iqspr (version 2.3)

get_linearBayes: get the computation of parameters issued from the training of a Bayesian linear regression

Description

Get the computation of parameters issued from the training of a Bayesian linear regression. See the iqspr package paper for details concerning the definition of the cited parameters.

Usage

get_linearBayes(X = NULL, Y = NULL, params = NA)

Arguments

X

is a matrix of features (e.g. fingerprints and/or physical descriptors) issued from a training set.

Y

is a one-dimensional vector, or a matrix, of observables (e.g. targeted chemical properties) issued from a training set.

params

corresponds to the initialization of the parameters (see get_Model_params for a parameters list) if known a priori (NA by default).

Value

the latest w0, V0_inv, a0 and b0 parameters after training over the data X and Y.

Examples

# NOT RUN {
linearBayes_model <- get_linearBayes(X = X[training,], Y = Y[training,],
params = c(list(w0),list(V0_inv),list(a0),list(b0)))
# }