我想知道如何在ggplot上添加回归线方程和R^2。我的代码是:
library(ggplot2)
df <- data.frame(x = c(1:100))
df$y <- 2 + 3 * df$x + rnorm(100, sd = 40)
p <- ggplot(data = df, aes(x = x, y = y)) +
geom_smooth(method = "lm", se=FALSE, color="black", formula = y ~ x) +
geom_point()
p
任何帮助都将不胜感激。
当前回答
我修改了Ramnath的帖子，a)使其更通用，以便它接受线性模型作为参数，而不是数据帧;b)更适当地显示负号。
lm_eqn = function(m) {
l <- list(a = format(coef(m)[1], digits = 2),
b = format(abs(coef(m)[2]), digits = 2),
r2 = format(summary(m)$r.squared, digits = 3));
if (coef(m)[2] >= 0) {
eq <- substitute(italic(y) == a + b %.% italic(x)*","~~italic(r)^2~"="~r2,l)
} else {
eq <- substitute(italic(y) == a - b %.% italic(x)*","~~italic(r)^2~"="~r2,l)
}
as.character(as.expression(eq));
}
用法将更改为:
p1 = p + geom_text(aes(x = 25, y = 300, label = lm_eqn(lm(y ~ x, df))), parse = TRUE)
其他回答
我修改了stat_smooth和相关函数的源代码中的几行代码，以创建一个添加了拟合方程和R平方值的新函数。这也适用于小面图!
library(devtools)
source_gist("524eade46135f6348140")
df = data.frame(x = c(1:100))
df$y = 2 + 5 * df$x + rnorm(100, sd = 40)
df$class = rep(1:2,50)
ggplot(data = df, aes(x = x, y = y, label=y)) +
stat_smooth_func(geom="text",method="lm",hjust=0,parse=TRUE) +
geom_smooth(method="lm",se=FALSE) +
geom_point() + facet_wrap(~class)
我使用了@Ramnath回答中的代码来格式化方程。stat_smooth_func函数不是很健壮，但是使用它应该不难。
https://gist.github.com/kdauria/524eade46135f6348140。如果出现错误，请尝试更新ggplot2。
这里有一个解决方案
# GET EQUATION AND R-SQUARED AS STRING
# SOURCE: https://groups.google.com/forum/#!topic/ggplot2/1TgH-kG5XMA
lm_eqn <- function(df){
m <- lm(y ~ x, df);
eq <- substitute(italic(y) == a + b %.% italic(x)*","~~italic(r)^2~"="~r2,
list(a = format(unname(coef(m)[1]), digits = 2),
b = format(unname(coef(m)[2]), digits = 2),
r2 = format(summary(m)$r.squared, digits = 3)))
as.character(as.expression(eq));
}
p1 <- p + geom_text(x = 25, y = 300, label = lm_eqn(df), parse = TRUE)
编辑。我找到了这个代码的来源。下面是ggplot2谷歌组中原始帖子的链接
真的很喜欢@Ramnath的解决方案。为了允许使用自定义回归公式(而不是固定为y和x作为字面变量名)，并将p值添加到打印输出中(正如@Jerry T评论的那样)，下面是mod:
lm_eqn <- function(df, y, x){
formula = as.formula(sprintf('%s ~ %s', y, x))
m <- lm(formula, data=df);
# formating the values into a summary string to print out
# ~ give some space, but equal size and comma need to be quoted
eq <- substitute(italic(target) == a + b %.% italic(input)*","~~italic(r)^2~"="~r2*","~~p~"="~italic(pvalue),
list(target = y,
input = x,
a = format(as.vector(coef(m)[1]), digits = 2),
b = format(as.vector(coef(m)[2]), digits = 2),
r2 = format(summary(m)$r.squared, digits = 3),
# getting the pvalue is painful
pvalue = format(summary(m)$coefficients[2,'Pr(>|t|)'], digits=1)
)
)
as.character(as.expression(eq));
}
geom_point() +
ggrepel::geom_text_repel(label=rownames(mtcars)) +
geom_text(x=3,y=300,label=lm_eqn(mtcars, 'hp','wt'),color='red',parse=T) +
geom_smooth(method='lm')
不幸的是，这对facet_wrap或facet_grid不起作用。
类似于@zx8754和@kdauria的答案，只是使用了ggplot2和ggpubr。我更喜欢使用ggpubr，因为它不需要自定义函数，比如这个问题的顶部答案。
library(ggplot2)
library(ggpubr)
df <- data.frame(x = c(1:100))
df$y <- 2 + 3 * df$x + rnorm(100, sd = 40)
ggplot(data = df, aes(x = x, y = y)) +
stat_smooth(method = "lm", se=FALSE, color="black", formula = y ~ x) +
geom_point() +
stat_cor(aes(label = paste(..rr.label..)), # adds R^2 value
r.accuracy = 0.01,
label.x = 0, label.y = 375, size = 4) +
stat_regline_equation(aes(label = ..eq.label..), # adds equation to linear regression
label.x = 0, label.y = 400, size = 4)
也可以把p值加到上图中吗
ggplot(data = df, aes(x = x, y = y)) +
stat_smooth(method = "lm", se=FALSE, color="black", formula = y ~ x) +
geom_point() +
stat_cor(aes(label = paste(..rr.label.., ..p.label.., sep = "~`,`~")), # adds R^2 and p-value
r.accuracy = 0.01,
p.accuracy = 0.001,
label.x = 0, label.y = 375, size = 4) +
stat_regline_equation(aes(label = ..eq.label..), # adds equation to linear regression
label.x = 0, label.y = 400, size = 4)
当您有多个组时，也可以很好地使用facet_wrap()
df$group <- rep(1:2,50)
ggplot(data = df, aes(x = x, y = y)) +
stat_smooth(method = "lm", se=FALSE, color="black", formula = y ~ x) +
geom_point() +
stat_cor(aes(label = paste(..rr.label.., ..p.label.., sep = "~`,`~")),
r.accuracy = 0.01,
p.accuracy = 0.001,
label.x = 0, label.y = 375, size = 4) +
stat_regline_equation(aes(label = ..eq.label..),
label.x = 0, label.y = 400, size = 4) +
theme_bw() +
facet_wrap(~group)
另一种选择是创建一个自定义函数，使用dplyr和broom库生成方程:
get_formula <- function(model) {
broom::tidy(model)[, 1:2] %>%
mutate(sign = ifelse(sign(estimate) == 1, ' + ', ' - ')) %>% #coeff signs
mutate_if(is.numeric, ~ abs(round(., 2))) %>% #for improving formatting
mutate(a = ifelse(term == '(Intercept)', paste0('y ~ ', estimate), paste0(sign, estimate, ' * ', term))) %>%
summarise(formula = paste(a, collapse = '')) %>%
as.character
}
lm(y ~ x, data = df) -> model
get_formula(model)
#"y ~ 6.22 + 3.16 * x"
scales::percent(summary(model)$r.squared, accuracy = 0.01) -> r_squared
现在我们需要将文本添加到情节中:
p +
geom_text(x = 20, y = 300,
label = get_formula(model),
color = 'red') +
geom_text(x = 20, y = 285,
label = r_squared,
color = 'blue')
