def test_from_data_frame_time_series_data_set_multi_call(
patch_time_series_data_set):
"""Tests that ``TabularForecastingData.from_data_frame`` calls ``TimeSeriesDataSet`` with the expected
parameters when called separately for each stage."""
patch_time_series_data_set.return_value.get_parameters.return_value = {
"test": None
}
train_data = MagicMock()
val_data = MagicMock()
train_datamodule = TabularForecastingData.from_data_frame(
"time_idx",
"target",
["series"],
train_data_frame=train_data,
additional_kwarg="test",
batch_size=4,
)
TabularForecastingData.from_data_frame(
val_data_frame=val_data,
parameters=train_datamodule.parameters,
batch_size=4,
)
patch_time_series_data_set.assert_called_once_with(train_data,
time_idx="time_idx",
group_ids=["series"],
target="target",
additional_kwarg="test")
patch_time_series_data_set.from_parameters.assert_called_once_with(
{"test": None}, val_data, stop_randomization=True)
def test_from_data_frame_misconfiguration():
"""Tests that a ``MisconfigurationException`` is raised when ``TabularForecastingData`` is constructed without
parameters."""
with pytest.raises(MisconfigurationException,
match="evaluation or inference requires parameters"):
TabularForecastingData.from_data_frame(
"time_idx",
"target",
["series"],
val_data_frame=MagicMock(),
additional_kwarg="test",
batch_size=4,
)
def test_testing_raises(sample_data):
"""Tests that ``NotImplementedError`` is raised when attempting to perform a test pass."""
data, training_cutoff, max_prediction_length = sample_data
datamodule = TabularForecastingData.from_data_frame(
time_idx="time_idx",
target="value",
categorical_encoders={"series": NaNLabelEncoder().fit(data.series)},
group_ids=["series"],
time_varying_unknown_reals=["value"],
max_encoder_length=60,
max_prediction_length=max_prediction_length,
train_data_frame=data[lambda x: x.time_idx <= training_cutoff],
test_data_frame=data,
batch_size=4,
)
model = TabularForecaster(
datamodule.parameters,
backbone="n_beats",
backbone_kwargs={
"widths": [32, 512],
"backcast_loss_ratio": 0.1
},
)
trainer = flash.Trainer(max_epochs=1,
fast_dev_run=True,
gradient_clip_val=0.01)
with pytest.raises(
NotImplementedError,
match=
"Backbones provided by PyTorch Forecasting don't support testing."
):
trainer.test(model, datamodule=datamodule)
def test_fast_dev_run_smoke(sample_data):
"""Test that fast dev run works with the NBeats example data."""
data, training_cutoff, max_prediction_length = sample_data
datamodule = TabularForecastingData.from_data_frame(
time_idx="time_idx",
target="value",
categorical_encoders={"series": NaNLabelEncoder().fit(data.series)},
group_ids=["series"],
time_varying_unknown_reals=["value"],
max_encoder_length=60,
max_prediction_length=max_prediction_length,
train_data_frame=data[lambda x: x.time_idx <= training_cutoff],
val_data_frame=data,
batch_size=4,
)
model = TabularForecaster(
datamodule.parameters,
backbone="n_beats",
backbone_kwargs={
"widths": [32, 512],
"backcast_loss_ratio": 0.1
},
)
trainer = flash.Trainer(max_epochs=1,
fast_dev_run=True,
gradient_clip_val=0.01)
trainer.fit(model, datamodule=datamodule)
# Example based on this tutorial: https://pytorch-forecasting.readthedocs.io/en/latest/tutorials/ar.html
# 1. Create the DataModule
data = generate_ar_data(seasonality=10.0, timesteps=400, n_series=100, seed=42)
data["date"] = pd.Timestamp("2020-01-01") + pd.to_timedelta(data.time_idx, "D")
max_prediction_length = 20
training_cutoff = data["time_idx"].max() - max_prediction_length
datamodule = TabularForecastingData.from_data_frame(
time_idx="time_idx",
target="value",
categorical_encoders={"series": NaNLabelEncoder().fit(data.series)},
group_ids=["series"],
# only unknown variable is "value" - and N-Beats can also not take any additional variables
time_varying_unknown_reals=["value"],
max_encoder_length=60,
max_prediction_length=max_prediction_length,
train_data_frame=data[lambda x: x.time_idx <= training_cutoff],
val_data_frame=data,
batch_size=32,
)
# 2. Build the task
model = TabularForecaster(
datamodule.parameters,
backbone="n_beats",
backbone_kwargs={
"widths": [32, 512],
"backcast_loss_ratio": 0.1
},