Implement deterministic Fibonacci grid sampler for Euclidean spaces

[Copilot]

Adds FibonacciGridSampler — a deterministic Gaussian sampler based on multi-dimensional Fibonacci grids (Frisch & Hanebeck, FUSION 2021), alongside a refactored GaussianSampler base class.

New classes

• AbstractEuclideanSampler — thin base class for Euclidean samplers
• GaussianSampler — stochastic standard normal sampler via GaussianDistribution
• FibonacciGridSampler — deterministic moment-matched samples on ℝᵈ using Fibonacci grids

Core implementation

• _fibonacci_eigen(d) — computes the Fibonacci eigenvector matrix V and scaling vector R per Purser's "Generalized Fibonacci Grids"; includes a special-case for d=4 (since 2*4+1=9 is not prime) and warns when 2d+1 is not prime
• _fibonacci_grid(d, l, ...) — builds the full grid: rotates a regular hypercube grid by V, selects l points inside [-½, ½]^d, applies probit transform, and moment-matches marginals to unit variance

Public API

sampler = FibonacciGridSampler()

# Deterministic standard-normal samples, shape (n, d)
samples = sampler.sample_stochastic(200, 2)

# Transformed to arbitrary Gaussian
samples = sampler.get_gaussian_samples(200, 2, covariance=Σ, mean=μ)

# Uniform on [0, 1]^d
samples = sampler.get_uniform_samples(100, 2)

Tests

15 tests covering shape, mean/std correctness, determinism, uniform range, Gaussian moment matching, and orthonormality of V for both general and d=4 cases.

[github-actions]

✅MegaLinter analysis: Success

Descriptor	Linter	Files	Fixed	Errors	Warnings	Elapsed time
✅ COPYPASTE	jscpd	yes		no	no	6.31s
✅ JSON	prettier	2	0	0	0	0.44s
✅ JSON	v8r	2		0	0	2.43s
✅ MARKDOWN	markdownlint	1	0	0	0	0.61s
✅ MARKDOWN	markdown-table-formatter	1	0	0	0	0.22s
✅ PYTHON	bandit	247		0	0	3.06s
✅ PYTHON	black	247	1	0	0	4.43s
✅ PYTHON	flake8	247		0	0	1.72s
✅ PYTHON	isort	247	1	0	0	0.47s
✅ PYTHON	mypy	247		0	0	4.05s
✅ PYTHON	pylint	247		0	0	69.81s
✅ PYTHON	ruff	247	1	0	0	0.04s
✅ REPOSITORY	checkov	yes		no	no	21.14s
✅ REPOSITORY	gitleaks	yes		no	no	4.03s
✅ REPOSITORY	git_diff	yes		no	no	0.04s
✅ REPOSITORY	secretlint	yes		no	no	5.45s
✅ REPOSITORY	syft	yes		no	no	3.56s
✅ REPOSITORY	trivy-sbom	yes		no	no	1.76s
✅ REPOSITORY	trufflehog	yes		no	no	18.26s
✅ YAML	prettier	4	0	0	0	0.44s
✅ YAML	v8r	4		0	0	4.66s
✅ YAML	yamllint	4		0	0	0.39s

See detailed reports in MegaLinter artifacts

Your project could benefit from a custom flavor, which would allow you to run only the linters you need, and thus improve runtime performances. (Skip this info by defining FLAVOR_SUGGESTIONS: false)

• Documentation: Custom Flavors
• Command: npx mega-linter-runner@9.4.0 --custom-flavor-setup --custom-flavor-linters PYTHON_PYLINT,PYTHON_BLACK,PYTHON_FLAKE8,PYTHON_ISORT,PYTHON_BANDIT,PYTHON_MYPY,PYTHON_RUFF,COPYPASTE_JSCPD,JSON_V8R,JSON_PRETTIER,MARKDOWN_MARKDOWNLINT,MARKDOWN_MARKDOWN_TABLE_FORMATTER,REPOSITORY_CHECKOV,REPOSITORY_GIT_DIFF,REPOSITORY_GITLEAKS,REPOSITORY_SECRETLINT,REPOSITORY_SYFT,REPOSITORY_TRIVY_SBOM,REPOSITORY_TRUFFLEHOG,YAML_PRETTIER,YAML_YAMLLINT,YAML_V8R

Show us your support by starring ⭐ the repository

[FlorianPfaff]

@copilot Can you fix the megalinter errors?

[Copilot]

@copilot Can you fix the megalinter errors?

Fixed in a02c38e. Changes made:

• Renamed parameter l → n_points to fix E741 ambiguous variable name (flagged by flake8 and ruff)
• Removed spaces before : in slice expressions to fix E203 (flake8)
• Added # pylint: disable=too-many-locals to _fibonacci_eigen and # pylint: disable=too-many-locals,too-many-statements to _fibonacci_grid to fix R0914/R0915

[github-actions]

Test Results

   12 files  ±  0     12 suites  ±0   3h 8m 47s ⏱️ + 2m 34s
  544 tests + 11    544 ✅ + 11      0 💤 ±0  0 ❌ ±0 
6 740 runs  +132  5 564 ✅ +132  1 176 💤 ±0  0 ❌ ±0 

Results for commit a02c38e. ± Comparison against base commit f5c0f75.