def train(config, train_data, validation_data, artifact_dir):
"""Barrage deep learning train.
Supported filetypes:
1. .csv
2. .json
Args:
config: filepath to barrage config [REQUIRED].
train-data: filepath to train data [REQUIRED].
validation-data: filepath to validation data [REQUIRED].
Note: artifact-dir cannot already exist.
"""
cfg = io_utils.load_json(config)
records_train = io_utils.load_data(train_data)
records_validation = io_utils.load_data(train_data)
BarrageModel(artifact_dir).train(cfg, records_train, records_validation)
def predict(score_data, artifact_dir, output):
"""Barrage deep learning predict.
Supported filetypes:
1. .csv
2. .json
Args:
score-data: filepath to score data [REQUIRED].
artifact-dir: location to load artifacts [REQUIRED].
"""
records_score = io_utils.load_data(score_data)
scores = BarrageModel(artifact_dir).predict(records_score)
io_utils.save_json(scores, output)
def test_load_data(artifact_path, sample_dict):
expected = pd.DataFrame([sample_dict])
expected.to_json(os.path.join(artifact_path, "unit_test.json"))
result = io_utils.load_data("unit_test.json", artifact_path)
assert result.equals(expected)
expected.to_csv(os.path.join(artifact_path, "unit_test.csv"), index=False)
result = io_utils.load_data("unit_test.csv", artifact_path)
assert result.equals(expected)
with pytest.raises(FileNotFoundError):
io_utils.load_data("test_unit.42", artifact_path)
expected.to_json(os.path.join(artifact_path, "unit_test.foo"))
with pytest.raises(ValueError):
io_utils.load_data("unit_test.foo", artifact_path)