_json = make_model_json()
hyperparams = make_hyperparams(split=1)
runner = DMLRunner(config_manager)
initialize_job = make_initialize_job(model_json)
initial_weights = runner.run_job(initialize_job).results['weights']
split_job = make_split_job(model_json, mnist_filepath)
job_results = runner.run_job(split_job)
session_filepath = job_results.results['session_filepath']
datapoint_count = job_results.results['datapoint_count']
train_job = make_train_job(model_json, initial_weights, hyperparams,
session_filepath, datapoint_count)
result = runner.run_job(train_job)
assert result.status == 'successful'
results = result.results
new_weights = results['weights']
omega = results['omega']
train_stats = results['train_stats']
assert result.job.job_type is JobTypes.JOB_TRAIN.name
assert type(new_weights) == list
assert type(new_weights[0]) == np.ndarray
assert type(omega) == int or type(omega) == float
assert type(train_stats) == dict
def split_dmlresult_obj(runner, mnist_filepath):
split_job = make_split_job(mnist_filepath, )
split_job.hyperparams['split'] = 0.75
job_results = runner.run_job(split_job)
return job_results