feature: Add four new distributions: uniform, beta, cauchy and pareto I type

[iraedeus]

No description provided.

[Copilot]

Pull Request Overview

This PR introduces four new probability distributions—Uniform, Beta, Cauchy, and Pareto Type I—into the mpest library.

• Added model implementations and corresponding unit tests for each new distribution.
• Updated mixture‐generation utilities and model registry to include the new distributions.
• Adjusted project configuration and documentation to reflect the additions.

Reviewed Changes

Copilot reviewed 38 out of 42 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
mpest/models/uniform.py	Added Uniform distribution model
mpest/models/beta.py	Added Beta distribution model
mpest/models/cauchy.py	Added Cauchy distribution model
mpest/models/pareto.py	Added Pareto distribution model
tests/models/test_uniform.py, test_beta.py, test_cauchy.py, test_pareto.py	Added tests for the new distributions
experimental_env/mixture_generators/utils.py	Updated standard and uniform parameter generators
mpest/models/init.py	Registered the new models in ALL_MODELS
experimental_env/analysis/analyze_summarizers/error_summarizer.py	Modified error summarizer logic
experimental_env/experiment/experiment_executors/random_executor.py	Adjusted seeding for random mixture executor
experimental_env/experiment/experiment_executors/standart_executor.py	Adjusted seeding for standard mixture executor
pyproject.toml	Updated project metadata, dependencies, and tooling exclusions

Comments suppressed due to low confidence (5)

tests/models/test_beta.py:51

• [nitpick] This variable is instantiating a Beta model but named pareto_model; rename it to beta_model for clarity.

        pareto_model = Beta()

experimental_env/analysis/analyze_summarizers/error_summarizer.py:46

• Median is computed on the unsorted errors list; you should sort errors before computing the median.

        median = errors[len(errors) // 2]

experimental_env/experiment/experiment_executors/random_executor.py:22

• By removing the seed argument (self._seed) you lose reproducibility; pass the executor's seed into RandomDatasetGenerator.

                RandomMixtureGenerator().create_mixture(models),

experimental_env/experiment/experiment_executors/standart_executor.py:22

• Dropping the seed parameter here breaks deterministic behavior; it should be StandartMixtureGenerator(self._seed).

                StandartMixtureGenerator().create_mixture(models),

pyproject.toml:8

• [nitpick] Poetry expects an SPDX license identifier (e.g. MIT) rather than the filename; consider using license = "MIT" and license-file for the path.

license = "LICENSE"

[VITYANA]

I think it's need to be a MixtureDistribution, not a Misture

[iraedeus]

Closed, split into three separate pull requests: PR1, PR2, PR3