如何从 R 中的绘图比例获得完整的中断向量?

How to get a complete vector of breaks from the scale of a plot in R?

我正在尝试使用此 and this 中的解决方案在图外添加字幕。

我想我设法得到了我想要的,但我正试图在数据发生变化时自动化代码。现在我的问题是我需要一种方法从图中的 y-axis 中获取所有 values/breaks 的向量。我不想更改 y-axis 并且我不想只获取范围(我发现这个 post 来获取范围,但我不想要那个)

另一方面,我发现了这个 post,但该解决方案不适用于 ggplot2 的新版本(我的是 3.3.5)。

这是我的例子:

library(ggplot2)
library(dplyr)

# DATA
val1 <- c(2.1490626,2.2035281,1.5927854,3.1399245,2.3967338,3.7915825,4.6691277,3.0727319,2.9230937,2.6239759,3.7664386,4.0160378,1.2500835,4.7648343,0.0000000,5.6740227,2.7510256,3.0709322,2.7998003,4.0809085,2.5178086,5.9713330,2.7779843,3.6724801,4.2648527,3.6841084,2.5597235,3.8477471,2.6587736,2.2742209,4.5862788,6.1989269,4.1167091,3.1769325,4.2404515,5.3627032,4.1576810,4.3387921,1.4024381,0.0000000,4.3999099,3.4381837,4.8269218,2.6308474,5.3481382,4.9549753,4.5389650,1.3002293,2.8648220,2.4015338,2.0962332,2.6774765,3.0581759,2.5786137,5.0539080,3.8545796,4.3429043,4.2233248,2.0434363,4.5980727)
val2 <- c(3.7691229,3.6478055,0.5435826,1.9665861,3.0802654,1.2248374,1.7311236,2.2492826,2.2365337,1.5726119,2.0147144,2.3550348,1.9527204,3.3689502,1.7847986,3.5901329,1.6833872,3.4240479,1.8372175,0.0000000,2.5701453,3.6551315,4.0327091,3.8781182)
val3 <- c(2.1490626,2.2035281,1.5927854,3.1399245,2.3967338,3.7915825,4.6691277,3.0727319,2.9230937,2.6239759,3.7664386,4.0160378,1.2500835,4.7648343,0.0000000,5.6740227,2.7510256,3.0709322,2.7998003,4.0809085,2.5178086,5.9713330,2.7779843,3.6724801,4.2648527,3.6841084,2.5597235,3.8477471,2.6587736,2.2742209,4.5862788,6.1989269,4.1167091,3.1769325,4.2404515,5.3627032,4.1576810,4.3387921,1.4024381,0.0000000,4.3999099,3.4381837,4.8269218,2.6308474,5.3481382,4.9549753,4.5389650,1.3002293,2.8648220,2.4015338,2.0962332,2.6774765,3.0581759,2.5786137,5.0539080,3.8545796,4.3429043,4.2233248,2.0434363,4.5980727)

df1 <- data.frame(value = val1)   
df2 <- data.frame(value = val2)   
df3 <- data.frame(value = val3)   

data <- bind_rows(lst(df1, df2, df3), .id = 'id')
data$Sex <- rep(c("Male", "Female"), times=72)
data$d <- "ff"
data <- as.data.frame(unclass(data), stringsAsFactors = TRUE)

# PLOT

p <- data %>% 
  ggplot(aes(value)) +
  geom_density(lwd = 1.2, colour="red", show.legend = FALSE) +
  geom_histogram(aes(y=..density.., fill = id), bins=10, col="black", alpha=0.2) +
  facet_grid(id ~ Sex ) +
  xlab("type_data") + 
  ylab("Density") +
  ggtitle("title") +
  guides(fill=guide_legend(title="legend_title")) +
  theme(strip.text.y = element_blank())

p

# ADD CAPTION

caption_df = data.frame(value = c(min(data$value), max(data$value)), id = c(rep(tail(levels(data$id), n=1), times=length(levels(data$Sex)))),
                        Sex = c(levels(data$Sex)))

p + coord_cartesian(clip = "off", 
                    ylim = layer_scales(p)$y$range$range, 
                    xlim = layer_scales(p)$x$range$range) +
  geom_text(data = caption_df,
            aes(y = -0.15, label = c(levels(data$Sex))))

添加标题之前:

标题后:

我的想法是避免每次更改数据时都必须设置 y 参数。想象一下 y-axis 是不同的(它是这样的:0.0000、0.0005、0.0010、0.0015)。在那种情况下,适当的 y 将是 -0.0005,因为“跳跃”是 0.0005,所以我只需要将其设为负数即可。

出于这个原因,我想知道是否有可能从 y-axis 中获取完整的值向量。 例如,如果我们想从以前的图像中获取 y-axis 的所有 values/breaks 将是:c(0.0, 0.2, 0.4, 0.6).

有谁知道我是否可以从绘图的 y-axis 中获取所有值?

提前致谢

您可以像这样从 p 对象获取 y 轴中断:

as.numeric(na.omit(layer_scales(p)$y$break_positions()))
#> [1] 0.0 0.2 0.4 0.6

但是,如果无论 y 轴刻度如何,您都希望标签位于面板下方的固定距离,最好使用整个面板范围的固定部分而不是中断:

yrange <- layer_scales(p)$y$range$range
ypos <- min(yrange) - 0.2 * diff(yrange)

p + coord_cartesian(clip = "off", 
                    ylim = layer_scales(p)$y$range$range, 
                    xlim = layer_scales(p)$x$range$range) +
  geom_text(data = caption_df,
            aes(y = ypos, label = c(levels(data$Sex))))

例如,假设您的 y 尺度是两倍大小:

p <- data %>% 
  ggplot(aes(value)) +
  geom_density(lwd = 1.2, colour="red", show.legend = FALSE) +
  geom_histogram(aes(y= 2 * ..density.., fill = id), bins=10, col="black", alpha=0.2) +
  facet_grid(id ~ Sex ) +
  xlab("type_data") + 
  ylab("Density") +
  ggtitle("title") +
  guides(fill=guide_legend(title="legend_title")) +
  theme(strip.text.y = element_blank())

那么完全相同的代码将为您提供完全相同的标签位置,而无需任何中断:

yrange <- layer_scales(p)$y$range$range
ypos <- min(yrange) - 0.2 * diff(yrange)

p + coord_cartesian(clip = "off", 
                    ylim = layer_scales(p)$y$range$range, 
                    xlim = layer_scales(p)$x$range$range) +
  geom_text(data = caption_df,
            aes(y = ypos, label = c(levels(data$Sex))))