Matrix of distances to the list of pairwise distances in R

Question

Is there any R package for getting a list of pairwise distances if my input file is a distance matrix For example, if my input is data.frame as follows:

        A1      B1      C1      D1
 A1     0      0.85    0.45    0.96 
 B1            0       0.85    0.56
 C1                    0       0.45
 D1                            0

I want the result to be as follows:

A1  B1  0.85
A1  C1  0.45
A1  D1  0.96
B1  C1  0.85
B1  D1  0.56
C1  D1  0.45

I found a question to make the opposite function using the 'reshape' package, but could not configure it to get what I wanted.

Answer 1

If you have data.frame, you can do something like:

df <- structure(list(A1 = c(0, 0, 0, 0), B1 = c(0.85, 0, 0, 0), C1 = c(0.45, 
0.85, 0, 0), D1 = c(0.96, 0.56, 0.45, 0)), .Names = c("A1", "B1", 
"C1", "D1"), row.names = c(NA, -4L), class = "data.frame")

data.frame( t(combn(names(df),2)), dist=t(df)[lower.tri(df)] )
  X1 X2 dist
1 A1 B1 0.85
2 A1 C1 0.45
3 A1 D1 0.96
4 B1 C1 0.85
5 B1 D1 0.56
6 C1 D1 0.45

Another approach, if you use it as matrixwith + col line names, is to use it directly reshape2:

mat <- structure(c(0, 0, 0, 0, 0.85, 0, 0, 0, 0.45, 0.85, 0, 0, 0.96, 
0.56, 0.45, 0), .Dim = c(4L, 4L), .Dimnames = list(c("A1", "B1", 
"C1", "D1"), c("A1", "B1", "C1", "D1")))

library(reshape2)
subset(melt(mat), value!=0)

   Var1 Var2 value
5    A1   B1  0.85
9    A1   C1  0.45
10   B1   C1  0.85
13   A1   D1  0.96
14   B1   D1  0.56
15   C1   D1  0.45

Answer 2

, , :

mat = matrix(c(0, 0.85, 0.45, 0.96, NA, 0, 0.85, 0.56, NA, NA, 0, 0.45, NA,NA,NA,0), ncol=4)
cont = as.table(t(mat))

#     A    B    C    D
#A 0.00 0.85 0.45 0.96
#B      0.00 0.85 0.56
#C           0.00 0.45
#D                0.00

data.frame NA/0's:

df = as.data.frame(cont)
df = df[complete.cases(df),]
df[df[,3]!=0,]

#   Var1 Var2 Freq
#5     A    B 0.85
#9     A    C 0.45
#10    B    C 0.85
#13    A    D 0.96
#14    B    D 0.56
#15    C    D 0.45

Answer 3

:

• D <- dist(cbind(runif(4), runif(4)), diag=TRUE, upper=TRUE) # generate dummy data
  m <- as.matrix(D) # coerce dist object to a matrix
  dimnames(m) <- dimnames(m) <- list(LETTERS[1:4], LETTERS[1:4]) 
  

• , , , :

  xy <- t(combn(colnames(m), 2))
  data.frame(xy, dist=m[xy])
  
  #  X1 X2      dist
  # 1 A  B 0.3157942
  # 2 A  C 0.5022090
  # 3 A  D 0.3139995
  # 4 B  C 0.1865181
  # 5 B  D 0.6297772
  # 6 C  D 0.8162084
  

• , ( ):

  data.frame(col=colnames(m)[col(m)], row=rownames(m)[row(m)], dist=c(m))
  
  #    col row      dist
  # 1    A   A 0.0000000
  # 2    A   B 0.3157942
  # 3    A   C 0.5022090
  # 4    A   D 0.3139995
  # 5    B   A 0.3157942
  # 6    B   B 0.0000000
  # 7    B   C 0.1865181
  # 8    B   D 0.6297772
  # 9    C   A 0.5022090
  # 10   C   B 0.1865181
  # 11   C   C 0.0000000
  # 12   C   D 0.8162084
  # 13   D   A 0.3139995
  # 14   D   B 0.6297772
  # 15   D   C 0.8162084
  # 16   D   D 0.0000000
  

  , NA, / ( , /):

  data.frame(which(!is.na(m), arr.ind=TRUE, useNames=FALSE), dist=c(m))
  

Answer 4

, spaa-.

exampleInput <- structure(list(A1 = c(0, 0, 0, 0), B1 = c(0.85, 0, 0, 0), 
C1 = c(0.45, 0.85, 0, 0), D1 = c(0.96, 0.56, 0.45, 0)), 
.Names = c("A1", "B1", "C1", "D1"), row.names = c(NA, -4L), class = "data.frame")

library(spaa)
pairlist <- dist2list(as.dist(t(exampleInput)))
pairlist[as.numeric(pairlist$col) > as.numeric(pairlist$row),]

:

   col row value
2   B1  A1  0.85
3   C1  A1  0.45
4   D1  A1  0.96
7   C1  B1  0.85
8   D1  B1  0.56
12  D1  C1  0.45