Classes and functions
This section documents all public classes and functions in Experanto.
Core Classes
High-level interface for loading and querying neuroscience experiments. |
|
PyTorch Dataset for chunked experiment data. |
Interpolators
Abstract base class for time series interpolation. |
|
Interpolator for time series data. |
|
Sequence interpolator with per-signal phase shifts. |
|
Interpolator for visual stimuli (images and videos). |
|
Interpolator for labeled time intervals. |
|
Interpolator for spike train data. |
|
Base class for visual stimulus trials. |
|
Trial containing a single static image. |
|
Trial containing a multi-frame video sequence. |
|
Trial containing a blank/gray screen (inter-stimulus interval). |
|
Placeholder for invalid or corrupted trials. |
Time Intervals
A time interval represented by start and end times. |
Merge overlapping or adjacent intervals into non-overlapping intervals. |
|
|
Find the intersection of two interval arrays. |
|
Find the common intersection across multiple interval arrays. |
Find the union of multiple interval arrays. |
|
Find gaps not covered by intervals within a range. |
|
Calculate statistics about valid and invalid intervals within a range. |
Dataloaders
Create a multi-session dataloader from multiple experiment paths. |
|
Create a concatenated multi-session dataloader. |
Utilities
Cycle through multiple dataloaders until the longest is exhausted. |
|
Cycle through multiple dataloaders until the shortest is exhausted. |
|
Optimized multi-session dataloader with state tracking. |
|
DataLoader that keeps workers alive across epochs. |
|
Memory-efficient concatenated dataset that reliably tracks sessions. |
|
A batch sampler that cycles through sessions, ensuring each session appears exactly once before repeating any session. |
|
A batch sampler specific to a single session that efficiently generates batches from the session's indices. |
Add behavioral data as additional channels to screen data. |
Filters
Create a filter that excludes time regions around NaN values. |