I want to make time based density plots of a variable for the factor water use management for the data set as follows
Seed(123)
ID = rep(c("BAU","IMP","SGR","CR"), each=25)
Time = rep (c(1,2,3,4,5), each = 20)
data <- data.frame( ID, Time, profits = runif(100,0,1))
I am using the following codes to make density plot for profits across IDs. or may be facet_wrap for group or time?
library(ggridges)
ggplot(
data, aes(x = profits, y=as.factor( Time), group = ID, fill=stat(x))) +
geom_density_ridges_gradient(scale = 3, size = 0.3, rel_min_height = 0.01) +
scale_fill_viridis_c(name = "Profits", option = "C") +
labs(title = 'Total Profits') + facet_wrap(~ID, scales = "free")+
theme_classic()
It gives nice density plots. But for the large data of million rows as I have originally; for instance as given below:
Seed(123)
ID = rep(c("BAU","IMP","SGR","CR"), each=5000)
Time = rep (c(1:1000), each = 20)
data <- data.frame( ID, Time, profits = runif(20000,0,1))
the codes give an untidy graph. Can we make factor of time say in interval of 20 each to make the graph understandable? or if any other faceting or wrapping can improve the visibility of graph. Please help
Thanks
take a look at this:
https://stackoverflow.com/a/55852972/13142581
Seed(123)
ID = rep(c("BAU","IMP","SGR","CR"), each=25)
Time = rep (c(1,2,3,4,5), each = 20)
data <- data.frame( ID, Time, profits = runif(100,0,1))
library(ggridges)
ggplot(
data, aes(x = profits, y=as.character(ID), group = as.character(Time), fill=stat(x))) +
geom_density_ridges_gradient(scale = 3, rel_min_height = 0.01) +
scale_fill_viridis_c(name = "Profits", option = "C") +
labs(title = 'Total Profits') + facet_wrap(~ID, scales = "free")+
theme_classic()
Related
Reproduced from this code:
library(haven)
library(survey)
library(dplyr)
nhanesDemo <- read_xpt(url("https://wwwn.cdc.gov/Nchs/Nhanes/2015-2016/DEMO_I.XPT"))
# Rename variables into something more readable
nhanesDemo$fpl <- nhanesDemo$INDFMPIR
nhanesDemo$age <- nhanesDemo$RIDAGEYR
nhanesDemo$gender <- nhanesDemo$RIAGENDR
nhanesDemo$persWeight <- nhanesDemo$WTINT2YR
nhanesDemo$psu <- nhanesDemo$SDMVPSU
nhanesDemo$strata <- nhanesDemo$SDMVSTRA
nhanesAnalysis <- nhanesDemo %>%
mutate(LowIncome = case_when(
INDFMIN2 < 40 ~ T,
T ~ F
)) %>%
# Select the necessary columns
select(INDFMIN2, LowIncome, persWeight, psu, strata)
# Set up the design
nhanesDesign <- svydesign(id = ~psu,
strata = ~strata,
weights = ~persWeight,
nest = TRUE,
data = nhanesAnalysis)
svyhist(~log10(INDFMIN2), design=nhanesDesign, main = '')
How do I color the histogram by independent variable, say, LowIncome? I want to have two separate histograms, one for each value of LowIncome. Unfortunately I picked a bad example, but I want them to be see-through in case their values overlap.
If you want to plot a histogram from your model, you can get its data from model.frame (this is what svyhist does under the hood). To get the histogram filled by group, you could use this data frame inside ggplot:
library(ggplot2)
ggplot(model.frame(nhanesDesign), aes(log10(INDFMIN2), fill = LowIncome)) +
geom_histogram(alpha = 0.5, color = "gray60", breaks = 0:20 / 10) +
theme_classic()
Edit
As Thomas Lumley points out, this does not incorporate sampling weights, so if you wanted this you could do:
ggplot(model.frame(nhanesDesign), aes(log10(INDFMIN2), fill = LowIncome)) +
geom_histogram(aes(weight = persWeight), alpha = 0.5,
color = "gray60", breaks = 0:20 / 10) +
theme_classic()
To demonstrate this approach works, we can replicate Thomas's approach in ggplot using the data example from svyhist. To get the uneven bin sizes (if this is desired), we need two histogram layers, though I'm guessing this would not be required for most use-cases.
ggplot(model.frame(dstrat), aes(enroll)) +
geom_histogram(aes(fill = "E", weight = pw, y = after_stat(density)),
data = subset(model.frame(dstrat), stype == "E"),
breaks = 0:35 * 100,
position = "identity", col = "gray50") +
geom_histogram(aes(fill = "Not E", weight = pw, y = after_stat(density)),
data = subset(model.frame(dstrat), stype != "E"),
position = "identity", col = "gray50",
breaks = 0:7 * 500) +
scale_fill_manual(NULL, values = c("#00880020", "#88000020")) +
theme_classic()
You can't just extract the data and use ggplot, because that won't use the weights and so misses the whole point of svyhist. You can use the add=TRUE argument, though. You do need to set the x and y axis ranges correctly to make sure the whole plot is visible
Using the data example from ?svyhist
svyhist(~enroll, subset(dstrat,stype=="E"), col="#00880020",ylim=c(0,0.003),xlim=c(0,3500))
svyhist(~enroll, subset(dstrat,stype!="E"), col="#88000020",add=TRUE)
Hi I have a much larger data frame but a sample dummy df is as follows:
set.seed(23)
df = data.frame(name = c(rep("Bob",8),rep("Tom",8)),
topic = c(rep(c("Reading","Writing"),8)),
subject = c(rep(c("English","English","Spanish","Spanish"),4)),
exam = c(rep("First",4),rep("Second",4),rep("First",4),rep("Second",4)),
score = sample(1:100,16))
I have to plot it in the way shown in the picture below (for my original data frame) but with lines connecting the scores corresponding to each name between the first and second class in the exam variable, I tried geom_line(aes(group=name)) but the lines are not connected in the right way. Is there any way to connect the points that also respects the grouping by the fill variable similar to how the position_dodge() helps separate the points by their fill grouping? Thanks a lot!
library(ggplot2)
df %>% ggplot(aes(x=topic,y=score,fill=exam)) +
geom_boxplot(outlier.shape = NA) +
geom_point(size=1.75,position = position_dodge(width = 0.75)) +
facet_grid(~subject,switch = "y")
One option to achieve your desired result would be to group the lines by name and topic and do the dodging of lines manually instead of relying on position_dogde. To this end convert topic to a numeric for the geom_line and shift the position by the necessary amount to align the lines with the dodged points:
set.seed(23)
df <- data.frame(
name = c(rep("Bob", 8), rep("Tom", 8)),
topic = c(rep(c("Reading", "Writing"), 8)),
subject = c(rep(c("English", "English", "Spanish", "Spanish"), 4)),
exam = c(rep("First", 4), rep("Second", 4), rep("First", 4), rep("Second", 4)),
score = sample(1:100, 16)
)
library(ggplot2)
ggplot(df, aes(x = topic, y = score, fill = exam)) +
geom_boxplot(outlier.shape = NA) +
geom_point(size = 1.75, position = position_dodge(width = 0.75)) +
geom_line(aes(
x = as.numeric(factor(topic)) + .75 / 4 * ifelse(exam == "First", -1, 1),
group = interaction(name, topic)
)) +
facet_grid(~subject, switch = "y")
A market survey on consumer satisfaction when using two cleaning products (Product A and Product B) was separated according to room (Kitchen, Bathroom, Bedroom), frequency of use (Daily, Weekly, Monthly) and product bottle size (Small, Medium, Large).
I thought the best way to represent these results is column plots. However, I think there are better ways to represent these results, so I come here to ask for suggestions for a better graphical representation, as I am not very satisfied with column plots.
In MWE the data is arranged ascending, but with real data, the different column sizes make the plot visually very polluted.
library(ggplot2)
Product <- c("Product A", "Product B")
Place <- c("Kitchen", "Bathroom", "Bedroom")
Bottle_size <- c("Small", "Medium", "Large")
Frequency <- c("Daily", "Weekly", "Monthly")
DF <- expand.grid(Bottle_size = Bottle_size,
Place = Place,
Frequency = Frequency,
Product = Product)
DF$Consumer_Approval <- seq(from = 10,
to = 100,
by = (100-10)/53)
ggplot(data = DF,
aes(x = Frequency,
y = Consumer_Approval)) +
geom_col(aes(fill = Bottle_size),
position = "dodge") +
facet_grid(Product ~ Place)
enter image description here
The real data is something like:
enter image description here
One option would be a lollipop chart, where the height of the lollipop shows the difference between the consumer rating for product A and product B. This allows a quick visual estimate of the preferred product in a given setting:
ProdA <- split(DF, Product)[[1]]
ProdB <- split(DF, Product)[[2]]
DF <- dplyr::left_join(ProdA, ProdB, c("Bottle_size", "Place", "Frequency"))
DF$AvsB <- DF$Consumer_Approval.x - DF$Consumer_Approval.y
ggplot(data = DF, aes(x = Frequency, y = AvsB, color = Bottle_size)) +
geom_point(position = position_dodge(width = 0.5)) +
geom_linerange(aes(ymin = AvsB, ymax = 0), position = position_dodge(width = 0.5)) +
geom_hline(yintercept = 0, linetype = 2) +
ylim(-100, 100) +
facet_grid(.~Place) +
labs(y = "Prefers Product B <- No preference -> Prefers Product A")
this is my first stack overflow post and I am a relatively new R user, so please go gently!
I have a data frame with three columns, a participant identifier, a condition (factor with 2 levels either Placebo or Experimental), and an outcome score.
set.seed(1)
dat <- data.frame(Condition = c(rep("Placebo",10),rep("Experimental",10)),
Outcome = rnorm(20,15,2),
ID = factor(rep(1:10,2)))
I would like to construct a bar plot with two bars with the mean outcome score for each condition and the standard deviation as an error bar. I would like to then overlay lines connecting points for each participant's score in each condition. So the plot displays the individual response as well as the group mean.If it is also possible I would like to include an axis break.
I don't seem to be able to find any advice in other threads, apologies if I am repeating a question.
Many Thanks.
p.s. I realise that presenting data in this way will not be to everyones tastes. It is for a specific requirement!
This ought to work:
library(ggplot2)
library(dplyr)
dat.summ <- dat %>% group_by(Condition) %>%
summarize(mean.outcome = mean(Outcome),
sd.outcome = sd(Outcome))
ggplot(dat.summ, aes(x = Condition, y = mean.outcome)) +
geom_bar(stat = "identity") +
geom_errorbar(aes(ymin = mean.outcome - sd.outcome,
ymax = mean.outcome + sd.outcome),
color = "dodgerblue", width = 0.3) +
geom_point(data = dat, aes(x = Condition, y = Outcome),
color = "firebrick", size = 1.2) +
geom_line(data = dat, aes(x = Condition, y = Outcome, group = ID),
color = "firebrick", size = 1.2, alpha = 0.5) +
scale_y_continuous(limits = c(0, max(dat$Outcome)))
Some people are better with ggplot's stat functions and arguments than I am and might do it differently. I prefer to just transform my data first.
set.seed(1)
dat <- data.frame(Condition = c(rep("Placebo",10),rep("Experimental",10)),
Outcome = rnorm(20,15,2),
ID = factor(rep(1:10,2)))
dat.w <- reshape(dat, direction = 'wide', idvar = 'ID', timevar = 'Condition')
means <- colMeans(dat.w[, 2:3])
sds <- apply(dat.w[, 2:3], 2, sd)
ci.l <- means - sds
ci.u <- means + sds
ci.width <- .25
bp <- barplot(means, ylim = c(0,20))
segments(bp, ci.l, bp, ci.u)
segments(bp - ci.width, ci.u, bp + ci.width, ci.u)
segments(bp - ci.width, ci.l, bp + ci.width, ci.l)
segments(x0 = bp[1], x1 = bp[2], y0 = dat.w[, 2], y1 = dat.w[, 3], col = 1:10)
points(c(rep(bp[1], 10), rep(bp[2], 10)), dat$Outcome, col = 1:10, pch = 19)
Here is a method using the transfomations inside ggplot2
ggplot(dat) +
stat_summary(aes(x=Condition, y=Outcome, group=Condition), fun.y="mean", geom="bar") +
stat_summary(aes(x=Condition, y=Outcome, group=Condition), fun.data="mean_se", geom="errorbar", col="green", width=.8, size=2) +
geom_line(aes(x=Condition, y=Outcome, group=ID), col="red")
The image below shows a chart that I created with the code below. I highlighted the missing or overlapping labels. Is there a way to tell ggplot2 to not overlap labels?
week = c(0, 1, 1, 1, 1, 2, 2, 3, 4, 5)
statuses = c('Shipped', 'Shipped', 'Shipped', 'Shipped', 'Not-Shipped', 'Shipped', 'Shipped', 'Shipped', 'Not-Shipped', 'Shipped')
dat <- data.frame(Week = week, Status = statuses)
p <- qplot(factor(Week), data = dat, geom = "bar", fill = factor(Status))
p <- p + geom_bar()
# Below is the most important line, that's the one which displays the value
p <- p + stat_bin(aes(label = ..count..), geom = "text", vjust = -1, size = 3)
p
You can use a variant of the well-known population pyramid.
Some sample data (code inspired by Didzis Elferts' answer):
set.seed(654)
week <- sample(0:9, 3000, rep=TRUE, prob = rchisq(10, df = 3))
status <- factor(rbinom(3000, 1, 0.15), labels = c("Shipped", "Not-Shipped"))
data.df <- data.frame(Week = week, Status = status)
Compute count scores for each week, then convert one category to negative values:
library("plyr")
plot.df <- ddply(data.df, .(Week, Status), nrow)
plot.df$V1 <- ifelse(plot.df$Status == "Shipped",
plot.df$V1, -plot.df$V1)
Draw the plot. Note that the y-axis labels are adapted to show positive values on either side of the baseline.
library("ggplot2")
ggplot(plot.df) +
aes(x = as.factor(Week), y = V1, fill = Status) +
geom_bar(stat = "identity", position = "identity") +
scale_y_continuous(breaks = 100 * -1:5,
labels = 100 * c(1, 0:5)) +
geom_text(aes(y = sign(V1) * max(V1) / 30, label = abs(V1)))
The plot:
For production purposes you'd need to determine the appropriate y-axis tick labels dynamically.
Made new sample data (inspired by code of #agstudy).
week <- sample(0:5,1000,rep=TRUE,prob=c(0.2,0.05,0.15,0.5,0.03,0.1))
statuses <- gl(2,1000,labels=c('Not-Shipped', 'Shipped'))
dat <- data.frame(Week = week, Status = statuses)
Using function ddply() from library plyr made new data frame text.df for labels. Column count contains number of observations in each combination of Week and Status. Then added column ypos that contains cumulative sum of count for each Week plus 15. This will be used for y position. For Not-Shipped ypos replaced with -10.
library(plyr)
text.df<-ddply(dat,.(Week,Status),function(x) data.frame(count=nrow(x)))
text.df<-ddply(text.df,.(Week),transform,ypos=cumsum(count)+15)
text.df$ypos[text.df$Status=="Not-Shipped"]<- -10
Now labels are plotted with geom_text() using new data frame.
ggplot(dat,aes(as.factor(Week),fill=Status))+geom_bar()+
geom_text(data=text.df,aes(x=as.factor(Week),y=ypos,label=count))
One solution to avoid overlaps is to use to dodge position of bars and texts. To avoid missing values you can set ylim. Here an example.
## I create some more realistic data similar to your picture
week <- sample(0:5,1000,rep=TRUE)
statuses <- gl(2,1000,labels=c('Not-Shipped', 'Shipped'))
dat <- data.frame(Week = week, Status = statuses)
## for dodging
dodgewidth <- position_dodge(width=0.9)
## get max y to set ylim
ymax <- max(table(dat$Week,dat$Status))+20
ggplot(dat,aes(x = factor(Week),fill = factor(Status))) +
geom_bar( position = dodgewidth ) +
stat_bin(geom="text", position= dodgewidth, aes( label=..count..),
vjust=-1,size=5)+
ylim(0,ymax)
Based on Didzis plot you could also increase readability by keeping the position on the y axis constant and by colouring the text in the same colour as the legend.
library(ggplot2)
week <- sample(0:5,1000,rep=TRUE,prob=c(0.2,0.05,0.15,0.5,0.03,0.1))
statuses <- gl(2,1000,labels=c('Not-Shipped', 'Shipped'))
dat <- data.frame(Week = week, Status = statuses)
library(plyr)
text.df<-ddply(dat,.(Week,Status),function(x) data.frame(count=nrow(x)))
text.df$ypos[text.df$Status=="Not-Shipped"]<- -15
text.df$ypos[text.df$Status=="Shipped"]<- -55
p <- ggplot(dat,aes(as.factor(Week),fill=Status))+geom_bar()+
geom_text(data=text.df,aes(x=as.factor(Week),y=ypos,label=count),colour=ifelse(text.df$Status=="Not-Shipped","#F8766D","#00BFC4"))