MultivariateNormalQMC — SciPy v1.15.2 Manual (original) (raw)

scipy.stats.qmc.

class scipy.stats.qmc.MultivariateNormalQMC(mean, cov=None, *, cov_root=None, inv_transform=True, engine=None, rng=None)[source]#

QMC sampling from a multivariate Normal \(N(\mu, \Sigma)\).

Parameters:

meanarray_like (d,)

The mean vector. Where d is the dimension.

covarray_like (d, d), optional

The covariance matrix. If omitted, use cov_root instead. If both cov and cov_root are omitted, use the identity matrix.

cov_rootarray_like (d, d’), optional

A root decomposition of the covariance matrix, where d' may be less than d if the covariance is not full rank. If omitted, use cov.

inv_transformbool, optional

If True, use inverse transform instead of Box-Muller. Default is True.

engineQMCEngine, optional

Quasi-Monte Carlo engine sampler. If None, Sobol is used.

rngnumpy.random.Generator, optional

Pseudorandom number generator state. When rng is None, a newnumpy.random.Generator is created using entropy from the operating system. Types other than numpy.random.Generator are passed to numpy.random.default_rng to instantiate a Generator.

Changed in version 1.15.0: As part of the SPEC-007transition from use of numpy.random.RandomState tonumpy.random.Generator, this keyword was changed from seed to_rng_. For an interim period, both keywords will continue to work, although only one may be specified at a time. After the interim period, function calls using the seed keyword will emit warnings. Following a deprecation period, the seed keyword will be removed.

Examples

import matplotlib.pyplot as plt from scipy.stats import qmc dist = qmc.MultivariateNormalQMC(mean=[0, 5], cov=[[1, 0], [0, 1]]) sample = dist.random(512) _ = plt.scatter(sample[:, 0], sample[:, 1]) plt.show()

Methods