Extend unit tests

[qododavid]

Hi, I used cover-agent to write the tests for this PR. It uses an AI-based workflow to add new test cases that increase code coverage.

All AI-generated tests have met these four essential criteria:

1. Execute successfully
2. Pass all assertions
3. Increase overall code coverage
4. Test previously uncovered behaviors (as specified in the LLM prompt)

Increased Coverage

Coverage Improvement Report
=========================

File: prophet/diagnostics.py
Coverage improvement: 91.98% → 96.62% (+4.64%)
Newly covered lines: 11
Remaining uncovered lines: 8


File: prophet/utilities.py
Coverage improvement: 65.52% → 100.00% (+34.48%)
Newly covered lines: 10
Remaining uncovered lines: 0


File: prophet/forecaster.py
Coverage improvement: 83.27% → 83.94% (+0.67%)
Newly covered lines: 5
Remaining uncovered lines: 120


File: prophet/serialize.py
Coverage improvement: 93.14% → 99.02% (+5.88%)
Newly covered lines: 6
Remaining uncovered lines: 1

Why adding unit tests is important

• Writing and maintaining unit tests can be tedious, especially as codebases grow larger

• Despite this challenge, unit tests provide key benefits:

  • Enable confident code changes through reliable test coverage
  • Allow faster development by preventing regressions
  • Make refactoring safer with comprehensive test validation

• Tests serve as executable documentation by:

  • Clearly demonstrating input/output relationships
  • Providing quick feedback during development
  • Presenting behavior changes in readable format

[facebook-github-bot]

Hi @qododavid!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

[facebook-github-bot]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[Copilot]

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.

[Copilot]

Pull Request Overview

This PR extends the unit tests for various components of the Prophet module, aiming to increase code coverage and validate new behaviors such as model serialization, parameter warm-starting, holiday validations, and diagnostics cross-validation.

• Added tests for warm-start parameter extraction in both MCMC and non-MCMC scenarios
• Introduced tests to verify model serialization behavior and error handling for unfitted models
• Extended Prophet validation tests covering invalid scaling parameters, holiday constraints, and diagnostics scenarios

Reviewed Changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

File	Description
python/prophet/tests/test_utilities.py	New tests for warm_start_params functionality with and without MCMC
python/prophet/tests/test_serialize.py	Tests for conversion of fit_kwargs and model serialization error handling for unfitted models
python/prophet/tests/test_prophet.py	Additional validations for scaling, holiday parameters, and error messaging in Prophet
python/prophet/tests/test_diagnostics.py	New tests for diagnostics cross-validation covering import errors, cutoff validations, and logging warnings

[Copilot]

[nitpick] The tests for warm_start_params with and without MCMC share similar setup code. Consider parameterizing these tests to reduce duplication.

[Copilot]

[nitpick] Consider using np.array_equal or np.allclose to compare numpy arrays instead of direct equality to a native list to avoid potential type issues.

Suggested change

	assert model_dict['fit_kwargs']['init']['param1'] == [1.0, 2.0]
	assert np.array_equal(model_dict['fit_kwargs']['init']['param1'], np.array([1.0, 2.0]))

[Copilot]

[nitpick] Instead of directly deleting dask from sys.modules, consider using monkeypatch.delitem to avoid side effects in other tests.

Suggested change

	if 'dask' in sys.modules:
	del sys.modules['dask']
	monkeypatch.delitem(sys.modules, 'dask', raising=False)