From 333ae86617bd2a596986d68a2b42e1840a6a8bf8 Mon Sep 17 00:00:00 2001 From: Javier Date: Thu, 19 Dec 2024 14:32:31 +0000 Subject: [PATCH 1/2] Apply suggestions from code review --- .../partitioner/vertical_even_partitioner.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/datasets/flwr_datasets/partitioner/vertical_even_partitioner.py b/datasets/flwr_datasets/partitioner/vertical_even_partitioner.py index 1afdb7c04271..d27e753e6b57 100644 --- a/datasets/flwr_datasets/partitioner/vertical_even_partitioner.py +++ b/datasets/flwr_datasets/partitioner/vertical_even_partitioner.py @@ -30,7 +30,7 @@ class VerticalEvenPartitioner(Partitioner): """Partitioner that splits features (columns) evenly into vertical partitions. - Enables selection of "active party" column(s) and palcement into + Enables selection of "active party" column(s) and placement into a specific partition or creation of a new partition just for it. Also enables droping columns and sharing specified columns across all partitions. @@ -175,7 +175,7 @@ def num_partitions(self) -> int: def _validate_parameters_in_init(self) -> None: if self._num_partitions < 1: - raise ValueError("column_distribution as int must be >= 1.") + raise ValueError("`column_distribution` as int must be >= 1.") # Validate columns lists for parameter_name, parameter_list in [ @@ -184,7 +184,7 @@ def _validate_parameters_in_init(self) -> None: ("active_party_column", self._active_party_columns), ]: if not all(isinstance(column, str) for column in parameter_list): - raise ValueError(f"All entries in {parameter_name} must be strings.") + raise ValueError(f"All entries in '{parameter_name}' must be strings.") valid_modes = { "add_to_first", @@ -198,7 +198,7 @@ def _validate_parameters_in_init(self) -> None: or self._active_party_columns_mode in valid_modes ): raise ValueError( - "active_party_column_mode must be an int or one of " + "`active_party_column_mode` must be an int or one of " "'add_to_first', 'add_to_last', 'create_as_first', 'create_as_last', " "'add_to_all'." ) From 382fbd60ddd1b564c26c17b075bc3a1e9b80d8f9 Mon Sep 17 00:00:00 2001 From: jafermarq Date: Thu, 19 Dec 2024 15:44:48 +0100 Subject: [PATCH 2/2] fix docstrings example --- .../partitioner/vertical_even_partitioner.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/datasets/flwr_datasets/partitioner/vertical_even_partitioner.py b/datasets/flwr_datasets/partitioner/vertical_even_partitioner.py index d27e753e6b57..87a80428f0c1 100644 --- a/datasets/flwr_datasets/partitioner/vertical_even_partitioner.py +++ b/datasets/flwr_datasets/partitioner/vertical_even_partitioner.py @@ -62,10 +62,13 @@ class VerticalEvenPartitioner(Partitioner): Examples -------- + >>> from flwr_datasets import FederatedDataset + >>> from flwr_datasets.partitioner import VerticalEvenPartitioner + >>> >>> partitioner = VerticalEvenPartitioner( ... num_partitions=3, - ... active_party_column="income", - ... active_party_column_mode="add_to_last", + ... active_party_columns="income", + ... active_party_columns_mode="add_to_last", ... shuffle=True, ... seed=42 ... ) @@ -73,7 +76,7 @@ class VerticalEvenPartitioner(Partitioner): ... dataset="scikit-learn/adult-census-income", ... partitioners={"train": partitioner} ... ) - >>> partitions = [fds.load_partition(i) for i in range(partitioner.num_partitions)] + >>> partitions = [fds.load_partition(i) for i in range(fds.partitioners["train"].num_partitions)] >>> print([partition.column_names for partition in partitions]) """