Add RetailHero and MovieLens25 bipartite datasets with causal parameters

[geopanag]

I would like to add two new bipartite networks in PyG.
One is based on the RetailHero (https://ods.ai/competitions/x5-retailhero-uplift-modeling/data) (users-buy-products) with causal outcomes and interventions from a marketing campaign, and the other is based on MovieLens25 (https://grouplens.org/datasets/movielens/25m/) (movies-ratedby-users) with observational causal parameters .

I use them to test a GNN for causal outcome prediction in https://hal.science/hal-04601553/document ( ECMLPKDD 2024 ) and I believe they re useful for this line of research.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 86.87%. Comparing base (dafbd30) to head (a63ab81).
Report is 37 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #9471      +/-   ##
==========================================
- Coverage   88.25%   86.87%   -1.38%     
==========================================
  Files         473      463      -10     
  Lines       30844    30617     -227     
==========================================
- Hits        27221    26599     -622     
- Misses       3623     4018     +395     

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