所有,
我一直在努力为我制作的时间序列数据的混合/匹配建立一个图例。这是一些代码:
我的理解是,我需要以某种方式清理数据并将其全部放在同一数据帧中,但是所有时间序列的排列都不尽人意。有些是15分钟,另一些是1小时。有什么方法可以为这些数据集添加图例?我不知道还要在此发布什么-因为5个数据集非常大。
q<- ggplot(subset(cr200_Auwai1, timedate>startd & timedate<endd), aes(timedate, Turb_SS)) +
geom_point(color="coral4")+
geom_point(data=subset(dsloi_wl, timedate>startd & timedate<endd), aes(timedate, level), color="blue")+
#geom_point(data=subset(flow_data, mdate>startd & mdate<endd), aes(as.POSIXct(mdate), flow_cfs*1000), color="red")+
geom_point(data=subset(cr300_Wai1, timedate>startd & timedate<endd), aes(timedate, Lvl_m*1000), color="forestgreen", size=1)+ #aquamarine3
geom_point(data=subset(cr300_Wai1, timedate>startd & timedate<endd), aes(timedate, Turb_SS), color="orange")+
#geom_point(data=subset(hihimanu_wl, timedate>startd & timedate<endd), aes(timedate, level), color="azure4", size=0.1)+
#geom_point(data=subset(rain_data, timedate>startd & timedate<endd), aes(timedate, rainmm), color="red",size=5)+
geom_point(data=subset(haptuk_ysi, datetime>startd & datetime<endd), aes(datetime, Turb), color="pink")+
#scale_x_date(breaks=date_breaks("month"), labels = date_format("%b-%y"))+
xlab("Date")+
ylab("Turbidity (NTU) and Water Level (mm)")+
coord_cartesian(ylim=c(0, 1500))+
theme_bw()+
theme(axis.text=element_text(size=14),
axis.title=element_text(size=16,face="bold"),
legend.justification = c(1, 1),
legend.position = c(1, 1),
legend.title=element_text(size=14),
legend.text=element_text(size=12))
这里是两个数据集的样本:请注意,时间根本就不对...因为我正在混合来源。
dsloi_wl:structure(list(ReceptionTime = c(1533895414.1134,1533895414.1733, 1533895414.19397、1533895414.20708、1533895414.22283、1533895414.23634, 1533895414.25135、1533895414.26387、1533895414.27653、1533895414.29126, 1533896013.68755、1533896013.7638、1533896013.79232、1533896013.80917, 1533896013.82312、1533896013.83648、1533896013.84988、1533896013.8648, 1533896013.87724,1533896013.8894),d2w = c(776.7,789.7,790.2, 777.1、777.2、777.7、778.4、793.4、779.6、794.1、819.9、780.7, 794.1,806.9,781.9,781.9,782.7,782.8,783.1,783.4),timedate = structure(c(1533895414.1134, 1533895414.1733、1533895414.19397、1533895414.20708、1533895414.22283, 1533895414.23634、1533895414.25135、1533895414.26387、1533895414.27653, 1533895414.29126、1533896013.68755、1533896013.7638、1533896013.79232, 1533896013.80917、1533896013.82312、1533896013.83648、1533896013.84988, 1533896013.8648、1533896013.87724、1533896013.8894),类= c(“ POSIXct”, “ POSIXt”),tzone =“”),级别= c(723.3,710.3,709.8,722.9, 722.8、722.3、721.6、706.6、720.4、705.9、680.1、719.3、705.9, 693.1,718.1,718.1,717.3,717.2,716.9,716.6))。.Names = c(“ ReceptionTime”, “ d2w”,“ timedate”,“ level”),row.names = c(NA,20L),class =“ data.frame”)
structure(list(RECORD = 73027:73046,Temp_C = c(24.62861,24.62332, 24.61533、24.60857、24.60189、24.59733、24.59068、24.58404、24.57869, 24.57327、24.56781、24.5606、24.55551、24.55218、24.54648、24.5416, 24.5358、24.5319、24.52781、24.52294),Turb_BS = c(94.50522, 88.65939、109.354、57.71527、134.1903、46.37191、78.17719、52.22319, 58.07111、96.95719、51.47488、44.65616、70.43825、99.58217、93.68374, 87.4787、175.5395、167.6757、110.8119、132.5971),Turb_SS = c(36.63349, 34.31228、37.02223、32.97258、36.68553、33.82083、37.43391、33.43639, 31.17306、33.6327、34.69954、30.99891、34.69988、33.64369、32.54948, 32.1177,32.86558,48.97706,30.65004,33.71646),Temp_C_2 = c(24.9014, 24.89474、24.88837、24.88279、24.87574、24.86852、24.86357、24.85751, 24.85236、24.84759、24.84091、24.83577、24.83192、24.82713、24.8229, 24.81832、24.81237、24.80821、24.8051、24.80015),WD_OBS = c(0L, 0L,0L,0L,0L,0L,0L,0L,0L,0L,0L,0L,0L,0L,0L,0L,0L, 0L,0L,0L),Lvl_m = c(0.6907353、0.6905226、0.6896195、0.6890779, 0.6881586、0.6878724、0.6862501、0.6848835、0.6844589、0.6837503, 0.6836612、0.6831629、0.6821692、0.6812283、0.6799452、0.6791196, 0.6782504、0.6772775、0.6763596、0.6755115),日期=结构(c(1533895500, 1533895800、1533896100、1533896400、1533896700、1533897000、1533897300, 1533897600、1533897900、1533898200、1533898500、1533898800、1533899100, 1533899400、1533899700、1533900000、1533900300、1533900600、1533900900, 1533901200),class = c(“ POSIXct”,“ POSIXt”),tzone =“”))).Names = c(“ RECORD”, “ Temp_C”,“ Turb_BS”,“ Turb_SS”,“ Temp_C_2”,“ WD_OBS”,“ Lvl_m”, “ timedate”),row.names = c(NA,20L),class =“ data.frame”)
答案 0 :(得分:0)
以下是使用模拟数据的解决方案(下一次提供数据示例):
library(tidyverse)
library(lubridate)
#>
#> Attachement du package : 'lubridate'
#> The following object is masked from 'package:base':
#>
#> date
# mock data
time_15m <- seq(as.POSIXct("2018-08-30 00:00:00"), as.POSIXct("2018-08-31 00:00:00"), by = "15 min")
time_30m <- seq(as.POSIXct("2018-08-30 00:00:00"), as.POSIXct("2018-08-31 00:00:00"), by = "30 min")
time_60m <- seq(as.POSIXct("2018-08-30 00:00:00"), as.POSIXct("2018-08-31 00:00:00"), by = "60 min")
data_1 <- data.frame(time = time_15m,
var_1 = cos(hour(time_15m) + minute(time_15m)))
data_2 <- data.frame(time = time_30m,
var_2 = sin(hour(time_30m) + minute(time_30m)))
data_3 <- data.frame(time = time_60m,
var_3 = cos(1 - hour(time_60m) + minute(time_60m)))
# the kind of plot you have (prefer the 2nd version)
ggplot(data_1, aes(x = time, y = var_1)) +
geom_point(color = "red") +
geom_point(data = data_2, aes(time, var_2), color = "green") +
geom_point(data = data_3, aes(time, var_3), color = "blue") +
theme_bw()
# a version with long format data and use of gather function
data_1 %>%
left_join(data_2) %>% # join data from data_2 (timestep = 30m), missing data is NA
left_join(data_3) %>% # join data from data_3 (timestep = 60m), missing data is NA
gather(variable_name, variable_value, var_1, var_2, var_3) %>% # gather var_1, var_2 and var_3 in a single column
ggplot(., aes(x = time, y = variable_value, color = variable_name)) +
theme_bw() +
geom_point(size = 2)
#> Joining, by = "time"
#> Joining, by = "time"
#> Warning: Removed 120 rows containing missing values (geom_point).
由reprex package(v0.2.0)于2018-08-22创建。
编辑1(包括提供的数据集)
library(tidyverse)
dsloi_wl %>%
full_join(cr300_Wai1) %>%
mutate(Lvl_m = 100 * Lvl_m) %>%
gather(variable_name, variable_value, level, Lvl_m, Turb_SS) %>%
ggplot(., aes(x = timedate, y = variable_value, color = variable_name)) +
geom_point() +
scale_color_manual("Legend title",
values = c("level" = "blue",
"Lvl_m" = "forestgreen",
"Turb_SS" = "orange"))
#> Joining, by = "timedate"
#> Warning: Removed 60 rows containing missing values (geom_point).
由reprex package(v0.2.0)于2018-08-23创建。