Skip to content

Commit

Permalink
format
Browse files Browse the repository at this point in the history
  • Loading branch information
KexinFeng committed Sep 27, 2022
1 parent d8e95ef commit 9d7bea8
Show file tree
Hide file tree
Showing 2 changed files with 4 additions and 4 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -42,9 +42,9 @@
* M5 Forecasting - Accuracy from <a
* href="https://www.kaggle.com/competitions/m5-forecasting-accuracy">https://www.kaggle.com/competitions/m5-forecasting-accuracy</a>
*
* <p>To improve the model performance, we coarse grain the target of the dataset by summing the sale
* amount every seven days. And set the column names of sum as 'w_i'. This can reduce occurrence of
* invalid values 0 and reduce the noise learned by model.
* <p>To improve the model performance, we coarse grain the target of the dataset by summing the
* sale amount every seven days. And set the column names of sum as 'w_i'. This can reduce
* occurrence of invalid values 0 and reduce the noise learned by model.
*/
public class M5Forecast extends CsvTimeSeriesDataset {

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ public class M5ForecastTest {

@Test
public void testM5Forecast() throws IOException, TranslateException {
// TestRequirements.weekly();
// TestRequirements.weekly();
TrainingConfig config =
new DefaultTrainingConfig(Loss.softmaxCrossEntropyLoss())
.optInitializer(Initializer.ONES, Parameter.Type.WEIGHT);
Expand Down

0 comments on commit 9d7bea8

Please sign in to comment.