多个组的ggplot条形图+折线图
Posted
技术标签:
【中文标题】多个组的ggplot条形图+折线图【英文标题】：ggplot bar plot by multiple groups + line graph 【发布时间】：2022-01-14 09:57:15 【问题描述】：我有这个数据集：
structure(list(team = c("bgb", "bgb", "bgb", "bgb", "bgb", "bgb",
"bgb", "bgb", "bgb", "bgb", "bgb", "bgb", "bgb", "bgb", "bgb",
"bgb", "bgb", "bgb", "bgb", "bgb", "bgb", "bgr", "bgr", "bgr",
"bgr", "bgr", "bgr", "bgr", "bgr", "bgr", "bgr", "bgr", "bgr",
"bgr", "bgr", "bgr", "bgr", "bgr", "bgr", "bgr", "bgr", "bgr",
"chj", "chj", "chj", "chj", "chj", "chj", "chj", "chj", "chj",
"chj", "chj", "chj", "chj", "chj", "chj", "chj", "chj", "chj",
"chj", "chj", "chn", "chn", "chn", "chn", "chn", "chn", "chn",
"chn", "chn", "chn", "chn", "chn", "chn", "chn", "chn", "chn",
"chn", "chn", "chn", "chn", "chn", "lev", "lev", "lev", "lev",
"lev", "lev", "lev", "lev", "lev", "lev", "lev", "lev", "lev",
"lev", "lev", "lev", "lev", "lev", "mbj", "mbj", "mbj", "mbj",
"mbj", "mbj", "mbj", "mbj", "mbj", "mbj", "mbj", "mbj", "mbj",
"mbj", "mbj", "mbj", "mbj", "mbj", "mbj", "mbj", "mbj", "mbn",
"mbn", "mbn", "mbn", "mbn", "mbn", "mbn", "mbn", "mbn", "mbn",
"mbn", "mbn", "mbn", "mbn", "mbn", "mbn", "mbn", "mbn", "mbn",
"mbn", "mbn", "mrb", "mrb", "mrb", "mrb", "mrb", "mrb", "mrb",
"mrb", "mrb", "mrb", "mrb", "mrb", "mrb", "mrb", "mrb", "mrb",
"mrb", "mrb", "mrb", "mrb", "mrb", "rwl", "rwl", "rwl", "rwl",
"rwl", "rwl", "rwl", "rwl", "rwl", "rwl", "rwl", "rwl", "rwl",
"rwl", "rwl", "rwl", "rwl", "rwl", "rwl", "rwl", "rwl"), tmp = c("P1",
"P1", "P1", "P1", "P1", "P1", "P1", "P2", "P2", "P2", "P2", "P2",
"P2", "P2", "P3", "P3", "P3", "P3", "P3", "P3", "P3", "P1", "P1",
"P1", "P1", "P1", "P1", "P1", "P2", "P2", "P2", "P2", "P2", "P2",
"P2", "P3", "P3", "P3", "P3", "P3", "P3", "P3", "P1", "P1", "P1",
"P1", "P1", "P1", "P1", "P2", "P2", "P2", "P2", "P2", "P2", "P2",
"P3", "P3", "P3", "P3", "P3", "P3", "P1", "P1", "P1", "P1", "P1",
"P1", "P1", "P2", "P2", "P2", "P2", "P2", "P2", "P2", "P3", "P3",
"P3", "P3", "P3", "P3", "P3", "P1", "P1", "P1", "P1", "P1", "P1",
"P1", "P2", "P2", "P2", "P2", "P2", "P2", "P2", "P3", "P3", "P3",
"P3", "P1", "P1", "P1", "P1", "P1", "P1", "P1", "P2", "P2", "P2",
"P2", "P2", "P2", "P2", "P3", "P3", "P3", "P3", "P3", "P3", "P3",
"P1", "P1", "P1", "P1", "P1", "P1", "P1", "P2", "P2", "P2", "P2",
"P2", "P2", "P2", "P3", "P3", "P3", "P3", "P3", "P3", "P3", "P1",
"P1", "P1", "P1", "P1", "P1", "P1", "P2", "P2", "P2", "P2", "P2",
"P2", "P2", "P3", "P3", "P3", "P3", "P3", "P3", "P3", "P1", "P1",
"P1", "P1", "P1", "P1", "P1", "P2", "P2", "P2", "P2", "P2", "P2",
"P2", "P3", "P3", "P3", "P3", "P3", "P3", "P3"), day_s = structure(c(2L,
4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L,
3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L,
6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L,
2L, 4L, 5L, 3L, 1L, 6L, 7L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L,
3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L,
6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L,
5L, 3L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L,
6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L,
2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L,
5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L,
1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L, 2L, 4L, 5L, 3L, 1L, 6L,
7L, 2L, 4L, 5L, 3L, 1L, 6L, 7L), .Label = c("Mo", "Di", "Mi",
"Do", "Fr", "Sa", "So"), class = c("ordered", "factor")), mpd = c(108,
93, 92, 60, 98, 96, 30, 57, 58, 60, 47, 78, 65, 87, 67, 72, 76,
27, 54, 63, 42, 96, 62, 73, 27, 17, 33, 45, 51, 69, 29, 29, 59,
38, 17, 120, 59, 30, 30, 68, 30, 18, 68, 32, 71, 73, 81, 28,
38, 90, 107, 60, 43, 38, 22, 5, 150, 120, 90, 120, 90, 113, 91,
89, 69, 80, 114, 30, 56, 169, 186, 69, 95, 132, 75, 104, 60,
189, 250, 139, 180, 58, 180, 117, 107, 50, 127, 162, 11, 130,
58, 88, 82, 98, 75, 110, 158, 80, 18, 120, 120, 70, 89, 106,
85, 103, 130, 50, 65, 84, 120, 84, 38, 100, 108, 30, 90, 50,
63, 120, 80, 70, 90, 71, 28, 77, 98, 70, 60, 64, 62, 63, 71,
34, 27, 51, 38, 104, 130, 90, 150, 105, 132, 66, 99, 23, 79,
77, 51, 26, 71, 80, 78, 102, 38, 66, 42, 52, 119, 44, 41, 133,
278, 51, 78, 55, 89, 71, 93, 56, 61, 79, 60, 150, 79, 52, 85,
52, 118, 98, 62, 58, 60, 68, 87), rpd = c(6, 5, 5, 5, 6, 5, 5,
5, 5, 7, 5, 6, 5, 6, 6, 6, 6, 5, 5, 4, 6, 7, 8, 7, 6, 6, 6, 6,
9, 7, 6, 6, 7, 8, 5, 9, 6, 6, 7, 7, 6, 6, 7, 7, 6, 8, 7, 7, 7,
9, 8, 9, 6, 8, 4, 3, 6, 6, 5, 2, 8, 8, 6, 6, 6, 5, 6, 6, 6, 7,
6, 6, 6, 5, 8, 7, 6, 6, 6, 5, 4, 6, 9, 6, 7, 4, 8, 6, 5, 6, 6,
4, 6, 8, 8, 6, 8, 8, 8, 10, 10, 8, 8, 6, 7, 6, 6, 4, 6, 6, 5,
7, 9, 7, 7, 9, 8, 7, 7, 7, 6, 7, 7, 7, 5, 7, 6, 8, 5, 4, 6, 7,
6, 6, 6, 7, 6, 8, 8, 8, 7, 8, 6, 7, 7, 6, 7, 7, 7, 6, 8, 7, 6,
7, 5, 7, 7, 5, 7, 5, 5, 8, 11, 8, 7, 7, 6, 7, 6, 7, 6, 7, 7,
7, 7, 8, 7, 7, 7, 8, 6, 10, 10, 7, 10)), row.names = c(NA, -185L
), groups = structure(list(team = c("bgb", "bgb", "bgb", "bgr",
"bgr", "bgr", "chj", "chj", "chj", "chn", "chn", "chn", "lev",
"lev", "lev", "mbj", "mbj", "mbj", "mbn", "mbn", "mbn", "mrb",
"mrb", "mrb", "rwl", "rwl", "rwl"), tmp = c("P1", "P2", "P3",
"P1", "P2", "P3", "P1", "P2", "P3", "P1", "P2", "P3", "P1", "P2",
"P3", "P1", "P2", "P3", "P1", "P2", "P3", "P1", "P2", "P3", "P1",
"P2", "P3"), .rows = structure(list(1:7, 8:14, 15:21, 22:28,
29:35, 36:42, 43:49, 50:56, 57:62, 63:69, 70:76, 77:83, 84:90,
91:97, 98:101, 102:108, 109:115, 116:122, 123:129, 130:136,
137:143, 144:150, 151:157, 158:164, 165:171, 172:178, 179:185), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr", "list"))), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -27L), .drop = TRUE), na.action = structure(c(`8` = 8L,
`16` = 16L, `24` = 24L, `32` = 32L, `40` = 40L, `48` = 48L, `56` = 56L,
`64` = 64L, `65` = 65L, `72` = 72L, `80` = 80L, `88` = 88L, `96` = 96L,
`104` = 104L, `112` = 112L, `113` = 113L, `118` = 118L, `126` = 126L,
`134` = 134L, `142` = 142L, `150` = 150L, `158` = 158L, `166` = 166L,
`174` = 174L, `182` = 182L, `190` = 190L, `198` = 198L, `206` = 206L,
`214` = 214L), class = "omit"), class = c("grouped_df", "tbl_df",
"tbl", "data.frame"))
我想将变量 mpd 说明为条形，但通过“day_s”（周一至周日）和 tmp（阶段 1 至 3）进行区分。 如果它只是区分变量 day_s，这就是我得到的图：
ggplot(tab_tra) +
geom_bar(aes(x=day_s, y=mpd), stat="identity")
但我希望在星期日之后它再次从星期一开始（P2 的星期一），然后是第三周。 x 轴基本上由三周（P1、P2 和 P3）组成。每周的酒吧应该有不同的颜色。例如，第一周的条形图是蓝色的，第二个是绿色的，第三个是红色的。 此外，我想添加一行，用单独的 y 轴说明变量“rpd”在这三周内的过程。
我还没有找到构建这个情节的正确方法。所以我希望有人可以帮助我。
在此先感谢，感谢任何形式的帮助。
干杯
更新：
我使用了@JKupzig 建议的方法。到目前为止它工作正常，但我无法添加折线图（见下文）：
ggplot(tab_tra, aes(fill = tmp)) +
geom_bar(aes(x=day_s, y=mpd), stat="identity") +
geom_line(aes(x=day_s, y=rpd*10))+
scale_y_continuous(sec.axis = sec_axis(trans=~.*10, name= "rpd Axis"))+
facet_grid(~ tmp)+
theme_bw()
【问题讨论】：
当您使用 +geom_point(aes(x=day_s, y=rpd*10, group=tmp),stat="identity") 时，您会注意到 rpd 有多个值（由于不同的“团队”）。在条形图中，汇总了团队的值 - 您是否希望对折线图中的 rpd 值做同样的事情？ 是的，我也想要汇总 rpd 值。 查看我的答案更新@psycho95 【参考方案1】：您可以使用 facet_wrap 将星期排列在一起：
ggplot(data, aes(fill=tmp)) +
geom_bar(aes(x=day_s, y=mpd, group=tmp) ,stat="identity") +
facet_wrap(.~tmp) +
theme_bw()
更新 要将 rpd 总结为线图，您可以执行以下操作：
library(dplyr)
rpd_sum <- data %>%
group_by(tmp, day_s) %>%
summarise(sum_rpd = sum(rpd)) %>%
mutate(newClass = paste(tmp, day_s))
data$newClass <- paste(data$tmp, data$day_s)
dataNew <- merge(data, rpd_sum )
ggplot(dataNew, aes(fill=tmp)) +
geom_bar(aes(x=day_s, y=mpd) ,stat="identity") +
geom_line(aes(x=day_s, y=sum_rpd*10, group=tmp),stat="identity") +
scale_y_continuous(sec.axis = sec_axis( trans=~./10, name="rpd Axis")) +
facet_wrap(.~tmp) +
theme_bw()
【讨论】：
谢谢@JKupzig，这正是我想要的。但是你也知道如何在这个图中添加折线图吗？ ``` + geom_line()``` 看这里一个例子如何解决这个问题：***.com/questions/41764312/… 我在代码中添加了geom_line(aes(x=day_s, y=rpd), stat = "identity")，但没有任何反应
因为 rpd 的比例与 mpd 不同，所以您必须转换 rpd，例如geom_line(...aes(...y=rpd*10)... 并添加第二个 y 轴，例如 scale_y_continuous(sec.axis = sec_axis( trans=~.*10, name="rpd Axis")) 【参考方案2】：
简单地添加一个方面可能是最简单的解决方案。
ggplot(tab_tra) +
geom_bar(aes(x=day_s, y=mpd), stat="identity") +
facet_grid(~ tmp)
【讨论】：
【参考方案3】：将tmp设置为因子
tab_tra$tmp<- as.factor(tab_tra$tmp)
然后
ggplot(tab_tra) +
geom_bar(aes(x=day_s, y=mpd, fill = tmp), stat="identity" )
【讨论】：
【参考方案4】：您可以使用dodge()进行自定义
ggplot(df, aes(fill=tmp)) +
geom_bar(aes(x=day_s, y=mpd, group=tmp),stat="identity", position = position_dodge(width = 0.9)) +
theme_bw()
或
ggplot(df, aes(fill=tmp)) +
geom_bar(aes(x=day_s, y=mpd, group=tmp),stat="identity", position = position_dodge2(width = 0.5, preserve = "single", padding = -0.5)) +
theme_bw()
【讨论】：
以上是关于多个组的ggplot条形图+折线图的主要内容，如果未能解决你的问题，请参考以下文章