FIX: Put lower threshold for difference

[LacombeLouis]

Description

Changes were made later in version 1.4.0: #27185 of the _sigmoid_calibration. (note slight changes in 1.3.0 #26913).

Note additional issues with environments:

• CI is limited to version 1.2.2 of scikit-learn (due to numpy 1.25.2) --> why do we need to fix the numpy version?

Fixes #(issue)

• Lower threshold for testing if different. This is just a short term fix.
• Remove class test with printing

Please remove options that are irrelevant.

• Bug fix (non-breaking change which fixes an issue)

Checklist

• [x] I have read the contributing guidelines
• [ ] I have updated the HISTORY.rst and AUTHORS.rst files
• [x] Linting passes successfully : make lint
• [x] Typing passes successfully : make type-check
• [ ] Unit tests pass successfully : make tests
• [ ] Coverage is 100% : make coverage
• [x] Documentation builds successfully : make doc

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Project coverage is 100.00%. Comparing base (614293e) to head (0228014). Report is 284 commits behind head on master.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## master #433 +/- ## ========================================== Coverage 100.00% 100.00% ========================================== Files 39 39 Lines 4616 4895 +279 Branches 487 801 +314 ========================================== + Hits 4616 4895 +279 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[LacombeLouis]

This closes with #440.