INFFC: Iterative Noise Filter based on the Fusion of Classifiers

In melissakey/NoiseFiltersR: Label Noise Filters for Data Preprocessing in Classification

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

## S3 method for class 'formula'
INFFC(formula, data, ...)

## Default S3 method:
INFFC(x, consensus = FALSE, p = 0.01, s = 3, k = 5,
  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.
consensus	Logical. If FALSE, majority voting scheme is used for 'preliminary filtering' and 'noise free filtering' (see 'Details' and References' section). If TRUE, consensus voting scheme is applied.
p	Real number between 0 and 1. It sets the minimum proportion of original instances which must be tagged as noisy in order to go for another iteration.
s	Positive integer setting the stop criterion together with p. The filter stops after s iterations with not enough noisy instances removed (according to the proportion p).
k	Parameter for the k-nearest neighbors algorithm used for the 'noise score' stage (see 'Details' and 'References').
threshold	Real number between -1 and 1. It sets the noise score value above which an instance is removed.
classColumn	Positive integer indicating the column which contains the (factor of) classes. By default, the last column is considered.

Details

The full description of the method can be looked up in the provided reference. A 'preliminary filtering' is carried out with a fusion of classifiers (FC), including C4.5, 3NN, and logistic regression. Then, potentially noisy instances are identified in a 'noise free filtering' process building the FC on the (preliminary) filtered instances. Finally, a 'noise score' is computed on these potentially noisy instances, removing those exceeding the threshold value. The process stops after s iterations with not enough (according to the proportion p) noisy instances removed.

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.

Note

By means of a message, the number of noisy instances removed in each iteration is displayed in the console.

References

S\'aez J. A., Galar M., Luengo J., Herrera F. (2016): INFFC: An iterative class noise filter based on the fusion of classifiers with noise sensitivity control. Information Fusion, 27, 19-32.

Examples

# Next example is not run because it might be time-consuming
## Not run: 
data(iris)
out <- INFFC(Species~., data = iris)
summary(out)
identical(out$cleanData, iris[setdiff(1:nrow(iris),out$remIdx),])

## End(Not run)

melissakey/NoiseFiltersR documentation built on Feb. 1, 2020, 8:45 p.m.