Low-level core functions#

frites.core:

Core functions of information theoretical measures.

This submodule contains all of the core functions to estimate information-based quantities (mutual-information, entropy etc.)

For further details about the Gaussian-Copula Mutual information see [12]

Gaussian-Copula (1d)#

Gaussian-Copula mutual-information supporting univariate / multivariate 2D inputs

copnorm_1d(x)

Copula normalization for a single vector.

copnorm_cat_1d(x, y)

Categorical Copula normalization for a single vector.

ent_1d_g(x[, biascorrect, demeaned])

Entropy of a Gaussian variable in bits.

mi_1d_gg(x, y[, biascorrect, demeaned])

Mutual information (MI) between two Gaussian variables in bits.

mi_model_1d_gd(x, y[, biascorrect, demeaned])

Mutual information between a Gaussian and a discrete variable in bits.

mi_mixture_1d_gd(x, y)

Mutual information between a Gaussian and a discrete variable in bits.

cmi_1d_ggg(x, y, z[, biascorrect, demeaned])

Conditional MI between two Gaussian variables conditioned on a third.

gcmi_1d_cc(x, y)

Gaussian-Copula MI between two continuous variables.

gcmi_model_1d_cd(x, y)

Gaussian-Copula MI between a continuous and a discrete variable.

gcmi_mixture_1d_cd(x, y)

Gaussian-Copula MI between a continuous and a discrete variable.

gccmi_1d_ccc(x, y, z[, biascorrect])

Gaussian-Copula CMI between three continuous variables.

gccmi_1d_ccd(x, y, z[, biascorrect, demeaned])

GCCMI between 2 continuous variables conditioned on a discrete variable.

Gaussian-copula (Nd)#

Gaussian-Copula mutual-information supporting univariate / multivariate multi-dimensional inputs

copnorm_nd(x[, axis])

Copula normalization for a multidimentional array.

copnorm_cat_nd(x, y[, axis])

Categorical Copula normalization for multidimentional array.

ent_nd_g(x[, mvaxis, traxis, biascorrect, ...])

Entropy of a continuous variable.

mi_nd_gg(x, y[, mvaxis, traxis, ...])

Multi-dimentional MI between two Gaussian variables in bits.

mi_model_nd_gd(x, y[, mvaxis, traxis, ...])

Multi-dimentional MI between a Gaussian and a discret variables in bits.

cmi_nd_ggg(x, y, z[, mvaxis, traxis, ...])

Multi-dimentional MI between three Gaussian variables in bits.

gcmi_nd_cc(x, y[, mvaxis, traxis, ...])

GCMI between two continuous variables.

gcmi_model_nd_cd(x, y[, mvaxis, traxis, ...])

GCMI between a continuous and discret variables.

gccmi_nd_ccnd(x, y, *z[, mvaxis, traxis, ...])

Conditional GCMI between two continuous variables.

gccmi_model_nd_cdnd(x, y, *z[, mvaxis, ...])

Conditional GCMI between a continuous and a discret variable.

gccmi_nd_ccc(x, y, z[, mvaxis, traxis, ...])

GCCMI between two continuous variables conditioned on a third.