NoiseFiltersR (version 0.1.0)

edgeBoostFilter: Edge Boosting Filter

Description

Ensemble-based filter for removing label noise from a dataset as a preprocessing step of classification. For more information, see 'Details' and 'References' sections.

Usage

"edgeBoostFilter"(formula, data, ...)
"edgeBoostFilter"(x, m = 15, percent = 0.05, threshold = 0, classColumn = ncol(x), ...)

Arguments

formula

A formula describing the classification variable and the attributes to be used.

data, x

Data frame containing the tranining dataset to be filtered.

...

Optional parameters to be passed to other methods.

m

Number of boosting iterations

percent

Real number between 0 and 1. It sets the percentage of instances to be removed (as long as their edge value exceeds the parameter threshold).

threshold

Real number between 0 and 1. It sets the minimum edge value required by an instance in order to be removed.

classColumn

Positive integer indicating the column which contains the (factor of) classes. By default, the last column is considered.

Value

An object of class filter, which is a list with seven components:

• cleanData is a data frame containing the filtered dataset.
• remIdx is a vector of integers indicating the indexes for removed instances (i.e. their row number with respect to the original data frame).
• repIdx is a vector of integers indicating the indexes for repaired/relabelled instances (i.e. their row number with respect to the original data frame).
• repLab is a factor containing the new labels for repaired instances.
• parameters is a list containing the argument values.
• call contains the original call to the filter.
• extraInf is a character that includes additional interesting information not covered by previous items.

Details

The full description of the method can be looked up in the provided reference.

An AdaBoost scheme (Freund & Schapire) is applied with a default C4.5 tree as weak classifier. After m iterations, those instances with larger (according to the constraints percent and threshold) edge values (Wheway, Freund & Schapire) are considered noisy and thus removed.

Notice that making use of extreme values (i.e. percent=1 or threshold=0) any 'removing constraints' can be ignored.

References

Freund Y., Schapire R. E. (1997): A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1), 119-139.

Wheway V. (2001, January): Using boosting to detect noisy data. In Advances in Artificial Intelligence. PRICAI 2000 Workshop Reader (pp. 123-130). Springer Berlin Heidelberg.

Examples

# Next example is not run in order to save time
## Not run: 
# data(iris)
# out <- edgeBoostFilter(Species~., data = iris, m = 10, percent = 0.05, threshold = 0)
# print(out)
# identical(out$cleanData, iris[setdiff(1:nrow(iris),out$remIdx),])
# ## End(Not run)