inference {gmgm}

Perform inference in a Gaussian mixture Bayesian network

Description

This function performs inference in a (non-temporal) Gaussian mixture Bayesian network. This task consists in estimating the state of the system given partial observations of it (the evidence). Inference is performed by likelihood weighting, which is a particle-based approximate method (Koller and Friedman, 2009).

Usage

inference(
  gmbn,
  evid,
  nodes = names(gmbn),
  n_part = 1000,
  max_part_sim = 1e+06,
  verbose = FALSE
)

Arguments

gmbn

A (non-temporal) object of class gmbn.

evid

A data frame containing the evidence. Its columns must explicitly be named after nodes of gmbn and can contain missing values (columns with no value can be removed).

nodes

A character vector containing the inferred nodes (by default all the nodes of gmbn).

n_part

A positive integer corresponding to the number of particles generated for each observation.

max_part_sim

An integer greater than or equal to n_part corresponding to the maximum number of particles that can be processed simultaneously. This argument is used to prevent memory overflow, dividing evid into smaller subsets that are handled sequentially.

verbose

A logical value indicating whether subsets of evid in progress are displayed.

Value

A data frame (tibble) with a structure similar to evid containing the estimated values of the inferred nodes.

References

Koller, D. and Friedman, N. (2009). Probabilistic Graphical Models: Principles and Techniques. The MIT Press.

See Also

filtering, prediction, smoothing

Examples

set.seed(0)
data(gmbn_body, data_body)
evid <- data_body
evid$GENDER[sample.int(2148, 430)] <- NA
evid$AGE[sample.int(2148, 430)] <- NA
evid$HEIGHT[sample.int(2148, 430)] <- NA
evid$WEIGHT[sample.int(2148, 430)] <- NA
evid$FAT[sample.int(2148, 430)] <- NA
evid$WAIST[sample.int(2148, 430)] <- NA
evid$GLYCO[sample.int(2148, 430)] <- NA
infer <- inference(gmbn_body, evid, verbose = TRUE)