def test_empty_inputs():
train_data_frame = TEST_DF_1.copy()
with pytest.raises(RuntimeError):
TabularData.from_data_frame(
numerical_fields=None,
categorical_fields=None,
target_fields="label",
train_data_frame=train_data_frame,
num_workers=0,
batch_size=1,
)
def test_categorical_target(tmpdir):
train_data_frame = TEST_DF_1.copy()
val_data_frame = TEST_DF_2.copy()
test_data_frame = TEST_DF_2.copy()
for df in [train_data_frame, val_data_frame, test_data_frame]:
# change int label to string
df["label"] = df["label"].astype(str)
dm = TabularData.from_data_frame(
categorical_fields=["category"],
numerical_fields=["scalar_b", "scalar_b"],
target_fields="label",
train_data_frame=train_data_frame,
val_data_frame=val_data_frame,
test_data_frame=test_data_frame,
num_workers=0,
batch_size=1,
)
for dl in [dm.train_dataloader(), dm.val_dataloader(), dm.test_dataloader()]:
data = next(iter(dl))
(cat, num) = data[DefaultDataKeys.INPUT]
target = data[DefaultDataKeys.TARGET]
assert cat.shape == (1, 1)
assert num.shape == (1, 2)
assert target.shape == (1, )
def test_classification(tmpdir):
train_data_frame = TEST_DF_1.copy()
val_data_frame = TEST_DF_1.copy()
test_data_frame = TEST_DF_1.copy()
data = TabularData.from_data_frame(
categorical_fields=["category"],
numerical_fields=["scalar_a", "scalar_b"],
target_fields="label",
train_data_frame=train_data_frame,
val_data_frame=val_data_frame,
test_data_frame=test_data_frame,
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_tabular_data(tmpdir):
train_data_frame = TEST_DF_1.copy()
val_data_frame = TEST_DF_2.copy()
test_data_frame = TEST_DF_2.copy()
dm = TabularData.from_data_frame(
categorical_cols=["category"],
numerical_cols=["scalar_b", "scalar_b"],
target_col="label",
train_data_frame=train_data_frame,
val_data_frame=val_data_frame,
test_data_frame=test_data_frame,
num_workers=0,
batch_size=1,
)
for dl in [dm.train_dataloader(), dm.val_dataloader(), dm.test_dataloader()]:
data = next(iter(dl))
(cat, num) = data[DefaultDataKeys.INPUT]
target = data[DefaultDataKeys.TARGET]
assert cat.shape == (1, 1)
assert num.shape == (1, 2)
assert target.shape == (1, )