I have a listed dataframe with the code:
df1 <- data.frame(ID = rep(c("P-1000", "P-10001", "P-10002", "P-1003", "P-1004"),3),
Visit = c(rep("M1",5), rep("M4",5), rep("M17",5)),
Value = runif(15))
df2 <- data.frame(ID = rep(c("P-1000", "P-10001", "P-10002", "P-1003", "P-1004"),3),
Visit = c(rep("M1",5), rep("M4",5), rep("M17",5)),
Value = runif(15))
df3 <- data.frame(ID = rep(c("P-1000", "P-10001", "P-10002", "P-1003", "P-1004"),3),
Visit = c(rep("M1",5), rep("M4",5), rep("M17",5)),
Value = runif(15))
sampledata<- list(df1, df2, df3)
names(sampledata)<- c("A", "C", "Z")
for which I am trying to make plots for. I am trying to make plots per ID per dataframe (e.g., 1 plot would be for P-1000 in dataframe A). In the end, I would like to save these plots in separate pdfs by dataframes (e.g., 1 pdf for all plots pertaining to dataframe A, another for dataframe B, etc). I'm not quite sure how to do this. My current trial of code is the following:
sample_data_plots <- lapply(seq_along(sampledata),function(i) {
sampledata[[i]] %>% filter(!is.na(Visit)) %>% group_by(ID) %>%
mutate(Visit = factor(Visit, levels = c("M1", "M4", "M17"))) %>%
ggplot(aes(x = Visit, y = Value)) geom_boxplot()
labs(title = paste("Values of", names(sampledata)[i], "for", "ID",
#this is the variable ID
),
y = "Value",
x = "Visit")})
I have no issues in running:
lapply(seq_along(sampledata), function(i) {
sampledata[[i]] %>% filter(!is.na(Visit)) %>%
mutate(Visit = factor(Visit, levels = c "M1", "M4", "M17"))) %>%
ggplot(aes(x = Visit, y = Value)) geom_boxplot()
labs(title = paste("Value", names(sampledata)[i]),
y = "Value",
x = "Visit") })
but this gives graphs per dataframes for all ID
Any help would be greatly appreciated. Thank you!
CodePudding user response:
Consider purrr::map2
to apply a function across list of data frames and their names and dplyr::group_map
to apply functions by ID groups.
build_plot <- function(sub_df) {
sub_df %>%
filter(!is.na(Visit)) %>%
mutate(Visit = factor(Visit, levels=c("M1", "M4", "M17"))) %>%
ggplot(aes(x=Visit, y=Value))
geom_boxplot()
labs(title = paste("Value", sub_df$ID[1]), y="Value", x="Visit")
}
run_groups <- function(main_df, df_name) {
# BUILD PLOTS BY ID
plot_list <- main_df %>%
group_by(ID) %>%
group_map(build_plot)
# SAVE PLOTS TO SINGLE PDF
ggplot2::ggsave(
filename = paste0(df_name, "_plots.pdf"),
plot = gridExtra::marrangeGrob(plot_list, nrow=1, ncol=1),
width = 15, height = 9
)
return(plot_list)
}
# CREATE PDFS BY DATA FRAME
myplots <- purr::map2(sample_data, names(sample_data), run_groups)
The analogous base
R methods respectively would be siblings to lapply
: Map
(wrapper to mapply
) and by
(wrapper to tapply
).
run_groups <- function(main_df, df_name) {
# BUILD PLOTS BY ID
plot_list <- by(main_df, main_df$ID, build_plot)
...
}
# CREATE PDFS BY DATA FRAME
myplots <- Map(run_groups, sample_data, names(sample_data))