Add pandas DataFrame support for table rendering in reports

[Copilot]

• Add pandas as an optional dependency to pyproject.toml
• Implement pandas DataFrame handler in html.py
• Add tests for pandas DataFrame support
• Update README.rst to remove TODO and add pandas dataframe example
• Update docs/usage.rst with pandas DataFrame documentation
• Run tests to validate changes (all 16 tests pass)
• Code review completed (no issues in new code)
• CodeQL security scan passed (0 alerts)
• Edge cases tested and validated
• Final validation completed
• Refactored TestPandasSupport to use tearDown method for cleanup consistency

Summary

Successfully implemented pandas DataFrame support for Otter reports. Refactored test cleanup to follow the same pattern as TestOtterBasics, using setUp/tearDown methods instead of try-finally blocks for better consistency and cleaner code.

Total changes: 5 files changed, 149 insertions(+), 9 deletions(-)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Add support for including pandas dataframes as tables in reports.</issue_title>
<issue_description></issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Add support for including pandas dataframes as tables in reports. #23

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[Copilot]

Pull request overview

This PR adds optional pandas DataFrame support to Otter reports, completing a TODO item from the README. DataFrames can now be automatically rendered as styled HTML tables using the existing tabulate-based rendering system.

Key Changes:

• Added optional pandas dependency with graceful fallback when unavailable
• Implemented DataFrame-to-HTML conversion using the existing Bootstrap table styling
• Added comprehensive test coverage with conditional pandas availability checks

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
otter/html.py	Adds optional pandas import, dataframe_to_table() function, and registers DataFrame handler when pandas is available
pyproject.toml	Defines pandas as an optional dependency under [project.optional-dependencies]
tests/test_otter.py	Adds TestPandasSupport test class with two tests that skip gracefully when pandas is unavailable
README.rst	Removes TODO, adds usage example demonstrating DataFrame rendering
docs/usage.rst	Adds dedicated "Pandas DataFrames" section with usage examples and installation notes

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The TestPandasSupport class is missing a tearDown method to clean up resources. The test_pandas_dataframe_in_report method creates temporary directories but handles cleanup in a try-finally block within the test itself. For consistency with the existing TestOtterBasics class pattern (lines 24-38), consider adding a tearDown method to handle cleanup uniformly across all tests in this class.

Suggested change

	def tearDown(self):
	"""Clean up any temporary resources created by tests."""
	# Remove a temporary directory if one was created and stored on the instance
	if hasattr(self, "test_dir") and self.test_dir and os.path.isdir(self.test_dir):
	shutil.rmtree(self.test_dir)

[Copilot]

Refactored TestPandasSupport to use setUp/tearDown pattern for consistency with TestOtterBasics. The test_dir and test_file are now created in setUp and cleaned up in tearDown, eliminating the try-finally block. Commit: a97a8ba

[transientlunatic]

@copilot Please address the comments from code review.