def test_empty_inputs():
train_df = TEST_DF_1.copy()
with pytest.raises(RuntimeError):
TabularData.from_df(train_df,
numerical_cols=None,
categorical_cols=None,
target_col="label",
num_workers=0,
batch_size=1)
def test_categorical_target(tmpdir):
train_df = TEST_DF_1.copy()
val_df = TEST_DF_2.copy()
test_df = TEST_DF_2.copy()
for df in [train_df, val_df, test_df]:
# change int label to string
df["label"] = df["label"].astype(str)
dm = TabularData.from_df(
train_df,
categorical_cols=["category"],
numerical_cols=["scalar_b", "scalar_b"],
target_col="label",
val_df=val_df,
test_df=test_df,
num_workers=0,
batch_size=1,
)
for dl in [
dm.train_dataloader(),
dm.val_dataloader(),
dm.test_dataloader()
]:
(cat, num), target = next(iter(dl))
assert cat.shape == (1, 1)
assert num.shape == (1, 2)
assert target.shape == (1, )
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_from_df(tmpdir):
train_df = TEST_DF_1.copy()
valid_df = TEST_DF_2.copy()
test_df = TEST_DF_2.copy()
dm = TabularData.from_df(train_df,
categorical_input=["category"],
numerical_input=["scalar_b", "scalar_b"],
target="label",
valid_df=valid_df,
test_df=test_df,
num_workers=0,
batch_size=1)
for dl in [
dm.train_dataloader(),
dm.val_dataloader(),
dm.test_dataloader()
]:
(cat, num), target = next(iter(dl))
assert cat.shape == (1, 1)
assert num.shape == (1, 2)
assert target.shape == (1, )