From c5e28d4c3bfc98884e1588412036c68ea02a4c36 Mon Sep 17 00:00:00 2001 From: Adam Narozniak <51029327+adam-narozniak@users.noreply.github.com> Date: Tue, 10 Sep 2024 20:14:03 +0200 Subject: [PATCH] docs(datasets) Clarify the split docs in FederatedDataset (#3912) --- datasets/flwr_datasets/federated_dataset.py | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/datasets/flwr_datasets/federated_dataset.py b/datasets/flwr_datasets/federated_dataset.py index e913b9095d17..64544b1c4463 100644 --- a/datasets/flwr_datasets/federated_dataset.py +++ b/datasets/flwr_datasets/federated_dataset.py @@ -161,6 +161,11 @@ def load_partition( not need to provide this argument, but if `partitioners={"train": 10, "test": 100}`, you need to set it to differentiate which partitioner should be used. + The split names you can choose from vary from dataset to dataset. You need + to check the dataset on the `Hugging Face Hub`_ to see which splits are available. You can resplit the dataset + by using the `preprocessor` parameter (to rename, merge, divide, etc. the + available splits). Returns ------- @@ -203,6 +208,11 @@ def load_split(self, split: str) -> Dataset: ---------- split : str Split name of the downloaded dataset (e.g. "train", "test"). + The split names you can choose from vary from dataset to dataset. You need + to check the dataset on the `Hugging Face Hub`_ to see which splits are available. You can resplit the dataset + by using the `preprocessor` parameter (to rename, merge, divide, etc. the + available splits). Returns -------