DataSimilarity (version 0.2.0)

findSimilarityMethod: Selection of Appropriate Methods for Quantifying the Similarity of Datasets

Description

Find a dataset similarity method for the dataset comparison at hand and display information on suitable methods.

Usage

findSimilarityMethod(Numeric = FALSE, Categorical = FALSE, 
                      Target.Inclusion = FALSE, Multiple.Samples = FALSE, 
                      only.names = TRUE, ...)

Value

Either a character vector of function names for only.names = TRUE or a subset of method.table of the selected methods for only.names = FALSE.

Arguments

Numeric

Is it required that the method is applicable to numeric data? (default: FALSE)

Categorical

Is it required that the method is applicable to categorical data? (default: FALSE)

Target.Inclusion

Is it required that the method is applicable to datasets that include a target variable? (default: FALSE)

Multiple.Samples

Is it required that the method is applicable to multiple datasets simultaneously? (default: FALSE)

only.names

Should only the function names be returned? (default: TRUE, only names are returned. Setting this to FALSE returns the whole method table, see method.table)

...

Further criteria that the method should fulfill, see colnames(method.table). Each criterion can be used as an argument by supplying criterion = TRUE to obtain only methods that fulfill the respective criterion.

Details

This function is intended to facilitate finding suitable methods. The criteria that a method should fulfill for the application at hand can be specified and a vector of the function names or the full information on the methods is returned.

References

Article describing the criteria and taxonomy: Stolte, M., Kappenberg, F., Rahnenführer, J., Bommert, A. (2024). Methods for quantifying dataset similarity: a review, taxonomy and comparison. Statist. Surv. 18, 163 - 298. tools:::Rd_expr_doi("10.1214/24-SS149")

Full interactive results table: https://shiny.statistik.tu-dortmund.de/data-similarity/

See Also

method.table, DataSimilarity

Examples

# Workflow for using the DataSimilarity package: 
# Prepare data example: comparing species in iris dataset
data("iris")
iris.split <- split(iris[, -5], iris$Species)
setosa <- iris.split$setosa
versicolor <- iris.split$versicolor
virginica <- iris.split$virginica

# 1. Find appropriate methods that can be used to compare 3 numeric datasets:
findSimilarityMethod(Numeric = TRUE, Multiple.Samples = TRUE)

# get more information 
findSimilarityMethod(Numeric = TRUE, Multiple.Samples = TRUE, only.names = FALSE)

# 2. Choose a method and apply it:
# All suitable methods
possible.methds <- findSimilarityMethod(Numeric = TRUE, Multiple.Samples = TRUE, 
                                          only.names = FALSE)
# Select, e.g., method with highest number of fulfilled criteria
possible.methds$Implementation[which.max(possible.methds$Number.Fulfilled)]

set.seed(1234)
if(requireNamespace("KMD")) {
  DataSimilarity(setosa, versicolor, virginica, method = "KMD")
}

# or directly 
set.seed(1234)
if(requireNamespace("KMD")) {
  KMD(setosa, versicolor, virginica)
}