Performs a benchmark procedure by partitioning the given data.
On each of times steps size observations are removed from the data, the DD-Classifier is trained on these data and tested on the removed observations.
Usage
ddalpha.getErrorRatePart(data, size = 0.3, times = 10, ...)
Arguments
data
Matrix containing training sample where each of n rows is one object of the training sample where first d entries are inputs and the last entry is output (class label).
size
the excluded sequences size. Either an integer between 1 and n, or a fraction of data between 0 and 1.
times
the number of times the classifier is trained.
...
additional parameters passed to ddalpha.train
Value
errors
the part of incorrectly classified data
errors_sd
the standart deviation of errors
time
the mean training time
time_sd
the standart deviation of training time
See Also
ddalpha.train to train the DDα-classifier,
ddalpha.classify for classification using DDα-classifier,
ddalpha.test to test the DD-classifier on particular learning and testing data,
ddalpha.getErrorRateCV to get error rate of the DD-classifier on particular data.
Examples
# Generate a bivariate normal location-shift classification task
# containing 200 objects
class1 <- mvrnorm(100, c(0,0),
matrix(c(1,1,1,4), nrow = 2, ncol = 2, byrow = TRUE))
class2 <- mvrnorm(100, c(2,2),
matrix(c(1,1,1,4), nrow = 2, ncol = 2, byrow = TRUE))
propertyVars <- c(1:2)
classVar <- 3
data <- rbind(cbind(class1, rep(1, 100)), cbind(class2, rep(2, 100)))
# Train 1st DDalpha-classifier (default settings)
# and get the classification error rate
stat <- ddalpha.getErrorRatePart(data, size = 10, times = 10)
cat("1. Classification error rate (defaults): ",
stat$error, ".\n", sep = "")
# Train 2nd DDalpha-classifier (zonoid depth, maximum Mahalanobis
# depth classifier with defaults as outsider treatment)
# and get the classification error rate
stat2 <- ddalpha.getErrorRatePart(data, depth = "zonoid",
outsider.methods = "depth.Mahalanobis", size = 0.2, times = 10)
cat("2. Classification error rate (depth.Mahalanobis): ",
stat2$error, ".\n", sep = "")