Related
I have a massive data file that I am breaking down into day blocks by person and then plotting events that occurred during the day and the duration of those events (either A, B or C)
Data is structured like below: t_z is the interval between rows, period is the event variable, this example is for one individual for one day ( actual data is xdays xpersons)
intervals <- c(0,5.1166667,6.2166667,3.5166667,0.06666667,3.0666667,6.3,
2.3833333,0.06666667,4.7,18.666667,17.383333,21.533333,
0.1,0.08333333,0.85)
period <- c("C", "B", "A", "B", "C", "B", "C", "B",
"C", "B", "C", "B", "C", "B", "C", "B")
i <- as.data.frame(intervals)
p <- as.data.frame(period)
d <- cbind(i,p)
Getting a bar plot is easy enough but it stacks all "periods" into blocks by day:
d$id<-1
e <- ggplot(d,aes(id))
e + geom_bar(aes(fill=period))
Simple aggregated stacked bar of time data:
However, I would like each "period" to be represented discretely and by its magnitude:
Periods as discrete stacked blocks example:
Thanks YBS but your method comes close but the size of the periods is not correct any ideas? The first C=5 is not the same size as the first A=5?
intervals <- c(5, 15, 5, 3,7,3,6, 2)
period <- c("C","B","A","B","C","B","C","B")
d <- data.frame(intervals,period)
colors=c("red","blue","green")
dc <- data.frame(period=unique(d$period),colors)
d2 <- d %>% mutate(nid = paste0(d$period,'_',row_number()))
d3 <- left_join(d2,dc, by="period")
d3$id<-1
e <- ggplot(d3,aes(x=id, y=intervals)) +
geom_col(aes(fill=nid))
e + scale_fill_manual(name='period', labels=d3$period, values=d3$colors )
The trick is to create a newid with all the discrete values, and then reverting back to initial period values via scale_fill_manual. You can use coord_flip() to make it horizontal and change the legend position as necessary. Perhaps this is the desired output.
intervals <- c(0, 5.1166667, 6.2166667, 3.5166667,0.6666667,3.0666667,6.3, 2.3833333)
#,0.06666667 , 4.7,18.666667,17.383333,21.533333, 0.1,0.08333333,0.85)
period <- c("C", "B", "A", "B", "C", "B", "C", "B")
# ,"C", "B", "C", "B", "C", "B", "C", "B")
d <- data.frame(intervals,period)
colors=c("red", "blue","green")
dc <- data.frame(period=unique(d$period),colors)
d2 <- d %>% mutate(nid = paste0(d$period,'_',row_number()))
d3 <- left_join(d2,dc, by="period")
d3$id<-1
e <- ggplot(d3,aes(x=id, y=intervals)) +
geom_col(aes(fill=nid))
e + scale_fill_manual(name='period', labels=d3$period, values=d3$colors )
I have data which provides information on flows by actor c, broken down by inputs originating from source s, to partner p.
Network data normally has only one information: Data / Information flows from A->B, B->C etc.
However, my data shows which flows from A->B then goes to C, and which from A->B goes to D.
The data is structured as a three-column edgelist.
source <- c("A", "D", "B", "B")
country <- c("B", "B", "A", "A")
partner <- c("C", "C", "C", "D")
value <- c("5", "0", "2", "4")
df <- data.frame(source, country, partner, value)
df
I kinda dont see how it would be possible to use this as network data - however, if anyone got an idea on how to use that way more fine-grained network that be amazing ((:
best,
moritz
Maybe like this:
library(igraph)
g <- graph_from_data_frame(
rbind(
setNames(df[, c(1, 2, 4)], c("from", "to", "value")),
setNames(df[, c(1, 3, 4)], c("from", "to", "value"))
)
)
plot(g)
I am not sure if the code below is what you want
library(igraph)
v <- c(3,1)
g <- Reduce(union,lapply(v, function(k) graph_from_data_frame(df[-k])))
such that plot(g) gives
I need to see all possible variations of these nucleotide string: GCGCTAAGCAAAAAACAT
with two caveats:
1. everything that is not Bold is fixed
2. Bold can be either A or C
I used the permutations function:
library(gtools)
x <- c('a', 'c')
permutations(n=2, r=8, v=x, repeats.allwed=T)
It works, the problem is that I would need the list of results to be in the nucleotide sequence, or else I will spend more time copying and pasting the results in the nucleotide sequence than doing the permutation by hand.
Thanks a lot!!!
Giacomo
I would use sprintf:
library(gtools)
x <- c('a', 'c')
p <- permutations(n=2, r=8, v=x, repeats.allowed=T)
#split columns
p <- asplit(p, 2)
#insert into format string
do.call(sprintf, c(p, fmt = "GCGCT%s%sGC%s%s%s%s%s%sCAT"))
#[1] "GCGCTaaGCaaaaaaCAT" "GCGCTaaGCaaaaacCAT" "GCGCTaaGCaaaacaCAT" "GCGCTaaGCaaaaccCAT" "GCGCTaaGCaaacaaCAT" ...
You might want to create the permutations from upper-case letters.
Here is a solution, resulting in a matrix with each line being a permutation
library(gtools)
x <- c('A', 'C')
perms <- permutations(n = 2, r = 8, v = x, repeats.allowed = TRUE)
nucleotid <- c("G", "C", "G", "C", "T", "A",
"A", "G", "C", "A", "A", "A",
"A", "A", "A", "C", "A", "T")
# Looping throught each permutation to create the string
result <- apply(perms, 1, function(x){
y <- nucleotid
y[c(6,7,10:15)] <- x
y
})
t(result)
I am struggling with a recursive function, who's goal is to determine which raw materials belong to which product. I clouldn't figure out, how to handle multiple possible paths in data frame "db". The wanted function should give: A-B-C-E, A-B-C-F, A-B-D-F for db. My function works for "da". I added it to show what I am after, and it is a bit like bill of materials explosion, but not exactly.
da <- data.frame(parent = c("A", "B", "B", "C", "D"),
child = c("B", "C", "D", "E", "F"),
stringsAsFactors = FALSE)
db <- data.frame(parent = c("A", "B", "B", "C", "D", "C"),
child = c("B", "C", "D", "E", "F", "F"),
stringsAsFactors = FALSE)
my_path <- function(a, df) {
b <- df$parent[df$child == a]
if (length(b) == 0) {
return(a)
} else {
return(c(my_path(b, df), a))
}
}
end_points <- da$child[is.na(match(da$child, da$parent))]
lapply(end_points, function(x) my_path(x, da)) # -> ok
end_points <- db$child[is.na(match(db$child, db$parent))]
lapply(end_points, function(x) my_path(x, db)) # -> not ok
Thx & kind regards
This is a job for igraph:
#the data
db <- data.frame(parent = c("A", "B", "B", "C", "D", "C"),
child = c("B", "C", "D", "E", "F", "F"),
stringsAsFactors = FALSE)
#create a graph
library(igraph)
g <- graph_from_data_frame(db)
#plot the graph
plot(g)
#find all vertices that have no ingoing resp. outgoing edges
starts <- V(g)[degree(g, mode = "in") == 0]
finals <- V(g)[degree(g, mode = "out") == 0]
#find paths, you need to loop if starts is longer than 1
res <- all_simple_paths(g, from = starts[[1]], to = finals)
#[[1]]
#+ 4/6 vertices, named, from 4b85bd1:
#[1] A B C E
#
#[[2]]
#+ 4/6 vertices, named, from 4b85bd1:
#[1] A B C F
#
#[[3]]
#+ 4/6 vertices, named, from 4b85bd1:
#[1] A B D F
#coerce to vectors
lapply(res, as_ids)
I implemented the FR test here and now I would like to test it by means of visualizing the resulting minimum spanning trees in R. The vertices and edges should be plotted in a coordinate system.
Moreover I want to set the color for every dot (depending on to which sample it belongs) and express a possible third dimension through the size of the dots.
This is what I have got so far:
library(ggplot2)
nodes <- data.frame(cbind(c("A", "A", "A", "B", "B", "B"), c(1,2,3,8,2,1), c(6,3,1,4,5,6)))
edges <- data.frame(cbind(c("A", "A", "A"), c("A", "B", "B"), c(1,3,2), c(6,1,5), c(2,8,1), c(3,4,6)))
p <- ggplot() +
geom_point(nodes, aes(x=nodes[,2], y=nodes[,3])) +
geom_line(edges)
p
I also think igraph would be best here...
nodes <- data.frame(a=c("A", "A", "A", "B", "B", "B"), b=c(1,2,3,8,2,1),
d=c(6,3,1,4,5,6))
#cbind made your nodes characters so i have removed it here
edges <- data.frame(a=c("A", "A", "A"), b=c("A", "B", "B"), d=c(1,3,2),
e=c(6,1,5), f=c(2,8,1), g=c(3,4,6))
Here is an example using your data as above, to produce the colours colouring with the coordinate layout system coords
library(igraph)
from <- c(rep(edges[,3],3),rep(edges[,4],2),edges[,5])
to <- c(edges[,4],edges[,5],edges[,6],edges[,5],edges[,6],edges[,6])
myedges <- data.frame(from,to)
actors <- data.frame(acts=c(1,2,3,4,5,6,8))
colouring <- sample(colours(), 7)
sizes <- sample(15,7)
coords<-cbind(x=runif(7,0,1),y=runif(7,0,1))
myg <- graph.data.frame(myedges, vertices=actors, directed=FALSE)
V(myg)$colouring <- colouring
V(myg)$sizes <- sizes
plot(myg,vertex.color=V(myg)$colouring,vertex.size=V(myg)$sizes,
layout=coords,edge.color="#55555533")
for plotting a spanning there are also many options, e.g.
d <- c(1,2,3)
E(myg)$colouring <- "#55555533"
E(myg, path=d)$colouring <- "red"
V(myg)[ d ]$colouring <- "red"
plot(myg,vertex.color=V(myg)$colouring,vertex.size=V(myg)$sizes
,edge.width=3,layout=coords,edge.color=E(myg)$colouring )
with axes:
plot(myg,vertex.color=V(myg)$colouring,vertex.size=V(myg)$sizes
,edge.width=3,layout=coords,edge.color=E(myg)$colouring, axes=TRUE )
and use rescale=FALSE to keep original axes scale