pyvinecopulib¶

The pyvinecopulib package¶

`BicopFamily`	A bivariate copula family identifier.
`Bicop`	A class for bivariate copula models.
`FitControlsBicop`	A class for controlling fits of bivariate copula models.
`Vinecop`	A class for vine copula models.
`FitControlsVinecop`	A class for controlling fits of vine copula models.
`CVineStructure`	A class for C-vine structures.
`DVineStructure`	A class for D-vine structures.
`RVineStructure`	A class for R-vine structures.

Functions¶

to_pseudo_obs(x: numpy.ndarray[numpy.float64[m, n]], ties_method: str = 'average') → numpy.ndarray[numpy.float64[m, n]]¶

Applies the empirical probability integral transform to a data matrix.

Gives pseudo-observations from the copula by applying the empirical distribution function (scaled by \(n + 1\)) to each margin/column.

Parameter x:: A matrix of real numbers.
Parameter ties_method:: Indicates how to treat ties; same as in R, see https://stat.ethz.ch/R-manual/R-devel/library/base/html/rank.html.

Returns: Pseudo-observations of the copula, i.e. \(F_X(x)\) (column-wise).

simulate_uniform(n: int, d: int, qrng: bool = False, seeds: List[int] = []) → numpy.ndarray[numpy.float64[m, n]]¶

Simulates from the multivariate uniform distribution.

Parameter n:: Number of observations.
Parameter d:: Dimension.
Parameter qrng:: If true, quasi-numbers are generated.
Parameter seeds:: Seeds of the random number generator; if empty (default), the random number generator is seeded randomly.

If qrng = TRUE, generalized Halton sequences (see ghalton()) are used for \(d \leq 300\) and Sobol sequences otherwise (see sobol()).

Returns: math:mathrm{U}[0, 1] random variables.
Return type: An \(n \times d\) matrix of independent

ghalton(n: int, d: int, seeds: List[int] = []) → numpy.ndarray[numpy.float64[m, n]]¶

Simulates from the multivariate Generalized Halton Sequence.

For more information on Generalized Halton Sequence, see Faure, H., Lemieux, C. (2009). Generalized Halton Sequences in 2008: A Comparative Study. ACM-TOMACS 19(4), Article 15.

Parameter n:: Number of observations.
Parameter d:: Dimension.
Parameter seeds:: Seeds to scramble the quasi-random numbers; if empty (default), the quasi-random number generator is seeded randomly.

Returns: math:mathrm{U}[0, 1] variables.
Return type: An \(n \times d\) matrix of quasi-random

sobol(n: int, d: int, seeds: List[int] = []) → numpy.ndarray[numpy.float64[m, n]]¶

Simulates from the multivariate Sobol sequence.

For more information on the Sobol sequence, see S. Joe and F. Y. Kuo (2008), constructing Sobol sequences with better two-dimensional projections, SIAM J. Sci. Comput. 30, 2635–2654.

Parameter n:: Number of observations.
Parameter d:: Dimension.
Parameter seeds:: Seeds to scramble the quasi-random numbers; if empty (default), the quasi-random number generator is seeded randomly.

Returns: math:mathrm{U}[0, 1] variables.
Return type: An \(n \times d\) matrix of quasi-random