Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Added value_type argument to choose what value to display #6

Merged
merged 1 commit into from
Mar 13, 2020
Merged

Added value_type argument to choose what value to display #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .Rbuildignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
^.*\.Rproj$
^\.Rproj\.user$
4 changes: 4 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
.Rproj.user
.Rhistory
.RData
.Ruserdata
114 changes: 57 additions & 57 deletions R/geom_venn.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,10 +21,10 @@
#'
#' # use data.frame as input
#' d <- tibble(value = c(1, 2, 3, 5, 6, 7, 8, 9, 10, 12, 13),
#' `Set 1` = c(T, F, T, T, F, T, F, T, F, F, F),
#' `Set 2` = c(T, F, F, T, F, F, F, T, F, F, T),
#' `Set 3` = c(T, T, F, F, F, F, T, T, F, F, F),
#' `Set 4` = c(F, F, F, F, T, T, F, F, T, T, F))
#' `Set 1` = c(TRUE, FALSE, TRUE, TRUE, FALSE, TRUE, FALSE, TRUE, FALSE, FALSE, FALSE),
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you very much to point out my bad writing. TRUE/FALSE is much better than T/F since T/F is not reserved keywords in R.

#' `Set 2` = c(TRUE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, TRUE),
#' `Set 3` = c(TRUE, TRUE, FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, FALSE, FALSE, FALSE),
#' `Set 4` = c(FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, FALSE, FALSE, TRUE, TRUE, FALSE))
#'
#' # ggplot gramma
#' ggplot(d) +
Expand Down Expand Up @@ -68,8 +68,8 @@ geom_venn <- function(mapping = NULL, data = NULL,
text_color = "black",
text_size = 4) {
l <- layer(mapping = mapping, data = data,
geom = GeomVenn, stat = stat, position = position,
params = list(na.rm = TRUE, ...))
geom = GeomVenn, stat = stat, position = position,
params = list(na.rm = TRUE, ...))
old_compute_aesthetics <- l$compute_aesthetics
l$compute_aesthetics <- function(self, data, plot) {
if (is.null(set_names)) {
Expand Down Expand Up @@ -99,55 +99,55 @@ geom_venn <- function(mapping = NULL, data = NULL,
}

GeomVenn <- ggproto("GeomVenn", Geom,
required_aes = c("A", "B"),
optional_aes = c("C", "D", "label"),
extra_params = c("na.rm"),
setup_data = function(self, data, params) {
data %>% mutate(xmin = -2, xmax = 2, ymin = -2, ymax = 2)
},
draw_panel = function(self, data, panel_params, coord, ...) {
attr <- self$customize_attributes
sets <- c("A", "B", "C", "D")
sets <- sets[sets %in% names(data)]
show_elements <- NA
if ("label" %in% names(data)) {
show_elements <- "label"
}
venn <- prepare_venn_data(data, sets, show_elements)
d0 <- coord_munch(coord, venn$shapes, panel_params)
d <- d0 %>%
filter(!duplicated(group)) %>%
mutate(fill_color = attr$fill_color[group],
fill_alpha = attr$fill_alpha,
stroke_color = attr$stroke_color,
stroke_alpha = attr$stroke_alpha,
stroke_size = attr$stroke_size,
stroke_linetype = attr$stroke_linetype)
d1 <- coord_munch(coord, venn$labels, panel_params)
d2 <- coord_munch(coord, venn$texts, panel_params)
ggplot2:::ggname("geom_venn",
grobTree(
polygonGrob(
d0$x, d0$y, default.units = "native", id = d0$group,
gp = gpar(col = NA,
fill = alpha(d$fill_color, d$fill_alpha))),
polygonGrob(
d0$x, d0$y, default.units = "native", id = d0$group,
gp = gpar(col = alpha(d$stroke_color, d$stroke_alpha),
fill = NA,
lwd = d$stroke_size * .pt,
lty = d$stroke_linetype)),
textGrob(
self$set_names, d1$x, d1$y, default.units = "native",
hjust = d1$hjust, vjust = d1$vjust,
gp = gpar(col = attr$set_name_color,
fontsize = attr$set_name_size * .pt)),
textGrob(
d2$text, d2$x, d2$y, default.units = "native",
hjust = d2$hjust, vjust = d2$vjust,
gp = gpar(col = attr$text_color,
fontsize = attr$text_size * .pt))
)
)
}
required_aes = c("A", "B"),
optional_aes = c("C", "D", "label"),
extra_params = c("na.rm"),
setup_data = function(self, data, params) {
data %>% mutate(xmin = -2, xmax = 2, ymin = -2, ymax = 2)
},
draw_panel = function(self, data, panel_params, coord, ...) {
attr <- self$customize_attributes
sets <- c("A", "B", "C", "D")
sets <- sets[sets %in% names(data)]
show_elements <- NA
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If value_type is added to ggvenn(), I strongly suggest adding the same parameter to geom_venn().

if ("label" %in% names(data)) {
show_elements <- "label"
}
venn <- prepare_venn_data(data, sets, show_elements)
d0 <- coord_munch(coord, venn$shapes, panel_params)
d <- d0 %>%
filter(!duplicated(group)) %>%
mutate(fill_color = attr$fill_color[group],
fill_alpha = attr$fill_alpha,
stroke_color = attr$stroke_color,
stroke_alpha = attr$stroke_alpha,
stroke_size = attr$stroke_size,
stroke_linetype = attr$stroke_linetype)
d1 <- coord_munch(coord, venn$labels, panel_params)
d2 <- coord_munch(coord, venn$texts, panel_params)
ggplot2:::ggname("geom_venn",
grobTree(
polygonGrob(
d0$x, d0$y, default.units = "native", id = d0$group,
gp = gpar(col = NA,
fill = alpha(d$fill_color, d$fill_alpha))),
polygonGrob(
d0$x, d0$y, default.units = "native", id = d0$group,
gp = gpar(col = alpha(d$stroke_color, d$stroke_alpha),
fill = NA,
lwd = d$stroke_size * .pt,
lty = d$stroke_linetype)),
textGrob(
self$set_names, d1$x, d1$y, default.units = "native",
hjust = d1$hjust, vjust = d1$vjust,
gp = gpar(col = attr$set_name_color,
fontsize = attr$set_name_size * .pt)),
textGrob(
d2$text, d2$x, d2$y, default.units = "native",
hjust = d2$hjust, vjust = d2$vjust,
gp = gpar(col = attr$text_color,
fontsize = attr$text_size * .pt))
)
)
}
)
58 changes: 35 additions & 23 deletions R/ggvenn.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
#' @param data A data.frame or a list as input data.
#' @param columns A character vector use as index to select columns/elements.
#' @param show_elements Show set elements instead of count/percentage.
#' @param value_type Display "count" data only or "both" counts and percentages
#' @param fill_color Filling colors in circles.
#' @param fill_alpha Transparency for filling circles.
#' @param stroke_color Stroke color for drawing circles.
Expand All @@ -29,10 +30,10 @@
#'
#' # use data.frame as input
#' d <- tibble(value = c(1, 2, 3, 5, 6, 7, 8, 9, 10, 12, 13),
#' `Set 1` = c(T, F, T, T, F, T, F, T, F, F, F),
#' `Set 2` = c(T, F, F, T, F, F, F, T, F, F, T),
#' `Set 3` = c(T, T, F, F, F, F, T, T, F, F, F),
#' `Set 4` = c(F, F, F, F, T, T, F, F, T, T, F))
#' `Set 1` = c(TRUE, FALSE, TRUE, TRUE, FALSE, TRUE, FALSE, TRUE, FALSE, FALSE, FALSE),
#' `Set 2` = c(TRUE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, TRUE),
#' `Set 3` = c(TRUE, TRUE, FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, FALSE, FALSE, FALSE),
#' `Set 4` = c(FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, FALSE, FALSE, TRUE, TRUE, FALSE))
#' ggvenn(d, c("Set 1", "Set 2"))
#' ggvenn(d, c("Set 1", "Set 2", "Set 3"))
#' ggvenn(d)
Expand All @@ -47,6 +48,7 @@
#' @export
ggvenn <- function(data, columns = NULL,
show_elements = FALSE,
value_type = "both",
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do you think show_percentage = TRUE is better than value_type = "both"?

fill_color = c("blue", "yellow", "green", "red"),
fill_alpha = .5,
stroke_color = "black",
Expand All @@ -57,7 +59,7 @@ ggvenn <- function(data, columns = NULL,
set_name_size = 6,
text_color = "black",
text_size = 4) {
venn <- prepare_venn_data(data, columns, show_elements)
venn <- prepare_venn_data(data, columns, show_elements, value_type)
venn$shapes %>%
mutate(group = LETTERS[group]) %>%
ggplot() +
Expand Down Expand Up @@ -88,10 +90,10 @@ gen_circle <- function(group, x_offset = 0, y_offset = 0, radius = 1,
radius_b = radius, theta_offset = 0, length.out = 100) {
tibble(group = group,
theta = seq(0, 2 * pi, length.out = length.out)) %>%
mutate(x_raw = radius * cos(theta),
y_raw = radius_b * sin(theta),
x = x_offset + x_raw * cos(theta_offset) - y_raw * sin(theta_offset),
y = y_offset + x_raw * sin(theta_offset) + y_raw * cos(theta_offset))
mutate(x_raw = radius * cos(theta),
y_raw = radius_b * sin(theta),
x = x_offset + x_raw * cos(theta_offset) - y_raw * sin(theta_offset),
y = y_offset + x_raw * sin(theta_offset) + y_raw * cos(theta_offset))
}

gen_circle_2 <- function() {
Expand Down Expand Up @@ -164,7 +166,7 @@ gen_label_pos_4 <- function() {
"D", 1.5, -1.3, 0, 1)
}

prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE) {
prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE, value_type = "both") {
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do you think show_percentage = TRUE is better than value_type = "both"? I personally do not prefer parameters of string type, because it often makes users have to check the manual for valid values before using it.

if (is.data.frame(data)) {
if (is.null(columns)) {
columns = data %>% select_if(is.logical) %>% names
Expand All @@ -184,7 +186,7 @@ prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE) {
stopifnot((d1 %>% count(A, B) %>% with(n)) == 1)
for (i in 1:nrow(d1)) {
idx <- ((!xor(d1$A[[i]], as_tibble(data)[,columns[[1]]])) &
(!xor(d1$B[[i]], as_tibble(data)[,columns[[2]]])))
(!xor(d1$B[[i]], as_tibble(data)[,columns[[2]]])))
d1$n[[i]] <- sum(idx)
if (!identical(show_elements, FALSE)) {
d1$text[[i]] <- paste(unlist(as_tibble(data)[idx,show_elements]), collapse = ",")
Expand All @@ -200,8 +202,8 @@ prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE) {
stopifnot((d1 %>% count(A, B, C) %>% with(n)) == 1)
for (i in 1:nrow(d1)) {
idx <- ((!xor(d1$A[[i]], as_tibble(data)[,columns[[1]]])) &
(!xor(d1$B[[i]], as_tibble(data)[,columns[[2]]])) &
(!xor(d1$C[[i]], as_tibble(data)[,columns[[3]]])))
(!xor(d1$B[[i]], as_tibble(data)[,columns[[2]]])) &
(!xor(d1$C[[i]], as_tibble(data)[,columns[[3]]])))
d1$n[[i]] <- sum(idx)
if (!identical(show_elements, FALSE)) {
d1$text[[i]] <- paste(unlist(as_tibble(data)[idx,show_elements]), collapse = ",")
Expand All @@ -218,9 +220,9 @@ prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE) {
stopifnot((d1 %>% count(A, B, C, D) %>% with(n)) == 1)
for (i in 1:nrow(d1)) {
idx <- ((d1$A[[i]] == as_tibble(data)[,columns[[1]], drop = TRUE]) &
(d1$B[[i]] == as_tibble(data)[,columns[[2]], drop = TRUE]) &
(d1$C[[i]] == as_tibble(data)[,columns[[3]], drop = TRUE]) &
(d1$D[[i]] == as_tibble(data)[,columns[[4]], drop = TRUE]))
(d1$B[[i]] == as_tibble(data)[,columns[[2]], drop = TRUE]) &
(d1$C[[i]] == as_tibble(data)[,columns[[3]], drop = TRUE]) &
(d1$D[[i]] == as_tibble(data)[,columns[[4]], drop = TRUE]))
d1$n[[i]] <- sum(idx)
if (!identical(show_elements, FALSE)) {
d1$text[[i]] <- paste(unlist(as_tibble(data)[idx,show_elements]), collapse = ",")
Expand All @@ -243,7 +245,7 @@ prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE) {
stopifnot((d1 %>% count(A, B) %>% with(n)) == 1)
for (i in 1:nrow(d1)) {
idx <- ((!xor(d1$A[[i]], a2 %in% data[[columns[[1]]]])) &
(!xor(d1$B[[i]], a2 %in% data[[columns[[2]]]])))
(!xor(d1$B[[i]], a2 %in% data[[columns[[2]]]])))
d1$n[[i]] <- sum(idx)
d1$text[[i]] <- paste(a2[idx], collapse = ",")
}
Expand All @@ -254,8 +256,8 @@ prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE) {
stopifnot((d1 %>% count(A, B, C) %>% with(n)) == 1)
for (i in 1:nrow(d1)) {
idx <- ((!xor(d1$A[[i]], a2 %in% data[[columns[[1]]]])) &
(!xor(d1$B[[i]], a2 %in% data[[columns[[2]]]])) &
(!xor(d1$C[[i]], a2 %in% data[[columns[[3]]]])))
(!xor(d1$B[[i]], a2 %in% data[[columns[[2]]]])) &
(!xor(d1$C[[i]], a2 %in% data[[columns[[3]]]])))
d1$n[[i]] <- sum(idx)
d1$text[[i]] <- paste(a2[idx], collapse = ",")
}
Expand All @@ -266,9 +268,9 @@ prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE) {
stopifnot((d1 %>% count(A, B, C, D) %>% with(n)) == 1)
for (i in 1:nrow(d1)) {
idx <- ((!xor(d1$A[[i]], a2 %in% data[[columns[[1]]]])) &
(!xor(d1$B[[i]], a2 %in% data[[columns[[2]]]])) &
(!xor(d1$C[[i]], a2 %in% data[[columns[[3]]]])) &
(!xor(d1$D[[i]], a2 %in% data[[columns[[4]]]])))
(!xor(d1$B[[i]], a2 %in% data[[columns[[2]]]])) &
(!xor(d1$C[[i]], a2 %in% data[[columns[[3]]]])) &
(!xor(d1$D[[i]], a2 %in% data[[columns[[4]]]])))
d1$n[[i]] <- sum(idx)
d1$text[[i]] <- paste(a2[idx], collapse = ",")
}
Expand All @@ -281,7 +283,17 @@ prepare_venn_data <- function(data, columns = NULL, show_elements = FALSE) {
stop("`data` should be a list")
}
if (!show_elements) {
d1 <- d1 %>% mutate(text = sprintf("%d\n(%.1f%%)", n, 100 * n / sum(n)))

Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I suggest removing empty lines here.

if(value_type == "both"){
d1 <- d1 %>% mutate(text = sprintf("%d\n(%.1f%%)", n, 100 * n / sum(n)))
}
if(value_type == "count"){
d1 <- d1 %>% mutate(text = sprintf("%d", n, 100 * n / sum(n)))
}


}


list(shapes = d, texts = d1, labels = d2)
}
17 changes: 17 additions & 0 deletions ggvenn.Rproj
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
Version: 1.0
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am OK to add Rproj files, although I am not using Rstudio very often yet. I am using vim, which has slightly different indent rules. Therefore, I accept the indent changes.


RestoreWorkspace: Default
SaveWorkspace: Default
AlwaysSaveHistory: Default

EnableCodeIndexing: Yes
UseSpacesForTab: Yes
NumSpacesForTab: 2
Encoding: UTF-8

RnwWeave: Sweave
LaTeX: pdfLaTeX

BuildType: Package
PackageUseDevtools: Yes
PackageInstallArgs: --no-multiarch --with-keep.source
8 changes: 4 additions & 4 deletions man/geom_venn.Rd
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

11 changes: 7 additions & 4 deletions man/ggvenn.Rd
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.