scikit-learn/scikit-learn
GroupKFold / StratifiedGroupKFold with sequence-cluster IDs
In: LABLOOP-W22 Notebook
WEEK 22 · BASELINES BEATEN HONESTLY
Do one thing.
Then you are ahead.
There is an old trick in sales: compare your product with a weak competitor and you always win. Science has the same trick, and reviewers hunt for it. The honest move is to compare against the strongest published baseline, on the exact same splits, and to split proteins by family so the model cannot cheat by recognising a close cousin it saw in training (like a student who memorised last year's exam because this yea…
If you only do one thing this week: the family-split table
▶
THE NEXT BLOCK
How long have you got?
By Sunday you should be able to say: “I can explain why my score dropped with family splits, and why the lower number is the one I publish.”
🔥
MOMENTUM
What you have actually done
0 min0 blocks on the timer
0 min0.0 hours measured, not estimated
0days in a row
11across the programme
0/10
Time on the timer, day by day last 14 days
S
M
T
W
T
F
S
S
M
T
W
T
F
S
2026-09-29 18:29Finished: SciPy docs, scipy.integrate.solve_ivp2026-09-29 17:44Finished: LearnChemE (CU Boulder) · "Monod Cell Growth Example (Bio)"2026-09-28 22:11Finished: Crash Course Biology #3 · "Biological Molecules2026-09-28 21:50Finished: OpenStax Biology 2e2026-09-25 11:16Finished: OpenStax Biology 2e