Loop with a defined ggplot function over multiple dataframes
You can create multiple ggplots in a loop with predifined function myplot() as follows:
list <- c("df1","df2","df3") #just one character vector as the titles are the same as the names of the data frames
myplot <- function(data, title){
ggplot(data, aes(x = x, y = y)) +
geom_point(color="grey") +
labs(title = title)
}
for(i in list){
print(myplot(get(i), i))
}
If you wanna work with 2 vectors giving the names if the data frames and of the titles you can do the following:
list <- c("df1","df2","df3")
titles <- c("Title 1","Plot 2","gg3")
myplot <- function(data, title){
ggplot(data, aes(x = x, y = y)) +
geom_point(color="grey") +
labs(title = title)
}
for(i in seq_along(list)){ #here could also be seq_along(titles) as they a re of the same length
print(myplot(get(list[i]), titles[i]))
}
Ggplot over multiple dataframes with loops
Your problem wasn't in the iteration over the list of dataframes, it was in the use of b1 within the annotate(). Here, I've created a new dataframe within each loop, and called the column name specifically. There is probably a nicer way of doing this, though. Also, the ggsave() needed to call the names of the items in the list, specifically.
library(tidyverse)
#Create dataframes(In this example n = 3)
df_1 <- data.frame(a1 = 1:1000,
b1 = 1:1000)
df_2 <- data.frame(a1 = 1:1000,
b1 = 1:1000)
df_3 <- data.frame(a1 = 1:1000,
b1 = 1:1000)
##Store dataframes in list
example.list<-lapply(1:3, function(x) eval(parse(text=paste0("df_", x)))) #In order to store all datasets in one list using their name
names(example.list)<-lapply(1:3, function(x) paste0("df_", x))
#Graph and save for each dataframe
for (i in 1:length(example.list)){
df_i <- example.list[[i]]
benp <-
df_i %>%
ggplot(aes(x=b1)) +
geom_histogram(fill="steelblue", aes(y=..density.., alpha=..count..), bins=60) +
labs(title="Beneficios", subtitle="") + ylab("Densidad") +
xlab("Beneficios ($millones)") +
geom_vline(aes(xintercept=mean(b1)), color="red4",linetype="dashed") +
theme(legend.position = "none") +
annotate("text", x= mean(df_i$b1), y=0, label=round(mean(df_i$b1), digits = 2),
colour="red4", size=3.5, vjust=-1.5, hjust=-0.5)
ggsave(benp, file=paste0(names(example.list)[i],"_histogram.png"))
}
How do you use loop in R with ggpie function and save a filename after the dataframe?
This works for me
library(tibble)
library(dplyr)
library(ggpubr)
DZmix_SC1 <- tibble(
Sample_ID = rep('SC1_18', 3),
Potential_Sources = c('Uintas', 'Sierra Madre', 'CMB'),
Relative_Contribution = c(0,22,78),
Metric = rep('KV', 3)
)
DZmix_5_SC <- tibble(
Sample_ID = rep('5-SC_18', 3),
Potential_Sources = c('Uintas', 'Sierra Madre', 'CMB'),
Relative_Contribution = c(0,29,71),
Metric = rep('KV', 3)
)
DZmix_PL3 <- tibble(
Sample_ID = rep('PL3_18', 3),
Potential_Sources = c('Uintas', 'Sierra Madre', 'CMB'),
Relative_Contribution = c(69,0,31),
Metric = rep('KV', 3)
)
Sample_list <- c("DZmix_SC1", "DZmix_5_SC", "DZmix_PL3")
DZpie.fn <- function(df,title) {
df <- df %>%
mutate(Relative_Contribution = round(Relative_Contribution,1)) %>%
arrange(desc(Potential_Sources))
ggpie(df, "Relative_Contribution", label = "Relative_Contribution",
fill = "Potential_Sources", color = "white", size = 1.5,
palette = c("#636363", "#cccccc", "#969696"),
lab.pos = c("in"),
lab.font = c(0, "bold", "black")) +
theme(legend.position = "none",
panel.background = element_rect(fill = "transparent"),
plot.background = element_rect(fill = "transparent", color = NA))
}
for(i in Sample_list){
print(DZpie.fn(get(i), i))
}
Your method is actually correct. You just miss placed + before lab.pos = c("in").
Then you can save images using
for (i in Sample_list){
ggsave(DZpie.fn(get(i), i), filename=paste0("temp/",i,".png"))
}
Or equivalently but without for loop
purrr::walk(Sample_list, function(name) ggsave(DZpie.fn(get(name), name),
filename=paste0("temp/",name,".png")))
loop over dataframes in ggplot2
The usual way to iterate over data.frames (which are just regularly organized lists) is with lapply:
df1 <- data.frame(date = as.Date(10*365*rbeta(100, .5, .1)),group="a")
df2 <- data.frame(date = as.Date(10*365*rbeta(50, .1, .5)),group="b")
df3 <- data.frame(date = as.Date(10*365*rbeta(25, 3,3)),group="c")
dfrmL <- list(df1,df2,df3)
lapply(dfrmL, NROW)
[[1]]
[1] 100
[[2]]
[1] 50
[[3]]
[1] 25
In the case of producing a list of ggplot-objects I would imagine that the Hadley-method would instead be to use llply, but I'm not a skilled plyr-user, so let me suggest this totally untested code template:
plts <- lapply(dfrmL, function(df) qplot(qplot(data= df,
V1, reorder(V2,V3), color = V3) +
coord_flip()
)
# you may need to explicitly print() or plot() the plots as stated in the R-FAQ.
lapply(plts, print)
Create ggplot multiple graphs dynamically with loop in R
You can create a function which includes the y variable you want to plot. Then it becomes relatively simple to create a for loop to cycle through multiple y variable options or you could use a function from purrr. Now included the loop, and I've had to go down the route of quoted variables names as @stefan explained.
library(ggplot2)
library(purrr)
gg_fun <- function(y_var){
Forecast_Monthly_Visits_FR_Graph <-
ggplot(data=Actual_Forecast_Monthly_France, aes(x=Date, y=!!sym(y_var), group=Type, linetype = factor(Type) , show.legend = FALSE)) +
geom_line(aes(color=Type)) +
geom_point(size = 0.5) +
geom_text(aes(label=round(Visits)), size = 3) +
theme(axis.text.x = element_text(angle = 90)) +
labs(title = y_var) +
theme(plot.title = element_text(hjust = 0.5)) +
scale_color_manual(values= c("#03a623", "#030063", "#ffaad7", "#b6b6b6"))
return(Forecast_Monthly_Visits_FR_Graph)
}
gg <- map(c("Visits", "Sales"), gg_fun)
gg[[1]]
gg[[2]]
Created on 2022-09-13 with reprex v2.0.2
data
Date <- as.Date(c('2022-01-01','2022-01-02','2022-01-03','2022-01-01','2022-01-02','2022-01-03'))
Type <- c("Actual", "Actual", "Actual", "Forecast", "Forecast", "Forecast")
Visits <- c(67398,63398,61398,53422,72726,92822)
Sales <- c(17398,23398,41398,12422,33726,53822)
Actual_Forecast_Monthly_France <- data.frame(Date , Type , Visits, Sales)
Created on 2022-09-13 with reprex v2.0.2
How to index a dataframe for using ggplot in a loop
(Up front: the reason that your plots are all identical is due to ggplot's "lazy" evaluation of code. See my #2 below, where I identify that the data[,i] is evaluated when you try to plot the data, at which point i is 4, the last pass in the for loop.)
It's generally preferred/recommended to use
data.frames instead of matrices or vectors (as you're doing here). It gives a bit more power and control.data <- data.frame(a,b,c,d,time)Also, I tend to prefer
lapplytofor-loops andlists, for various (some subjective) reasons. Ultimately, the issue you're having is thatggplot2is evaluating the data lazily, soplotsis a list with four plots that make reference toi... and that is realized when you try to plot them all, at which pointiis 4 (from the last pass through the loop). One benefit of usinglapplyis that theireferenced is a local-only (inside of the anon-func) version ofithat is preserved as you would expect.plots <- lapply(names(data)[1:4],
function(nm) ggplot(data, aes(x = time, y = .data[[nm]])) + geom_line())
gridExtra::grid.arrange(plots[[1]], plots[[2]])
I also prefer
patchworktogridExtra, mostly because it makes more-customized layouts a bit more intuitive, plus adds functionality such as axis-alignment, shared legends, shared titles, etc. (None of those other features are demonstrated here.)library(patchwork)
plots[[1]] / plots[[2]] # same plot
plots[[1]] + plots[[2]] # side-by-side instead of top/bottom
(plots[[1]] + plots[[2]]) / (plots[[3]] + plots[[4]]) # gridUltimately, though, I suggest that facets can be useful and very powerful. For this, we need to melt/pivot the data into a "long format" so that the column names
a-bare actually in one column.reshape2::melt(data, id.vars = "time") |>
ggplot(aes(time, value)) +
geom_line() +
facet_grid(variable ~ ., scales = "free_y")
I assumed the preference for independent (free) y-scales, ergo the
scales="free_y". Try it without if you want to see the options. (There are alsoscales="free_x"andscales="free"(both).)To see what I mean by "long" format:
reshape2::melt(data, id.vars = "time")
# time variable value
# 1 1 a 1
# 2 2 a 2
# 3 3 a 3
# 4 4 a 4
# 5 1 b 5
# 6 2 b 6
# 7 3 b 7
# 8 4 b 8
# 9 1 c 9
# 10 2 c 10
# 11 3 c 11
# 12 4 c 12
# 13 1 d 13
# 14 2 d 14
# 15 3 d 15
# 16 4 d 16This can also be done with
tidyr::pivot_longer(data, -time), albeit thevariablename is nowname. For this use, there is no advantage toreshape2::meltortidyr::pivot_longer; there are opportunities for significantly more complex pivoting in the latter, not relevant with this data.
Data
data <- structure(list(a = c(1, 2, 3, 4), b = c(5, 6, 7, 8), c = c(9, 10, 11, 12), d = c(13, 14, 15, 16), time = c(1, 2, 3, 4)), class = "data.frame", row.names = c(NA, -4L))
ggplot2: output multiple plots by looping
Following this answer:
library(ggplot2)
point1 <- c(1,2)
point2 <- c(2,2)
points <-as.data.frame(rbind(point1,point2))
point_plots_list <- vector('list', ncol(points))
point_plots_list <- list()
for (i in 1:nrow(points)) {
message(i)
point_plots_list[[i]] <- local({
i <- i
p <- ggplot(data = points) +
geom_point(aes(x = points[i, 1], y = points[i, 2])) +
xlim(-3, 3) +
ylim(-3, 3) +
theme_bw()
})
}
#> 1
#> 2
point_plots_list
#> [[1]]
#>
#> [[2]]
Using lapply instead of a for loop and displaying plots with ggarrange or multiplot:
library(ggplot2)
library(ggpubr)
point1 <- c(1, 2)
point2 <- c(2, 2)
points <- as.data.frame(rbind(point1, point2))
plot_data <- function(data) {
ggplot(data) +
geom_point(aes(x = data[, 1], y = data[, 2])) +
xlim(-3, 3) +
ylim(-3, 3) +
theme_bw()
}
myplots <- list()
myplots <- lapply(1:nrow(points), function(i) plot_data(points[i, ]))
ggarrange(myplots[[1]], myplots[[2]],
labels = c("A", "B"),
ncol = 2, nrow = 1)
source("http://peterhaschke.com/Code/multiplot.R") #load multiplot function
multiplot(plotlist = myplots, cols = 2)
#> Loading required package: grid
Created on 2021-04-09 by the reprex package (v0.3.0)
Looping through a list of dataframes and saving individual graphs for each
What if you facet_wrap?
Creating df from your data...
ID <- c(1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027,
1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027,
1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027,
1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027,
1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027, 1027)
Week = 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, 51, 52, 53, 54, 55, 56, 57,
58, 59, 60, 61, 62, 63, 64)
MDD_PSR = c(NA, NA, NA, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)
ADHD_PSR = c(NA, NA, NA, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA)
GAD_PSR = c(NA, NA, NA, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)
b <- data.frame(ID,Week, MDD_PSR,ADHD_PSR,GAD_PSR)
ID <- c(1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038,
1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038,
1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038,
1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038,
1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038,
1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038, 1038,
1038, 1038, 1038, 1038, 1038)
Week <- 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, 51,
52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64)
MDD_PSR <- c(NA,2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 6, 6, 6, 6, 6, 6, 5, 5, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA)
ADHD_PSR <- c(NA, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA)
GAD_PSR <- c(NA, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2,
2, 2, 2, 2, 2, 2, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)
c <- data.frame(ID,Week, MDD_PSR,ADHD_PSR,GAD_PSR)
f <- rbind.data.frame(b,c)
Getting the graphs to show up next to each other
c_plot <- f %>%
group_by(ID) %>%
gather(key = "Module", value = "PSR", -Week, -ID)
ggplot(data = c_plot , aes(x = Week, y = PSR)) +
geom_line(aes(color = Module, linetype = Module)) +
scale_color_manual(values = c("yellow4", "blue", "darkred")) +
scale_linetype_manual(values = c("solid","twodash", "solid")) +
ylim(1, 6)+
facet_wrap(.~ID)
Alternatively...This gets the error out of your code
c_plot <- f %>%
group_by(ID) %>%
gather(key = "Module", value = "PSR", -Week, -ID)
ALIFE_transpose_split = split(c_plot, c_plot$ID)
plotdata <- function(x) {
ggplot(data = x, aes(x = Week, y = PSR)) +
geom_line(aes(color = Module, linetype = Module)) +
scale_color_manual(values = c("yellow4", "blue", "darkred")) +
scale_linetype_manual(values = c("solid","twodash", "solid")) +
ylim(1, 6)
ggsave(
filename="figure%03d.pdf",
plot = last_plot(),
device = "pdf",
path = "./",
scale = 1,
width = 13,
height = 8,
dpi = 300,
units = c("in"),
limitsize = TRUE)
}
Related Topics
Block Bootstrap from Subject List
How to Plot Grid Plots on a Same Page
Importing Multiple .Csv Files into R and Adding a New Column with File Name
How to Align or Center The Bars of a Histogram on The X Axis
Shapefile to Raster Conversion in R
Devtools::Install_Git Over Ssh
Dynamically Formatting Individual Axis Labels in Ggplot2
Strange Behaviour Dropping Column from Data.Frame in R
Plot Histogram with Points Instead of Bars
Segfault in R Using Reshape2 Package and Dcast
R Not Responding Request to Interrupt Stop Process
What Does The "More Columns Than Column Names" Error Mean