aims-umich/pyMAISE

Timers for tuning and postprocessor for early stopping

Open

#79 opened on Feb 20, 2025

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (13 forks)auto 404
documentationenhancementgood first issue

Repository metrics

Stars
 (32 stars)
PR merge metrics
 (PR metrics pending)

Description

Background

Other AutoML libraries use timers to limit the amount of time models take in training. I think this would be good to add here so tuning times don't take longer than 3 hours or something that the user can set.

Tasks

  • Add timers for each model and/or in total where once the time is met, iterations are stopped for that model or in total, and the top models found thus far are returned. This should be something the user can override with a different time or possibly setting it to -1 to turn off timers.
  • Changes are documented in documentation.

Definition of Done

The above functionality is implemented for classical and machine learning models.

Contributor guide

Research direction
Examine the existing training loop in pyMAISE and implement a timer that checks elapsed time after each iteration. If the timer exceeds the user set limit (or default), stop training for that model and proceed to the next. Document the new parameters and behavior.
Tech stack
python
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonMachine Learning
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65