Encoding model: running/LP/pupil regressor issues found during methods verification
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 48/100
- Issue type
- Bug
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- jupyter-notebook, python
- Domain
- data, machine-learning
Research direction
Start by reading io_utils.running and io_utils.facial_features, then trace how the LP and pupil regressors are loaded for the five listed sessions. Compare the binning, z-scoring, displacement calculation, and lick threshold with the stated expected behavior and related npc_sessions issues. Done means the regressors exclude invalid epochs and sessions, use a meaningful displacement measure, and match the NWB lick threshold.
Written by the indexing model from the issue text.
Description
Impact: UNKNOWN–MEDIUM (affects how the encoding-model regressors are interpreted) · Fix: EASY
Found while writing the behaviour methods (npc_sessions methods draft, 2026-10-19):
io_utils.runningbins the whole running series.- Running speed contains values up to 1e11 cm/s in optotagging and RF-mapping epochs, and is delayed by seconds in 8 task sessions (see npc_sessions issues).
- Check that the time bins and any z-scoring exclude non-task epochs, and exclude the delayed sessions.
io_utils.facial_featurescomputes "Euclidean displacement" as √(x² + y²): the distance from the image corner, not a displacement. A displacement from a reference (e.g. the session median), or frame-to-frame motion, is probably intended.- Video-derived regressors (LP, pupil) in 644864_2023-02-02, 644866_2023-02-10, 649943_2023-02-13, 666986_2023-08-15 and 666986_2023-08-17 are mis-timed by up to 23 s (npc_sessions video-timing issue). Exclude these sessions until the timing is fixed.
- Minor: the lick threshold is
< 0.5here vs<= 0.5in the NWBis_likely_lickflag.
- Dominant language
- Jupyter Notebook
- Stars
- 3
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Similar issues
-
Add: ESP 2 PTOpencheck:passed feeds:add
Difficulty 1/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 4 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
yt-project/yt#5624 ·
Maintainers usually reply within 1 day
-
automation missing-model model-sync provider:fireworks-ai
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
anomalyco/models.dev#12458 ·
Maintainers usually reply within 1 day
-
correction metadata
Difficulty 2/5 Under an hour Newbie friendliness 65/100
acl-org/acl-anthology#10753 · 1 comment ·
Maintainers usually reply within 1 day
-
Interactive node: valid JSON with mixed-type arrays (e.g. `[1, "a"]`) is rejectedPossibly taken @phil-opp claimed this today. Opendaemon rust
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day