Question

我想使用ggplot2绘制两个每周平均时间序列（来自代表不同乐器的两个不同数据帧）。这应该很简单，但我必须遗漏一些东西。我查看了以下帖子：

using-both-geom-point-and-geom-line-for-multiple-x-in-ggplot2 object-not-found-error-with-ggplot2-when-adding-shape-aesthetic

和好老cookbook for r但我在错误后一直遇到错误。我正在使用的数据框来自使用ddply进行汇总，它们在这里是为了重现性：

mean_TS_Cond_use<-
structure(list(week_DOY = c(207, 207, 230, 230, 237, 237, 237, 
239, 239, 239, 246, 246, 246, 253, 253, 253, 260, 267, 267, 281, 
281, 281, 288, 288, 288, 295, 295, 316, 316, 323, 323, 330, 330, 
330, 337, 337), Leaf.age.ordered = structure(c(1L, 4L, 1L, 3L, 
1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 3L, 2L, 3L, 1L, 
2L, 3L, 1L, 2L, 3L, 2L, 3L, 2L, 3L, 2L, 3L, 1L, 2L, 3L, 2L, 3L
), .Label = c("young", "mature", "old", "old1"), class = "factor"), 
    week_N_Cond = c(7L, 2L, 7L, 2L, 4L, 6L, 3L, 6L, 2L, 10L, 
    3L, 6L, 7L, 2L, 5L, 4L, 1L, 3L, 1L, 3L, 3L, 6L, 4L, 11L, 
    2L, 5L, 4L, 4L, 6L, 2L, 3L, 6L, 20L, 7L, 6L, 2L), week_mean_Cond = c(46.675, 
    28, 38.125, 59.1, 23.5333333333333, 101.5, 58.1333333333333, 
    16.8, 35.5, 62.4, 31.4, 144, 49.3, 49.7, 55.6333333333333, 
    57.65, 7.3, 4.74, NaN, 69.4, 112.3, 80.35, 47.85, 21.6416666666667, 
    6.41, 70.3333333333333, 59.1, 41.6, 24.9666666666667, 64.3, 
    NaN, 39.1, 95.8909090909091, 44.7333333333333, 20.9733333333333, 
    40), week_sd_Cond = c(17.6941374471885, NA, 24.1760728820874, 
    17.1119841047145, 18.1934970067146, 86.4448379025607, 43.4743985965687, 
    NA, NA, NA, NA, 1.4142135623731, 9.61665222413704, NA, 30.8034630087809, 
    28.0721392131059, NA, 1.40007142674936, NA, 31.5912962697006, 
    23.0774781984514, 20.545478010177, 5.30330085889911, 13.7910353732657, 
    NA, 9.97513575513302, 1.69705627484771, 5.23259018078045, 
    6.02522475376092, NA, NA, 9.33380951166242, 59.2789584008602, 
    7.7693843599949, 20.8945957925329, 33.799704140717)), .Names = c("week_DOY", 
"Leaf.age.ordered", "week_N_Cond", "week_mean_Cond", "week_sd_Cond"
), row.names = c(NA, -36L), class = "data.frame")

mean_TS_Gs_use<-structure(list(week_DOY = c(232, 232, 239, 239, 246, 246, 246, 
267, 267, 267, 281, 316, 316, 316, 323, 323, 330, 330, 330, 337, 
337), Leaf.age.ordered = structure(c(2L, 3L, 1L, 3L, 1L, 2L, 
3L, 1L, 2L, 3L, 3L, 1L, 2L, 3L, 2L, 3L, 1L, 2L, 3L, 2L, 3L), .Label = c("young", 
"mature", "old"), class = "factor"), week_N_GS = c(56L, 49L, 
30L, 30L, 55L, 21L, 54L, 7L, 21L, 19L, 6L, 3L, 8L, 4L, 30L, 15L, 
36L, 99L, 70L, 52L, 23L), week_mean_GS = c(73.2017857142857, 
170.422448979592, 88.1133333333333, 66.4866666666667, 125.794545454545, 
103.247619047619, 70.0981481481481, 154.414285714286, 258.757142857143, 
114.073684210526, 254.15, 167.5, 175.8125, 136.25, 87.9866666666667, 
46.46, 112.455555555556, 111.778787878788, 88.4242857142857, 
169.346153846154, 160.895652173913), week_sd_GS = c(27.4044421818562, 
112.736252423718, 30.7610561377961, 26.4143473727146, 98.1052296302704, 
59.4644819959581, 43.7727299045695, 77.6537062556456, 84.1063943551771, 
67.674177268777, 79.52214157076, 47.4155037935906, 45.4656365527071, 
9.46449505608548, 58.2085118395473, 17.0402800111132, 33.7885563420893, 
97.9779549056591, 76.6287028293478, 130.657736481864, 93.5849467220259
)), .Names = c("week_DOY", "Leaf.age.ordered", "week_N_GS", "week_mean_GS", 
"week_sd_GS"), row.names = c(NA, -21L), class = "data.frame")

第一个数据帧的geom_point和geom_errorbar的所有内容都很常见：

mGts<-ggplot(data=mean_TS_Cond_use, aes(x = week_DOY, y = week_mean_Cond, color=Leaf.age.ordered, ymax = week_mean_Cond + week_sd_Cond, ymin=week_mean_Cond - week_sd_Cond))+
  geom_point(size=4) +
  geom_errorbar() 
mGts

我尝试在新数据框中添加新的时间序列，如下所示：

mGts_situ<-mGts + 
  geom_point(aes(x = week_DOY, y = week_mean_GS, color=Leaf.age.ordered), data=mean_TS_Gs_use, size=4, shape=18) +
  geom_errorbar(aes(ymax = week_mean_GS + week_sd_GS, ymin=week_mean_GS - week_sd_GS), data=mean_TS_Gs_use)
mGts_situ

但是我收到了'对象'week_mean_Cond'找不到的错误。由于ggplot正在寻找第一个数据帧中的对象，我试图摆脱继承的aes并在aes调用之前移动'data ='的定义。（我还定义了ggplot调用之外的errorbar限制和其他小的更改）。这是新的尝试：

Gs_upper<-mean_TS_Gs_use$week_mean_GS + mean_TS_Gs_use$week_sd_GS
Gs_lower<-mean_TS_Gs_use$week_mean_GS - mean_TS_Gs_use$week_sd_GS

mGts_situ<-mGts + 
  geom_point(data=mean_TS_Gs_use, inherit.aes = FALSE, aes(x = week_DOY, y = week_mean_GS, color=Leaf.age.ordered, ymax = Gs_upper, ymin = Gs_lower), size=4, shape=18) +
  geom_errorbar()+
  scale_x_continuous("DOY", limits = c(200, 350)) +
  scale_y_continuous("Weekly Mean", limits = c(0, 345))+
  theme_bw()
mGts_situ

这不会给出任何对象的错误，但它仍然不会显示新数据集的错误栏（'mean_TS_Gs_use'）。您可以看到第一个绘制的数据框（圆圈）具有错误栏，但第二个绘制的数据框（三角形）不具有：

Answer 1

你不能用inherit.aes来吃蛋糕，你可以继承所有东西或指定一切。

在您的情况下，您的新数据的ymin和ymax列名称不同，因此我们确实需要在新的inherit.aes = F图层中设置geom_errorbar ，但是我们需要指定所有的美学。

如果原始图中的ymin和ymax仅设置为geom_errorbar级别，而不是顶级级别，我们可以省去一点麻烦：

mGts <-
    ggplot(
        data = mean_TS_Cond_use,
        aes(
            x = week_DOY,
            y = week_mean_Cond,
            color = Leaf.age.ordered
        )
    ) +
    geom_point(size = 4) +
    geom_errorbar(
        # move these down here
        aes(ymax = week_mean_Cond + week_sd_Cond,
            ymin = week_mean_Cond - week_sd_Cond)
    )

通过这项更改，新geom_point图层就可以了，但我们会设置inherit.aes = F并重新指定geom_errorbar的美学：

mGts_situ <- mGts +
    geom_point(
        mapping = aes(
            x = week_DOY,
            y = week_mean_GS,
            color = Leaf.age.ordered
        ),
        data = mean_TS_Gs_use,
        size = 4,
        shape = 18
    ) +
    geom_errorbar(
        mapping = aes(
            ymax = week_mean_GS + week_sd_GS,
            ymin = week_mean_GS - week_sd_GS,
            x = week_DOY,
            color = Leaf.age.ordered
        ),
        data = mean_TS_Gs_use,
        inherit.aes = FALSE
    )
mGts_situ

Answer 2

我认为如果我们合并两个数据框，这个图将更容易创建：

library(dplyr)
library(ggplot2)

重命名列，以便我们在两个数据框中具有通用名称。添加新列以区分源数据来自哪个数据帧。然后组合两个数据框：

mean_TS_Cond_use = mean_TS_Cond_use %>% 
  rename(week_mean=week_mean_Cond, week_sd=week_sd_Cond) %>%
  mutate(Source="Cond")

mean_TS_Gs_use = mean_TS_Gs_use %>% 
  rename(week_mean=week_mean_GS, week_sd=week_sd_GS) %>%
  mutate(Source="Gs")

df = bind_rows(list(mean_TS_Cond_use, mean_TS_Gs_use))

重置Leaf.age.ordered的订单：

df$Leaf.age.ordered = factor(df$Leaf.age.ordered, levels=c("young","mature","old","old1"))

将week_DOY转换为因子（因此躲避将正常工作）：

df$week_DOY_f = factor(df$week_DOY, levels=min(df$week_DOY):max(df$week_DOY))

躲避以避免重叠。 group审美是为了让躲避正确：

pd = position_dodge(0.5)

ggplot(df, aes(x=week_DOY_f, 
               y=week_mean, colour=Source, fill=Source,
               ymax=week_mean + week_sd, ymin=week_mean - week_sd)) +
  geom_errorbar(position=pd, aes(group=interaction(Leaf.age.ordered, Source)), 
                width=0.1, alpha=0.5) +
  geom_point(position=pd, aes(group=interaction(Leaf.age.ordered, Source),
                              size=Leaf.age.ordered), 
             pch=21, color="black", stroke=0.2) +
  theme_bw() +
  scale_size_discrete(range=c(1,3)) +
  guides(size=guide_legend(override.aes=list(fill="grey30")))

情节仍然非常繁忙，但希望更容易阅读：

或者也许文字标签可以更好地区分年龄：

ggplot(df, aes(x=week_DOY_f, 
               y=week_mean, colour=Source,
               ymax=week_mean + week_sd, ymin=week_mean - week_sd)) +
  geom_errorbar(position=pd, aes(group=interaction(Leaf.age.ordered, Source)), 
                                 width=0.1, alpha=0.5) +
  geom_label(position=pd, aes(label=toupper(substr(Leaf.age.ordered,1,1)), 
                              group=interaction(Leaf.age.ordered, Source)), 
             fontface="bold", fill="white", label.size=0, size=2.5,
             label.padding=unit(0.05,"lines"), show.legend=FALSE) +
  theme_bw() +
  guides(colour=guide_legend(override.aes=list(alpha=1,lwd=1)))

使用ggplot2的多个数据帧的geom_point和geom_errorbar

2 个答案: