Change raster panel titles using levelplot - r

I'm using RasterVis and levelplot to make a trellis plot of some rasters. I am currently ok for most things but I would like to change the header for each panel from the filename to a chosen string (the filename is convoluted and long, i want to use just a year, for example '2004').
Looking at the levelplot page, it would indicate that levelplot goes looking for some settings as per the argument 'useRaster', either it goes to panel.levelplot or panel.levelplot.raster, but im struggling to use these latter functions.
Any help much appreciated, here's some sample code;
require(rasterVis)
layers <- c(1:4)
s2 <- stack()
for (i in layers) {
r <- raster(nrows=100, ncols=100,ext)
r[] <- sample(seq(from = 1, to = 6, by = 1), size = 10000, replace = TRUE)
rasc <- ratify(r)
rat <- levels(rasc)[[1]]
rat$legend <- c("A","B","C","D","E","F")
levels(rasc) <- rat
s2 <- stack(s2, rasc)
}
levelplot(s2, col.regions=rev(terrain.colors(6)),main = "example")
In the above e.g., I would like "layer.1.1" to be "2004", and so on through to 2007

require(rasterVis)
layers <- c(1:4)
s2 <- stack()
for (i in layers) {
r <- raster(nrows=100, ncols=100)
r[] <- sample(seq(from = 1, to = 6, by = 1), size = 10000, replace = TRUE)
rasc <- ratify(r)
rat <- levels(rasc)[[1]]
rat$legend <- c("A","B","C","D","E","F")
levels(rasc) <- rat
s2 <- stack(s2, rasc)
}
levelplot(s2, col.regions=rev(terrain.colors(6)),main = "example", names.attr=2004:2007)
p.strip <- list(cex=1.5, lines=1, col="blue", fontfamily='Serif')
levelplot(s2, col.regions=rev(terrain.colors(6)), main = "example",
names.attr=2004:2007, par.strip.text=p.strip)

Related

Dendrogram plot remove tree labels at end of the branches

Using the example located here https://www.datacamp.com/community/tutorials/hierarchical-clustering-R and the data located https://archive.ics.uci.edu/ml/datasets/seeds# i am trying to remove the labels at the bottom of the dendrogram when using the color_branches
when plot(hclust_avg, labels=FALSE) it works but not later when using color_branches. is there a way to remove them?
`set.seed(786)
seeds_df <- read.csv("seeds_dataset.txt",sep = '\t',header = FALSE)
feature_name <- c('area','perimeter','compactness','length.of.kernel','width.of.kernal','asymmetry.coefficient','length.of.kernel.groove','type.of.seed')
colnames(seeds_df) <- feature_name
seeds_df<- seeds_df[complete.cases(seeds_df), ]
seeds_label <- seeds_df$type.of.seed
seeds_df$type.of.seed <- NULL
seeds_df_sc <- as.data.frame(scale(seeds_df))
dist_mat <- dist(seeds_df_sc, method = 'euclidean')
hclust_avg <- hclust(dist_mat, method = 'average')
cut_avg <- cutree(hclust_avg, k = 3)
suppressPackageStartupMessages(library(dendextend))
avg_dend_obj <- as.dendrogram(hclust_avg)
avg_col_dend <- color_branches(avg_dend_obj, h = 3)
plot(avg_col_dend)`
Figured this out by colouring the the labels white to the background
avg_dend_obj <- as.dendrogram(hclust_avg)
labels_colors(avg_dend_obj) <- "white"
plot(avg_dend_obj)

R: Making common legend and colour scheme for multiple shapefiles

A sample data first:
library(raster)
# download a sample shape file
shape.file <- getData('GADM', country='FRA', level=2)
ID_2 <- rep(shape.file#data$ID_2,times=2)
group.id <- rep(c(100,200),each=96)
set.seed(1)
cat1<- runif(192,min=0,max=100)
set.seed(2)
cat2<- runif(192,min=0,max=100)
set.seed(3)
cat3<- runif(192,min=0,max=100)
dat <- as.data.frame(cbind(ID_2,group.id,cat1,cat2,cat3))
# extract the data for group.id = 100 and group.id = 200 in two seprate df
group.id.100 <- dat[dat$group.id==100,]
group.id.200 <- dat[dat$group.id==200,]
# merge with shape file
merge.shp.100 <- merge(shape.file,group.id.100, by="ID_2")
merge.shp.200 <- merge(shape.file,group.id.200, by="ID_2")
# plot them together
par(mfrow=c(3,2))
plot(merge.shp.100,col=merge.shp$cat1,main="Group.id.100,cat1")
plot(merge.shp.100,col=merge.shp$cat2,main="Group.id.100,cat2")
plot(merge.shp.100,col=merge.shp$cat3,main="Group.id.100,cat3")
plot(merge.shp.200,col=merge.shp$cat1,main="Group.id.200,cat1")
plot(merge.shp.200,col=merge.shp$cat2,main="Group.id.200,cat2")
plot(merge.shp.200,col=merge.shp$cat3,main="Group.id.200,cat3")
I want to insert a common legend and colour scheme for all the 6 figures.
For example, the legend should go from minimum = min(c(cat1,cat2,cat3)) to max(c(cat1,cat2,cat3))
for all the six figures. Similarly, a value of 50 should have the same colour in all the 6 figures.
Thank you
You can use spplot
Example data:
library(raster)
s <- getData('GADM', country='FRA', level=2)[, c('GID_1', 'NAME_1', 'GID_2', 'NAME_2')]
set.seed(1)
m <- matrix(runif(96*6, 0, 100), nrow=96, ncol=6)
vars <- paste0("cat", 1:6)
colnames(m) <- vars
d <- data.frame(GID_2 = s$GID_2, m)
sd <- merge(s, d)
Use spplot:
spplot(sd, vars)
With base plot, you could do something like
brks <- seq(0,100,20)
par(mfrow=c(2,3), mai=c(0,0,0.5,0))
cols = rainbow(length(brks))
for (v in vars) {
cuts <- cut(data.frame(sd)[, v], brks)
plot(s, col=cols[cuts], main=v)
}

Dissolving hexmap polygon shape files

I am trying to produce an outline for a hexagonal cartogram by dissolving the inner polygons via the unionSpatialPolygons or aggregate functions. I am getting stray hexs that do not dissolve... a dummy example to show the problem:
# grab a dummy example shape file
library(raster)
g <- getData(name = "GADM", country = "GBR", level = 2)
# par(mar = rep(0,4))
# plot(g)
# create a hexagonal cartogram
# library(devtools)
# install_github("sassalley/hexmapr")
library(hexmapr)
h <- calculate_cell_size(shape = g, seed = 1,
shape_details = get_shape_details(g),
learning_rate = 0.03, grid_type = 'hexagonal')
i <- assign_polygons(shape = g, new_polygons = h)
par(mar = rep(0,4))
plot(i)
# dissolve the polygons to get coastline
library(maptools)
j <- unionSpatialPolygons(SpP = i, IDs = rep(1, length(i)))
par(mar = rep(0,4))
plot(j)
# same result with aggregate in the raster package
k <- aggregate(x = i)
par(mar = rep(0,4))
plot(k)
With the shapefile I am actually using (not for the UK) I get even more stray hexagons - some complete - some not.
Suggested solution from Roger Bivand (via an email exchange):
g1 <- spTransform(x = g, CRSobj = CRS("+init=epsg:27700"))
# cellsize from calculate_cell_size() above
h1 <- spsample(x = g1, type="hexagonal", cellsize=38309)
i2 <- HexPoints2SpatialPolygons(hex = h1)
j2 <- unionSpatialPolygons(SpP = i2, IDs = rep(1, length(i2)))
plot(j2)
i.e. avoid assign_polygons() in hexmapr and utilize 1) spsample to generate shape positions and 2) HexPoints2SpatialPolygons for the hexagonal grid (both in sp package).

How to color branches in R dendogram as a function of the classes in it?

I wish to visualize how well a clustering algorithm is doing (with certain distance metric). I have samples and their corresponding classes.
To visualize, I cluster and I wish to color the branches of a dendrogram by the items in the cluster. The color will be the color most items in the hierarchical cluster correspond to (given by the data\classes).
Example: If my clustering algorithm chose indexes 1,21,24 to be a certain cluster (at a certain level) and I have a csv file containing a class number in each row corresponding to lets say 1,2,1. I want this edge to be coloured 1.
Example Code:
require(cluster)
suppressPackageStartupMessages(library(dendextend))
dir <- 'distance_metrics/'
filename <- 'aligned.csv'
my.data <- read.csv(paste(dir, filename, sep=""), header = T, row.names = 1)
my.dist <- as.dist(my.data)
real.clusters <-read.csv("clusters", header = T, row.names = 1)
clustered <- diana(my.dist)
# dend <- colour_branches(???dend, max(real.clusters)???)
plot(dend)
EDIT:
another example partial code
dir <- 'distance_metrics/' # csv in here contains a symmetric matrix
clust.dir <- "clusters/" #csv in here contains a column vector with classes
my.data <- read.csv(paste(dir, filename, sep=""), header = T, row.names = 1)
filename <- 'table.csv'
my.dist <- as.dist(my.data)
real.clusters <-read.csv(paste(clust.dir, filename, sep=""), header = T, row.names = 1)
clustered <- diana(my.dist)
dnd <- as.dendrogram(clustered)
Both node and edge color attributes can be set recursively on "dendrogram" objects (which are just deeply nested lists) using dendrapply. The cluster package also features an as.dendrogram method for "diana" class objects, so conversion between the object types is seamless. Using your diana clustering and borrowing some code from #Edvardoss iris example, you can create the colored dendrogram as follows:
library(cluster)
set.seed(999)
iris2 <- iris[sample(x = 1:150,size = 50,replace = F),]
clust <- diana(iris2)
dnd <- as.dendrogram(clust)
## Duplicate rownames aren't allowed, so we need to set the "labels"
## attributes recursively. We also label inner nodes here.
rectify_labels <- function(node, df){
newlab <- df$Species[unlist(node, use.names = FALSE)]
attr(node, "label") <- (newlab)
return(node)
}
dnd <- dendrapply(dnd, rectify_labels, df = iris2)
## Create a color palette as a data.frame with one row for each spp
uniqspp <- as.character(unique(iris$Species))
colormap <- data.frame(Species = uniqspp, color = rainbow(n = length(uniqspp)))
colormap[, 2] <- c("red", "blue", "green")
colormap
## Now color the inner dendrogram edges
color_dendro <- function(node, colormap){
if(is.leaf(node)){
nodecol <- colormap$color[match(attr(node, "label"), colormap$Species)]
attr(node, "nodePar") <- list(pch = NA, lab.col = nodecol)
attr(node, "edgePar") <- list(col = nodecol)
}else{
spp <- attr(node, "label")
dominantspp <- levels(spp)[which.max(tabulate(spp))]
edgecol <- colormap$color[match(dominantspp, colormap$Species)]
attr(node, "edgePar") <- list(col = edgecol)
}
return(node)
}
dnd <- dendrapply(dnd, color_dendro, colormap = colormap)
## Plot the dendrogram
plot(dnd)
The function you are looking for is color_brances from the dendextend R package, using the arguments clusters and col. Here is an example (based on Shaun Wilkinson's example):
library(cluster)
set.seed(999)
iris2 <- iris[sample(x = 1:150,size = 50,replace = F),]
clust <- diana(iris2)
dend <- as.dendrogram(clust)
temp_col <- c("red", "blue", "green")[as.numeric(iris2$Species)]
temp_col <- temp_col[order.dendrogram(dend)]
temp_col <- factor(temp_col, unique(temp_col))
library(dendextend)
dend %>% color_branches(clusters = as.numeric(temp_col), col = levels(temp_col)) %>%
set("labels_colors", as.character(temp_col)) %>%
plot
there are suspicions that misunderstood the question however I'll try to answer:
from my previous objectives were rewritten by the example of iris
clrs <- rainbow(n = 3) # create palette
clrs <- clrs[iris$Species] # assign colors
plot(x = iris$Sepal.Length,y = iris$Sepal.Width,col=clrs) # simple test colors
# cluster
dt <- cbind(iris,clrs)
dt <- dt[sample(x = 1:150,size = 50,replace = F),] # create short dataset for visualization convenience
empty.labl <- gsub("."," ",dt$Species) # create a space vector with length of names intended for reserve place to future text labels
dst <- dist(x = scale(dt[,1:4]),method = "manhattan")
hcl <- hclust(d = dst,method = "complete")
plot(hcl,hang=-1,cex=1,labels = empty.labl, xlab = NA,sub=NA)
dt <- dt[hcl$order,] # sort rows for order objects in dendrogramm
text(x = seq(nrow(dt)), y=-.5,labels = dt$Species,srt=90,cex=.8,xpd=NA,adj=c(1,0.7),col=as.character(dt$clrs))

R plotly heatmap tick labels being cutoff

Trying to produce a gene-expression heatmap using R's plotly. The gene names are quite long and the dimensions are quite big:
require(permute)
require(plotly)
set.seed(1)
mat <- matrix(shuffle(c(rnorm(5000,2,1),rnorm(5000,-2,1))),nrow=2500,ncol=4)
rownames(mat) <- paste("very_long_gene_name",1:2500,sep=".")
colnames(mat) <- paste("s",1:4,sep=".")
Clustering:
hc.col <- hclust(dist(t(mat)))
dd.col <- as.dendrogram(hc.col)
col.order <- order.dendrogram(dd.col)
hc.row <- hclust(dist(mat))
dd.row <- as.dendrogram(hc.row)
row.order <- order.dendrogram(dd.row)
mat <- mat[row.order,col.order]
Producing the plot and saving the html file:
heatmap.plotly <- plot_ly(x=colnames(mat),y=rownames(mat),z=mat,type="heatmap",colors=colorRamp(c("darkblue","white","darkred")))
htmlwidgets::saveWidget(heatmap.plotly,"heatmap.plotly.html")
The figure I get has the gene names cut off, and I'm not sure it's presenting all the data:
Any idea how to fix these two issues?
Increase your margins
m <- list(
l = 200,
r = 10,
b = 50,
t = 10,
pad = 2
)
heatmap.plotly <- plot_ly(x=colnames(mat),y=rownames(mat),z=mat,type="heatmap",
colors=colorRamp(c("darkblue","white","darkred"))) %>%
layout(margin = m)
heatmap.plotly

Resources