Mixing
How to plot one factor level as a base on geom_col/geom_area
5
I've written following function that makes a customised stacked plot:
stacked_plot <- function(data, what, by = NULL, date_col = date, date_unit = NULL, type = 'area'){
by <- enquo(by)
what <- ensym(what)
date_col <- ensym(date_col)
date_unit <- enquo(date_unit)
if (!rlang::as_string(date_col) %in% names(data)){
return(cat('Nie odnaleziono kolumny "', as_string(date_col), '".', sep = ''))
}
if (!rlang::quo_is_null(date_unit)){
data <- data %>%
mutate(!!date_col := floor_date(!!date_col, unit = !!date_unit, week_start = 1))
}
if (!rlang::quo_is_null(by)) {
data <- data %>%
filter(!is.na(!!by)) %>%
group_by(!!date_col, !!by) %>%
summarise(!!what := sum(!!what, na.rm = TRUE)) %>%
ungroup() %>%
complete(!!date_col, !!by, fill = rlang::list2(!!what := 0))
} else {
data <- data %>%
group_by(!!date_col) %>%
summarise(!!what := sum(!!what, na.rm = TRUE)) %>%
complete(!!date_col, fill = rlang::list2(!!what := 0))
}
if (type == 'area'){
p <- data %>%
ggplot(aes(!!date_col, !!what, fill = !!by)) +
geom_area(position = 'stack')
} else if (type == 'col'){
p <- data %>%
ggplot(aes(!!date_col, !!what, fill = !!by)) +
geom_col(position = 'stack')
}
p <- p +
scale_x_date(breaks = '1 month', date_labels = '%Y-%m', expand = c(.01, .01)) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90, vjust = .4)) +
labs(fill = '')
return(p)
}
Now, I want to use it with the data like below:
data <- structure(list(category1 = structure(c(7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L,
1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L, 1L,
1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L, 5L,
5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L,
1L, 1L, 8L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L,
1L, 1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L,
1L, 1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L,
5L, 5L, 1L), .Label = c("base", "cat1", "cat2", "cat3", "cat4",
"cat5", "cat6", "cat7"), class = "factor"), date = structure(c(14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431), class = "Date"), value = c(0.0296166578938365,
7.02892806393191e-05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, -23.1966033032737, 0, -17195.0853457778, 0, 0, 0, 0, 0,
7861.28404641463, 12189.6349251651, 0, 0, -3741.93702617252,
0, 176.303827249194, 391.710849761278, 131970.980379196, -1587.22123177257,
297.978554303167, -51860.1739251141, 0, 0, 0, 0, -391.332709445819,
0.000172964963558834, 0.0098722192979455, 2.34186560613466e-05,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -7.73219962306076,
0, -17218.0930016352, 0, 0, 0, 0, 0, 7781.23968988082, 12189.6349251651,
0, 0, 0, 0, 449.478850296707, 293.783137320959, 131970.980379196,
-1404.7589064091, 250.836431075847, -56540.9156671359, 0, 0,
0, 0, -558.95740304599, 5.77335368827169e-05, 0.00329073976598183,
7.79511453535577e-06, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, -2.57739987435359, 0, -17241.1006574926, 0, 0, 0, 0, 0,
6598.97373566299, 12189.6349251651, 0, -3324.25546024928, 0,
0, 549.603379062553, 195.855424880639, 131970.980379196, -529.148187957385,
219.828510450391, -64437.2982346174, 0, 0, 0, 0, -1447.22409849783,
1.92288024882845e-05, 0.00109691325532728, 2.60503400284112e-06,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -0.859131813420729,
0, -17264.10831335, 0, 0, 0, 0, 0, 5437.37054226604, 0, 0, 0,
0, 0, 293.381058210822, 293.783137320959, 131970.980379196, 526.728756878514,
207.979955414647, -65107.9475533677, 0, 0, 0, 0, -336.514645781955,
6.40960082942816e-06, 0.000366094798965479, 8.69455082789682e-07,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -127.057071107617,
0, -17287.1159692073, 0, 0, 0, 0, 0, 5343.46624155083, 0, 0,
0)), class = "data.frame", row.names = c(NA, -201L))
so I make the following plot:
data %>% stacked_plot(value, category1, date, type = 'col')
And here's my problem. I can't figure out in what order my factor variable (category1) is stacked. And what I would like to do is to reorder the factor levels within my function so that base category would be always displayed as starting from 0 and the rest of levels would be stacked on or below it. Well, it doesn't always have to be named as base, but I think we can add an argument to our function and supply it with the name of base variable. Of course, input data file can have different number of categories.
r ggplot2 forcats geom-col
edited Nov 16 '18 at 19:39
markus
12.3k1234
asked Nov 16 '18 at 16:56
Kuba_Kuba_
14912
add a comment |
5
I've written following function that makes a customised stacked plot:
stacked_plot <- function(data, what, by = NULL, date_col = date, date_unit = NULL, type = 'area'){
by <- enquo(by)
what <- ensym(what)
date_col <- ensym(date_col)
date_unit <- enquo(date_unit)
if (!rlang::as_string(date_col) %in% names(data)){
return(cat('Nie odnaleziono kolumny "', as_string(date_col), '".', sep = ''))
}
if (!rlang::quo_is_null(date_unit)){
data <- data %>%
mutate(!!date_col := floor_date(!!date_col, unit = !!date_unit, week_start = 1))
}
if (!rlang::quo_is_null(by)) {
data <- data %>%
filter(!is.na(!!by)) %>%
group_by(!!date_col, !!by) %>%
summarise(!!what := sum(!!what, na.rm = TRUE)) %>%
ungroup() %>%
complete(!!date_col, !!by, fill = rlang::list2(!!what := 0))
} else {
data <- data %>%
group_by(!!date_col) %>%
summarise(!!what := sum(!!what, na.rm = TRUE)) %>%
complete(!!date_col, fill = rlang::list2(!!what := 0))
}
if (type == 'area'){
p <- data %>%
ggplot(aes(!!date_col, !!what, fill = !!by)) +
geom_area(position = 'stack')
} else if (type == 'col'){
p <- data %>%
ggplot(aes(!!date_col, !!what, fill = !!by)) +
geom_col(position = 'stack')
}
p <- p +
scale_x_date(breaks = '1 month', date_labels = '%Y-%m', expand = c(.01, .01)) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90, vjust = .4)) +
labs(fill = '')
return(p)
}
Now, I want to use it with the data like below:
data <- structure(list(category1 = structure(c(7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L,
1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L, 1L,
1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L, 5L,
5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L,
1L, 1L, 8L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L,
1L, 1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L,
1L, 1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L,
5L, 5L, 1L), .Label = c("base", "cat1", "cat2", "cat3", "cat4",
"cat5", "cat6", "cat7"), class = "factor"), date = structure(c(14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431), class = "Date"), value = c(0.0296166578938365,
7.02892806393191e-05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, -23.1966033032737, 0, -17195.0853457778, 0, 0, 0, 0, 0,
7861.28404641463, 12189.6349251651, 0, 0, -3741.93702617252,
0, 176.303827249194, 391.710849761278, 131970.980379196, -1587.22123177257,
297.978554303167, -51860.1739251141, 0, 0, 0, 0, -391.332709445819,
0.000172964963558834, 0.0098722192979455, 2.34186560613466e-05,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -7.73219962306076,
0, -17218.0930016352, 0, 0, 0, 0, 0, 7781.23968988082, 12189.6349251651,
0, 0, 0, 0, 449.478850296707, 293.783137320959, 131970.980379196,
-1404.7589064091, 250.836431075847, -56540.9156671359, 0, 0,
0, 0, -558.95740304599, 5.77335368827169e-05, 0.00329073976598183,
7.79511453535577e-06, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, -2.57739987435359, 0, -17241.1006574926, 0, 0, 0, 0, 0,
6598.97373566299, 12189.6349251651, 0, -3324.25546024928, 0,
0, 549.603379062553, 195.855424880639, 131970.980379196, -529.148187957385,
219.828510450391, -64437.2982346174, 0, 0, 0, 0, -1447.22409849783,
1.92288024882845e-05, 0.00109691325532728, 2.60503400284112e-06,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -0.859131813420729,
0, -17264.10831335, 0, 0, 0, 0, 0, 5437.37054226604, 0, 0, 0,
0, 0, 293.381058210822, 293.783137320959, 131970.980379196, 526.728756878514,
207.979955414647, -65107.9475533677, 0, 0, 0, 0, -336.514645781955,
6.40960082942816e-06, 0.000366094798965479, 8.69455082789682e-07,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -127.057071107617,
0, -17287.1159692073, 0, 0, 0, 0, 0, 5343.46624155083, 0, 0,
0)), class = "data.frame", row.names = c(NA, -201L))
so I make the following plot:
data %>% stacked_plot(value, category1, date, type = 'col')
And here's my problem. I can't figure out in what order my factor variable (category1) is stacked. And what I would like to do is to reorder the factor levels within my function so that base category would be always displayed as starting from 0 and the rest of levels would be stacked on or below it. Well, it doesn't always have to be named as base, but I think we can add an argument to our function and supply it with the name of base variable. Of course, input data file can have different number of categories.
r ggplot2 forcats geom-col
edited Nov 16 '18 at 19:39
markus
12.3k1234
asked Nov 16 '18 at 16:56
Kuba_Kuba_
14912
add a comment |
5
5
5
I've written following function that makes a customised stacked plot:
stacked_plot <- function(data, what, by = NULL, date_col = date, date_unit = NULL, type = 'area'){
by <- enquo(by)
what <- ensym(what)
date_col <- ensym(date_col)
date_unit <- enquo(date_unit)
if (!rlang::as_string(date_col) %in% names(data)){
return(cat('Nie odnaleziono kolumny "', as_string(date_col), '".', sep = ''))
}
if (!rlang::quo_is_null(date_unit)){
data <- data %>%
mutate(!!date_col := floor_date(!!date_col, unit = !!date_unit, week_start = 1))
}
if (!rlang::quo_is_null(by)) {
data <- data %>%
filter(!is.na(!!by)) %>%
group_by(!!date_col, !!by) %>%
summarise(!!what := sum(!!what, na.rm = TRUE)) %>%
ungroup() %>%
complete(!!date_col, !!by, fill = rlang::list2(!!what := 0))
} else {
data <- data %>%
group_by(!!date_col) %>%
summarise(!!what := sum(!!what, na.rm = TRUE)) %>%
complete(!!date_col, fill = rlang::list2(!!what := 0))
}
if (type == 'area'){
p <- data %>%
ggplot(aes(!!date_col, !!what, fill = !!by)) +
geom_area(position = 'stack')
} else if (type == 'col'){
p <- data %>%
ggplot(aes(!!date_col, !!what, fill = !!by)) +
geom_col(position = 'stack')
}
p <- p +
scale_x_date(breaks = '1 month', date_labels = '%Y-%m', expand = c(.01, .01)) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90, vjust = .4)) +
labs(fill = '')
return(p)
}
Now, I want to use it with the data like below:
data <- structure(list(category1 = structure(c(7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L,
1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L, 1L,
1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L, 5L,
5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L,
1L, 1L, 8L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L,
1L, 1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L,
1L, 1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L,
5L, 5L, 1L), .Label = c("base", "cat1", "cat2", "cat3", "cat4",
"cat5", "cat6", "cat7"), class = "factor"), date = structure(c(14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431), class = "Date"), value = c(0.0296166578938365,
7.02892806393191e-05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, -23.1966033032737, 0, -17195.0853457778, 0, 0, 0, 0, 0,
7861.28404641463, 12189.6349251651, 0, 0, -3741.93702617252,
0, 176.303827249194, 391.710849761278, 131970.980379196, -1587.22123177257,
297.978554303167, -51860.1739251141, 0, 0, 0, 0, -391.332709445819,
0.000172964963558834, 0.0098722192979455, 2.34186560613466e-05,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -7.73219962306076,
0, -17218.0930016352, 0, 0, 0, 0, 0, 7781.23968988082, 12189.6349251651,
0, 0, 0, 0, 449.478850296707, 293.783137320959, 131970.980379196,
-1404.7589064091, 250.836431075847, -56540.9156671359, 0, 0,
0, 0, -558.95740304599, 5.77335368827169e-05, 0.00329073976598183,
7.79511453535577e-06, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, -2.57739987435359, 0, -17241.1006574926, 0, 0, 0, 0, 0,
6598.97373566299, 12189.6349251651, 0, -3324.25546024928, 0,
0, 549.603379062553, 195.855424880639, 131970.980379196, -529.148187957385,
219.828510450391, -64437.2982346174, 0, 0, 0, 0, -1447.22409849783,
1.92288024882845e-05, 0.00109691325532728, 2.60503400284112e-06,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -0.859131813420729,
0, -17264.10831335, 0, 0, 0, 0, 0, 5437.37054226604, 0, 0, 0,
0, 0, 293.381058210822, 293.783137320959, 131970.980379196, 526.728756878514,
207.979955414647, -65107.9475533677, 0, 0, 0, 0, -336.514645781955,
6.40960082942816e-06, 0.000366094798965479, 8.69455082789682e-07,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -127.057071107617,
0, -17287.1159692073, 0, 0, 0, 0, 0, 5343.46624155083, 0, 0,
0)), class = "data.frame", row.names = c(NA, -201L))
so I make the following plot:
data %>% stacked_plot(value, category1, date, type = 'col')
And here's my problem. I can't figure out in what order my factor variable (category1) is stacked. And what I would like to do is to reorder the factor levels within my function so that base category would be always displayed as starting from 0 and the rest of levels would be stacked on or below it. Well, it doesn't always have to be named as base, but I think we can add an argument to our function and supply it with the name of base variable. Of course, input data file can have different number of categories.
r ggplot2 forcats geom-col
edited Nov 16 '18 at 19:39
markus
12.3k1234
asked Nov 16 '18 at 16:56
Kuba_Kuba_
14912
I've written following function that makes a customised stacked plot:
stacked_plot <- function(data, what, by = NULL, date_col = date, date_unit = NULL, type = 'area'){
by <- enquo(by)
what <- ensym(what)
date_col <- ensym(date_col)
date_unit <- enquo(date_unit)
if (!rlang::as_string(date_col) %in% names(data)){
return(cat('Nie odnaleziono kolumny "', as_string(date_col), '".', sep = ''))
}
if (!rlang::quo_is_null(date_unit)){
data <- data %>%
mutate(!!date_col := floor_date(!!date_col, unit = !!date_unit, week_start = 1))
}
if (!rlang::quo_is_null(by)) {
data <- data %>%
filter(!is.na(!!by)) %>%
group_by(!!date_col, !!by) %>%
summarise(!!what := sum(!!what, na.rm = TRUE)) %>%
ungroup() %>%
complete(!!date_col, !!by, fill = rlang::list2(!!what := 0))
} else {
data <- data %>%
group_by(!!date_col) %>%
summarise(!!what := sum(!!what, na.rm = TRUE)) %>%
complete(!!date_col, fill = rlang::list2(!!what := 0))
}
if (type == 'area'){
p <- data %>%
ggplot(aes(!!date_col, !!what, fill = !!by)) +
geom_area(position = 'stack')
} else if (type == 'col'){
p <- data %>%
ggplot(aes(!!date_col, !!what, fill = !!by)) +
geom_col(position = 'stack')
}
p <- p +
scale_x_date(breaks = '1 month', date_labels = '%Y-%m', expand = c(.01, .01)) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90, vjust = .4)) +
labs(fill = '')
return(p)
}
Now, I want to use it with the data like below:
data <- structure(list(category1 = structure(c(7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L,
1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L, 1L,
1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L, 5L,
5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L,
1L, 1L, 8L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L,
1L, 1L, 1L, 6L, 6L, 5L, 5L, 1L, 1L, 8L, 3L, 1L, 1L, 8L, 1L, 1L,
1L, 1L, 1L, 1L, 4L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 2L, 1L, 8L, 1L, 1L, 1L, 1L, 6L, 6L,
5L, 5L, 1L), .Label = c("base", "cat1", "cat2", "cat3", "cat4",
"cat5", "cat6", "cat7"), class = "factor"), date = structure(c(14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403, 14403,
14403, 14403, 14403, 14403, 14403, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410, 14410,
14410, 14410, 14410, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417, 14417,
14417, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424,
14424, 14424, 14424, 14424, 14424, 14424, 14424, 14424, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431, 14431,
14431, 14431), class = "Date"), value = c(0.0296166578938365,
7.02892806393191e-05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, -23.1966033032737, 0, -17195.0853457778, 0, 0, 0, 0, 0,
7861.28404641463, 12189.6349251651, 0, 0, -3741.93702617252,
0, 176.303827249194, 391.710849761278, 131970.980379196, -1587.22123177257,
297.978554303167, -51860.1739251141, 0, 0, 0, 0, -391.332709445819,
0.000172964963558834, 0.0098722192979455, 2.34186560613466e-05,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -7.73219962306076,
0, -17218.0930016352, 0, 0, 0, 0, 0, 7781.23968988082, 12189.6349251651,
0, 0, 0, 0, 449.478850296707, 293.783137320959, 131970.980379196,
-1404.7589064091, 250.836431075847, -56540.9156671359, 0, 0,
0, 0, -558.95740304599, 5.77335368827169e-05, 0.00329073976598183,
7.79511453535577e-06, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, -2.57739987435359, 0, -17241.1006574926, 0, 0, 0, 0, 0,
6598.97373566299, 12189.6349251651, 0, -3324.25546024928, 0,
0, 549.603379062553, 195.855424880639, 131970.980379196, -529.148187957385,
219.828510450391, -64437.2982346174, 0, 0, 0, 0, -1447.22409849783,
1.92288024882845e-05, 0.00109691325532728, 2.60503400284112e-06,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -0.859131813420729,
0, -17264.10831335, 0, 0, 0, 0, 0, 5437.37054226604, 0, 0, 0,
0, 0, 293.381058210822, 293.783137320959, 131970.980379196, 526.728756878514,
207.979955414647, -65107.9475533677, 0, 0, 0, 0, -336.514645781955,
6.40960082942816e-06, 0.000366094798965479, 8.69455082789682e-07,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -127.057071107617,
0, -17287.1159692073, 0, 0, 0, 0, 0, 5343.46624155083, 0, 0,
0)), class = "data.frame", row.names = c(NA, -201L))
so I make the following plot:
data %>% stacked_plot(value, category1, date, type = 'col')
And here's my problem. I can't figure out in what order my factor variable (category1) is stacked. And what I would like to do is to reorder the factor levels within my function so that base category would be always displayed as starting from 0 and the rest of levels would be stacked on or below it. Well, it doesn't always have to be named as base, but I think we can add an argument to our function and supply it with the name of base variable. Of course, input data file can have different number of categories.
r ggplot2 forcats geom-col
r ggplot2 forcats geom-col
edited Nov 16 '18 at 19:39
markus
12.3k1234
asked Nov 16 '18 at 16:56
Kuba_Kuba_
14912
edited Nov 16 '18 at 19:39
markus
12.3k1234
asked Nov 16 '18 at 16:56
Kuba_Kuba_
14912
edited Nov 16 '18 at 19:39
markus
12.3k1234
edited Nov 16 '18 at 19:39
markus
12.3k1234
edited Nov 16 '18 at 19:39
markus
12.3k1234
12.3k1234
asked Nov 16 '18 at 16:56
Kuba_Kuba_
14912
asked Nov 16 '18 at 16:56
Kuba_Kuba_
14912
asked Nov 16 '18 at 16:56
Kuba_Kuba_
14912
14912
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
4
+25
Take a look at the answer by @Inhabitant in this question:
How to control ordering of stacked bar chart using identity on ggplot2
Basically the categories are stacked based on the order of the levels in the factor, and the stacking order starts from top to bottom.
Here's how I reordered the stacking with your data:
df_0 <- df_0 %>%
filter(!is.na(category1)) %>%
group_by(date, category1) %>%
summarise(value := sum(value, na.rm = TRUE)) %>%
ungroup() %>%
complete(date, category1, fill = rlang::list2(value := 0))
df_0$category1 <- df_0$category1 %>%
factor(levels = c("cat1", "cat2", "cat3", "cat4", "cat5", "cat6", "cat7", "base"))
df_0 %>%
ggplot(aes(date, value, fill = category1)) +
geom_col(position = 'stack')
Two remarks:
I changed the name of the data from
datatodf_0to avoid confusion with the R functiondata()To make it easier for myself I worked with the data immediately without the function, but of-course all can be integrated with the function
answered Nov 21 '18 at 15:51
DS_UNIDS_UNI
1,012312
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53342279%2fhow-to-plot-one-factor-level-as-a-base-on-geom-col-geom-area%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
4
+25
Take a look at the answer by @Inhabitant in this question:
How to control ordering of stacked bar chart using identity on ggplot2
Basically the categories are stacked based on the order of the levels in the factor, and the stacking order starts from top to bottom.
Here's how I reordered the stacking with your data:
df_0 <- df_0 %>%
filter(!is.na(category1)) %>%
group_by(date, category1) %>%
summarise(value := sum(value, na.rm = TRUE)) %>%
ungroup() %>%
complete(date, category1, fill = rlang::list2(value := 0))
df_0$category1 <- df_0$category1 %>%
factor(levels = c("cat1", "cat2", "cat3", "cat4", "cat5", "cat6", "cat7", "base"))
df_0 %>%
ggplot(aes(date, value, fill = category1)) +
geom_col(position = 'stack')
Two remarks:
I changed the name of the data from
datatodf_0to avoid confusion with the R functiondata()To make it easier for myself I worked with the data immediately without the function, but of-course all can be integrated with the function
answered Nov 21 '18 at 15:51
DS_UNIDS_UNI
1,012312
add a comment |
4
+25
Take a look at the answer by @Inhabitant in this question:
How to control ordering of stacked bar chart using identity on ggplot2
Basically the categories are stacked based on the order of the levels in the factor, and the stacking order starts from top to bottom.
Here's how I reordered the stacking with your data:
df_0 <- df_0 %>%
filter(!is.na(category1)) %>%
group_by(date, category1) %>%
summarise(value := sum(value, na.rm = TRUE)) %>%
ungroup() %>%
complete(date, category1, fill = rlang::list2(value := 0))
df_0$category1 <- df_0$category1 %>%
factor(levels = c("cat1", "cat2", "cat3", "cat4", "cat5", "cat6", "cat7", "base"))
df_0 %>%
ggplot(aes(date, value, fill = category1)) +
geom_col(position = 'stack')
Two remarks:
I changed the name of the data from
datatodf_0to avoid confusion with the R functiondata()To make it easier for myself I worked with the data immediately without the function, but of-course all can be integrated with the function
answered Nov 21 '18 at 15:51
DS_UNIDS_UNI
1,012312
add a comment |
4
+25
4
+25
4
+25
Take a look at the answer by @Inhabitant in this question:
How to control ordering of stacked bar chart using identity on ggplot2
Basically the categories are stacked based on the order of the levels in the factor, and the stacking order starts from top to bottom.
Here's how I reordered the stacking with your data:
df_0 <- df_0 %>%
filter(!is.na(category1)) %>%
group_by(date, category1) %>%
summarise(value := sum(value, na.rm = TRUE)) %>%
ungroup() %>%
complete(date, category1, fill = rlang::list2(value := 0))
df_0$category1 <- df_0$category1 %>%
factor(levels = c("cat1", "cat2", "cat3", "cat4", "cat5", "cat6", "cat7", "base"))
df_0 %>%
ggplot(aes(date, value, fill = category1)) +
geom_col(position = 'stack')
Two remarks:
I changed the name of the data from
datatodf_0to avoid confusion with the R functiondata()To make it easier for myself I worked with the data immediately without the function, but of-course all can be integrated with the function
answered Nov 21 '18 at 15:51
DS_UNIDS_UNI
1,012312
Take a look at the answer by @Inhabitant in this question:
How to control ordering of stacked bar chart using identity on ggplot2
Basically the categories are stacked based on the order of the levels in the factor, and the stacking order starts from top to bottom.
Here's how I reordered the stacking with your data:
df_0 <- df_0 %>%
filter(!is.na(category1)) %>%
group_by(date, category1) %>%
summarise(value := sum(value, na.rm = TRUE)) %>%
ungroup() %>%
complete(date, category1, fill = rlang::list2(value := 0))
df_0$category1 <- df_0$category1 %>%
factor(levels = c("cat1", "cat2", "cat3", "cat4", "cat5", "cat6", "cat7", "base"))
df_0 %>%
ggplot(aes(date, value, fill = category1)) +
geom_col(position = 'stack')
Two remarks:
I changed the name of the data from
datatodf_0to avoid confusion with the R functiondata()To make it easier for myself I worked with the data immediately without the function, but of-course all can be integrated with the function
answered Nov 21 '18 at 15:51
DS_UNIDS_UNI
1,012312
answered Nov 21 '18 at 15:51
DS_UNIDS_UNI
1,012312
answered Nov 21 '18 at 15:51
DS_UNIDS_UNI
1,012312
answered Nov 21 '18 at 15:51
DS_UNIDS_UNI
1,012312
1,012312
add a comment |
add a comment |
draft saved
draft discarded
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53342279%2fhow-to-plot-one-factor-level-as-a-base-on-geom-col-geom-area%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
