Related
I'm trying to add significance annotations to an errorbar plot with a factor x-axis and dodged groups within each level of the x-axis. It is a similar but NOT identical use case to this
My base errorbar plot is:
library(ggplot2)
library(dplyr)
pres_prob_pd = structure(list(x = structure(c(1, 1, 1, 2, 2, 2, 3, 3, 3), labels = c(`1` = 1,
`2` = 2, `3` = 3)), predicted = c(0.571584427222816, 0.712630712634987,
0.156061969566517, 0.0162388386564817, 0.0371877245103279, 0.0165022541901018,
0.131528946944238, 0.35927812866896, 0.0708662221985375), std.error = c(0.355802875027348,
0.471253661425626, 0.457109887762665, 0.352871728451576, 0.442646879181155,
0.425913568532558, 0.376552208691762, 0.48178172708116, 0.451758041335245
), conf.low = c(0.399141779923204, 0.496138837620712, 0.0701919316506831,
0.00819832576725402, 0.0159620304815404, 0.00722904089045731,
0.0675129352870401, 0.17905347369819, 0.030504893442457), conf.high = c(0.728233665534388,
0.861980236164486, 0.311759350126477, 0.031911364587827, 0.0842227723261319,
0.0372248587668487, 0.240584344249407, 0.590437963881823, 0.156035177669385
), group = structure(c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), .Label = c("certain",
"neutral", "uncertain"), class = "factor"), group_col = structure(c(1L,
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), .Label = c("certain", "neutral",
"uncertain"), class = "factor"), language = structure(c(2L, 2L,
2L, 1L, 1L, 1L, 3L, 3L, 3L), .Label = c("english", "dutch", "german"
), class = "factor"), top = c(0.861980236164486, 0.861980236164486,
0.861980236164486, 0.0842227723261319, 0.0842227723261319, 0.0842227723261319,
0.590437963881823, 0.590437963881823, 0.590437963881823)), row.names = c(NA,
-9L), groups = structure(list(language = structure(1:3, .Label = c("english",
"dutch", "german"), class = "factor"), .rows = structure(list(
4:6, 1:3, 7:9), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr", "list"))), row.names = c(NA, 3L), class = c("tbl_df",
"tbl", "data.frame"), .drop = TRUE), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"))
#dodge
pd = position_dodge(.75)
#plot
p = ggplot(pres_prob_pd,aes(x=language,y=predicted,color=group,shape=group)) +
geom_point(position=pd,size=2) +
geom_errorbar(aes(ymax=conf.high,ymin=conf.low),width=.125,position=pd)
p
What I want to do is annotate the plot such that the contrasts between group within each level of language are annotated for significance. I've plotted points representing the relevant contrasts and (toy) sig. annotations as follows:
#bump function
f = function(x){
v = c()
bump=0.025
constant = 0
for(i in x){
v = c(v,i+constant+bump)
bump = bump + 0.075
}
v
}
#create contrasts
combs = data.frame(gtools::combinations(3, 2, v=c("certain", "neutral", "uncertain"), set=F, repeats.allowed=F)) %>%
mutate(contrast=c("cont_1","cont_2","cont_3"))
combs = rbind(combs %>% mutate(language = 'english'),
combs %>% mutate(language='dutch'),
combs %>% mutate(language = "german")) %>%
left_join(select(pres_prob_pd,language:top)%>%distinct(),by='language') %>%
group_by(language)
#long transform and calc y_pos
combs_long = mutate(combs,y_pos=f(top)) %>% gather(long, probability, X1:X2, factor_key=TRUE) %>% mutate(language=factor(language,levels=c("english","dutch","german"))) %>%
arrange(language,contrast)
#back to wide
combs_wide =combs_long %>% spread(long,probability)
combs_wide$p = rep(c('***',"*","ns"),3)
#plot
p +
geom_point(data=combs_long,
aes(x = language,
color=probability,
shape=probability,
y=y_pos),
inherit.aes = T,
position=pd,
size=2) +
geom_text(data=combs_wide,
aes(x=language,
label=p,
y=y_pos+.025,
group=X1),
color='black',
position=position_dodge(.75),
inherit.aes = F)
What I am failing to achieve is plotting a line connecting each of the contrasts of group within each level of language, as is standard when annotating significant group-wise differences. Any help much appreciated!
We have a survey that asks for 'select all that apply' so the result is a string inside quotes with the values separated by commas. i.e. "red, black,green"
There are other question about income so I have a factor with 'low, medium, high'
I want to be able to answer questions: What percent selected 'Red', then group that by income.
I can split the string with
'''df4 <- c("black,silver,green")'''
I can create a data frame with a timestamp and the split string with
'''t2 <- as.data.frame(c(df2[2],l2))'''
I am not able to understand how to do this for all rows at one time.
Here is a DPUT of the input:
structure(list(RespData = structure(1:2, .Label = c("1/20/2020",
"1/21/2020"), class = "factor"), CarColor = c("red,blue,green,yellow",
"black,silver,green")), row.names = c(NA, -2L), class = "data.frame")
and here is a DPUT of the desired output:
structure(list(RespData = structure(c(1L, 1L, 1L, 1L, 2L, 2L,
2L), .Label = c("1/20/2020", "1/21/2020"), class = "factor"),
Cars = structure(c(3L, 1L, 2L, 4L, 5L, 6L, 2L), .Label = c("blue",
"green", "red", "yellow", "black", "silver"), class = "factor")), row.names = c(NA,
-7L), class = "data.frame")
Example of Function:
MySplitFunc <- function(ListIn) {
# build an empty data frame and set the column names
x1.all <- ListIn[0,]
names(x1.all) <- c("ResponseTime", "Descriptive")
# for each row build the data and combine to growing list
for(x in 1:nrow(ListIn)) {
#print(x)
r1 <- ListIn[x,1]
c1 <- strsplit(ListIn[x,2],",")
x1 <- as.data.frame(c(r1,c1))
# set the names and combine to all
names(x1) <- c("ResponseTime", "Descriptive")
x1.all <- rbind(x1.all,x1)
}
# strip the whitespace
x1.all <- data.frame(lapply(x1.all, trimws), stringsAsFactors = TRUE)
return(x1.all)
}
I have problem ploting credibility interval like this:
My data structure is following，L1,L2,M,U1,U2 stand for 0.025quant,0.25quant,0.5quant,0.75quant,0.975quant,respectively.
`
structure(list(approach = structure(c(1L, 2L, 1L, 2L, 1L, 2L), class = "factor", .Label = c("INLA",
"rjags")), param = structure(c(1L, 2L, 3L, 1L, 2L, 3L), class = "factor", .Label = c("alpha",
"beta", "sig2")), L1 = c(0.0844546867936143, 1.79242348175439,
0.163143886545317, 0.0754165380733685, 1.79067991488052, 3.66675821267498
), L2 = c(0.60090835904286, 1.95337968870806, 0.898159977552433,
0.606017177641373, 1.95260448314298, 4.07080184844179), M = c(0.870204161297956,
2.03768437879748, 2.20651061559405, 0.87408237273113, 2.03725552264872,
4.32531027636171), U2 = c(1.13905085248391, 2.12210930874551,
4.26836270504725, 1.66260576926063, 2.28900567640091, 5.10063756831338
), U1 = c(1.65214011950274, 2.28396345192398, 4.9109804477583,
1.1450384685802, 2.12117799328209, 4.55657971279654), AP = structure(c(1L,
4L, 5L, 2L, 3L, 6L), .Label = c("INLA.alpha", "rjags.alpha",
"INLA.beta", "rjags.beta", "INLA.sig2", "rjags.sig2"), class = "factor")), .Names = c("approach",
"param", "L1", "L2", "M", "U2", "U1", "AP"), row.names = c(NA,
-6L), class = "data.frame")`
I referenced this answerenter link description here,but 'fill' seems only work for boxplot case.the code I tried so far is:
CI$AP=interaction(CI$approach,CI$param)
p=ggplot(CI,aes(y=AP))+geom_point(aes(x=M))
p=p+geom_segment(aes(x=L1,xend=U1,y=AP,yend=AP))
p=p+geom_segment(aes(x=L2,xend=U2,y=AP,yend=AP),size=1.5)
It is far away from what I want.
Many thanks!
How about the following:
ggplot(df, aes(x = param, y = M, colour = approach)) +
geom_point(position = position_dodge2(width = 0.3), size = 3) +
geom_linerange(
aes(ymin = L2, ymax = U2, x = param),
position = position_dodge2(width = 0.3),
size = 2) +
geom_linerange(
aes(ymin = L1, ymax = U1, x = param),
position = position_dodge2(width = 0.3),
size = 1) +
coord_flip() +
labs(x = "Parameter", y = "Estimate")
Sample data
df <- structure(list(approach = structure(c(1L, 2L, 1L, 2L, 1L, 2L), class = "factor", .Label = c("INLA",
"rjags")), param = structure(c(1L, 2L, 3L, 1L, 2L, 3L), class = "factor", .Label = c("alpha",
"beta", "sig2")), L1 = c(0.0844546867936143, 1.79242348175439,
0.163143886545317, 0.0754165380733685, 1.79067991488052, 3.66675821267498
), L2 = c(0.60090835904286, 1.95337968870806, 0.898159977552433,
0.606017177641373, 1.95260448314298, 4.07080184844179), M = c(0.870204161297956,
2.03768437879748, 2.20651061559405, 0.87408237273113, 2.03725552264872,
4.32531027636171), U2 = c(1.13905085248391, 2.12210930874551,
4.26836270504725, 1.66260576926063, 2.28900567640091, 5.10063756831338
), U1 = c(1.65214011950274, 2.28396345192398, 4.9109804477583,
1.1450384685802, 2.12117799328209, 4.55657971279654), AP = structure(c(1L,
4L, 5L, 2L, 3L, 6L), .Label = c("INLA.alpha", "rjags.alpha",
"INLA.beta", "rjags.beta", "INLA.sig2", "rjags.sig2"), class = "factor")), .Names = c("approach",
"param", "L1", "L2", "M", "U2", "U1", "AP"), row.names = c(NA,
-6L), class = "data.frame")
I've got a data set that looks like this:
date, location, value, tally, score
2016-06-30T09:30Z, home, foo, 1,
2016-06-30T12:30Z, work, foo, 2,
2016-06-30T19:30Z, home, bar, , 5
I need to aggregate these rows together, to obtain a result such as:
date, location, value, tally, score
2016-06-30, [home, work], [foor, bar], 3, 5
There are several challenges for me:
The resulting row (a daily aggregate) must include the rows for this day (2016-06-30 in my above example
Some rows (strings) will result in an array containing all the values present on this day
Some others (ints) will result in a sum
I've had a look at dplyr, and if possible I'd like to do this in R.
Thanks for your help!
Edit:
Here's a dput of the data
structure(list(date = structure(1:3, .Label = c("2016-06-30T09:30Z",
"2016-06-30T12:30Z", "2016-06-30T19:30Z"), class = "factor"),
location = structure(c(1L, 2L, 1L), .Label = c("home", "work"
), class = "factor"), value = structure(c(2L, 2L, 1L), .Label = c("bar",
"foo"), class = "factor"), tally = c(1L, 2L, NA), score = c(NA,
NA, 5L)), .Names = c("date", "location", "value", "tally",
"score"), class = "data.frame", row.names = c(NA, -3L))
mydat<-structure(list(date = structure(1:3, .Label = c("2016-06-30T09:30Z",
"2016-06-30T12:30Z", "2016-06-30T19:30Z"), class = "factor"),
location = structure(c(1L, 2L, 1L), .Label = c("home", "work"
), class = "factor"), value = structure(c(2L, 2L, 1L), .Label = c("bar",
"foo"), class = "factor"), tally = c(1L, 2L, NA), score = c(NA,
NA, 5L)), .Names = c("date", "location", "value", "tally",
"score"), class = "data.frame", row.names = c(NA, -3L))
mydat$date <- as.Date(mydat$date)
require(data.table)
mydat.dt <- data.table(mydat)
mydat.dt <- mydat.dt[, lapply(.SD, paste0, collapse=" "), by = date]
cbind(mydat.dt, aggregate(mydat[,c("tally", "score")], by=list(mydat$date), FUN = sum, na.rm=T)[2:3])
which gives you:
date location value tally score
1: 2016-06-30 home work home foo foo bar 3 5
Note that if you wanted to you could probably do it all in one step in the reshaping of the data.table but I found this to be a quicker and easier way for me to achieve the same thing in 2 steps.
I have the following data.
> dput(testdat)
structure(list(Type = structure(c(2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Saline",
"Compound1"), class = "factor"), Treatment = structure(c(1L,
2L, 3L, 4L, 6L, 5L), .Label = c(".0032uM", ".016uM", ".08uM",
".4uM", "2uM", "10uM"), class = "factor"), Peak = c(1071.28430020209,
1458.23366806524, 2714.49856342393, 3438.83453920159, 3938.86391759534,
2980.10159109856), Area1 = c(3312.99749863082, 4798.35142770291,
9044.21362002965, 11241.1497514069, 11575.3444645068, 9521.69011119236
), SS1 = c(781.759834505516, 1191.6273298958, 2180.02082601411,
2601.33855989239, 2492.11886600804, 2185.39715502702), Conc = c(0.0032,
0.016, 0.08, 0.4, 10, 2), logconc = c(-2.49485002168009, -1.79588001734408,
-1.09691001300806, -0.397940008672038, 1, 0.301029995663981),
Conc_nm = c(3.2, 16, 80, 400, 10000, 2000), logconc_nm = c(0.505149978319906,
1.20411998265592, 1.90308998699194, 2.60205999132796, 4,
3.30102999566398)), .Names = c("Type", "Treatment", "Peak",
"Area1", "SS1", "Conc", "logconc", "Conc_nm", "logconc_nm"), row.names = 2:7, class = "data.frame")
I've fitted the data (Peak) with a nls regression using the following code:
fit = nls(Peak ~ SSlogis(logconc_nm,Asym,xmid,scal),data=testdat)
This gives me a nice fit and I'm happy with it so I plot the dose response as follows:
m <- coef(fit)
vallog <- as.numeric(format((m[3]),dig=4))
val =round(10^val,2)
ggplot(data = testdat,aes(logconc_nm,Peak))+
geom_point()+
scale_x_log10(breaks=round(testdat$logconc_nm,2))+
geom_smooth(method = 'nls',
formula = y ~ SSfpl(x,A,B,xmid,scal),se=FALSE)+
geom_vline(color='red',xintercept = vallog,alpha=.5)+
geom_text(aes(x=vallog,y=max(Peak),label = paste0('EC50',val,'nM')),color='red')#,angle=90)
My Question is:
How can I add a big ol' red point on the blue line where the blue and red line meet. I'd like to replace the need for the red line with the red dot. I know i have to use geom_point but because it's a fitted line, i can't just say x=vallog can i?