[ENH] Addition of Set representation and support-aware plotting

[Khushmagrawal]

Reference Issues/PRs

Fixes #244

What does this implement/fix? Explain your changes.

I have implemented hierarchy of set classes to represent the mathematical support of distributions: RealSet, IntegerSet, IntervalSet, FiniteSet, and EmptySet, UnionSet and IntersectionSet. These sets are designed to be tabular, meaning a single set object can store parameters (bounds/values) as arrays

The BaseDistribution now includes a support property). This would allow distributions to programmatically communicate where their probability mass/density resides. This method was overrided currently only in few distributions to test different types of set - Binomial (IntegerSet), Poisson (IntegerSet), Empirical (FiniteSet), TruncatedDistribution (IntersectionSet), and ZeroInflated (UnionSet) have been updated.

The plot functionality has been changed to use support.boundary() to determine exact x-axis limits. For discrete and mixed distributions, the plotter now queries the support for FiniteSet or IntegerSet components to identify exact coordinates for stem plots.

Does your contribution introduce a new dependency? If yes, which one?

No new dependencies are introduced.

What should a reviewer concentrate their feedback on?

• _plot_single, mixed distributions (like ZeroInflated) for pdf currently plot the continuous part as a line and the discrete mass as stems. Mathematically, a PDF of a mixed distribution includes Dirac delta spikes (infinite density). To distinguish Mass from Density, we mask the PDF line at spike points using np.isclose, would that be right?
• Broadcasting logic in _get_bc_params (We currently utilize oned_as="col" to force 1D parameter arrays ) into column vectors (N, 1))
• In UnionSet and IntersectionSet, we allow a mix of scalar and tabular children. We currently force the output to match the parent set's ndim
• Are the current Set types sufficient?

Did you add any tests for the change?

Yes, test_set.py has been added to verify the symbolic set logic

Any other comments?

Includes a minor fix for ZeroInflated._iloc to ensure scalar-scalar indexing correctly delegates to _iat, which was necessary for cell-level plotting in array distributions

PR checklist

For all contributions

• I've added myself to the list of contributors with any new badges I've earned :-)
  How to: add yourself to the all-contributors file in the skpro root directory (not the CONTRIBUTORS.md). Common badges: code - fixing a bug, or adding code logic. doc - writing or improving documentation or docstrings. bug - reporting or diagnosing a bug (get this plus code if you also fixed the bug in the PR).maintenance - CI, test framework, release.
  See here for full badge reference
• The PR title starts with either [ENH], [MNT], [DOC], or [BUG]. [BUG] - bugfix, [MNT] - CI, test framework, [ENH] - adding or improving code, [DOC] - writing or improving documentation or docstrings.

[Khushmagrawal]

Adding two plotting examples here as well, the current plotting shows the continuous density and the point mass at zero separately and the support is {0} union R.

For zero-inflated Poisson, the support is {0} union the inner discrete support, and the plot shows the added mass at zero