R version 4.2.0 (2022-04-22) -- "Vigorous Calisthenics"
Copyright (C) 2022 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> #################################
> ## Test for dist calls
> ##################################
>
> library(proxy)
Attaching package: 'proxy'
The following objects are masked from 'package:stats':
as.dist, dist
The following object is masked from 'package:base':
as.matrix
>
> set.seed(20140107)
>
> ## get all measures
> proxies = pr_DB$get_entry_names()
>
> ## remove special cases
> proxies = setdiff(proxies, c("Mahalanobis", "Minkowski", "Stiles", "Levenshtein", "fJaccard"))
>
> ## create test data
> x = matrix(1:100, 10)
>
> ## test function: checks if dist(x) == dist(x,x) for all measures,
> ## and if diag(dist(x, x)) == diag(x, x, pairwise = TRUE)
> prtest <- function(...) {
+ CD <- dist(x, x, ...)
+ all(as.matrix(dist(x, ...)) == CD) &&
+ all(diag(CD) == dist(x, x, pairwise = TRUE, ...))
+ }
>
> ## loop over all measures (except special cases)
> for (i in proxies)
+ {cat(i); prtest(i); cat(": OK.\n")}
Jaccard: OK.
Kulczynski1: OK.
Kulczynski2: OK.
Mountford: OK.
Fager: OK.
Russel: OK.
simple matching: OK.
Hamman: OK.
Faith: OK.
Tanimoto: OK.
Dice: OK.
Phi: OK.
Michael: OK.
Mozley: OK.
Yule: OK.
Yule2: OK.
Ochiai: OK.
Simpson: OK.
Braun-Blanquet: OK.
cosine: OK.
angular: OK.
eJaccard: OK.
eDice: OK.
correlation: OK.
Chi-squared: OK.
Phi-squared: OK.
Tschuprow: OK.
Cramer: OK.
Pearson: OK.
Gower: OK.
Euclidean: OK.
Bhjattacharyya: OK.
Manhattan: OK.
supremum: OK.
Canberra: OK.
Wave: OK.
divergence: OK.
Kullback: OK.
Bray: OK.
Soergel: OK.
Podani: OK.
Chord: OK.
Geodesic: OK.
Whittaker: OK.
Hellinger: OK.
>
> ## Minkowski
> for (j in c(0.5, 1, 2, 3, Inf))
+ {cat("Minkowski: p =", j); prtest("Minkowski", p = j); cat(": OK.\n")}
Minkowski: p = 0.5: OK.
Minkowski: p = 1: OK.
Minkowski: p = 2: OK.
Minkowski: p = 3: OK.
Minkowski: p = Inf: OK.
>
> ## Mahalanobis (need non-singular matrix)
> x = as.matrix(iris[1:50,-5])
> prtest("Mahalanobis")
[1] TRUE
>
> ## fJaccard (needs values in unit interval)
> x = as.matrix(1:100/100, 10)
> prtest("fJaccard")
[1] TRUE
>
> ## produce binary matrix
> x = matrix(rbinom(100,1,0.7), 10)
>
> ## Stiles (gives a lot of warnings due to log)
> tmp = dist(x, "Stiles")
There were 27 warnings (use warnings() to see them)
> tmp = dist(x, x, "Stiles")
There were 50 or more warnings (use warnings() to see the first 50)
>
> ## try again (almost) all measures, this time with binary data to check
> ## conversions
> for (i in proxies)
+ {cat(i); prtest(i); cat(": OK.\n")}
Jaccard: OK.
Kulczynski1: OK.
Kulczynski2: OK.
Mountford: OK.
Fager: OK.
Russel: OK.
simple matching: OK.
Hamman: OK.
Faith: OK.
Tanimoto: OK.
Dice: OK.
Phi: OK.
Michael: OK.
Mozley: OK.
Yule: OK.
Yule2: OK.
Ochiai: OK.
Simpson: OK.
Braun-Blanquet: OK.
cosine: OK.
angular: OK.
eJaccard: OK.
eDice: OK.
correlation: OK.
Chi-squared: OK.
Phi-squared: OK.
Tschuprow: OK.
Cramer: OK.
Pearson: OK.
Gower: OK.
Euclidean: OK.
Bhjattacharyya: OK.
Manhattan: OK.
supremum: OK.
Canberra: OK.
Wave: OK.
divergence: OK.
Kullback: OK.
Bray: OK.
Soergel: OK.
Podani: OK.
Chord: OK.
Geodesic: OK.
Whittaker: OK.
Hellinger: OK.
> ## Minkowski
> for (j in c(0.5, 1, 2, 3, Inf))
+ {cat("Minkowski: p =", j); prtest("Minkowski", p = j); cat(": OK.\n")}
Minkowski: p = 0.5: OK.
Minkowski: p = 1: OK.
Minkowski: p = 2: OK.
Minkowski: p = 3: OK.
Minkowski: p = Inf: OK.
>
> ## Levenshtein distance
> s <- c("A", "quick", "brown", "fox", "jumps", "over", "the", "lazy", "dog")
> all(as.matrix(dist(s, "Levenshtein")) == dist(s, s, "Levenshtein"))
[1] TRUE
>
> ## Test auto-conversion
> x = iris[,-5]
> prtest()
[1] TRUE
>
>
>
> proc.time()
user system elapsed
0.585 0.012 0.591
Generated by dwww version 1.15 on Sat May 18 10:08:14 CEST 2024.