Add a new project focused on Darts library + timeseries forecasting

[htahir1]

Summary

Please provide a short summary explaining the motivation behind these changes.

Checklist

• I have read the contributing guidelines.
• I have run the necessary tests and linters.
• I have updated relevant documentation where applicable.

Related Issues

Please link to any relevant issues or discussions.

[dagshub]

Join the discussion on DagsHub!

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[strickvl]

Ok so some bigger things and then some comments also attached with nits.

Inference Pipeline Doesn't Use the Trained Scaler

The training data is scaled before the model sees it, but the inference pipeline feeds un-scaled data to the model. This will cause the model to produce incorrect and nonsensical predictions.

The fix:

• Modify the training preprocessing step to link the fitted Scaler object to the ZenML model version
• Remove the incorrect preprocessing step from the inference pipeline.
• Update the batch inference step to load the Scaler from the model version and apply it to the new data before prediction.

Duplicated code

• iterative prediction logic is duplicated in steps/evaluate.py and steps/batch_infer.py
• (This duplicated iterative prediction logic also contains a bug where the prediction chunk size is hardcoded to 14, which might not match the model's output_chunk_length)

[htahir1]

@strickvl good catch on the scaler. i fixed this

[strickvl]

@htahir1 needs formatting to pass the tests, though...