def test_init_train(tmpdir):
train_dl = torch.utils.data.DataLoader(DummyDataset(), batch_size=16)
model = TabularClassifier(num_classes=10,
num_features=16 + 16,
embedding_sizes=16 * [(10, 32)])
trainer = Trainer(default_root_dir=tmpdir, fast_dev_run=True)
trainer.fit(model, train_dl)
def test_jit(tmpdir):
model = TabularClassifier(num_classes=10,
num_features=8,
embedding_sizes=4 * [(10, 32)])
model.eval()
# torch.jit.script doesn't work with tabnet
model = torch.jit.trace(
model, ((torch.randint(0, 10, size=(1, 4)), torch.rand(1, 4)), ))
# TODO: torch.jit.save doesn't work with tabnet
# path = os.path.join(tmpdir, "test.pt")
# torch.jit.save(model, path)
# model = torch.jit.load(path)
out = model((torch.randint(0, 10, size=(1, 4)), torch.rand(1, 4)))
assert isinstance(out, torch.Tensor)
assert out.shape == torch.Size([1, 10])
def test_classification(tmpdir):
train_df = TEST_DF_1.copy()
val_df = TEST_DF_1.copy()
test_df = TEST_DF_1.copy()
data = TabularData.from_df(
train_df,
categorical_cols=["category"],
numerical_cols=["scalar_a", "scalar_b"],
target_col="label",
val_df=val_df,
test_df=test_df,
num_workers=0,
batch_size=2,
)
model = TabularClassifier(num_features=3, num_classes=2, embedding_sizes=data.emb_sizes)
trainer = pl.Trainer(fast_dev_run=True, default_root_dir=tmpdir)
trainer.fit(model, data)
def test_module_import_error(tmpdir):
with pytest.raises(ModuleNotFoundError, match="[tabular]"):
TabularClassifier(num_classes=10, num_features=16, embedding_sizes=[])