Adding regression equation and r2 to plot in ggplot2 with R

Question

I have a series of csv files that I am plotting a 3rd order polynomial regression per csv file.

I set the directory and all .csv files within that directory:

setwd("tester/results")
filenames = dir(pattern="*.csv")

I then iterate through the files and plot volume against time with a 3rd order polynomial lm.

for (i in 1:length(filenames)) { tmp <-read.csv(filenames[i]); print(ggplot(aes(x = Volume, y = time), data = tmp) + geom_point(aes(color = id)) + geom_smooth(aes(color = id), method= "lm", se = F, formula=y ~ poly(x, 3, raw=TRUE)))}

Thus, giving

I now wish to add the formula of the lm function I have plotted on the graph with the r2 value.

From this SO question, I tried:

for (i in 1:length(filenames)) { tmp <-read.csv(filenames[i]); print(ggplot(aes(x = Volume, y = time_normalised), data = tmp) + geom_point(aes(color = id)) + geom_smooth(aes(color = id), method= "lm", se = F, formula=y ~ poly(x, 3, raw=TRUE)) + stat_smooth_func(geom="text",method="lm",formula=y~poly(x,3,raw=TRUE),hjust=0,parse=TRUE))}

However, as you can see from the output, the label is not a 3rd order polynomial

Function `"stat_smooth_func"` is not in ggplot2 library but should be added from gist or coppied from link provided in @kdauria answer in SO question you provided. — Didzis Elferts, Apr 22 '16 at 08:07
Right! However, an issue remains. The label doesn't appear to be correct — LearningSlowly, Apr 22 '16 at 08:15
Function `"stat_smooth_func"` is made just for first oder regression and not for third. You have to modify this code to work with this funcion. — Didzis Elferts, Apr 22 '16 at 08:20

score 3 · Accepted Answer · edited Apr 26 '16 at 12:19

You can use function stat_poly_eq() from the package ggpmisc to add equation of third order polynomial to your plot.

This example is taken from the vignette of this package.

set.seed(4321)
x <- 1:100
y <- (x + x^2 + x^3) + rnorm(length(x), mean = 0, sd = mean(x^3) / 4)
my.data <- data.frame(x, 
                      y, 
                      group = c("A", "B"), 
                      y2 = y * c(0.5,2),
                      block = c("a", "a", "b", "b"))

formula <- y ~ poly(x, 3, raw = TRUE)
ggplot(my.data, aes(x, y)) +
      geom_point() +
      geom_smooth(method = "lm", formula = formula) +
      stat_poly_eq(aes(label =  paste(..eq.label.., ..adj.rr.label.., sep = "~~~~")),
                   formula = formula, parse = TRUE)

Adding regression equation and r2 to plot in ggplot2 with R

1 Answers1