phylo4d is a generic constructor which merges a phylogenetic tree with
data frames to create a combined object of class phylo4d## S3 method for class 'phylo':
phylo4d(x, tip.data = NULL, node.data = NULL,
all.data = NULL, check.node.labels = c("keep", "drop", "asdata"),
annote=list(), metadata=list(), ...)
## S3 method for class 'phylo4':
phylo4d(x, tip.data = NULL, node.data = NULL,
all.data = NULL, merge.data = TRUE, metadata = list(), ...)
## S3 method for class 'matrix':
phylo4d(x, tip.data = NULL, node.data = NULL,
all.data = NULL, merge.data = TRUE, metadata = list(),
edge.length = NULL, tip.label = NULL, node.label = NULL,
edge.label = NULL, order = "unknown", annote=list(), ...)phylo4, phylo or a matrix of
edges (see above)tip.data and node.data are
provided, should columns with common names will be merged together
(default TRUE) or not (FALSE)? See details.phylo4_orderings, currently "unknown", "preorder"
(="cladewise" in ape), and "postorder", with "cladewise"
and "pruningwise" also allowed for compatibilitx is of class phylo, use
either formatData. Notably, these additional arguments
control the behavior of the constructor in the case of missing/extra
data and where to look for labels in theformatData; these include positional matching, matching
exclusively on node labels, and matching based on a column of data
rather than on row names. See formatData for more
information.Matching rules will apply the same way to all supplied data frames. This means that you need to be consistent with the row names of your data frames. It is good practice to use tip and node labels (or node numbers) when you combine data with a tree.
If you provide both tip.data and node.data, the
treatment of columns with common names will depend on the
merge.data argument. If TRUE, columns with the same name in
both data frames will be merged; when merging columns of different
data types, coercion to a common type will follow standard R rules. If
merge.data is FALSE, columns with common names will be
preserved independently, with tip.data
and node.data have no column names in common.
If you provide all.data along with either of tip.data
and node.data, it must have distinct column names, otherwise an
error will result. Additionally, although supplying columns with the
same names within data frames is not illegal, automatic
renaming for uniqeness may lead to surprising results, so this
practice should be avoided.
coerce-methods for translation functions. The
formatData
function to check the validity of phylo4d objects;
treeOwls <- "((Strix_aluco:4.2,Asio_otus:4.2):3.1,Athene_noctua:7.3);"
tree.owls.bis <- ape::read.tree(text=treeOwls)
try(phylo4d(as(tree.owls.bis,"phylo4"),data.frame(wing=1:3)), silent=TRUE)
obj <- phylo4d(as(tree.owls.bis,"phylo4"),data.frame(wing=1:3), match.data=FALSE)
obj
print(obj)
####
data(geospiza_raw)
geoTree <- geospiza_raw$tree
geoData <- geospiza_raw$data
## fix differences in tip names between the tree and the data
geoData <- rbind(geoData, array(, dim = c(1,ncol(geoData)),
dimnames = list("olivacea", colnames(geoData))))
### Example using a tree of class 'phylo'
exGeo1 <- phylo4d(geoTree, tip.data = geoData)
### Example using a tree of class 'phylo4'
geoTree <- as(geoTree, "phylo4")
## some random node data
rNodeData <- data.frame(randomTrait = rnorm(nNodes(geoTree)),
row.names = nodeId(geoTree, "internal"))
exGeo2 <- phylo4d(geoTree, tip.data = geoData, node.data = rNodeData)
### Example using 'merge.data'
data(geospiza)
trGeo <- extractTree(geospiza)
tDt <- data.frame(a=rnorm(nTips(trGeo)), row.names=nodeId(trGeo, "tip"))
nDt <- data.frame(a=rnorm(nNodes(trGeo)), row.names=nodeId(trGeo, "internal"))
(matchData1 <- phylo4d(trGeo, tip.data=tDt, node.data=nDt, merge.data=FALSE))
(matchData2 <- phylo4d(trGeo, tip.data=tDt, node.data=nDt, merge.data=TRUE))
## Example with 'all.data'
nodeLabels(geoTree) <- as.character(nodeId(geoTree, "internal"))
rAllData <- data.frame(randomTrait = rnorm(nTips(geoTree) + nNodes(geoTree)),
row.names = labels(geoTree, 'all'))
exGeo5 <- phylo4d(geoTree, all.data = rAllData)
## Examples using 'rownamesAsLabels' and comparing with match.data=FALSE
tDt <- data.frame(x=letters[1:nTips(trGeo)],
row.names=sample(nodeId(trGeo, "tip")))
tipLabels(trGeo) <- as.character(sample(1:nTips(trGeo)))
(exGeo6 <- phylo4d(trGeo, tip.data=tDt, rownamesAsLabels=TRUE))
(exGeo7 <- phylo4d(trGeo, tip.data=tDt, rownamesAsLabels=FALSE))
(exGeo8 <- phylo4d(trGeo, tip.data=tDt, match.data=FALSE))
## generate a tree and some data
set.seed(1)
p3 <- ape::rcoal(5)
dat <- data.frame(a = rnorm(5), b = rnorm(5), row.names = p3$tip.label)
dat.defaultnames <- dat
row.names(dat.defaultnames) <- NULL
dat.superset <- rbind(dat, rnorm(2))
dat.subset <- dat[-1, ]
## create a phylo4 object from a phylo object
p4 <- as(p3, "phylo4")
## create phylo4d objects with tip data
p4d <- phylo4d(p4, dat)
###checkData(p4d)
p4d.sorted <- phylo4d(p4, dat[5:1, ])
try(p4d.nonames <- phylo4d(p4, dat.defaultnames))
p4d.nonames <- phylo4d(p4, dat.defaultnames, match.data=FALSE)
p4d.subset <- phylo4d(p4, dat.subset)
p4d.subset <- phylo4d(p4, dat.subset)
try(p4d.superset <- phylo4d(p4, dat.superset))
p4d.superset <- phylo4d(p4, dat.superset)
## create phylo4d objects with node data
nod.dat <- data.frame(a = rnorm(4), b = rnorm(4))
p4d.nod <- phylo4d(p4, node.data = nod.dat, match.data=FALSE)
## create phylo4 objects with node and tip data
p4d.all1 <- phylo4d(p4, node.data = nod.dat, tip.data = dat, match.data=FALSE)
nodeLabels(p4) <- as.character(nodeId(p4, "internal"))
p4d.all2 <- phylo4d(p4, all.data = rbind(dat, nod.dat, match.data=FALSE))Run the code above in your browser using DataLab