Darshan
Darshan
What this fix does: Added a download_entire_repo flag to _cache_dataset, _load_dataset, and load_UCR_UEA_dataset so large benchmarking jobs can request a single HuggingFace snapshot instead of per-dataset API pulls; the flag...
I extended NaiveForecaster with a new strategy="rolling" that aggregates the last window_length observations using aggfunc. It works with "mean", "median", or any callable that returns a scalar and currently targets...
Updated OpenML/docker/config/php.ini to harden the PHP runtime: turned off expose_php so responses no longer include the PHP signature, and raised max_input_time to 3600 seconds to keep multi‑GB multipart uploads from...
## Summary - Allow scalar (0‑D) distributions to accept vector inputs by relaxing the coercion helpers so they no longer broadcast every input to shape `()`, while still returning scalars...
#### Reference Issues/PRs #### What does this implement/fix? Explain your changes. #### Does your contribution introduce a new dependency? If yes, which one? #### What should a reviewer concentrate their...
Made distribution the single source of truth for probabilistic regressors: added a helper to reconcile the old aliases, rewired CyclicBoosting, ResidualDouble, and XGBoostLSS to use it, updated docs/changelog, and added...