Purpose of training dataset in testing?

[ozanbarism]

Hi, i was checking your starter code shown below.

Split into train/test set

train, test_template = split(
ds, offset=-TEST
) # assign last TEST time steps as test set

Construct rolling window evaluation

test_data = test_template.generate_instances(
prediction_length=PDT, # number of time steps for each prediction
windows=TEST // PDT, # number of windows in rolling window evaluation
distance=PDT, # number of time steps between each window - distance=PDT for non-overlapping windows
)

Prepare pre-trained model by downloading model weights from huggingface hub

model = MoiraiForecast(
module=MoiraiModule.from_pretrained(f"Salesforce/moirai-1.0-R-{SIZE}"),
prediction_length=PDT,
context_length=CTX,
patch_size=PSZ,
num_samples=100,
target_dim=1,
feat_dynamic_real_dim=ds.num_feat_dynamic_real,
past_feat_dynamic_real_dim=ds.num_past_feat_dynamic_real,
)

predictor = model.create_predictor(batch_size=BSZ)
forecasts = predictor.predict(test_data.input)

here the train is never used again. Additionally, the predictor takes test_data as input. however, i believe it should take some context window from training data as input and then make predictions that will be compared to the test data. how can i achieve that? what do i need to change?

[gorold]

test_data.input contains the context windows, whereas test_data.labels contain the forecast horizon, no need to make any changes.