Superimposing two plots in R with same axis and limits - r

Question

I have two plots from two different data frames
The DPUT from data frame 1 is as follows
ppv_npv2 <- structure(list(pred.prob = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27,
28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
44, 45, 46, 47, 48, 49, 50, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27,
28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
44, 45, 46, 47, 48, 49, 50, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27,
28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
44, 45, 46, 47, 48, 49, 50), 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, 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, 2L, 2L, 2L, 2L,
2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L), .Label = c("ppv_2.5", "ppv_50", "ppv_97.5"), class = "factor"),
value = c(4.8, 9.3, 13.4, 17.2, 20.8, 24.2, 27.3, 30.3, 33.1,
35.7, 38.2, 40.5, 42.8, 44.9, 46.9, 48.8, 50.6, 52.3, 54,
55.6, 57.1, 58.5, 59.9, 61.2, 62.5, 63.7, 64.9, 66, 67.1,
68.2, 69.2, 70.2, 71.1, 72, 72.9, 73.8, 74.6, 75.4, 76.2,
76.9, 77.7, 78.4, 79, 79.7, 80.4, 81, 81.6, 82.2, 82.8, 83.3,
7.2, 13.6, 19.3, 24.4, 28.9, 33, 36.8, 40.2, 43.3, 46.2,
48.9, 51.3, 53.6, 55.7, 57.7, 59.6, 61.3, 62.9, 64.5, 65.9,
67.3, 68.6, 69.8, 70.9, 72, 73.1, 74.1, 75, 75.9, 76.8, 77.6,
78.4, 79.2, 79.9, 80.6, 81.3, 82, 82.6, 83.2, 83.8, 84.3,
84.8, 85.4, 85.9, 86.3, 86.8, 87.3, 87.7, 88.1, 88.5, 11.7,
21.1, 28.8, 35.3, 40.8, 45.5, 49.7, 53.3, 56.4, 59.3, 61.8,
64.1, 66.2, 68.1, 69.8, 71.4, 72.9, 74.2, 75.5, 76.6, 77.7,
78.7, 79.7, 80.5, 81.4, 82.2, 82.9, 83.6, 84.3, 84.9, 85.5,
86, 86.6, 87.1, 87.6, 88.1, 88.5, 88.9, 89.3, 89.7, 90.1,
90.5, 90.8, 91.1, 91.5, 91.8, 92.1, 92.4, 92.6, 92.9)),
.Names =c("pred.prob","variable", "value"), row.names = c(NA, -150L),
class = "data.frame")
The plot that i have created is from the following code
p1 <- ggplot(ppv_npv2,aes(x=pred.prob,y=value))+
geom_line(data=ppv_npv2[ppv_npv2$variable=="ppv_50",],
colour="red",linetype=2)+
geom_line(data=ppv_npv2[ ppv_npv2$variable=="ppv_2.5", ],
colour="blue",linetype=4)+
geom_line(data=ppv_npv2[ ppv_npv2$variable=="ppv_97.5", ],
colour="blue",linetype=4)+
theme_classic()+
ylab("Predicted positive predictive value (%) \n")+
xlab("\n Prevalence (%)")+
scale_x_continuous(limits=c(0,50),breaks=seq(0,50,2))+
scale_y_continuous(limits=c(0,100),breaks=seq(0,100,10), expand=c(0,0))+
theme(axis.text.x = element_text(size=12,hjust=.5,vjust=.8,face="plain"),
axis.text.y = element_text(size=12,hjust=.5,vjust=.8,face="plain"))+
theme(axis.title.x = element_text(size=14,face="bold"),
axis.title.y = element_text(size=14,face="bold"))
p1
The dput for the second data frame is
dat <- structure(list(PPV = c(57, 89, 19, 52, 52, 62, 63, 46, 31, 52,
54, 13, 17, 47, 48, 52, 96, 88, 64, 33, 62, 77, 75, 72), Prevalence = c(19,
35, 12, 16, 24, 6, 28, 13, 8, 19, 30, 6, 8, 20, 11, 25, 29, 55,
46, 13, 16, 22, 23, 20), total = c(939L, 323L, 306L, 703L, 137L,
833L, 360L, 317L, 440L, 2072L, 209L, 386L, 142L, 358L, 167L,
503L, 180L, 233L, 342L, 478L, 4870L, 1104L, 1813L, 1567L),
Author = structure(c(1L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 9L, 10L, 11L, 12L,
15L,18L, 19L, 8L, 14L, 16L, 17L, 21L, 20L, 20L, 13L, 10L),
.Label = c("Aldous",
"Bahrmann", "Body", "Christ ", "Collinson", "Eggers", "Freund",
"Giannitis", "Hammerer-Lercher", "Hoeller", "Inoue", "Invernizi",
"Keller", "Khan", "Lotze", "Melki ", "Normann", "Santalol", "Sebbane",
"Shah", "Thelin "), class = "factor"), Study.assay = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L), .Label = c("TnI", "TnT"), class = "factor")),
.Names = c("PPV", "Prevalence", "total", "Author", "Study.assay"),
class ="data.frame", row.names = c(NA, -24L))
And the plot from dataframe 2 is as follows
p2 <- ggplot(dat, aes(x=dat$Prevalence, y=dat$PPV, size=dat$total,
label=dat$Author),guide=F)+
geom_point(colour="white", fill="red", shape=21)+
scale_size_area(max_size = 10)+
scale_x_continuous(name="\n Prevalence", limits=c(0,100))+
scale_y_continuous(name="Predicted positive predictive value (%) \n",
limits=c(0,100))+
geom_text(size=2.5)+
theme_classic()+
ylab("Predicted positive predictive value (%) \n")+
xlab("\n Prevalence (%)")+
scale_x_continuous(limits=c(0,50),breaks=seq(0,50,2))+
scale_y_continuous(limits=c(0,100),breaks=seq(0,100,10), expand=c(0,0))+
theme(axis.text.x = element_text(size=12,hjust=.5,vjust=.8,face="plain"),
axis.text.y = element_text(size=12,hjust=.5,vjust=.8,face="plain"))+
theme(axis.title.x = element_text(size=14,face="bold"),
axis.title.y = element_text(size=14,face="bold"))+
theme(legend.position='none')
p2
As you can see both plots have the same axis and limits. I have two questions:
a) Can i overlay plot 2 onto plot 1?
b) Can i make the bubbles on plot 2 more transparent and choose colours by the factor dat$Study.assay (green and purple)?
Many thanks in advance - have spent a day researching this but no solution yet.

Answer 1

Here's a start using your data,
(plot2 <- ggplot() +
geom_line(data = ppv_npv2,aes(pred.prob, value,
group= variable, colour = variable)) +
geom_point(data = dat, aes(Prevalence, PPV, label=Author, size = total,
colour = Study.assay), alpha = I(0.4)) +
geom_text(data = dat, aes(Prevalence, PPV, label=Author,
size = total), size=3, hjust=-1, vjust=0)
)
It's not the orthodox ggplot2 way, but it's a start.