【发布时间】:2016-02-16 18:22:46
【问题描述】:
假设我在 Stack Overflow 中收集帖子并将它们分类为 N 个类别。我的目标是绘制每天的 N 百分比和每天的帖子总数。
为了玩,我将使用一个玩具数据框。我可以绘制每天每个类别的百分比:
data(beav1)
beav1$day <- as.factor(beav1$day)
beav1[beav1$day==346,]$time <- 1:sum(beav1$day==346)
beav1[beav1$day==347,]$time <- 1:sum(beav1$day==347)
beav1 <- filter(beav1, time<23)
ggplot(beav1, aes(x=time, y=temp, group=day, fill=day, color=day)) +
geom_line()
但是如何添加总温度线?还是意思?
编辑:与this other question 的不同之处在于,我希望所有组都使用一行,而不是每组一行。
数据集
dput(beav1)
structure(list(day = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L), .Label = c("346", "347"), class = "factor"),
time = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L,
13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 1L, 2L,
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L,
16L, 17L, 18L, 19L, 20L, 21L, 22L), temp = c(36.33, 36.34,
36.35, 36.42, 36.55, 36.69, 36.71, 36.75, 36.81, 36.88, 36.89,
36.91, 36.85, 36.89, 36.89, 36.67, 36.5, 36.74, 36.77, 36.76,
36.78, 36.82, 36.93, 36.83, 36.8, 36.75, 36.71, 36.73, 36.75,
36.72, 36.76, 36.7, 36.82, 36.88, 36.94, 36.79, 36.78, 36.8,
36.82, 36.84, 36.86, 36.88, 36.93, 36.97), activ = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L)), class = "data.frame", row.names = c(NA,
-44L), .Names = c("day", "time", "temp", "activ"))
【问题讨论】:
-
链接的帖子要求“每组”手段,而我要求整体手段(我想要一行,而不是 N)
-
如果我知道你想要每组的温度和总温度?你可以试试
ggplot(beav1, aes(x=time, y=temp, group=day, fill=day, color=day)) + stat_summary(fun.y = sum, na.rm=TRUE, geom='line') -
谢谢马蒙。但是你的线没有画出温度的总和(或平均值),是吗?