Question

我想创建一个显示四个不同数据系列的时间线图。但是，第一个数据条目是一个单点，这四个序列应从该点开始，但并非如此。我怎么能告诉所有人都从t0开始而不是从t1开始，而无需手动更改原始数据帧？

这是一个复杂的问题。可以操纵数据框，也可以告诉ggplot想要什么。

因此，我测量了一种物质，然后将其分成四个不同的反应器，并在第一天之后分别进行了测量。我的数据框（plotdataframe = pldf）对于t0有一个条目，从那时起有四个条目。 y是测量值，形状是四条线的微分。

t0的区别（“ Versuchsbezeichnung”和“ Reaktorbezeichung”）为“全部”，之后分别为“ 30.1”，“ 30.2”，“ 50.1”和“ 50.2”。

df有一列用于实验的列（2个级别），而反应堆（5个列，t0的“全部”和其余的“ 30.1”，“ 30.2”，“ 50.1”和“ 50.2”）每天（t）和反应堆之间大约有20行。

这是带有dput（）的pldf的一部分，并缩减为t0，t1和t2（仍然显得凌乱，抱歉）：

structure(list(X = c(599L, 619L, 639L, 659L, 679L, 699L, 719L, 
738L, 757L, 776L, 796L, 816L, 836L, 856L, 875L, 894L, 914L, 934L, 
954L, 974L, 994L, 1013L, 1032L, 1052L, 1072L, 1092L, 1112L, 1132L, 
1151L, 1171L, 1191L, 1211L, 1231L, 1292L, 1312L, 1332L, 1352L, 
1372L, 1393L, 1414L, 1435L, 1456L, 1477L, 1498L, 1519L, 1540L, 
1560L, 1581L, 1602L, 1623L, 1788L, 1809L, 1830L, 1851L, 1872L, 
1893L, 1914L, 1935L, 1956L, 1977L, 1998L, 2019L, 2040L, 2061L, 
2082L, 2103L, 2124L, 2145L, 2166L, 2187L, 2208L, 2228L, 2249L, 
2270L, 2291L, 2312L, 2333L, 2354L, 2375L, 2396L, 2417L, 2438L
), Datum.Probenahme = structure(c(2L, 3L, 4L, 5L, 6L, 7L, 8L, 
9L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 3L, 
4L, 5L, 6L, 7L, 8L, 9L, 10L, 10L, 10L, 10L, 11L, 11L, 11L, 11L, 
12L, 12L, 12L, 12L, 13L, 13L, 13L, 13L, 14L, 15L, 15L, 15L, 15L, 
16L, 16L, 16L, 16L, 17L, 17L, 17L, 17L, 18L, 18L, 18L, 18L, 19L, 
19L, 19L, 19L, 20L, 20L, 20L, 20L, 21L, 21L, 21L, 21L, 22L, 22L, 
22L, 22L, 1L, 1L, 1L, 1L), .Label = c("01.07.2019", "05.06.2019", 
"06.06.2019", "07.06.2019", "08.06.2019", "09.06.2019", "10.06.2019", 
"11.06.2019", "12.06.2019", "13.06.2019", "14.06.2019", "15.06.2019", 
"16.06.2019", "20.06.2019", "21.06.2019", "22.06.2019", "23.06.2019", 
"24.06.2019", "25.06.2019", "26.06.2019", "28.06.2019", "30.06.2019"
), class = "factor"), Uhrzeit.Probenahme = structure(c(50L, 12L, 
10L, 11L, 4L, 8L, 8L, 14L, 12L, 12L, 13L, 8L, 12L, 8L, 19L, 12L, 
12L, 22L, 15L, 17L, 20L, 24L, 12L, 12L, 31L, 18L, 22L, 23L, 30L, 
5L, 9L, 20L, 16L, 7L, 11L, 19L, 21L, 15L, 20L, 30L, 26L, 1L, 
2L, 6L, 3L, 38L, 35L, 39L, 43L, 46L, 20L, 23L, 28L, 30L, 20L, 
22L, 25L, 28L, 28L, 30L, 33L, 35L, 43L, 36L, 27L, 32L, 29L, 34L, 
37L, 42L, 35L, 45L, 41L, 48L, 49L, 47L, 44L, 40L, 35L, 35L, 35L, 
35L), .Label = c("09:23", "09:29", "09:37", "09:40", "09:42", 
"09:43", "09:47", "09:50", "09:51", "09:52", "09:55", "10:00", 
"10:05", "10:06", "10:10", "10:11", "10:12", "10:15", "10:16", 
"10:20", "10:24", "10:25", "10:30", "10:34", "10:35", "10:36", 
"10:37", "10:40", "10:43", "10:45", "10:50", "10:51", "10:55", 
"10:57", "11:00", "11:01", "11:03", "11:04", "11:05", "11:06", 
"11:07", "11:09", "11:10", "11:13", "11:14", "11:15", "11:20", 
"11:21", "11:25", "12:10"), class = "factor"), Versuchsbezeichnung = structure(c(2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 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 = c("MUN", "WAS"), class = "factor"), Probenzeitpunkt = structure(c(1L, 
2L, 5L, 6L, 7L, 8L, 9L, 10L, 2L, 5L, 6L, 7L, 8L, 9L, 10L, 2L, 
5L, 6L, 7L, 8L, 9L, 10L, 2L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 11L, 
11L, 11L, 12L, 12L, 12L, 12L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 
1L, 2L, 2L, 2L, 2L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 
7L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 11L, 11L, 11L, 11L, 3L, 3L, 
3L, 3L, 4L, 4L, 4L, 4L), .Label = c("t0", "t1", "t10", "t11", 
"t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"), class = "factor"), 
    Reaktorbezeichnung = structure(c(1L, 2L, 2L, 2L, 2L, 2L, 
    2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 
    4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 2L, 3L, 5L, 4L, 2L, 3L, 5L, 
    4L, 2L, 3L, 5L, 4L, 2L, 3L, 5L, 4L, 1L, 2L, 3L, 4L, 5L, 2L, 
    3L, 4L, 5L, 2L, 3L, 4L, 5L, 2L, 3L, 4L, 5L, 2L, 3L, 4L, 5L, 
    2L, 3L, 4L, 5L, 2L, 3L, 4L, 5L, 2L, 3L, 4L, 5L, 2L, 3L, 4L, 
    5L), .Label = c("Alle", "T30.1", "T30.2", "T50.1", "T50.2"
    ), class = "factor"), eingestellte_Temperatur = c(NA, 30L, 
    30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 
    30L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 
    50L, 50L, 50L, 30L, 30L, 50L, 50L, 30L, 30L, 50L, 50L, 30L, 
    30L, 50L, 50L, 30L, 30L, 50L, 50L, NA, 30L, 30L, 50L, 50L, 
    30L, 30L, 50L, 50L, 30L, 30L, 50L, 50L, 30L, 30L, 50L, 50L, 
    30L, 30L, 50L, 50L, 30L, 30L, 50L, 50L, 30L, 30L, 50L, 50L, 
    30L, 30L, 50L, 50L, 30L, 30L, 50L, 50L), Parameter_lang = 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, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L), .Label = "substance", class = "factor"), 
    mittelwert = c(195.510146467184, 590.04453797041, 650.046710519628, 
    805.023970909082, 680.056275644273, 605.038628373497, 655.013494757377, 
    510.014882632685, 535.033292951283, 670.029819108804, 675.023180234177, 
    635.030532865876, 705.020509801388, 700.016350845922, 630.031948130196, 
    575.020958779739, 515.034675161434, 515.010423214009, 484.525917325803, 
    525.034977749943, 535.030449153043, 545.005715243447, 540.041962411875, 
    545.046361460258, 461.558379907788, 510.029446766068, 600.036907210817, 
    520.031560570813, 515.023911897655, 645.052575729496, 705.012975914544, 
    550.022784174821, 560.017740283, 630.066260242174, 675.022704031091, 
    545.053372419458, 540.016063199975, 700.028692986007, 604.992609005687, 
    545.038604346887, 500.023450688633, 685.031134646166, 765.044624693392, 
    575.045832850911, 545.018905606243, 9.30989225859789, 14.6996919068786, 
    20.2006993402116, 11.6396196601576, 9.81990236026879, 29.7991367947917, 
    29.1989874363788, 4.11997199560799, 4.44042193773157, 32.9990403063925, 
    57.5020579022581, 21.0483199248758, 22.0038515217912, 90.4030580857021, 
    89.000336284423, 8.34032878685458, 10.3604802171955, 96.1034261675684, 
    105.004535949448, 8.89931984186634, 9.92024857606832, 101.002678657527, 
    132.007031226063, 10.7206828322988, 10.7809908792647, 107.003512180122, 
    101.001589580275, 12.3191266322172, 10.0618514094455, 102.005883436079, 
    93.29828183675, 8.46966678357295, 5.40058933971296, 45.7032091854773, 
    49.8010426068819, 7.61983731205152, 6.9002829183213)), class = "data.frame", row.names = c(NA, 
-82L))

这是我尝试使用的方法：

ggplot(data = pldf, aes(x = day, y = mittelwert, col = Versuchsbezeichnung, shape = Reaktorbezeichnung)) +
  geom_line() +
  theme_classic() +
  scale_y_continuous(breaks = seq(0, 1000, 100))

结果：Current plot where the firstpoint for 2 different experiment runs are not connected to the rest of the data

标准绘图的临时解决方法是：

reaktor301 <- pldf[pldf$Reaktorbezeichnung %in% c("Alle", "T30.1"),] reaktor302 <- pldf[pldf$Reaktorbezeichnung %in% c("Alle", "T30.2"),] reaktor501 <- pldf[pldf$Reaktorbezeichnung %in% c("Alle", "T50.1"),] reaktor502 <- pldf[pldf$Reaktorbezeichnung %in% c("Alle", "T50.2"),]

但是在ggplot中如何工作？我的意思是我该如何告诉ggplot从四个不同的数据框中提取数据？

以前我没有包含df，很抱歉它看起来很凌乱，因为我是r和stackoverflow等所有的新手，所以我不知道如何更好地集成它（更漂亮）。

我希望图形显示从t0到t11的线。我可能最终只能在原始df中复制“ Alle”行一次。但是，如果您知道未来的发展之路，答案将是万分感谢。

Answer 1

啊。我开始了解您的问题。但首先，要对您的数据进行调整：

pldf$day <- as.numeric(gsub("t", "", pldf$Probenzeitpunkt))

是的，我认为您应该创建数据框的副本，并为每次出现的“ Alle”添加一行零点：

n.react <- length(unique(pldf$Reaktorbezeichnung)) - 1 # should be 4
reactors <- setdiff(unique(pldf$Reaktorbezeichnung), "Alle")

pldf2 <- pldf %>% filter(Reaktorbezeichnung == "Alle") %>% 
         mutate(count=rep(n.react, 2)) %>% uncount(count) %>% 
         mutate(Reaktorbezeichnung=rep(reactors, 2)) %>%
         rbind(pldf) %>% filter(Reaktorbezeichnung != "Alle")

说明：首先，我们仅采用包含“ Alle”的行。接下来，我们创建一个临时列count，然后使用uncount函数将其复制到每一行（因此，如果count是4，而不是一行，则得到4 ）。接下来，将“ Reaktorbezeichnung”从“ Alle”更改为可能的值，每个值两次（每个试验类型一次），最后绑定到原始pldf并删除“ Alle”。 ff

最下面的一行是，对于每条“ Alle”行，pldf2现在应包含四行，其中“ Alle”被“ T30.1”，“ T30.2”，“ T50.1”，“ T50”替换。 2“。对于点美学，您需要原始数据框。对于这些行，您需要此修改后的数据框。

那你就可以做

ggplot(data = pldf, aes(x = day, y = mittelwert, col = Versuchsbezeichnung, shape =       Reaktorbezeichnung)) + 
  geom_point() +
  geom_line(data=pldf2, mapping=aes(x=day, y=mittelwert, col=Versuchsbezeichnung)) +
  theme_classic() +
  scale_y_continuous(breaks = seq(0, 1000, 100))

由于我无法使用您的数据段，因此我制作了一个模拟数据，其数据类似：

pldf <- data.frame(React=rep(LETTERS[1:4], each=12), 
                  day=rep(1:6, 8), 
                  trial=rep(rep(c("WAS", "MUN"), each=6), 4))
pldf$y <- 10 * as.numeric(factor(pldf$trial)) + rnorm(48)
pldf <- rbind(pldf, data.frame(React=rep("Alle", 2), 
    day=0, 
    trial=c("WAS", "MUN"), y=c(5, 10)))

使用您的命令，会得到类似的画面：

好的，我使用建议的命令：

pldf2 <- pldf %>% filter(React == "Alle") %>% 
         mutate(count=c(4, 4)) %>% uncount(count) %>% 
         mutate(React=rep(LETTERS[1:4], 2)) %>%
         rbind(pldf) %>% filter(React != "Alle")


ggplot(data=pldf, aes(x=day, y=y, color=trial, shape=React)) + geom_point() + 
  geom_line(data=pldf2, aes(x=day, y=y, color=trial)) + 
  scale_y_continuous(breaks = seq(0, 20, 5)) + 
  theme_classic()

这是您想要的吗？

好的，既然我证明了你可以做到，那么我将劝阻你不要这样做。为什么只需要一点就需要一个附加符号？您为什么要不必要地给图表查看者带来混乱？从图中可以很明显地看出，一种颜色的所有线都起源于一个点。您应该始终努力减少在数据上显示的墨水和符号的数量。例如：在图上区分T30.1和T30.2重要吗？反应堆类型是否根本重要？

多个数据系列共享单个数据点，出现连接问题

1 个答案: