def test_from_parquet_multilabel(tmpdir):
parquet_path = parquet_data(tmpdir, True)
dm = TextClassificationData.from_parquet(
"sentence",
["lab1", "lab2"],
train_file=parquet_path,
val_file=parquet_path,
test_file=parquet_path,
predict_file=parquet_path,
batch_size=1,
)
assert dm.multi_label
batch = next(iter(dm.train_dataloader()))
assert all([label in [0, 1] for label in batch[DataKeys.TARGET][0]])
assert isinstance(batch[DataKeys.INPUT][0], str)
batch = next(iter(dm.val_dataloader()))
assert all([label in [0, 1] for label in batch[DataKeys.TARGET][0]])
assert isinstance(batch[DataKeys.INPUT][0], str)
batch = next(iter(dm.test_dataloader()))
assert all([label in [0, 1] for label in batch[DataKeys.TARGET][0]])
assert isinstance(batch[DataKeys.INPUT][0], str)
batch = next(iter(dm.predict_dataloader()))
assert isinstance(batch[DataKeys.INPUT][0], str)
def test_from_parquet(tmpdir):
parquet_path = parquet_data(tmpdir, False)
dm = TextClassificationData.from_parquet(
"sentence",
"lab1",
train_file=parquet_path,
val_file=parquet_path,
test_file=parquet_path,
predict_file=parquet_path,
batch_size=1,
)
batch = next(iter(dm.train_dataloader()))
assert batch[DataKeys.TARGET].item() in [0, 1]
assert isinstance(batch[DataKeys.INPUT][0], str)
batch = next(iter(dm.val_dataloader()))
assert batch[DataKeys.TARGET].item() in [0, 1]
assert isinstance(batch[DataKeys.INPUT][0], str)
batch = next(iter(dm.test_dataloader()))
assert batch[DataKeys.TARGET].item() in [0, 1]
assert isinstance(batch[DataKeys.INPUT][0], str)
batch = next(iter(dm.predict_dataloader()))
assert isinstance(batch[DataKeys.INPUT][0], str)
