[ENH] Implement NBeatsKAN in v2 interface

[Dev10-sys]

Reference Issues/PRs

Partially addresses #1736 and #1992.

What does this implement/fix? Explain your changes.

Adds a v2 implementation of NBeatsKAN as NBeatsKAN_v2.

• Implemented NBeatsKAN_v2 inheriting from BaseModel with Kolmogorov-Arnold Network (KAN) spline layers (Generic, Seasonal, and Trend blocks).
• Implemented NBeatsKAN_pkg_v2 inheriting from Base_pkg.
• Added unit and estimator compliance tests in tests/test_models/test_nbeatskan_v2.py.

What should a reviewer concentrate their feedback on?

• KAN block integration (NBEATSGenericBlockKAN, NBEATSSeasonalBlockKAN, NBEATSTrendBlockKAN) with DataModule metadata inputs
• Package metadata in NBeatsKAN_pkg_v2

Did you add any tests for the change?

• Added tests/test_models/test_nbeatskan_v2.py with check_estimator compliance.

PR checklist

• Title starts with [ENH]
• Added tests (tests/test_models/test_nbeatskan_v2.py)
• Used pre-commit hooks

[codecov]

Codecov Report

❌ Patch coverage is 93.86792% with 13 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (main@062aeb4). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...ch_forecasting/models/nbeats/_nbeats_adapter_v2.py	91.93%	5 Missing ⚠️
pytorch_forecasting/models/nbeats/_nbeats_v2.py	91.83%	4 Missing ⚠️
pytorch_forecasting/models/nbeats/_nbeatskan_v2.py	92.30%	4 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #2383   +/-   ##
=======================================
  Coverage        ?   88.29%           
=======================================
  Files           ?      201           
  Lines           ?    11262           
  Branches        ?        0           
=======================================
  Hits            ?     9944           
  Misses          ?     1318           
  Partials        ?        0           

Flag	Coverage Δ
cpu	88.29% <93.86%> (?)
pytest	88.29% <93.86%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[phoeenniixx]

Nice!
Can you also look at #2373, maybe we can use the adapter here to make things easier. You can stack this PR on #2373.

FYI @Faakhir30

[Faakhir30]

@Dev10-sys for stacking upon adapter being contributed in #2373 , you can do:

git pull https://github.com/faakhir30/pytorch-forecasting nbeatsv2

And, then use that adapter instead of BaseModel as base class.

[Dev10-sys]

@phoeenniixx @Faakhir30 I have made the requested changes. Please review.