provide re-ranking runs from datasets

[seanmacavaney]

It's becoming increasingly common for datasets to include a standard initial result set for re-ranking experiments. ir_datasets provides these, but they are a bit inconvenient to use in pyterrier right now because it involves using irds_ref, building an appropriate dataframe, and merging in the query/document text.

This PR exposes the functionality more conveniently through dataset.get_reranking_run(). (I'm open to alternative names here.)

I also considered including the document text, but it's not always going to be needed and it seems more suitable to use the existing pt.text.get_text() pipeline for this.

[seanmacavaney]

If this looks good, I'll add documentation for it too.

[cmacdonald]

Thanks. A smaller name would be appreciated. Why not just get_run()?

We need to discuss timing. I wasnt planning to release 0.8 until March, i.e. after IR(H)

Can we fix #212 in 0.8 as well.

[cmacdonald]

or get_results()? As I dont think we use the word run in PyTerrier.

[seanmacavaney]

get_results seems a bit generic, but it'll probably work.

I don't think this urgently needs to hit pypi. Sorry I lost track of #212-- I'll fix it as well.