IBLBrainWideBenchTS1#

class ts1.IBLBrainWideBenchTS1(root, split, task, recording_id, dirname='ibl_brain_wide_bench_2026', transform=None, normalize_behavior=True, context_length=1.0)[source]#

Bases: core.dataset.VariableContextMixin, core.dataset.IBLBrainWideBench2026

Dataset for the IBL BrainWideBench benchmark.

Parameters:

  • root (str) – The root directory of the dataset.

  • split (Literal['train', 'val', 'test']) – The split of the dataset (train, val, test).

  • task (Literal['choice', 'reward', 'stimulus_contrast', 'whisker_motion_energy', 'wheel_speed', 'right_paw_speed', 'left_paw_speed', 'licking_rate']) – The task to include in the dataset. One task at a time.

  • recording_id (str) – The recording id to include in the dataset.

  • dirname (str) – The name of the dataset (and the directory containing its data).

  • transform (Optional[Any]) – The transform(s) to apply to the data.

  • normalize_behavior (bool) – Whether to normalize the behavior data. This should be set to True unless the user wants to use custom target preprocessing.

  • context_length (float) – Total sampled window size in seconds (preceding context plus the fixed 1s target). Defaults to 1.0 (no extra context).

classmethod get_ts1_supported_tasks(target_resolution=None)[source]#

Returns the tasks the benchmark supports, as the string values of TS1Task.

Parameters:

target_resolution (Optional[TargetResolution]) – If given, keep only the tasks with this target resolution.

Returns:

The supported tasks.

Return type:

list[TS1Task]

Example

>>> tasks = IBLBrainWideBenchTS1.get_ts1_supported_tasks()
>>> print(tasks)
['choice', ...]
dataset_transform(data)[source]#

Defines dataset-level transformations that are applied to all recordings in the Dataset.

This method can be applied on an entire recording or a single slice.

Parameters:

data (Data) – The Data object to apply the transformations to.

Return type:

Data

Returns:

The Data object with the transformations applied.

Example

>>> dataset = IBLBrainWideBenchTS1(...)
>>> data = dataset.get_recording(...)
>>> data = dataset.dataset_transform(data)
>>> slice = data.slice(0.5, 1.5)
>>> slice = dataset.dataset_transform(slice)
get_sampling_intervals()[source]#

The intervals a sampler may draw windows from: this split’s task-aligned trials.