Related
Similar questions have been asked before in other forms. Some can be found here and here. However, I cant seem to adapt them when using a facet wrap displaying multiple density plots.
I tried adapting the other examples, but failed... I also tried using the ggpattern package, but when there is a large amount of data, it takes several minutes on my machine to create a plot.
I am trying to create a gradient under the density curve... but with the gradient pointing down. Something like in the example image below:
Some example data to work with:
library(ggplot2)
set.seed(321)
# create data
varNames <- c("x1", "x2", "x3")
df <- data.frame(
var = sample(varNames, 100, replace = T),
val = runif(100)
)
# create plot
ggplot(df, aes(x = val)) +
geom_density(aes(colour = var, fill = var)) +
facet_wrap(~var) +
theme_bw() +
theme(legend.position = "none")
You can use teunbrand's function, but you will need to apply it to each facet. Here simply looping over it with lapply
library(tidyverse)
library(polyclip)
#> polyclip 1.10-0 built from Clipper C++ version 6.4.0
## This is teunbrands function copied without any change!!
## from https://stackoverflow.com/a/64695516/7941188
fade_polygon <- function(x, y, n = 100) {
poly <- data.frame(x = x, y = y)
# Create bounding-box edges
yseq <- seq(min(poly$y), max(poly$y), length.out = n)
xlim <- range(poly$x) + c(-1, 1)
# Pair y-edges
grad <- cbind(head(yseq, -1), tail(yseq, -1))
# Add vertical ID
grad <- cbind(grad, seq_len(nrow(grad)))
# Slice up the polygon
grad <- apply(grad, 1, function(range) {
# Create bounding box
bbox <- data.frame(x = c(xlim, rev(xlim)),
y = c(range[1], range[1:2], range[2]))
# Do actual slicing
slice <- polyclip::polyclip(poly, bbox)
# Format as data.frame
for (i in seq_along(slice)) {
slice[[i]] <- data.frame(
x = slice[[i]]$x,
y = slice[[i]]$y,
value = range[3],
id = c(1, rep(0, length(slice[[i]]$x) - 1))
)
}
slice <- do.call(rbind, slice)
})
# Combine slices
grad <- do.call(rbind, grad)
# Create IDs
grad$id <- cumsum(grad$id)
return(grad)
}
## now here starts the change, loop over your variables. I'm creating the data frame directly instead of keeping the density object
dens <- lapply(split(df, df$var), function(x) {
dens <- density(x$val)
data.frame(x = dens$x, y = dens$y)
}
)
## we need this one for the plot, but still need the list
dens_df <- bind_rows(dens, .id = "var")
grad <- bind_rows(lapply(dens, function(x) fade_polygon(x$x, x$y)), .id = "var")
ggplot(grad, aes(x, y)) +
geom_line(data = dens_df) +
geom_polygon(aes(alpha = value, group = id),
fill = "blue") +
facet_wrap(~var) +
scale_alpha_continuous(range = c(0, 1))
Created on 2021-12-05 by the reprex package (v2.0.1)
How can I include a legend inside one of the empty panels of the following matrix plot?
I have color coded different regression lines in the plots. I need a legend based on color.
I believe this answer comes closest to answer my question, yet I do not know how exactly to modify my code to get a legend based on color for different regression lines.
As for the background of the code, I am trying to study different robust and non-robust regression methods applied to multivariate data with and without outliers.
library(ggplot2)
library(GGally)
library(MASS)
library(robustbase)
## Just create data -- you can safely SKIP this function.
##
## Take in number of input variables (k), vector of ranges of k inputs
## ranges = c(min1, max1, min2, max2, ...) (must have 2k elements),
## parameters to create data (must be consistent with the number of
## input variables plus one), parameters are vector of linear
## coefficients (b) and random seed (seed), number of observations
## (n), vector of outliers (outliers)
##
## Return uncontaminated dataframe and contaminated dataframe
create_data <- function(k, ranges, b, seed = 6, n,
outliers = NULL) {
x <- NULL # x: matrix of input variables
for (i in 1:k) {
set.seed(seed^i)
## x <- cbind(x, runif(n, ranges[2*i-1], ranges[2*i]))
x <- cbind(x, rnorm(n, ranges[2*i-1], ranges[2*i]))
}
set.seed(seed - 2)
x_aug = cbind(rep(1, n), x)
y <- x_aug %*% b
y_mean = mean(y)
e <- rnorm(n, 0, 0.20 * y_mean) # rnorm x
y <- y + e
df <- data.frame(x = x, y = y)
len <- length(outliers)
n_rows <- len %/% (k+1)
if (!is.null(outliers)) {
outliers <- matrix(outliers, n_rows, k+1, byrow = TRUE)
df_contamin <- data.frame(x = rbind(x, outliers[,1:k]), y = c(y, outliers[,k+1]))
} else {
df_contamin <- df
}
dat <- list(df, df_contamin)
}
# plot different regression models (some are robust) for two types of
# data (one is contaminated with outliers)
plot_models <- function(data, mapping, data2) {
cb_palette <- c("#999999", "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7")
## 1.grey, 2.light orange, 3.light blue, 4.green, 5.yellow, 6.blue, 7.red, 8.purple
plt <- ggplot(data = data, mapping = mapping) +
geom_point() +
theme_bw() +
geom_smooth(method = lm, formula = y ~ x, data = data2, color = cb_palette[3], se = FALSE) +
geom_smooth(method = lm, formula = y ~ x, color = cb_palette[7], se = FALSE) +
geom_smooth(method = rlm, formula = y ~ x, color = cb_palette[4], se = FALSE) +
geom_smooth(method = lmrob, formula = y ~ x, color = cb_palette[1], se = FALSE)
plt
}
# trim the upper and right panels of plots
trim_gg <- function(gg) {
n <- gg$nrow
gg$nrow <- gg$ncol <- n-1
v <- 1:n^2
gg$plots <- gg$plots[v > n & v%%n != 0]
gg$xAxisLabels <- gg$xAxisLabels[-n]
gg$yAxisLabels <- gg$yAxisLabels[-1]
gg
}
dat <- create_data(3, c(1, 10, 1, 10, 1, 10), c(5, 8, 6, 7), 6, 20, c(30, 30, 50, 400))
df <- dat[[1]]
df_contamin <- dat[[2]]
## Note that plot_models is called here
g <- ggpairs(df_contamin, columns = 1:4, lower = list(continuous = wrap(plot_models, data2 = df)), diag = list(continuous = "blankDiag"), upper = list(continuous = "blank")) #, legend = lgd)
gr <- trim_gg(g)
print(gr)
Created on 2019-10-09 by the reprex package (v0.3.0)
Sorry for the long code, but most probably only the plot_models function and the line where ggpairs is called need to be modified.
I want to get a legend in the blank upper half of the plots. It may be done by somehow tweaking the plot_models function, setting the mapping in ggpairs to color using ggplot2::aes_string, and using getPlot and putPlot of the GGally package. But I can't wrap my head around how to do it exactly.
I have made a contour plot in R with the following code:
library(mvtnorm)
# Define the parameters for the multivariate normal distribution
mu = c(0,0)
sigma = matrix(c(1,0.2,0.2,3),nrow = 2)
# Make a grid in the x-y plane centered in mu, +/- 3 standard deviations
xygrid = expand.grid(x = seq(from = mu[1]-3*sigma[1,1], to = mu[1]+3*sigma[1,1], length.out = 100),
y = seq(from = mu[2]-3*sigma[2,2], to = mu[2]+3*sigma[2,2], length.out = 100))
# Use the mvtnorm library to calculate the multivariate normal density for each point in the grid
distribution = as.matrix(dmvnorm(x = xygrid, mean = mu, sigma = sigma))
# Plot contours
df = as.data.frame(cbind(xygrid, distribution))
myPlot = ggplot() + geom_contour(data = df,geom="polygon",aes( x = x, y = y, z = distribution))
myPlot
I want to illustrate cumulative probability by shading/colouring certain parts of the plot, for instance everything in the region {x<0, y<0} (or any other self defined region).
Is there any way of achieving this in R with ggplot?
So you are able to get the coordinates used to draw the circles in the plot using ggplot_build. Subsequently you could try to use these coordinates in combination with geom_polygon to shade a particular region. My best try:
library(dplyr)
data <- ggplot_build(myPlot)$data[[1]]
xCoor <- 0
yCoor <- 0
df <- data %>% filter(group == '-1-001', x <= xCoor, y <= yCoor) %>% select(x,y)
# Insert the [0,0] coordinate in the right place
index <- which.max(abs(diff(rank(df$y))))
df <- rbind( df[1:index,], data.frame(x=xCoor, y=yCoor), df[(index+1):nrow(df),] )
myPlot + geom_polygon(data = df, aes(x=x, y=y), fill = 'red', alpha = 0.5)
As you can see it's not perfect because the [x,0] and [0,y] coordinates are not included in the data, but it's a start.
i have this code and i create a loess surface of my dataframe.
library(gstat)
library(sp)
x<-c(0,55,105,165,270,65,130,155,155,225,250,295,
30,100,110,135,160,190,230,300,30,70,105,170,
210,245,300,0,85,175,300,15,60,90,90,140,210,
260,270,295,5,55,55,90,100,140,190,255,285,270)
y<-c(305,310,305,310,310,260,255,265,285,280,250,
260,210,240,225,225,225,230,210,215,160,190,
190,175,160,160,170,120,135,115,110,85,90,90,
55,55,90,85,50,50,25,30,5,35,15,0,40,20,5,150)
z<-c(870,793,755,690,800,800,730,728,710,780,804,
855,813,762,765,740,765,760,790,820,855,812,
773,812,827,805,840,890,820,873,875,873,865,
841,862,908,855,850,882,910,940,915,890,880,
870,880,960,890,860,830)
dati<-data.frame(x,y,z)
x.range <- as.numeric(c(min(x), max(x)))
y.range <- as.numeric(c(min(y), max(y)))
meuse.loess <- loess(z ~ x * y, dati, degree=2, span = 0.25,
normalize=F)
meuse.mar <- list(x = seq(from = x.range[1], to = x.range[2], by = 1), y = seq(from = y.range[1],
to = y.range[2], by = 1))
meuse.lo <- predict(meuse.loess, newdata=expand.grid(meuse.mar), se=TRUE)
Now I want to plot meuse.lo[[1]] with ggplot2 function... but i don't know how to convert meuse.lo[[1]] in a dataframe with x,y (grid's coordinates) and z (interpolated value) columns. Thanks.
Your problem here is that loess() returns a matrix if you use grid.expand() to generate the new data for loess().
This is mentioned in the help for ?loess.predict:
If newdata was the result of a call to expand.grid, the predictions (and s.e.'s if requested) will be an array of the appropriate dimensions.
Now, you can still use grid.expand() to compute the new data, but force this function to return a data frame and dropping the attributes.
From ?grid.expand:
KEEP.OUT.ATTRS: a logical indicating the "out.attrs" attribute (see below) should be computed and returned.
So, try this:
nd <- expand.grid(meuse.mar, KEEP.OUT.ATTRS = FALSE)
meuse.lo <- predict(meuse.loess, newdata=nd, se=TRUE)
# Add the fitted data to the `nd` object
nd$z <- meuse.lo$fit
library(ggplot2)
ggplot(nd, aes(x, y, col = z)) +
geom_tile() +
coord_fixed()
The result:
ggplot2 is probably not the best choice for 3d graphs. However here is an easy solution with rgl
library(rgl)
plot3d(x, y, z, type="s", size=0.75, lit=FALSE,col="red")
surface3d(meuse.mar[[1]], meuse.mar[[2]], meuse.lo[[1]],
alpha=0.4, front="lines", back="lines")
I have data in the following form:
x <- seq(from = 0.01,to = 1, by = 0.01)
y <- seq(from = 0.01,to = 1, by = 0.01)
xAxis <- x/(1+x*y)
yAxis <- x/(1+x*y)
z <- (0.9-xAxis)^2 + (0.5-yAxis)^2
df <- expand.grid(x,y)
xAxis <- df$Var1/(1+df$Var1*df$Var2)
yAxis <- df$Var2/(1+df$Var1*df$Var2)
df$x <- xAxis
df$y <- yAxis
df$z <- z
I would like to plot te (x,y,z) data as a surface and contour plots, possibily interpolating data to obtain as smooth a figure as possible.
Searching I reached the akima package which does the interpolation:
im <- with(df,interp(x,y,z))
I am having trouble plotting the data with this output. Ideally I would like to use ggplot2 since I want to add stuff to the original plot.
Thanks!
I'm a bit puzzled as to what you are looking for, but how about something like this?
im <- with(df, akima::interp(x, y, z, nx = 1000, ny = 1000))
df2 <- data.frame(expand.grid(x = im$x, y = im$y), z = c(im$z))
ggplot(df2, aes(x, y, fill = z)) +
geom_raster() +
viridis::scale_fill_viridis()
For contour plots, I use the "rgl" package. This allows real-time manipulation of the plot in order to have the best view.
library("rgl")
x <- seq(from = 0.01,to = 1, by = 0.01)
y <- seq(from = 0.01,to = 1, by = 0.01)
#z <- (0.9-xAxis)^2 + (0.5-yAxis)^2
df <- expand.grid(x,y)
xAxis <- df$Var1/(1+df$Var1*df$Var2)
yAxis <- df$Var2/(1+df$Var1*df$Var2)
df$z <- (0.9-xAxis)^2 + (0.5-yAxis)^2
surface3d(x=x, y=y, z=df$z, col="blue", back="lines")
title3d(xlab="x", zlab="z", ylab="y")
axes3d(tick="FALSE")
The rgl package is comparable to the ggplot2 package to customize the final plot. The 0.01 grid spacing is more than close enough for this type of smooth surface.