问题
I have a data frame defined in a format of distance matrix:
> df
DA DB DC DD
DB 0.39 NA NA NA
DC 0.44 0.35 NA NA
DD 0.30 0.48 0.32 NA
DE 0.50 0.80 0.91 0.7
I want to use it as distance matrix in hclust
function. But when I try to convert it to a dist
object, it changes:
> as.dist(df)
DB DC DD
DC 0.44
DD 0.30 0.48
DE 0.50 0.80 0.91
You can see that DA
is no longer part of the matrix. If I try to use df
directly in hclust
, it does not work:
> hclust(d = df)
Error in if (is.na(n) || n > 65536L) stop("size cannot be NA nor exceed 65536") :
missing value where TRUE/FALSE needed
How can I use df
as distance matrix?
回答1:
temp = as.vector(na.omit(unlist(df1)))
NM = unique(c(colnames(df1), row.names(df1)))
mydist = structure(temp, Size = length(NM), Labels = NM,
Diag = FALSE, Upper = FALSE, method = "euclidean", #Optional
class = "dist")
mydist
# DA DB DC DD
#DB 0.39
#DC 0.44 0.35
#DD 0.30 0.48 0.32
#DE 0.50 0.80 0.91 0.70
plot(hclust(mydist))
DATA
df1 = structure(list(DA = c(0.39, 0.44, 0.3, 0.5), DB = c(NA, 0.35,
0.48, 0.8), DC = c(NA, NA, 0.32, 0.91), DD = c(NA, NA, NA, 0.7
)), .Names = c("DA", "DB", "DC", "DD"), class = "data.frame", row.names = c("DB",
"DC", "DD", "DE"))
回答2:
Since you call your object df, I am a little worried that it is a data.frame and not a matrix. However, proceeding as if it is a matrix ...
## creating your data
df = as.matrix(read.table(text="DA DB DC DD
0.39 NA NA NA
0.44 0.35 NA NA
0.30 0.48 0.32 NA
0.50 0.80 0.91 0.7",
header=TRUE))
You just need to give it the zero diagonal as well.
DM = matrix(0, nrow=5, ncol=5)
DM[lower.tri(DM)] = df[lower.tri(df, diag=TRUE)]
as.dist(DM)
1 2 3 4
2 0.39
3 0.44 0.35
4 0.30 0.48 0.32
5 0.50 0.80 0.91 0.70
来源:https://stackoverflow.com/questions/48324940/how-to-convert-data-frame-into-distance-matrix-for-hierarchical-clustering