Batch NDCG

[donglihe-hub]

What does this PR do?

The original NDCG metric calculates scores for one instance at a time, which is inefficient. The new NDCG metric calculate scores in batch.

Performance Test Settings:

Number of labels = 100

Batch size = 40 Number of batchs = 100 Effective number of validation samples = 4000

Results:

Test CLI & API (bash tests/autotest.sh)

Test APIs used by main.py.

• [ ] Test Pass
  • (Copy and paste the last outputted line here.)
• [ ] Not Applicable (i.e., the PR does not include API changes.)

Check API Document

If any new APIs are added, please check if the description of the APIs is added to API document.

• [ ] API document is updated (linear, nn)
• [ ] Not Applicable (i.e., the PR does not include API changes.)

Test quickstart & API (bash tests/docs/test_changed_document.sh)

If any APIs in quickstarts or tutorials are modified, please run this test to check if the current examples can run correctly after the modified APIs are released.

[donglihe-hub]

We should review the use of plurals vs singulars.

A doubt that has haunted me for years is that why it is preds and target, rather than preds and targets or pred and target. Therefore, I prefer using singular form for all variables except for those concepts that have been accepted by the general public.