Aliases: pr_DB registry summary.pr_DB
Keywords: cluster
### ** Examples ## create a new distance measure mydist <- function(x,y) x * y ## create a new entry in the registry with two aliases pr_DB$set_entry(FUN = mydist, names = c("test", "mydist")) ## look it up (index is case insensitive): pr_DB$get_entry("TEST")
names test, mydist
FUN function (x, y) x * y
distance TRUE
PREFUN NA
POSTFUN NA
convert NA
type other
loop TRUE
C_FUN FALSE
PACKAGE proxy
abcd FALSE
formula NA
reference NA
description NA
## modify the content of the description field in the new entry pr_DB$modify_entry(names = "test", description = "foo function") ## create a new field pr_DB$set_field("New") ## look up the test entry again (two ways) pr_DB$get_entry("test")
names test, mydist
FUN function (x, y) x * y
distance TRUE
PREFUN NA
POSTFUN NA
convert NA
type other
loop TRUE
C_FUN FALSE
PACKAGE proxy
abcd FALSE
formula NA
reference NA
description foo function
New NA
pr_DB[["test"]]
names test, mydist
FUN function (x, y) x * y
distance TRUE
PREFUN NA
POSTFUN NA
convert NA
type other
loop TRUE
C_FUN FALSE
PACKAGE proxy
abcd FALSE
formula NA
reference NA
description foo function
New NA
## show total number of entries length(pr_DB)
[1] 51
## show all entries (short list) pr_DB$get_entries(pattern = "foo")
$test
names test, mydist
FUN function (x, y) x * y
distance TRUE
PREFUN NA
POSTFUN NA
convert NA
type other
loop TRUE
C_FUN FALSE
PACKAGE proxy
abcd FALSE
formula NA
reference NA
description foo function
New NA
## show more details summary(pr_DB, "long")
* Similarity measures:
Jaccard/binary/Reyssac/Roux (binary) = a / (a + b + c)
Kulczynski1 (binary) = a / (b + c)
Kulczynski2 (binary) = [a / (a + b) + a / (a + c)] / 2
Mountford (binary) = 2a / (ab + ac + 2bc)
Fager/McGowan (binary) = a / sqrt((a + b)(a + c)) - sqrt(a + c) / 2
Russel/Rao (binary) = a / n
simple matching/Sokal/Michener (binary) = (a + d) / n
Hamman (binary) = ([a + d] - [b + c]) / n
Faith (binary) = (a + d/2) / n
Tanimoto/Rogers (binary) = (a + d) / (a + 2b + 2c + d)
Dice/Czekanowski/Sorensen (binary) = 2a / (2a + b + c)
Phi (binary) = (ad - bc) / sqrt[(a + b)(c + d)(a + c)(b + d)]
Stiles (binary) = log(n(|ad-bc| - 0.5n)^2 / [(a + b)(c + d)(a + c)(b + d)])
Michael (binary) = 4(ad - bc) / [(a + d)^2 + (b + c)^2]
Mozley/Margalef (binary) = an / (a + b)(a + c)
Yule (binary) = (ad - bc) / (ad + bc)
Yule2 (binary) = (sqrt(ad) - sqrt(bc)) / (sqrt(ad) + sqrt(bc))
Ochiai (binary) = a / sqrt[(a + b)(a + c)]
Simpson (binary) = a / min{(a + b), (a + c)}
Braun-Blanquet (binary) = a / max{(a + b), (a + c)}
cosine (metric) = xy / sqrt(xx * yy)
angular (metric) = 1 - acos(xy / sqrt(xx * yy)) / pi
eJaccard/extended_Jaccard (metric) = xy / (xx + yy - xy)
eDice/extended_Dice/eSorensen (metric) = 2xy / (xx + yy)
correlation (metric) = xy / sqrt(xx * yy) for centered x,y
Chi-squared (nominal) = sum_ij (o_i - e_i)^2 / e_i
Phi-squared (nominal) = [sum_ij (o_i - e_i)^2 / e_i] / n
Tschuprow (nominal) = sqrt{[sum_ij (o_i - e_i)^2 / e_i] / n / sqrt((p - 1)(q - 1))}
Cramer (nominal) = sqrt{[Chi / n)] / min[(p - 1), (q - 1)]}
Pearson/contingency (nominal) = sqrt{Chi / (n + Chi)}
Gower (other) = Sum_k (s_ijk * w_k) / Sum_k (d_ijk * w_k)
* Distance measures:
Euclidean/L2 (metric) = sqrt(sum_i (x_i - y_i)^2))
Mahalanobis (metric) = sqrt((x - y) Sigma^(-1) (x - y))
Bhjattacharyya (metric) = sqrt(sum_i (sqrt(x_i) - sqrt(y_i))^2))
Manhattan/City-Block/L1/taxi (metric) = sum_i |x_i - y_i|
supremum/max/maximum/Tschebyscheff/Chebyshev (metric) = max_i |x_i - y_i|
Minkowski/Lp (metric) = (sum_i (x_i - y_i)^p)^(1/p)
Canberra (metric) = sum_i |x_i - y_i| / |x_i + y_i|
Wave/Hedges (metric) = sum_i (1 - min(x_i, y_i) / max(x_i, y_i))
divergence (metric) = sum_i (x_i - y_i)^2 / (x_i + y_i)^2
Kullback/Leibler (metric) = sum_i [x_i * log((x_i / sum_j x_j) / (y_i / sum_j y_j)) / sum_j x_j)]
Bray/Curtis (metric) = sum_i |x_i - y_i| / sum_i (x_i + y_i)
Soergel (metric) = sum_i |x_i - y_i| / sum_i max{x_i, y_i}
Levenshtein (other) = Number of insertions, edits, and deletions between to strings
Podani/discordance (metric) = 1 - 2 * (a - b + c - d) / (n * (n - 1))
Chord (metric) = sqrt(2 * (1 - xy / sqrt(xx * yy)))
Geodesic (metric) = arccos(xy / sqrt(xx * yy))
Whittaker (metric) = sum_i |x_i / sum_i x - y_i / sum_i y| / 2
Hellinger (metric) = sqrt(sum_i (sqrt(x_i / sum_i x) - sqrt(y_i / sum_i y)) ^ 2)
fJaccard/fuzzy_Jaccard (metric) = sum_i (min{x_i, y_i} / max{x_i, y_i})
test/mydist (other) = NA
## get all entries in a list (and extract first two ones) pr_DB$get_entries()[1:2]
$Jaccard
names Jaccard, binary, Reyssac, Roux
FUN R_bjaccard
distance FALSE
PREFUN pr_Jaccard_prefun
POSTFUN NA
convert pr_simil2dist
type binary
loop FALSE
C_FUN TRUE
PACKAGE proxy
abcd FALSE
formula a / (a + b + c)
reference Jaccard, P. (1908). Nouvelles recherches sur la
distribution florale. Bull. Soc. Vaud. Sci. Nat., 44, pp.
223--270.
description The Jaccard Similarity (C implementation) for binary data.
It is the proportion of (TRUE, TRUE) pairs, but not
considering (FALSE, FALSE) pairs. So it compares the
intersection with the union of object sets.
New NA
$Kulczynski1
names Kulczynski1
FUN pr_Kulczynski1
distance FALSE
PREFUN NA
POSTFUN NA
convert pr_simil2dist
type binary
loop TRUE
C_FUN FALSE
PACKAGE proxy
abcd TRUE
formula a / (b + c)
reference Kurzcynski, T.W. (1970). Generalized distance and discrete
variables. Biometrics, 26, pp. 525--534.
description Kulczynski Similarity for binary data. Relates the (TRUE,
TRUE) pairs to discordant pairs.
New NA
## get all entries as a data frame (select first 3 fields) as.data.frame(pr_DB)[,1:3]
FUN
Jaccard R_bjaccard
Kulczynski1 pr_Kulczynski1
Kulczynski2 pr_Kulczynski2
Mountford pr_Mountford
Fager pr_fagerMcgowan
Russel pr_RusselRao
simple matching pr_SimpleMatching
Hamman pr_Hamman
Faith pr_Faith
Tanimoto pr_RogersTanimoto
Dice pr_Dice
Phi pr_Phi
Stiles pr_Stiles
Michael pr_Michael
Mozley pr_MozleyMargalef
Yule pr_Yule
Yule2 pr_Yule2
Ochiai pr_Ochiai
Simpson pr_Simpson
Braun-Blanquet pr_BraunBlanquet
cosine R_cosine
angular function (x, y) 1 - acos(crossprod(x, y)/sqrt(crossprod(x) * crossprod(y)))/pi
eJaccard R_ejaccard
eDice R_edice
correlation pr_cor
Chi-squared pr_ChiSquared
Phi-squared pr_PhiSquared
Tschuprow pr_Tschuprow
Cramer pr_Cramer
Pearson pr_Pearson
Gower pr_Gower
Euclidean R_euclidean_dist
Mahalanobis pr_Mahalanobis
Bhjattacharyya pr_Bhjattacharyya
Manhattan R_manhattan_dist
supremum R_maximum_dist
Minkowski R_minkowski_dist
Canberra R_canberra_dist
Wave pr_WaveHedges
divergence pr_Divergence
Kullback pr_KullbackLeibler
Bray pr_BrayCurtis
Soergel pr_Soergel
Levenshtein sdists
Podani pr_Podani
Chord function (x, y) sqrt(2 * (1 - crossprod(x, y)/sqrt(crossprod(x) * crossprod(y))))
Geodesic function (x, y) acos(crossprod(x, y)/sqrt(crossprod(x) * crossprod(y)))
Whittaker function (x, y) sum(abs(x/sum(x) - y/sum(y)))/2
Hellinger function (x, y) sqrt(crossprod(sqrt(x/sum(x)) - sqrt(y/sum(y))))
fJaccard R_fuzzy_dist
test function (x, y) x * y
distance PREFUN
Jaccard FALSE pr_Jaccard_prefun
Kulczynski1 FALSE <NA>
Kulczynski2 FALSE <NA>
Mountford FALSE <NA>
Fager FALSE <NA>
Russel FALSE <NA>
simple matching FALSE <NA>
Hamman FALSE <NA>
Faith FALSE <NA>
Tanimoto FALSE <NA>
Dice FALSE <NA>
Phi FALSE <NA>
Stiles FALSE <NA>
Michael FALSE <NA>
Mozley FALSE <NA>
Yule FALSE <NA>
Yule2 FALSE <NA>
Ochiai FALSE <NA>
Simpson FALSE <NA>
Braun-Blanquet FALSE <NA>
cosine FALSE pr_cos_prefun
angular FALSE <NA>
eJaccard FALSE pr_eJaccard_prefun
eDice FALSE pr_eDice_prefun
correlation FALSE <NA>
Chi-squared FALSE <NA>
Phi-squared FALSE <NA>
Tschuprow FALSE <NA>
Cramer FALSE <NA>
Pearson FALSE <NA>
Gower FALSE pr_Gower_prefun
Euclidean TRUE pr_Euclidean_prefun
Mahalanobis TRUE pr_Mahalanobis_prefun
Bhjattacharyya TRUE <NA>
Manhattan TRUE pr_Manhattan_prefun
supremum TRUE pr_supremum_prefun
Minkowski TRUE pr_Minkowski_prefun
Canberra TRUE pr_Canberra_prefun
Wave TRUE <NA>
divergence TRUE <NA>
Kullback TRUE <NA>
Bray TRUE <NA>
Soergel TRUE <NA>
Levenshtein TRUE pr_Levenshtein_prefun
Podani TRUE <NA>
Chord TRUE <NA>
Geodesic TRUE <NA>
Whittaker TRUE <NA>
Hellinger TRUE <NA>
fJaccard TRUE pr_fJaccard_prefun
test TRUE <NA>
## delete test entry pr_DB$delete_entry("test") ## check if it is really gone pr_DB$entry_exists("test")
[1] FALSE