我正在绘制某些数据记录的开始和结束时间。下面是我正在使用的数据框,而我已经制作完成了。基本上我有2个循环遍历我的数据,寻找开始和结束时间,每个循环产生一个数据框,然后将其粘贴到“数据原始数据”中。打印重叠点ggplot2时间系列数据
现在我想提醒我的观众了解每个离散数据集的开始和结束时间,并且暂时只用不同颜色标记“开始”和“结束”点就足够了。老实说,尽管我想让这个更花哨的东西在画布周围画一个带有交替颜色的褪色背景的盒子,如果可能的话,使用我选择的角点。这样第一个“开始”点是1个角,第一个“结束”点是下一个角。没有线索是可能的,虽然我想我跑之前爬行。
下面是我正在使用的数据框和我用来标记点的ggplot2函数。
老实说,我觉得这是一个非常简单的问题,由于我不了解ggplot映射如何指向数据或优先化数据。
require(ggplot2)
dataraw <- structure(list(Time = c(1383817893L, 1383817970L, 1383818010L,
1383818080L, 1383818170L, 1383818250L, 1383817923L, 1383818003L,
1383818043L, 1383818113L, 1383818203L, 1383818286L, 1383817890L,
1383817893L, 1383817896L, 1383817899L, 1383817902L, 1383817905L,
1383817908L, 1383817911L, 1383817914L, 1383817917L, 1383817920L,
1383817923L, 1383817970L, 1383817973L, 1383817976L, 1383817979L,
1383817982L, 1383817985L, 1383817988L, 1383817991L, 1383817994L,
1383817997L, 1383818000L, 1383818003L, 1383818010L, 1383818013L,
1383818016L, 1383818019L, 1383818022L, 1383818025L, 1383818028L,
1383818031L, 1383818034L, 1383818037L, 1383818040L, 1383818043L,
1383818080L, 1383818083L, 1383818086L, 1383818089L, 1383818092L,
1383818095L, 1383818098L, 1383818101L, 1383818104L, 1383818107L,
1383818110L, 1383818113L, 1383818170L, 1383818173L, 1383818176L,
1383818179L, 1383818182L, 1383818185L, 1383818188L, 1383818191L,
1383818194L, 1383818197L, 1383818200L, 1383818203L, 1383818250L,
1383818253L, 1383818256L, 1383818259L, 1383818262L, 1383818265L,
1383818268L, 1383818271L, 1383818274L, 1383818277L, 1383818280L,
1383818283L, 1383818286L), value = c(4307L, 4748L, 5419L, 4663L,
4779L, 4532L, 5539L, 4589L, 5541L, 5403L, 5277L, 5183L, 4246L,
4307L, 4368L, 4416L, 4930L, 5417L, 5444L, 5461L, 5485L, 5507L,
5520L, 5539L, 4748L, 4730L, 4741L, 4706L, 4717L, 4684L, 4673L,
4673L, 4660L, 4651L, 4585L, 4589L, 5419L, 5463L, 5487L, 5510L,
5513L, 5535L, 5535L, 5538L, 5532L, 5543L, 5534L, 5541L, 4663L,
4632L, 4598L, 4586L, 4577L, 4565L, 4546L, 5316L, 5348L, 5340L,
5363L, 5403L, 4779L, 4790L, 4790L, 4779L, 4762L, 4771L, 5249L,
5294L, 5286L, 5290L, 5267L, 5277L, 4532L, 4361L, 4327L, 4319L,
4307L, 4288L, 4285L, 5098L, 5151L, 5158L, 5163L, 5177L, 5183L
), variable = c("Start", "Start", "Start", "Start", "Start",
"Start", "End", "End", "End", "End", "End", "End", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1",
"rawPressure1", "rawPressure1", "rawPressure1", "rawPressure1"
)), .Names = c("Time", "value", "variable"), row.names = c(NA,
85L), class = "data.frame")
p <- ggplot(dataraw,aes(Time, value,group=variable)) +
geom_point(aes(colour=variable))
编辑:这是以前的循环,发现“开始”和“结束”,这没有重复的数据。如下所述,最好将开始和结束添加为一个因子,而不是将其复制并添加为变量。
dataraw <-structure(list(Time = c(1383817890L, 1383817893L, 1383817896L,
1383817899L, 1383817902L, 1383817905L, 1383817908L, 1383817911L,
1383817914L, 1383817917L, 1383817920L, 1383817923L, 1383817970L,
1383817973L, 1383817976L, 1383817979L, 1383817982L, 1383817985L,
1383817988L, 1383817991L, 1383817994L, 1383817997L, 1383818000L,
1383818003L, 1383818010L, 1383818013L, 1383818016L, 1383818019L,
1383818022L, 1383818025L, 1383818028L, 1383818031L, 1383818034L,
1383818037L, 1383818040L, 1383818043L, 1383818080L, 1383818083L,
1383818086L, 1383818089L, 1383818092L, 1383818095L, 1383818098L,
1383818101L, 1383818104L, 1383818107L, 1383818110L, 1383818113L,
1383818170L, 1383818173L, 1383818176L, 1383818179L, 1383818182L,
1383818185L, 1383818188L, 1383818191L, 1383818194L, 1383818197L,
1383818200L, 1383818203L, 1383818250L, 1383818253L, 1383818256L,
1383818259L, 1383818262L, 1383818265L, 1383818268L, 1383818271L,
1383818274L, 1383818277L, 1383818280L, 1383818283L, 1383818286L
), variable = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L
), .Label = "rawPressure1", class = "factor"), value = c(4246L,
4307L, 4368L, 4416L, 4930L, 5417L, 5444L, 5461L, 5485L, 5507L,
5520L, 5539L, 4748L, 4730L, 4741L, 4706L, 4717L, 4684L, 4673L,
4673L, 4660L, 4651L, 4585L, 4589L, 5419L, 5463L, 5487L, 5510L,
5513L, 5535L, 5535L, 5538L, 5532L, 5543L, 5534L, 5541L, 4663L,
4632L, 4598L, 4586L, 4577L, 4565L, 4546L, 5316L, 5348L, 5340L,
5363L, 5403L, 4779L, 4790L, 4790L, 4779L, 4762L, 4771L, 5249L,
5294L, 5286L, 5290L, 5267L, 5277L, 4532L, 4361L, 4327L, 4319L,
4307L, 4288L, 4285L, 5098L, 5151L, 5158L, 5163L, 5177L, 5183L
), dt = c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 47L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 7L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 37L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 57L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
47L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, NA)), .Names = c("Time",
"variable", "value", "dt"), row.names = c(NA, -73L), class = "data.frame")
这是通过下面的循环推入的数据帧。
这些循环只是摘掉了我认为是每个离散数据集的开始和结束时间。而不是Rbind的观点,我应该增加一个因素,而不是数据点。
Start <- data.frame()
for (i in 2:(length(dataraw[,1])-1))
{
if ((i == 2) || (dataraw$dt[i-1] > 3 && dataraw$dt[i]==3)) {
Start <- rbind(Start,c(dataraw[i,1],dataraw[i,3]))
}
{next}
}
colnames(Start) <- c('Time','value')
Start$variable <- paste("Start")
End <- data.frame()
for (i in 1:(length(dataraw[,1])))
{
if ((dataraw$dt[i] > 3 && dataraw$dt[i-1]==3) || is.na(dataraw$dt[i])==TRUE) {
End <- rbind(End,c(dataraw[i,1],dataraw[i,3]))
}
{next}
}
colnames(End) <- c('Time','value')
End$variable <- paste("End")
Events <- rbind(Start,End)
dataraw <- dataraw[,1:3]
dataraw <- rbind(Events,dataraw)
你是我的问题是正确的。这些是重复的数据点。因为他们被从整个集合中取出并用循环弹出。而不是铸造它们,我可以让它们成为这个过程中的一个因素吗?因为这看起来是正确的,但我宁愿按照你的建议去做,并把它变成一个属性而不是重复的数据点。我将编辑我的文章并添加我的循环样本以获得可重复性。 – ZDwhite
点亮,希望编辑中的代码有帮助?首先使用你的循环来获得正确的格式。如果添加另一列作为描述每个点在哪个集合中的变量,则可以使用facet_grid将每个集合放入其自己的框中。目前没有偶数的分数,所以很难看到你的组合应该在哪里? –