dotnet / dotnet/machinelearning-modelbuilder

Can't disable binary variants in Data Classification task

Open
#3,047 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Dockerfile
Stars
285
Forks
66
PR merge metrics
No merged PRs in 30d

Description

**System Information (please complete the following information):**
Model Builder Version (available in Manage Extensions dialog): 17.19.2.211501
Visual Studio Version 2022

**Describe the bug**
xBinary variants are trained even if the algorithm has been disabled.

**To Reproduce**
1. Scenario: data classification
2. Set label to categorical . Make sure Boolean is not selected as type, but it just has 2 categories. For example, set 1/0 to numeric, true/false to text so binary algorithm variants will activated
3. Disable most algorithms
4. Train
5. Observe binary variants are included

**Expected behavior**
Binary variants should be disabled along the main variant,
or there should be way to disable binary variants separately.

This could be a problem if user does not want a specific algo,
or lead to an inferior models being selected if #3046 is as I suspect.

**Screenshots**

![Image](https://github.com/user-attachments/assets/cbe192ac-7415-4777-8c8e-6c5448036934)

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.