openml / openml/OpenML

Comparing flows on the same benchmark suite

Open
#1,028 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
PHP
Stars
755
Forks
128
PR merge metrics
No merged PRs in 30d

Description

Let's say I have 2 flows and I want to compare their performances on the same benchmark suite.

Is there a recommended workflow for this?

My understanding is that I should create a study with different flows (as done e.g. in https://www.openml.org/s/226/flows), optionally publish it, and then use the API to retrieve the runs, flows, etc., and compare them locally with e.g. run.get_metric_fn(). Or is there a better way to do this?

Thanks a lot!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the study, flow, and run API workflow described in the issue, including the cited OpenML study 226 and run.get_metric_fn(). Done means documenting a recommended, reproducible process for comparing two flows on the same benchmark suite, including whether publishing a study is necessary.

Written by the indexing model from the issue text.

Assessment

Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.