Goodnight,
I'm starting my studies with R and I'm studying the pls library, through the Introduction to the pls Package file.
I'm running the example:
`library(pls)
data(gasoline)
gasTrain <- gasoline[1:50,]
gasTest <- gasoline[51:60,]
gas1 <- plsr(octane ~ NIR, ncomp = 10, data = gasTrain, validation = "LOO")
summary(gas1)
plot(RMSEP(gas1), legendpos = "topright")
plot(gas1, ncomp = 2, asp = 1, line = TRUE)
plot(gas1, plottype = "scores", comps = 1:3)
explvar(gas1)
plot(gas1, "loadings", comps = 1:2, legendpos = "topleft",
+ labels = "numbers", xlab = "nm")
abline(h = 0)`
when I try to run the line
plot(gas1, "loadings", comps = 1:2, legendpos = "topleft", + labels = "numbers", xlab = "nm")
the message appears:
Error: unexpected '=' in: "plot(gas1, "loadings", comps = 1:2, legendpos = "topleft", + labels ="
I can't see where the error is.
I used FormatR (ctrl + shift + A) on the line.
`
plot(
gas1,
"loadings",
comps = 1:2,
legendpos = "topleft",
labels = "numbers",
xlab = "nm"
)
and remove the + sign. Now the line rotates however I get a graph like this. enter image description here.
But in the reference file it is:
enter image description here
How to fix this error?
thank you for the help.
Related
Error in RStudio barplot
I work for a research lab and last worker left without explaining how her RStudio programs work, I have to adapt one to get the data of participants in the month of September, but I get 2 errors, it should be an easy fix but I can't see it.
I have the parameter days:
dias <- c("01","02","05","06","07","08","09","12","13","14","16","19","20","21","22","23","26","27","28","29","30")
and a part that reads data from an excel and then makes a barplot but I get the error:
Error in barplot.default(Volun_citados_dias_mes, ylim = c(0, 100), names.arg = dias, :
incorrect number of names
In this part for the barplot:
jpeg("x.jpeg", width = 800, height = 800)
text(barplot(Volun_citados_dias_mes, ylim = c(0, 100), names.arg = dias, cex.names = 0.9, col = "khaki", xlab = "Días",
ylab = "Voluntarios", main = "Número de voluntarios citados en Septiembre de 2022"),
Volun_citados_dias_mes + 4, labels = round(Volun_citados_dias_mes, 1))
dev.off()
And here when putting that data on an excel i get this other error:
Error in data.frame(dias, Volun_citadosSep) :
arguments imply differing number of rows: 21, 2
write.xlsx(data.frame(dias, Volun_citadosSep), "X:/Cohorte Cantabria/2. PROYECTO/INFORMES/Exito reclutamiento/Asistencia/Septiembre/Tablas/VolunCitadosDiasMes.xlsx", row.names = FALSE)
on.exit(par(opar))
dev.off()
I tried changing that 4 (Volun_citados_dias_mes + 4) to a 21... but not really sure what else to change, i was expecting a graph with at least 2 days added 01 and 02 that are the ones added by now, I prefer fixing this before adding 20 more.
CODE resumed:
#"..." is parts that are omitted
#libraries
library(readxl)
library("stringr")
library("xlsx")
dir <- "**...**"
#days
dias <- c("01","02","05","06","07","08","09","12","13","14","16","19","20","21","22","23","26","27","28","29","30")
#Redcap
df <- file.info(list.files("**...**", pattern = "**...**", full.names = TRUE))
lastFileCallcenter <- rownames(df)[which.max(df$mtime)]
ccList <- read.csv2(lastFileCallcenter, header = TRUE, sep = ",", quote = "\"",
dec = ",", stringsAsFactors = FALSE, encoding = "UTF-8")
colnames(ccList)[[which(str_detect(colnames(ccList), "codigo_registro"))]] <- "codigo_registro"
ccList <- unified_df(ccList)
ccList$codigo_registro <- toupper(ccList$codigo_registro)
ccList$dni_nie <- toupper(ccList$dni_nie)
septiembre_22 <- read.csv2(file.path(dir, "**...**.csv"), header = TRUE, sep = ",",
quote = "\"", dec = ",", stringsAsFactors = FALSE, encoding = "UTF-8")
colnames(septiembre_22)[[which(str_detect(colnames(septiembre_22), "codigo_registro"))]] <- "codigo_registro"
septiembre_22 <- unified_df(septiembre_22)
septiembre_22$codigo_registro <- toupper(septiembre_22$codigo_registro)
septiembre_22$dni_nie <- toupper(septiembre_22$dni_nie)
#-------------------Volunteers days of the month ---------------------------------------------------
septiembre_22_01 <- dim(septiembre_22[which(septiembre_22$fecha_extraccion == "01/09/2022"),])[1] + dim(septiembre_22[which(septiembre_22$fecha_extraccion_vt == "01/09/2022"),])[1]
septiembre_22_02 <- dim(septiembre_22[which(septiembre_22$fecha_extraccion == "02/09/2022"),])[1] + dim(septiembre_22[which(septiembre_22$fecha_extraccion_vt == "02/09/2022"),])[1]
**#...TODO, other days**
Volun_citadosSep <- c(septiembre_22_01, septiembre_22_02,**#...TODO**)
jpeg("x.jpeg", width = 800, height = 800)
text(barplot(Volun_citadosSep, ylim = c(0, 100), names.arg = dias, cex.names = 0.9, col = "khaki", xlab = "Días",
ylab = "Voluntarios", main = "Número de voluntarios citados en Septiembre de 2022"),
Volun_citadosSep + 4, labels = round(Volun_citadosSep, 1))
dev.off()
write.xlsx(data.frame(dias, Volun_citadosSep), "VolunCitadosDiasMes.xlsx", row.names = FALSE)
on.exit(par(opar))
dev.off()
I am trying to run this code for wgcna to relate modules * traits:
weight <- as.data.frame(datTraits[, "weight", drop = FALSE])
names(weight) = "weight"
modNames = substring(names(MEs), 3)
geneModuleMembership = as.data.frame(cor(datExpr, MEs, use = "p"));
MMPvalue = as.data.frame(corPvalueStudent(as.matrix(geneModuleMembership), nSamples));
names(geneModuleMembership) = paste("MM", modNames, sep="");
names(MMPvalue) = paste("p.MM", modNames, sep="");
geneTraitSignificance = as.data.frame(cor(datExpr, weight, use = "p"));
GSPvalue = as.data.frame(corPvalueStudent(as.matrix(geneTraitSignificance), nSamples));
names(geneTraitSignificance) = paste("GS.", names(weight), sep="");
names(GSPvalue) = paste("p.GS.", names(weight), sep="");
##Plotting the graph
module = "plum1"
column = match(module, modNames);
moduleGenes = moduleColors==module;
pdf("plum1.pdf", width = 7, height = 7);
par(mfrow = c(1,1));
verboseScatterplot(abs(geneModuleMembership[moduleGenes, column]),
abs(geneTraitSignificance[moduleGenes, 1]),
xlab = paste("Module Membership in", module, "module"),
ylab = "Gene significance",
main = paste("Module membership vs. gene significance\n"),
cex.main = 1.2, cex.lab = 1.2, cex.axis = 1.2, col = module)
It runs without any error but does not give the scatter plot output. Thank you!
I'm trying to do a plot with a trend line but I'm obtaining this: https://imgur.com/a/xeAI1
How can I fix the trend line to the plot??
Thanks in advance
library("igraph")
tfile<-tempfile()
download.file("http://pdg.cnb.uam.es/pazos/tmp/Yeast_int.txt", tfile)
datosraw <- subset(read.delim(tfile, sep="\t", header=F, stringsAsFactors = F), !is.na(V3) & V3!="" & V3!="METHOD")
names(datosraw)<-c("orf1","orf2","method")
datos<-split(datosraw,datosraw$method)
df.y2h <- graph.data.frame(d = datos$Y2H[1:5125,c(1,2)], directed = FALSE)
plot_degree_distribution = function(graph) {
# calculate degree
d = degree(graph, mode = "all")
dd = degree.distribution(graph, mode = "all", cumulative = FALSE)
degree = 1:max(d)
probability = dd[-1]
# delete blank values
nonzero.position = which(probability != 0)
probability = probability[nonzero.position]
degree = degree[nonzero.position]
# plot
plot(probability ~ degree, log = "xy", xlab = "Degree (log)", ylab = "Probability (log)",
col = 1, main = "Degree Distribution")
mod <- (lm(log10(probability) ~ log10(degree)))
abline((mod), col="red")
coef(mod)[2]
}
plot_degree_distribution(df.y2h)
I have a question about the par function in R.
I want to change the color and/or width of a line in a graph with par function. (I am using par function because the gaps.plot command below does not allow "col" option to be included. The gaps.plot command is used after the synth command).
So, I used the following command. But I noticed that the lines of the BOX are changed rather than the lines of the GRAPHS.
synth1<-read.csv(file="C:\\Users\\Research\\R\\synthinR_v4.csv",header=TRUE)
attach(synth1)
library("Synth")
dataprep.out34 <- dataprep(foo = synth1, predictors = c("lncdsales", "md1", "md2","md3", "md4", "md5", "md6", "md7", "md8", "md9", "md10", "md11", "yd1", "yd2", "yd3", "yd4", "yd5", "yd6", "yd7", "yd8"), predictors.op = "mean", time.predictors.prior = -13:1, dependent = "lndigital", unit.variable = "artistalbumcode", time.variable = "release", treatment.identifier = 34, controls.identifier = c(1:33, 35:49), time.optimize.ssr = -13:1, time.plot = -13:25)
synth.out34 <- synth(data.prep.obj = dataprep.out34, method = "BFGS")
par(lwd = 2, col="#cccccc")
gaps.plot(synth.res = synth.out34, dataprep.res = dataprep.out34, Ylab = " Log Digital Sales ", Xlab = "Release", Ylim = c(-7, 7) , Main = NA)
Does anyone know how to fix this problem??
Thank you in advance for your willingness to help. I greatly appreciate it!
The col argument to par sets the default plotting colour (i.e. when col is not explicitly specified in plotting calls), but unfortunately col = "black" is hard-coded into the source of gaps.plot.
You can make a modified copy of the function by either (1) viewing the source (F2 in RStudio, or just executing gaps.plot), editing it and assigning it to a new object, or (2) doing something like the following:
gaps.plot2 <- eval(parse(text=gsub('col = "black"', 'col = "red"',
deparse(Synth:::gaps.plot))))
and then using gaps.plot2 as you would use gaps.plot:
gaps.plot2(synth.res = synth.out34, dataprep.res = dataprep.out34,
Ylab = " Log Digital Sales ", Xlab = "Release", Ylim = c(-7, 7) ,
Main = NA)
Alter the lwd similarly. For example to make lines red and have width of 3, use nested gsub calls like this:
gaps.plot2 <- eval(parse(text=gsub('lwd = 2', 'lwd = 3',
gsub('col = "black"', 'col = "red"',
deparse(Synth:::gaps.plot)))))
I'm trying to save several xyplots created with a "for" loop in R and I'm not able to get complete pdf files (all files have the same size and I can't open them) if I execute the following loop:
for (i in 1:length(gases.names)) {
# Set ylim;
r_y <- round(range(ratio.cal[,i][ratio.cal[,i]<999], na.rm = T), digits = 1);
r_y <- c(r_y[1]-0.1, r_y[2]+0.1);
outputfile <- paste (path, "/cal_ratio_",gases.names[i], ".pdf", sep="");
dev.new();
xyplot(ratio.cal[,i] ~ data.GC.all$data.time, groups = data.vial, panel =
panel.superpose, xlab = "Date", ylab = gases.names[i], xaxt="n", ylim = r_y);
savePlot(filename = outputfile, type = 'pdf', device = dev.cur());
dev.off();
}
(a previous version was using trellis.device() instead of dev.new() + savePlot())
Do you know why I can't get good pdf files? If I do it "manually" it works... Any idea?
use pdf directly
for (i in seq_along(gases.names)) {
# Set ylim
r_y <- round(range(ratio.cal[,i][ratio.cal[,i]<999], na.rm = T), digits = 1)
r_y <- c(r_y[1]-0.1, r_y[2]+0.1)
outputfile <- paste (path, "/cal_ratio_",gases.names[i], ".pdf", sep="")
pdf(file = outputfile, width = 7, height = 7)
print(xyplot(ratio.cal[,i] ~ data.GC.all$data.time, groups = data.vial,
panel = panel.superpose, xlab = "Date", ylab = gases.names[i],
xaxt="n", ylim = r_y))
dev.off()
}