Have more coherent testing of the summary method

[drbenvincent]

At the moment it seems that we only test the summary method for the pymc_experiments.DifferenceInDifferences class, and that is in the test_pymc_experiments.py file...

CausalPy/causalpy/tests/test_pymc_experiments.py

Lines 10 to 23 in 3bb81a7

	def test_did_summary():
	"""Test that the summary stat function returns a string."""
	df = cp.load_data("did")
	result = cp.pymc_experiments.DifferenceInDifferences(
	df,
	formula="y ~ 1 + group*post_treatment",
	time_variable_name="t",
	group_variable_name="group",
	model=cp.pymc_models.LinearRegression(sample_kwargs=sample_kwargs),
	)
	round_to = None
	print(type(result._causal_impact_summary_stat(round_to)))
	print(result._causal_impact_summary_stat(round_to))
	assert isinstance(result._causal_impact_summary_stat(round_to), str)

We should make sure that we are testing the summary method for all of the pymc_experiment classes. Though I believe the InstrumentalVariable class doesn't have a summery method.

This could be done by adding more to the current test_pymc_experiments.py file, but it could be worth thinking about simply adding to existing tests in test_integration_pymc_examples.py. My thinking is that this would involve less setup / computation time as we wouldn't be doing any additional model fitting.