making 2 box plots from the same data frame in R - r

I want to make a 2 box plots with y being weight and x being the before and after. so two different boxplot will be displayed at the same time.
`rats_before = data.frame(
rat_num = paste0(rep("rat number",200),1:200),
weight = rweibull(200,shape= 10,scale = 20))
rats_after = data.frame(
rat_num = paste0(rep("rat number",200),1:200),
weight = rweibull(200,shape= 9,scale = 21))
rats = merge(rats_before,rats_after, by = c("rat_num"))`
i know the next part is not even close but it will give you a idea of what im trying to do.
rat_boxplot = qplot(y = weight, x = (rats_after, rats_before), geom = "boxplot", data = rats)

Or, if you want to do this in base R -
rats_before = data.frame(
rat_num = paste0(rep("rat number",200),1:200),
weight = rweibull(200,shape= 10,scale = 20))
rats_after = data.frame(
rat_num = paste0(rep("rat number",200),1:200),
weight = rweibull(200,shape= 9,scale = 21))
rats <- rbind(rats_before, rats_after)
rats$type <- c(rep("before", nrow(rats_before)), rep("after", nrow(rats_after)))
rats$type <- factor(rats$type)
rats$type <- relevel(rats$type, ref = 2)
boxplot(weight ~ type, data = rats)

You can add a column to each df ans userbind which will bind the rows of the two df instead of merge you can use. Then you simply have to use the aes of a ggplot.
rats_before$condition = "before"
rats_after$condition = "after"
rats = rbind(rats_before,rats_after)
ggplot(rats)+geom_boxplot(aes(condition,weight))
Hope I understood your question.
Tom

Related

Interactively identify 3D object in rgl plot

I want to identify 3d cylinders in an rgl plot to obtain one attribute of the nearest / selected cylinder. I tried using labels to simply spell out the attribute, but I work on data with more than 10.000 cylinders. Therefore, it gets so crowded that the labels are unreadable and it takes ages to render.
I tried to understand the documentation of rgl and I guess the solution to my issue is selecting the cylinder in the plot manually. I believe the function selectpoints3d() is probably the way to go. I believe it returns all vertices within the drawn rectangle, but I don't know how to go back to the cylinder data? I could calculate which cylinder is closest to the mean of the selected vertices, but this seems like a "quick & dirty" way to do the job.
Is there a better way to go? I noticed the argument value=FALSE to get the indices only, but I don't know how to go back to the cylinders.
Here is some dummy data and my code:
# dummy data
cylinder <- data.frame(
start_X = rep(1:3, 2)*2,
start_Y = rep(1:2, each = 3)*2,
start_Z = 0,
end_X = rep(1:3, 2)*2 + round(runif(6, -1, 1), 2),
end_Y = rep(1:2, each = 3)*2 + round(runif(6, -1, 1), 2),
end_Z = 0.5,
radius = 0.25,
attribute = sample(letters[1:6], 6)
)
# calculate centers
cylinder$center_X <- rowMeans(cylinder[,c("start_X", "end_X")])
cylinder$center_Y <- rowMeans(cylinder[,c("start_Y", "end_Y")])
cylinder$center_Z <- rowMeans(cylinder[,c("start_Z", "end_Z")])
# create cylinders
cylinder_list <- list()
for (i in 1:nrow(cylinder)) {
cylinder_list[[i]] <- cylinder3d(
center = cbind(
c(cylinder$start_X[i], cylinder$end_X[i]),
c(cylinder$start_Y[i], cylinder$end_Y[i]),
c(cylinder$start_Z[i], cylinder$end_Z[i])),
radius = cylinder$radius[i],
closed = -2)
}
# plot cylinders
open3d()
par3d()
shade3d(shapelist3d(cylinder_list, plot = FALSE), col = "blue")
text3d(cylinder$center_X+0.5, cylinder$center_Y+0.5, cylinder$center_Z+0.5, cylinder$attribute, color="red")
# get attribute
nearby <- selectpoints3d(value=TRUE, button = "right")
nearby <- colMeans(nearby)
cylinder$dist <- sqrt(
(nearby["x"]-cylinder$center_X)**2 +
(nearby["y"]-cylinder$center_Y)**2 +
(nearby["z"]-cylinder$center_Z)**2)
cylinder$attribute[which.min(cylinder$dist)]
If you call selectpoints3d(value = FALSE), you get two columns. The first column is the id of the object that was found. Your cylinders get two ids each. One way to mark the cylinders is to use "tags". For example, this modification of your code:
# dummy data
cylinder <- data.frame(
start_X = rep(1:3, 2)*2,
start_Y = rep(1:2, each = 3)*2,
start_Z = 0,
end_X = rep(1:3, 2)*2 + round(runif(6, -1, 1), 2),
end_Y = rep(1:2, each = 3)*2 + round(runif(6, -1, 1), 2),
end_Z = 0.5,
radius = 0.25,
attribute = sample(letters[1:6], 6)
)
# calculate centers
cylinder$center_X <- rowMeans(cylinder[,c("start_X", "end_X")])
cylinder$center_Y <- rowMeans(cylinder[,c("start_Y", "end_Y")])
cylinder$center_Z <- rowMeans(cylinder[,c("start_Z", "end_Z")])
# create cylinders
cylinder_list <- list()
for (i in 1:nrow(cylinder)) {
cylinder_list[[i]] <- cylinder3d(
center = cbind(
c(cylinder$start_X[i], cylinder$end_X[i]),
c(cylinder$start_Y[i], cylinder$end_Y[i]),
c(cylinder$start_Z[i], cylinder$end_Z[i])),
radius = cylinder$radius[i],
closed = -2)
# Add tag here:
cylinder_list[[i]]$material$tag <- cylinder$attribute[i]
}
# plot cylinders
open3d()
par3d()
shade3d(shapelist3d(cylinder_list, plot = FALSE), col = "blue")
text3d(cylinder$center_X+0.5, cylinder$center_Y+0.5, cylinder$center_Z+0.5, cylinder$attribute, color="red")
# Don't get values, get the ids
nearby <- selectpoints3d(value=FALSE, button = "right", closest = FALSE)
ids <- nearby[, "id"]
# Convert them to tags. If you select one of the labels, you'll get
# a blank in the list of tags, because we didn't tag the text.
unique(tagged3d(id = ids))
When I was trying this, I found that using closest = TRUE in selectpoints3d seemed to get too many ids; there may be a bug there.

How to plot multiple lines in radar chart using split in plotly

I have tried using split trace with scatterpolar and it seems to partly work but can't get it to plot the values for all 10 variables. So I want each row (identified by "ean") be plotted as its own line using the values from X1 to X10.
library(tidyverse)
library(vroom)
library(plotly)
types <- rep(times = 10, list(
col_integer(f = stats::runif,
min = 1,
max = 5)))
products = bind_cols(
tibble(ean = sample.int(1e9, 25)),
tibble(kategori = sample(c("kat1", "kat2", "kat3"), 25, replace = TRUE)),
gen_tbl(25, 10, col_types = types)
)
plot_ly(
products,
type = 'scatterpolar',
mode = "lines+markers",
r = ~X1,
theta = ~"X1",
split = ~ean
)
How can I get plotly to plot all variables in the radarchart (X1-X10)? Usually I would select the columns with X1:X10 but I can't do that here (I think it has to do with that ~ is used to select variable here).
So I want the result to look something like this (but I only show lines and not filled polygons and I would have more products). So in the end 25 products is a lot but I am connecting it so that the user can select the diagrams it wants to show.
In plotly it's convenient to use data in long format - see ?gather.
Please check the following:
library(dplyr)
library(tidyr)
library(vroom)
library(plotly)
types <- rep(times = 10, list(
col_integer(f = stats::runif,
min = 1,
max = 5)))
products = bind_cols(
tibble(ean = sample.int(1e9, 25)),
tibble(kategori = sample(c("kat1", "kat2", "kat3"), 25, replace = TRUE)),
gen_tbl(25, 10, col_types = types)
)
products_long <- gather(products, "key", "value", -ean, -kategori)
plot_ly(
products_long,
type = 'scatterpolar',
mode = "lines+markers",
r = ~value,
theta = ~key,
split = ~ean
)

How to programmatically determine the column indices of principal components using FactoMineR package?

Given a data frame containing mixed variables (i.e. both categorical and continuous) like,
digits = 0:9
# set seed for reproducibility
set.seed(17)
# function to create random string
createRandString <- function(n = 5000) {
a <- do.call(paste0, replicate(5, sample(LETTERS, n, TRUE), FALSE))
paste0(a, sprintf("%04d", sample(9999, n, TRUE)), sample(LETTERS, n, TRUE))
}
df <- data.frame(ID=c(1:10), name=sample(letters[1:10]),
studLoc=sample(createRandString(10)),
finalmark=sample(c(0:100),10),
subj1mark=sample(c(0:100),10),subj2mark=sample(c(0:100),10)
)
I perform unsupervised feature selection using the package FactoMineR
df.princomp <- FactoMineR::FAMD(df, graph = FALSE)
The variable df.princomp is a list.
Thereafter, to visualize the principal components I use
fviz_screeplot() and fviz_contrib() like,
#library(factoextra)
factoextra::fviz_screeplot(df.princomp, addlabels = TRUE,
barfill = "gray", barcolor = "black",
ylim = c(0, 50), xlab = "Principal Component",
ylab = "Percentage of explained variance",
main = "Principal Component (PC) for mixed variables")
factoextra::fviz_contrib(df.princomp, choice = "var",
axes = 1, top = 10, sort.val = c("desc"))
which gives the following Fig1
and Fig2
Explanation of Fig1: The Fig1 is a scree plot. A Scree Plot is a simple line segment plot that shows the fraction of total variance in the data as explained or represented by each Principal Component (PC). So we can see the first three PCs collectively are responsible for 43.8% of total variance. The question now naturally arises, "What are these variables?". This I have shown in Fig2.
Explanation of Fig2: This figure visualizes the contribution of rows/columns from the results of Principal Component Analysis (PCA). From here I can see the variables, name, studLoc and finalMark are the most important variables that can be used for further analysis.
Further Analysis- where I'm stuck at: To derive the contribution of the aforementioned variables name, studLoc, finalMark. I use the principal component variable df.princomp (see above) like df.princomp$quanti.var$contrib[,4]and df.princomp$quali.var$contrib[,2:3].
I've to manually specify the column indices [,2:3] and [,4].
What I want: I want to know how to do dynamic column index assignment, such that I do not have to manually code the column index [,2:3] in the list df.princomp?
I've already looked at the following similar questions 1, 2, 3 and 4 but cannot find my solution? Any help or suggestions to solve this problem will be helpful.
Not sure if my interpretation of your question is correct, apologies if not. From what I gather you are using PCA as an initial tool to show you what variables are the most important in explaining the dataset. You then want to go back to your original data, select these variables quickly without manual coding each time, and use them for some other analysis.
If this is correct then I have saved the data from the contribution plot, filtered out the variables that have the greatest contribution, and used that result to create a new data frame with these variables alone.
digits = 0:9
# set seed for reproducibility
set.seed(17)
# function to create random string
createRandString <- function(n = 5000) {
a <- do.call(paste0, replicate(5, sample(LETTERS, n, TRUE), FALSE))
paste0(a, sprintf("%04d", sample(9999, n, TRUE)), sample(LETTERS, n, TRUE))
}
df <- data.frame(ID=c(1:10), name=sample(letters[1:10]),
studLoc=sample(createRandString(10)),
finalmark=sample(c(0:100),10),
subj1mark=sample(c(0:100),10),subj2mark=sample(c(0:100),10)
)
df.princomp <- FactoMineR::FAMD(df, graph = FALSE)
factoextra::fviz_screeplot(df.princomp, addlabels = TRUE,
barfill = "gray", barcolor = "black",
ylim = c(0, 50), xlab = "Principal Component",
ylab = "Percentage of explained variance",
main = "Principal Component (PC) for mixed variables")
#find the top contributing variables to the overall variation in the dataset
#here I am choosing the top 10 variables (although we only have 6 in our df).
#note you can specify which axes you want to look at with axes=, you can even do axes=c(1,2)
f<-factoextra::fviz_contrib(df.princomp, choice = "var",
axes = c(1), top = 10, sort.val = c("desc"))
#save data from contribution plot
dat<-f$data
#filter out ID's that are higher than, say, 20
r<-rownames(dat[dat$contrib>20,])
#extract these from your original data frame into a new data frame for further analysis
new<-df[r]
new
#finalmark name studLoc
#1 53 b POTYQ0002N
#2 73 i LWMTW1195I
#3 95 d VTUGO1685F
#4 39 f YCGGS5755N
#5 97 c GOSWE3283C
#6 58 g APBQD6181U
#7 67 a VUJOG1460V
#8 64 h YXOGP1897F
#9 15 j NFUOB6042V
#10 81 e QYTHG0783G
Based on your comment, where you said you wanted to 'Find variables with value greater than 5 in Dim.1 AND Dim.2 and save these variables to a new data frame', I would do this:
#top contributors to both Dim 1 and 2
f<-factoextra::fviz_contrib(df.princomp, choice = "var",
axes = c(1,2), top = 10, sort.val = c("desc"))
#save data from contribution plot
dat<-f$data
#filter out ID's that are higher than 5
r<-rownames(dat[dat$contrib>5,])
#extract these from your original data frame into a new data frame for further analysis
new<-df[r]
new
(This keeps all the original variables in our new data frame since they all contributed more than 5% to the total variance)
There are a lot of ways to extract contributions of individual variables to PCs. For numeric input, one can run a PCA with prcomp and look at $rotation (I spoke to soon and forgot you've got factors here so prcomp won't work directly). Since you are using factoextra::fviz_contrib, it makes sense to check how that function extracts this information under the hood. Key factoextra::fviz_contrib and read the function:
> factoextra::fviz_contrib
function (X, choice = c("row", "col", "var", "ind", "quanti.var",
"quali.var", "group", "partial.axes"), axes = 1, fill = "steelblue",
color = "steelblue", sort.val = c("desc", "asc", "none"),
top = Inf, xtickslab.rt = 45, ggtheme = theme_minimal(),
...)
{
sort.val <- match.arg(sort.val)
choice = match.arg(choice)
title <- .build_title(choice[1], "Contribution", axes)
dd <- facto_summarize(X, element = choice, result = "contrib",
axes = axes)
contrib <- dd$contrib
names(contrib) <- rownames(dd)
theo_contrib <- 100/length(contrib)
if (length(axes) > 1) {
eig <- get_eigenvalue(X)[axes, 1]
theo_contrib <- sum(theo_contrib * eig)/sum(eig)
}
df <- data.frame(name = factor(names(contrib), levels = names(contrib)),
contrib = contrib)
if (choice == "quanti.var") {
df$Groups <- .get_quanti_var_groups(X)
if (missing(fill))
fill <- "Groups"
if (missing(color))
color <- "Groups"
}
p <- ggpubr::ggbarplot(df, x = "name", y = "contrib", fill = fill,
color = color, sort.val = sort.val, top = top, main = title,
xlab = FALSE, ylab = "Contributions (%)", xtickslab.rt = xtickslab.rt,
ggtheme = ggtheme, sort.by.groups = FALSE, ...) + geom_hline(yintercept = theo_contrib,
linetype = 2, color = "red")
p
}
<environment: namespace:factoextra>
So it's really just calling facto_summarize from the same package. By analogy you can do the same thing, simply call:
> dd <- factoextra::facto_summarize(df.princomp, element = "var", result = "contrib", axes = 1)
> dd
name contrib
ID ID 0.9924561
finalmark finalmark 21.4149175
subj1mark subj1mark 7.1874438
subj2mark subj2mark 16.6831560
name name 26.8610132
studLoc studLoc 26.8610132
And that's the table corresponding to your figure 2. For PC2 use axes = 2 and so on.
Regarding "how to programmatically determine the column indices of the PCs", I'm not 100% sure I understand what you want, but if you just want to say for column "finalmark", grab its contribution to PC3 you can do the following:
library(tidyverse)
# make a tidy table of all column names in the original df with their contributions to all PCs
contribution_df <- map_df(set_names(1:5), ~factoextra::facto_summarize(df.princomp, element = "var", result = "contrib", axes = .x), .id = "PC")
# get the contribution of column 'finalmark' by name
contribution_df %>%
filter(name == "finalmark")
# get the contribution of column 'finalmark' to PC3
contribution_df %>%
filter(name == "finalmark" & PC == 3)
# or, just the numeric value of contribution
filter(contribution_df, name == "finalmark" & PC == 3)$contrib
BTW I think ID in your example is treated as numeric instead of factor, but since it's just an example I'm not bothering with it.

Why the labels are not arranged properly in `stars()` in R?

I am using following function to generate stars(), one the visualization technique for multivariate data.
library(randomNames)
set.seed(3)
Name = randomNames(50, which.names = 'first')
height = sample(160:180, 50, replace = TRUE)
weight = sample(45:85, 50, replace = TRUE)
tumour_size = runif(50, 0,1)
df = data.frame(Name, height, weight, tumour_size, rnorm(50, 10,3))
stars(df,labels = Name)
But, I get the output like this:
How to align the names exactly below the stars?
Use option flip.labels=FALSE.
stars(df, labels = Name, flip.labels = FALSE)
Result

Skip empty panel using lattice package, R programming

I want to skip a empty panel using lattice package in R.
set.seed(1)
df1 <- data.frame("treatment" = c(rep("A",16),rep("B",16),rep("C",16)),
"disease_type" = c(rep("1",8),rep("2",8)),
"days_after_application" = rep(c(rep("10-24",4),rep("24-48",4)),6),
"severity" = rnorm(48, mean = 80, sd = 5))
df1[(df1$disease_type == "2" & df1$days_after_application == "24-48"),"severity"] <- NA
library(lattice)
figure1 <- bwplot(treatment~severity|days_after_application+disease_type,
data = df1,layout = c(2,2),
strip = strip.custom(strip.names = TRUE))
jpeg("figure1.jpeg")
print(figure1)
dev.off()
Here is what I get
My question is how I can remove/skip empty panel in the top right WITHOUT changing layout?
I have tried following code. However, it doesn't work.
figure2 <- bwplot(treatment~severity|days_after_application+disease_type,
data = df1,layout = c(2,2),
strip = strip.custom(strip.names = TRUE),
skip = c(FALSE,FALSE,FALSE,TRUE))
jpeg("figure2.jpeg")
print(figure2)
dev.off()
Here is what I got
I also tried following codes. But it is not what I want since I do want 2 levels strips.
df1[(df1$disease_type == "2" & df1$days_after_application == "24-48"),] <- NA
bwplot(treatment~severity|interaction(days_after_application,disease_type),
data = df1,layout = c(2,2),
strip = strip.custom(strip.names = TRUE))
Thank you!
Get help from a Professor in Temple University.
Here is his solution:
figure4 <- bwplot(treatment~severity|days_after_application+disease_type,
data = df1,layout = c(2,2),
strip = strip.custom(strip.names = TRUE),
skip = c(FALSE,FALSE,FALSE,TRUE),
scales=list(alternating=FALSE), ## keep x-scale on bottom
between=list(x=1, y=1)) ## space between panels
pdf("figure4%03d.pdf",onefile = FALSE) ## force two pages in file.
print(figure4)
dev.off()

Resources