getWeightsByOutcome {edl} | R Documentation |
Extract the change of connection weights between all cues and a specific outcome.
Description
Extract the change of connection weights between all cues and a specific outcome. The values are returned as data frame.
Usage
getWeightsByOutcome(wmlist, outcome, select.cues = NULL, init.value = 0)
Arguments
wmlist |
A list with weightmatrices, generated by
|
outcome |
String: outcome for which to extract the connection weights. |
select.cues |
Optional selection of cues to limit the number of
connection weights that are returned. The value of NULL (default) will
return all connection weights. Note that specified values that are not in
the weightmatrices will return the initial value without error or warning.
Please use |
init.value |
Value of connection weights for non-existing connections. Typically set to 0. |
Value
Data frame.
Author(s)
Jacolien van Rij
See Also
plotCueWeights
, plotOutcomeWeights
,
getWeightsByCue
Examples
# load example data:
data(dat)
# add obligatory columns Cues, Outcomes, and Frequency:
dat$Cues <- paste("BG", dat$Shape, dat$Color, sep="_")
dat$Outcomes <- dat$Category
dat$Frequency <- dat$Frequency1
head(dat)
dim(dat)
# now use createTrainingData to sample from the specified frequencies:
train <- createTrainingData(dat)
# this training data can actually be used train network:
wm <- RWlearning(train)
# final weight matrix:
getWM(wm)
# Inspect the change in connection weights
# for cue=car
outweights <- getWeightsByOutcome(wm, outcome='vehicle')
head(outweights)
emptyPlot(nrow(outweights), range(outweights), h0=0,
main="Outcome='vehicle'", ylab='connection weights', xlab='learning events')
lines(outweights$BG)
lines(outweights$car, lty=4)
lines(outweights$bicycle, lty=2)
lines(outweights$cat, col=2)
lines(outweights$red, col='blue', lty=4)
lines(outweights$gray, col='blue', lty=2)
legend('bottomright', legend=c('BG', 'car', 'bicycle', 'cat', 'red', 'gray'),
col=c(1,1,1,2,'blue', 'blue'), lty=c(1,4,2,1,4,2), lwd=1)