def load_data(
self,
data: DataFrame,
time_idx: Optional[str] = None,
target: Optional[Union[str, List[str]]] = None,
group_ids: Optional[List[str]] = None,
parameters: Optional[Dict[str, Any]] = None,
**time_series_dataset_kwargs: Any,
):
if self.training:
time_series_dataset = TimeSeriesDataSet(
data,
time_idx=time_idx,
group_ids=group_ids,
target=target,
**time_series_dataset_kwargs)
parameters = time_series_dataset.get_parameters()
# Add some sample data so that we can recreate the `TimeSeriesDataSet` later on
parameters["data_sample"] = data.iloc[[0]].to_dict()
self.parameters = parameters
else:
if parameters is None:
raise MisconfigurationException(
"Loading data for evaluation or inference requires parameters from the train data. Either "
"construct the train data at the same time as evaluation and inference or provide the train "
"`datamodule.parameters` to `from_data_frame` in the `parameters` argument."
)
parameters = copy(parameters)
parameters.pop("data_sample")
time_series_dataset = TimeSeriesDataSet.from_parameters(
parameters,
data,
stop_randomization=True,
)
return time_series_dataset
# create the dataset from the pandas dataframe
dataset = TimeSeriesDataSet(
test_data,
group_ids=["group"],
target="value",
time_idx="time_idx",
min_encoder_length=5,
max_encoder_length=5,
min_prediction_length=2,
max_prediction_length=2,
time_varying_unknown_reals=["value"],
)
# %%
dataset.get_parameters()
# %% [markdown]
# Now, we take a look at the output of the dataloader. It's `x` will be fed to the model's forward method, that is why it is so important to understand it.
# %%
# convert the dataset to a dataloader
dataloader = dataset.to_dataloader(batch_size=4)
# and load the first batch
x, y = next(iter(dataloader))
print("x =", x)
print("\ny =", y)
print("\nsizes of x =")
for key, value in x.items():
print(f"\t{key} = {value.size()}")
