Here is the t-SNE code using IRIS data:
library(Rtsne)
iris_unique <- unique(iris) # Remove duplicates
iris_matrix <- as.matrix(iris_unique[,1:4])
set.seed(42) # Set a seed if you want reproducible results
tsne_out <- Rtsne(iris_matrix) # Run TSNE
# Show the objects in the 2D tsne representation
plot(tsne_out$Y,col=iris_unique$Species)
Which produces this plot:
How can I use GGPLOT to make that figure?
I think the easiest/cleanest ggplot way would be to store all the info you need in a data.frame and then plot it. From your code pasted above, this should work:
library(ggplot2)
tsne_plot <- data.frame(x = tsne_out$Y[,1], y = tsne_out$Y[,2], col = iris_unique$Species)
ggplot(tsne_plot) + geom_point(aes(x=x, y=y, color=col))
My plot using the regular plot function is:
plot(tsne_out$Y,col=iris_unique$Species)
Related
I'm fitting a dose-response curve to many data sets that I want to plot to a single file.
Here's how one data set looks like:
df <- data.frame(dose=c(10,0.625,2.5,0.156,0.0391,0.00244,0.00977,0.00061,10,0.625,2.5,0.156,0.0391,0.00244,0.00977,0.00061,10,0.625,2.5,0.156,0.0391,0.00244,0.00977,0.00061),viability=c(6.12,105,57.9,81.9,86.5,98.3,96.4,81.8,27.3,85.2,80.8,92,82.5,110,90.2,76.6,11.9,89,35.4,79,95.8,117,82.1,95.1),stringsAsFactors=F)
Here's the dose-response fit:
library(drc)
fit <- drm(viability~dose,data=df,fct=LL.4(names=c("Slope","Lower Limit","Upper Limit","ED50")))
Now I'm predicting values in order to plot the curve:
pred.df <- expand.grid(dose=exp(seq(log(max(df$dose)),log(min(df$dose)),length=100)))
pred <- predict(fit,newdata=pred.df,interval="confidence")
pred.df$viability <- pred[,1]
pred.df$viability.low <- pred[,2]
pred.df$viability.high <- pred[,3]
And this is how a single plot looks like:
library(ggplot2)
p <- ggplot(df,aes(x=dose,y=viability))+geom_point()+geom_ribbon(data=pred.df,aes(x=dose,y=viability,ymin=viability.low,ymax=viability.high),alpha=0.2)+labs(y="viability")+
geom_line(data=pred.df,aes(x=dose,y=viability))+coord_trans(x="log")+theme_bw()+scale_x_continuous(name="dose",breaks=sort(unique(df$dose)),labels=format(signif(sort(unique(df$dose)),3),scientific=T))+ggtitle(label="all doses")
adding a few parameter estimates to the plot:
params <- signif(summary(fit)$coefficient[-1,1],3)
names(params) <- c("lower","upper","ed50")
p <- p + annotate("text",size=3,hjust=0,x=2.4e-3,y=5,label=paste(sapply(1:length(params),function(p) paste0(names(params)[p],"=",params[p])),collapse="\n"),colour="black")
Which gives:
Now suppose I have 20 of these that I want to cram in a single figure file.
I thought that a reasonable solution would be to use grid.arrange:
As an example I'll loop 20 times on this example data set:
plot.list <- vector(mode="list",20)
for(i in 1:20){
plot.list[[i]] <- ggplot(df,aes(x=dose,y=viability))+geom_point()+geom_ribbon(data=pred.df,aes(x=dose,y=viability,ymin=viability.low,ymax=viability.high),alpha=0.2)+labs(y="viability")+
geom_line(data=pred.df,aes(x=dose,y=viability))+coord_trans(x="log")+theme_bw()+scale_x_continuous(name="dose",breaks=sort(unique(df$dose)),labels=format(signif(sort(unique(df$dose)),3),scientific=T))+ggtitle(label="all doses")+
annotate("text",size=3,hjust=0,x=2.4e-3,y=5,label=paste(sapply(1:length(params),function(p) paste0(names(params)[p],"=",params[p])),collapse="\n"),colour="black")
}
And then plot using:
library(grid)
library(gridExtra)
grid.arrange(grobs=plot.list,ncol=3,nrow=ceiling(length(plot.list)/3))
Which is obviously poorly scaled. So my question is how to create this figure with better scaling - meaning that all objects are compressed proportionally in way that produces a figure that is still visually interperable.
You should set the device size so that the plots remain readable, e.g.
pl = replicate(11, qplot(1,1), simplify = FALSE)
g = arrangeGrob(grobs = pl, ncol=3)
ggsave("plots.pdf", g, width=15, height=20)
I want to create a correlation matrix plot, i.e. a plot where each variable is plotted in a scatterplot against each other variable like with pairs() or splom(). I want to do this with ggplot2. See here for examples. The link mentions some code someone wrote for doing this in ggplot2, however, it is outdated and no longer works (even after you swap out the deprecated parts).
One could do this with a loop in a loop and then multiplot(), but there must be a better way. I tried melting the dataset to long, and copying the value and variable variables and then using facets. This almost gives you something correct.
d = data.frame(x1=rnorm(100),
x2=rnorm(100),
x3=rnorm(100),
x4=rnorm(100),
x5=rnorm(100))
library(reshape2)
d = melt(d)
d$value2 = d$value
d$variable2 = d$variable
library(ggplot2)
ggplot(data=d, aes(x=value, y=value2)) +
geom_point() +
facet_grid(variable ~ variable2)
This gets the general structure right, but only works for the plotting each variable against itself. Is there some more clever way of doing this without resorting to 2 loops?
library(GGally)
set.seed(42)
d = data.frame(x1=rnorm(100),
x2=rnorm(100),
x3=rnorm(100),
x4=rnorm(100),
x5=rnorm(100))
# estimated density in diagonal
ggpairs(d)
# blank
ggpairs(d, diag = list("continuous"="blank")
Using PerformanceAnalytics library :
library("PerformanceAnalytics")
chart.Correlation(df, histogram = T, pch= 19)
The whole dataset describes a module (or cluster if you prefer).
In order to reproduce the example, the dataset is available at:
https://www.dropbox.com/s/y1905suwnlib510/example_dataset.txt?dl=0
(54kb file)
You can read as:
test_example <- read.table(file='example_dataset.txt')
What I would like to have in my plot is this
On the plot, the x-axis is my Timepoints column, and the y-axis are the columns on the dataset, except for the last 3 columns. Then I used facet_wrap() to group by the ConditionID column.
This is exactly what I want, but the way I achieved this was with the following code:
plot <- ggplot(dataset, aes(x=Timepoints))
plot <- plot + geom_line(aes(y=dataset[,1],colour = dataset$InModule))
plot <- plot + geom_line(aes(y=dataset[,2],colour = dataset$InModule))
plot <- plot + geom_line(aes(y=dataset[,3],colour = dataset$InModule))
plot <- plot + geom_line(aes(y=dataset[,4],colour = dataset$InModule))
plot <- plot + geom_line(aes(y=dataset[,5],colour = dataset$InModule))
plot <- plot + geom_line(aes(y=dataset[,6],colour = dataset$InModule))
plot <- plot + geom_line(aes(y=dataset[,7],colour = dataset$InModule))
plot <- plot + geom_line(aes(y=dataset[,8],colour = dataset$InModule))
...
As you can see it is not very automated. I thought about putting in a loop, like
columns <- dim(dataset)[2] - 3
for (i in seq(1:columns))
{
plot <- plot + geom_line(aes(y=dataset[,i],colour = dataset$InModule))
}
(plot <- plot + facet_wrap( ~ ConditionID, ncol=6) )
That doesn't work.
I found this topic
Use for loop to plot multiple lines in single plot with ggplot2 which corresponds to my problem.
I tried the solution given with the melt() function.
The problem is that when I use melt on my dataset, I lose information of the Timepoints column to plot as my x-axis. This is how I did:
data_melted <- dataset
as.character(data_melted$Timepoints)
dataset_melted <- melt(data_melted)
I tried using aggregate
aggdata <-aggregate(dataset, by=list(dataset$ConditionID), FUN=length)
Now with aggdata at least I have the information on how many Timepoints for each ConditionID I have, but I don't know how to proceed from here and combine this on ggplot.
Can anyone suggest me an approach.
I know I could use the ugly solution of creating new datasets on a loop with rbind(also given in that link), but I don't wanna do that, as it sounds really inefficient. I want to learn the right way.
Thanks
You have to specify id.vars in your call to melt.data.frame to keep all information you need. In the call to ggplot you then need to specify the correct grouping variable to get the same result as before. Here's a possible solution:
melted <- melt(dataset, id.vars=c("Timepoints", "InModule", "ConditionID"))
p <- ggplot(melted, aes(Timepoints, value, color = InModule)) +
geom_line(aes(group=paste0(variable, InModule)))
p
How would one use the smooth.spline() method in a ggplot2 scatterplot?
If my data is in the data frame called data, with two columns, x and y.
The smooth.spline would be sm <- smooth.spline(data$x, data$y). I believe I should use geom_line(), with sm$x and sm$y as the xy coordinates. However, how would one plot a scatterplot and a lineplot on the same graph that are completely unrelated? I suspect it has something to do with the aes() but I am getting a little confused.
You can use different data(frames) in different geoms and call the relevant variables using aes or you could combine the relevant variables from the output of smooth.spline
# example data
set.seed(1)
dat <- data.frame(x = rnorm(20, 10,2))
dat$y <- dat$x^2 - 20*dat$x + rnorm(20,10,2)
# spline
s <- smooth.spline(dat)
# plot - combine the original x & y and the fitted values returned by
# smooth.spline into a data.frame
library(ggplot2)
ggplot(data.frame(x=s$data$x, y=s$data$y, xfit=s$x, yfit=s$y)) +
geom_point(aes(x,y)) + geom_line(aes(xfit, yfit))
# or you could use geom_smooth
ggplot(dat, aes(x , y)) + geom_point() + geom_smooth()
What I really want to do is plot a histogram, with the y-axis on a log-scale. Obviously this i a problem with the ggplot2 geom_histogram, since the bottom os the bar is at zero, and the log of that gives you trouble.
My workaround is to use the freqpoly geom, and that more-or less does the job. The following code works just fine:
ggplot(zcoorddist) +
geom_freqpoly(aes(x=zcoord,y=..density..),binwidth = 0.001) +
scale_y_continuous(trans = 'log10')
The issue is that at the edges of my data, I get a couple of garish vertical lines that really thro you off visually when combining a bunch of these freqpoly curves in one plot. What I'd like to be able to do is use points at every vertex of the freqpoly curve, and no lines connecting them. Is there a way to to this easily?
The easiest way to get the desired plot is to just recast your data. Then you can use geom_point. Since you don't provide an example, I used the standard example for geom_histogram to show this:
# load packages
require(ggplot2)
require(reshape)
# get data
data(movies)
movies <- movies[, c("title", "rating")]
# here's the equivalent of your plot
ggplot(movies) + geom_freqpoly(aes(x=rating, y=..density..), binwidth=.001) +
scale_y_continuous(trans = 'log10')
# recast the data
df1 <- recast(movies, value~., measure.var="rating")
names(df1) <- c("rating", "number")
# alternative way to recast data
df2 <- as.data.frame(table(movies$rating))
names(df2) <- c("rating", "number")
df2$rating <- as.numeric(as.character(df$rating))
# plot
p <- ggplot(df1, aes(x=rating)) + scale_y_continuous(trans="log10", name="density")
# with lines
p + geom_linerange(aes(ymax=number, ymin=.9))
# only points
p + geom_point(aes(y=number))