caret (version 6.0-86)

safs_initial: Ancillary simulated annealing functions


Built-in functions related to simulated annealing

These functions are used with the functions argument of the safsControl function. More information on the details of these functions are at

The initial function is used to create the first predictor subset. The function safs_initial randomly selects 20% of the predictors. Note that, instead of a function, safs can also accept a vector of column numbers as the initial subset.

safs_perturb is an example of the operation that changes the subset configuration at the start of each new iteration. By default, it will change roughly 1% of the variables in the current subset.

The prob function defines the acceptance probability at each iteration, given the old and new fitness (i.e. energy values). It assumes that smaller values are better. The default probability function computed the percentage difference between the current and new fitness value and using an exponential function to compute a probability:

= exp[(current-new)/current*iteration] 


safs_initial(vars, prob = 0.2, ...)

safs_perturb(x, vars, number = floor(length(x) * 0.01) + 1)

safs_prob(old, new, iteration = 1)






the total number of possible predictor variables


The probability that an individual predictor is included in the initial predictor set

not currently used


the integer index vector for the current subset


the number of predictor variables to perturb

old, new

fitness values associated with the current and new subset


the number of iterations overall or the number of iterations since restart (if improve is used in safsControl)


The return value depends on the function. Note that the SA code encodes the subsets as a vector of integers that are included in the subset (which is different than the encoding used for GAs).

The objects caretSA, rfSA and treebagSA are example lists that can be used with the functions argument of safsControl.

In the case of caretSA, the ... structure of safs passes through to the model fitting routine. As a consequence, the train function can easily be accessed by passing important arguments belonging to train to safs. See the examples below. By default, using caretSA will used the resampled performance estimates produced by train as the internal estimate of fitness.

For rfSA and treebagSA, the randomForest and bagging functions are used directly (i.e. train is not used). Arguments to either of these functions can also be passed to them though the safs call (see examples below). For these two functions, the internal fitness is estimated using the out-of-bag estimates naturally produced by those functions. While faster, this limits the user to accuracy or Kappa (for classification) and RMSE and R-squared (for regression).


An object of class list of length 8.


See Also

safs, safsControl


selected_vars <- safs_initial(vars = 10 , prob = 0.2)


safs_perturb(selected_vars, vars = 10, number = 1)


safs_prob(old = .8, new = .9, iteration = 1)
safs_prob(old = .5, new = .6, iteration = 1)

grid <- expand.grid(old = c(4, 3.5),
                    new = c(4.5, 4, 3.5) + 1,
                    iter = 1:40)
grid <- subset(grid, old < new)

grid$prob <- apply(grid, 1,
                     safs_prob(new = x["new"],
                               old= x["old"],
                               iteration = x["iter"]))

grid$Difference <- factor(grid$new - grid$old)
grid$Group <- factor(paste("Current Value", grid$old))

ggplot(grid, aes(x = iter, y = prob, color = Difference)) +
  geom_line() + facet_wrap(~Group) + theme_bw() +
  ylab("Probability") + xlab("Iteration")

# }
## Hypothetical examples
lda_sa <- safs(x = predictors,
               y = classes,
               safsControl = safsControl(functions = caretSA),
               ## now pass arguments to `train`
               method = "lda",
               metric = "Accuracy"
               trControl = trainControl(method = "cv", classProbs = TRUE))

rf_sa <- safs(x = predictors,
              y = classes,
              safsControl = safsControl(functions = rfSA),
              ## these are arguments to `randomForest`
              ntree = 1000,
              importance = TRUE)
# }

# }