aggregation {gmgm}

Aggregate particles to obtain inferred values

Description

This function aggregates particles to obtain inferred values. Assuming that the particles have been propagated to a given time slice t, the weighted average of the samples is computed to estimate the state of the system at t or at previous time slices (Koller and Friedman, 2009).

Usage

aggregation(part, nodes, col_seq = NULL, col_weight = "weight", lag = 0)

Arguments

part

A data frame containing the particles propagated to time slice t, as obtained from function particles or propagation.

nodes

A character vector containing the inferred nodes.

col_seq

A character vector containing the column names of part that describe the observation sequence. If NULL (the default), all the particles belong to a single sequence.

col_weight

A character string corresponding to the column name of part that describes the particle weight.

lag

A non-negative integer vector containing the time lags l_1, l_2, \dots such that the samples of time slices t - l_1, t - l_2, \dots are aggregated.

Value

If lag has one element, a data frame (tibble) containing the aggregated values of the inferred nodes and their observation sequences (if col_seq is not NULL). If lag has two or more elements, a list of data frames (tibbles) containing these values for each time lag.

References

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

See Also

aggregation, particles

Examples

library(dplyr)
set.seed(0)
data(gmdbn_air, data_air)
evid <- data_air %>%
  group_by(DATE) %>%
  slice(1:3) %>%
  ungroup()
evid$NO2[sample.int(150, 30)] <- NA
evid$O3[sample.int(150, 30)] <- NA
evid$TEMP[sample.int(150, 30)] <- NA
evid$WIND[sample.int(150, 30)] <- NA
aggreg <- particles(data.frame(DATE = unique(evid$DATE))) %>%
  propagation(gmdbn_air, evid, col_seq = "DATE", n_times = 3) %>%
  aggregation(c("NO2", "O3", "TEMP", "WIND"), col_seq = "DATE", lag = c(0, 1))