Related
I first make a plot
df <- data.frame(x = c(1:40, rep(1:20, 3), 15:40))
p <- ggplot(df, aes(x=x, y = x)) +
stat_density2d(aes(fill='red',alpha=..level..),geom='polygon', show.legend = F)
Then I want to change the geom_density values and use these in another plot.
# build plot
q <- ggplot_build(p)
# Change density
dens <- q$data[[1]]
dens$y <- dens$y - dens$x
Build the other plot using the changed densities, something like this:
# Built another plot
ggplot(df, aes(x=x, y =1)) +
geom_point(alpha = 0.3) +
geom_density2d(dens)
This does not work however is there a way of doing this?
EDIT: doing it when there are multiple groups:
df <- data.frame(x = c(1:40, rep(1:20, 3), 15:40), group = c(rep('A',40), rep('B',60), rep('C',26)))
p <- ggplot(df, aes(x=x, y = x)) +
stat_density2d(aes(fill=group,alpha=..level..),geom='polygon', show.legend = F)
q <- ggplot_build(p)
dens <- q$data[[1]]
dens$y <- dens$y - dens$x
ggplot(df, aes(x=x, y =1)) +
geom_point(aes(col = group), alpha = 0.3) +
geom_polygon(data = dens, aes(x, y, fill = fill, group = piece, alpha = alpha)) +
scale_alpha_identity() +
guides(fill = F, alpha = F)
Results when applied to my own dataset
Although this is exactly what I'm looking for the fill colors seem not to correspond to the initial colors (linked to A, B and C):
Like this? It is possible to plot a transformation of the shapes plotted by geom_density. But that's not quite the same as manipulating the underlying density...
ggplot(df, aes(x=x, y =1)) +
geom_point(alpha = 0.3) +
geom_polygon(data = dens, aes(x, y, fill = fill, group = piece, alpha = alpha)) +
scale_alpha_identity() +
guides(fill = F, alpha = F)
Edit - OP now has multiple groups. We can plot those with the code below, which produces an artistic plot of questionably utility. It does what you propose, but I would suggest it would be more fruitful to transform the underlying data and summarize that, if you are looking for representative output.
ggplot(df, aes(x=x, y =1)) +
geom_point(aes(col = group), alpha = 0.3) +
geom_polygon(data = dens, aes(x, y, fill = group, group = piece, alpha = alpha)) +
scale_alpha_identity() +
guides(fill = F, alpha = F) +
theme_minimal()
Hi have some code to simulate a Gaussian process. Please can someone help me add a legend to my plots on the top right corner. I want to state the different parameter values for each of the line styles/colours, e.g. l=1, l=5, l=10. Thanks.
# simulate a gaussian process
simGP = function(K){
n = nrow(K)
U = chol(K) # cholesky decomposition
z = rnorm(n)
c(t(U) %*% z)
}
# choose points to simulate the covariance.
x = seq(-1, 1, length.out = 500)
# Exponential kernel ------------------------------------------------------
kernel_exp = function(x, l = 1) {
d = as.matrix(dist(x))/l
K = exp(-d)
diag(K) = diag(K) + 1e-8
K
}
{y1 = simGP(kernel_exp(x,l=10))
y2 = simGP(kernel_exp(x,l=1))
y3 = simGP(kernel_exp(x,l=0.1))
data1 <- as.data.frame(x,y1)
data2 <- as.data.frame(x,y2)
data3 <- as.data.frame(x,y3)
df=data.frame(data1,data2,data3)
ggplot() +
geom_line(data=data1, aes(x=x, y=y1), color="green4", linetype = "twodash", size=0.5) +
geom_line(data=data2, aes(x=x, y=y2), color='red', linetype="longdash", size=0.5) +
geom_line(data=data3, aes(x=x, y=y3), color='blue') +
scale_color_manual(values = colors) +
theme_classic() +
labs(x='input, x',
y='output, f(x)')+
theme(axis.text=element_text(size=16),
axis.title=element_text(size=14))}
You can do it using a dataframe variable to group the linetype and colour.
If you want to specify color and linetype, use scale_color_discrete and scale_linetype_discrete
y1 = simGP(kernel_exp(x,l=10))
y2 = simGP(kernel_exp(x,l=1))
y3 = simGP(kernel_exp(x,l=0.1))
data1 <- data.frame(x, y = y1, value = "10")
data2 <- data.frame(x, y = y2, value = "1")
data3 <- data.frame(x, y = y3, value = "0.1")
df=rbind(data1,data2,data3)
ggplot(data = df, aes(x=x, y=y, color = value, linetype = value, group = value)) +
geom_line(size=0.5) +
theme_classic() +
labs(x='input, x',
y='output, f(x)')+
theme(axis.text=element_text(size=16),
axis.title=element_text(size=14))
I would like to change the spread display of the legend bar as on the jpeg below. In example 1, I'd like to display the "100" threshold value in the middle of the legend bar. In example 2, I'd like to display the mean value (white colour) in the middle of the legend bar. I suspect both would require similar line of code. Could someone very kindly help me with this?
#library
library(raster)
library(ggplot2)
#sample raster
r <- raster(ncol=36, nrow=18)
r[] <- (-ncell(r)/2+1):(ncell(r)/2)
r[1,] <- 5000
plot(r)
var_df <- as.data.frame(rasterToPoints(r))
### example 1
p <- ggplot()
p <- p + geom_raster(data = var_df , aes(x = x, y = y, fill = layer))
p <- p + coord_equal()
p <- p + scale_fill_gradientn(
colours=c("red", "yellow", "skyblue", "darkblue"),
values = rescale(c(min(var_df$layer),
100,
100.01,
max(var_df$layer))))
p
### example 2
meanval <- mean(var_df$layer)
p <- ggplot()
p <- p + geom_raster(data = var_df , aes(x = x, y = y, fill = layer))
p <- p + coord_equal()
p <- p + scale_fill_gradient2(low = muted("red"), mid = "white",
high = muted("blue"), midpoint = meanval)
p
I've plotted a confusion matrix (predicting 5 outcomes) in R using ggplot and scales for geom_text labeling.
The way geom_text(aes(label = percent(Freq/sum(Freq))) is written in code, it's showing Frequency of each box divided by sum of all observations, but what I want to do is get Frequency of each box divided by sum Frequency for each Reference.
In other words, instead of A,A = 15.8%,
it should be A,A = 15.8%/(0.0%+0.0%+0.0%+0.0%+15.8%%) = 100.0%
library(ggplot2)
library(scales)
valid_actual <- as.factor(c("A","B","B","C","C","C","E","E","D","D","A","A","A","E","E","D","D","C","B"))
valid_pred <- as.factor(c("A","B","C","C","E","C","E","E","D","B","A","B","A","E","D","E","D","C","B"))
cfm <- confusionMatrix(valid_actual, valid_pred)
ggplotConfusionMatrix <- function(m){
mytitle <- paste("Accuracy", percent_format()(m$overall[1]),
"Kappa", percent_format()(m$overall[2]))
p <-
ggplot(data = as.data.frame(m$table) ,
aes(x = Reference, y = Prediction)) +
geom_tile(aes(fill = log(Freq)), colour = "white") +
scale_fill_gradient(low = "white", high = "green") +
geom_text(aes(x = Reference, y = Prediction, label = percent(Freq/sum(Freq)))) +
theme(legend.position = "none") +
ggtitle(mytitle)
return(p)
}
ggplotConfusionMatrix(cfm)
The problem is that, as far as I know, ggplot is not able to do group calculation. See this recent post for similar question.
To solve your problem you should take advantage of the dplyrpackage.
This should work
library(ggplot2)
library(scales)
library(caret)
library(dplyr)
valid_actual <- as.factor(c("A","B","B","C","C","C","E","E","D","D","A","A","A","E","E","D","D","C","B"))
valid_pred <- as.factor(c("A","B","C","C","E","C","E","E","D","B","A","B","A","E","D","E","D","C","B"))
cfm <- confusionMatrix(valid_actual, valid_pred)
ggplotConfusionMatrix <- function(m){
mytitle <- paste("Accuracy", percent_format()(m$overall[1]),
"Kappa", percent_format()(m$overall[2]))
data_c <- mutate(group_by(as.data.frame(m$table), Reference ), percentage =
percent(Freq/sum(Freq)))
p <-
ggplot(data = data_c,
aes(x = Reference, y = Prediction)) +
geom_tile(aes(fill = log(Freq)), colour = "white") +
scale_fill_gradient(low = "white", high = "green") +
geom_text(aes(x = Reference, y = Prediction, label = percentage)) +
theme(legend.position = "none") +
ggtitle(mytitle)
return(p)
}
ggplotConfusionMatrix(cfm)
And the result:
I'm plotting 11 curves and the program bellow works well. BUT I'm not able two change the wild colors to plot 11 black curves:
library(ggplot2)
#library(latex2exp)
library(reshape)
fn <- "img/plot.eps"
fct1 <- function(x0 ){
return(1/sin(x0)+1/tan(x0))
}
fct2 <- function(beta, t ){
return(2*atan(exp(t)/beta))
}
t<-seq(from=0,to=10,by=0.01)
s1<-cbind(t, fct2(fct1(-pi+0.0001),t),
fct2(fct1(-1.5),t),
fct2(fct1(-0.5),t),
fct2(fct1(-0.05),t),
fct2(fct1(-0.01),t),
fct2(fct1(0),t),
fct2(fct1(0.01),t),
fct2(fct1(0.05),t),
fct2(fct1(0.5),t),
fct2(fct1(1.5),t),
fct2(fct1(pi),t))
colnames(s1)<-c("time","y1","y2","y3","y4","y5","y6","y7","y8","y9","y10","y11")
s2 <- melt(as.data.frame(s1), id = "time")
q <- ggplot(s2, aes(x = time, y = value, color = variable))
q <- q + geom_line() + ylab("y") + xlab("t")+ ylab("x(t)")+
theme_bw(base_size = 7) + guides(colour = FALSE)
ggsave(file = fn, width = 2, height = 1)
q
EDIT Now the code should be reproducible
You need to map the variable to the grouping, and it will produce black lines by default.
q <- ggplot() +
geom_line(data = s2, aes(x = time, y = value,
group = variable)) +
xlab("t")+ ylab("x(t)") +
theme_bw(base_size = 7) + guides(colour = FALSE)
q
To be perfectly clear, it is possible to map the color to the variable, which can produce black lines, but not without changing the legend. Here is how you would amend the colors after the fact, if you wanted to, having already mapped the color to the variable.
q <- ggplot() +
geom_line(data = s2, aes(x = time, y = value,
color = variable)) +
xlab("t")+ ylab("x(t)") +
theme_bw(base_size = 7) + guides(colour = FALSE) +
scale_color_manual(values = rep("black",11))
q