Converting table to matrix for clustering analysis - r

So I have a table that that tells the freq (N) of two variables (V1 and V2) appearing together. Here is a sample:
> dput(ans)
structure(list(V1 = c(2L, 7L, 7L, 7L, 7L, 7L, 9L, 9L, 9L, 10L,
10L, 11L, 12L, 12L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 14L, 14L,
14L, 14L, 15L, 15L, 15L, 16L, 16L, 16L, 16L, 17L, 17L, 17L, 20L,
20L, 21L, 25L, 29L, 29L, 29L, 33L, 35L, 38L, 42L, 46L, 46L, 46L,
46L, 46L, 46L, 46L, 46L, 46L, 46L, 46L, 46L, 47L, 47L, 48L, 52L,
52L, 52L, 52L, 52L, 56L, 56L, 56L, 56L, 56L, 56L, 56L, 57L, 57L,
57L, 57L, 57L, 57L, 58L, 58L, 58L, 58L, 58L, 59L, 59L, 59L, 59L,
60L, 60L, 60L, 61L, 61L, 62L, 65L, 65L, 65L, 65L, 67L, 67L, 67L,
68L, 70L, 70L, 71L, 73L, 73L, 74L), V2 = c(3L, 8L, 20L, 21L,
22L, 78L, 10L, 11L, 12L, 11L, 12L, 12L, 38L, 39L, 14L, 15L, 16L,
17L, 18L, 29L, 64L, 15L, 16L, 17L, 18L, 16L, 17L, 18L, 17L, 18L,
29L, 30L, 18L, 29L, 30L, 21L, 22L, 22L, 26L, 30L, 47L, 64L, 34L,
36L, 39L, 43L, 47L, 48L, 49L, 52L, 65L, 67L, 70L, 71L, 72L, 73L,
74L, 75L, 48L, 49L, 49L, 65L, 67L, 73L, 74L, 75L, 57L, 58L, 59L,
60L, 61L, 62L, 63L, 58L, 59L, 60L, 61L, 62L, 63L, 59L, 60L, 61L,
62L, 63L, 60L, 61L, 62L, 63L, 61L, 62L, 63L, 62L, 63L, 63L, 67L,
73L, 74L, 75L, 73L, 74L, 75L, 69L, 71L, 72L, 72L, 74L, 75L, 75L
), N = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L)),
row.names = c(NA, -108L), class = c("data.table", "data.frame"))
I want to convert it to a 696x696 matrix where I have V1 and V2 as the rows and columns (from 1-696 in both rows and columns), and N as the values. V1 and V2 represents materials in my dataset. If a V1 and V2 combination does not exist in the table, the value should be 0. This is because I want to cluster the materials based on their freq of appearing together, using the hclust with centroid function.
EDIT: Only way I can give an example of the expected output is a picture from an article i'm following:


To duplicate the picture you have added to the original question, I'd do something like this:
# convert your contingency table to the appropriate matrix
M <- sparseMatrix(df$V1, df$V2, x = df$N, dims = c(696, 696))
M <- as.matrix(M)
rownames(M) <- 1:696
colnames(M) <- 1:696
There are many formatting options for displaying the matrix to image, but to start, try:
View(M)


That's a common task for rasters... using the raster package and converting it back to matrix may not be the fastest solution, but it works well on your test data (here named as df)...
library(raster)
r <- raster(nrow=696, ncol=696, crs = NA,
xmn = 0, xmx = 696, ymn = 0, ymx = 696)
# some indexing corrections
new_xy <- cbind(df[, 2] - 1, 697 - df[, 1])
cells <- cellFromXY(r, new_xy)
r[] <- 0
r[cells] <- unlist(df[, 3])
r <- as.matrix(r)
Then we can check with str(r) it is a 696x696 numeric, and max(r) is a value of 3, as expected. Also, r[2, 3] = 1

Related

Is there a way to produce multiple x-y scatterplots at once based on grouping value, ordered by a third variable?

I have multi-level data. The group level is individual persons, which are designated by id. The variable index indicates different time points. Is there a way to make a separate scatterplot (x vs. y) for each individual, all displayed in the same output, and ordered based on a third variable (z)? If so, can color then be added to indicate degree of third variable (z)? Data below, Thanks.
> dput(dat1.1)
structure(list(id = c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L), index = c(1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L,
1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L,
15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L,
9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L,
16L, 17L, 18L, 19L, 20L), x = c(7.443917, 7.520429, 7.446833,
8.07893, 8.534033, 8.263931, 7.598647, 6.902987, 7.672617, 7.739256,
7.591341, 8.101125, 7.811751, 6.596834, 6.637652, 8.467165, 7.835399,
6.500149, 7.083198, 7.531798, 6.110208, 6.368534, 5.26318, 6.735778,
5.580152, 5.460161, 5.844303, 6.258181, 7.191627, 5.105033, 6.760193,
5.857215, 5.866264, 6.769086, 6.547294, 5.623804, 4.675815, 6.153901,
6.040519, 6.236045, 8.216397, 6.097841, 5.491311, 5.831432, 6.297337,
6.655688, 5.553445, 6.37449, 6.271961, 6.959645, 7.080341, 6.46092,
6.476955, 7.221111, 6.219023, NA, NA, NA, NA, NA, 8.21752, 7.589581,
8.363739, 8.849697, 7.78645, 7.494006, 7.827766, 9.11352, 7.80884,
6.701855, 6.259061, 5.523358, 6.186617, 6.548538, 6.6937, 7.213297,
5.243428, 7.510827, 7.054297, 7.603241), y = c(106L, 114L, 50L,
50L, 56L, 46L, 50L, 52L, 114L, 50L, 56L, 26L, 48L, 52L, 48L,
54L, 54L, 56L, 52L, 50L, 84L, 86L, 88L, 86L, 82L, 84L, 88L, 84L,
86L, 84L, 86L, 86L, 84L, 84L, 88L, 88L, 88L, 84L, 86L, 120L,
106L, 168L, 116L, 56L, 108L, 68L, 68L, 70L, 74L, 76L, 76L, 76L,
72L, 70L, 118L, NA, NA, NA, NA, NA, 60L, 62L, 52L, 90L, 50L,
50L, 54L, 56L, 52L, 30L, 78L, 30L, 52L, 54L, 52L, 80L, 86L, 46L,
54L, 84L), z = c(33L, 33L, 33L, 33L, 33L, 33L, 33L, 33L, 33L,
33L, 33L, 33L, 33L, 33L, 33L, 33L, 33L, 33L, 33L, 33L, 54L, 54L,
54L, 54L, 54L, 54L, 54L, 54L, 54L, 54L, 54L, 54L, 54L, 54L, 54L,
54L, 54L, 54L, 54L, 54L, 56L, 56L, 56L, 56L, 56L, 56L, 56L, 56L,
56L, 56L, 56L, 56L, 56L, 56L, 56L, 56L, 56L, 56L, 56L, 56L, 50L,
50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L,
50L, 50L, 50L, 50L, 50L, 50L)), class = "data.frame", row.names = c(NA,
-80L))

Does this come close to giving you what you want?
library(tidyverse)
d %>%
group_by(id) %>%
mutate(z=as.factor(z)) %>%
group_map(
function(.x, .y) {
.x %>%
ggplot() +
geom_point(aes(x=x, y=y, colour=z)) +
facet_wrap(vars(z)) +
scale_colour_manual(drop=FALSE, values=d %>% distinct(z) %>% pull(z)) +
labs(title=.x$id[1])
},
.keep=TRUE
)
Points to note:
group_map applies a function to each group of a grouped data frame. .x refers to the data in the current group, .y is a one row tibble defining the group. .keep requests that the grouping variables are kept in .x.
drop=FALSE in the call to scale_colour_manual() ensures that unused factor levels are retained in the legend (and hence different levels of z are distinguishable between plots).

How to adjust error box to violin plot using geom_violin?

***editing:
errbar_lims <- group_by(dt, together) %>%
dplyr::summarize(mean=mean(score), se=sd(score)/sqrt(n()),
upper=mean+(2*se), lower=mean-(2*se))
> dput(dt)
structure(list(ï..count = c(50L, 7L, 21L, 22L, 94L, 58L, 147L,
4L, 30L, 67L, 91L, 75L, 143L, 15L, 64L, 141L, 39L, 18L, 27L,
70L, 142L, 95L, 26L, 78L, 8L, 146L, 46L, 138L, 36L, 63L, 66L,
97L, 56L, 25L, 19L, 59L, 99L, 5L, 33L, 17L, 55L, 98L, 31L, 42L,
76L, 23L, 44L, 32L, 52L, 60L, 20L, 37L, 140L, 93L, 65L, 87L,
13L, 68L, 51L, 16L, 152L, 81L, 54L, 35L, 149L, 77L, 90L, 38L,
48L, 153L, 2L, 14L, 12L, 10L, 3L, 28L, 61L, 71L, 6L, 45L, 69L,
43L, 53L, 47L, 34L, 92L, 9L, 57L, 145L, 11L, 62L, 49L, 148L,
144L, 1L, 40L, 24L, 88L, 13L, 96L), condition = c(2L, 3L, 1L,
2L, 2L, 2L, 3L, 4L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 1L, 3L, 2L, 3L,
2L, 2L, 3L, 3L, 2L, 4L, 2L, 3L, 2L, 4L, 3L, 2L, 4L, 4L, 1L, 3L,
3L, 3L, 1L, 1L, 1L, 3L, 2L, 4L, 2L, 4L, 3L, 4L, 1L, 4L, 4L, 4L,
4L, 4L, 4L, 1L, 2L, 2L, 1L, 3L, 3L, 4L, 1L, 2L, 3L, 1L, 1L, 2L,
2L, 4L, 2L, 1L, 2L, 4L, 2L, 3L, 4L, 1L, 3L, 2L, 2L, 1L, 4L, 1L,
3L, 1L, 4L, 3L, 1L, 1L, 3L, 2L, 1L, 4L, 4L, 1L, 4L, 2L, 3L, 1L,
1L), together = structure(c(2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L,
2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L), .Label = c("Shared Negative",
"Shared Positive"), class = "factor", label = "together"), second = structure(c(1L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L,
1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L,
1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L,
2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L,
2L, 1L, 1L), .Label = c("Negative Second", "Positive Second"), class = "factor"),
experimenter = c(1L, 1L, 4L, 4L, 4L, 1L, 1L, 2L, 4L, 2L,
2L, 2L, 1L, 2L, 1L, 4L, 3L, 4L, 2L, 4L, 2L, 4L, 2L, 4L, 1L,
2L, 4L, 4L, 3L, 3L, 2L, 2L, 4L, 3L, 4L, 1L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 3L, 2L, 1L, 2L, 3L, 1L, 2L, 4L, 2L, 1L, 4L, 2L,
2L, 4L, 4L, 1L, 4L, 4L, 3L, 2L, 3L, 2L, 4L, 2L, 4L, 2L, 4L,
2L, 2L, 1L, 3L, 3L, 2L, 2L, 4L, 2L, 2L, 3L, 4L, 1L, 2L, 2L,
4L, 2L, 4L, 1L, 3L, 3L, 1L, 2L, 1L, 3L, 3L, 4L, 3L, 1L, 4L
), age = structure(c(23L, 24L, 25L, 23L, 24L, 35L, 25L, 23L,
23L, 24L, 23L, 24L, 31L, 23L, 25L, 23L, 20L, 23L, 23L, 22L,
27L, 22L, 25L, 25L, 23L, 31L, 23L, 24L, 25L, 23L, 26L, 24L,
24L, 26L, 22L, 24L, 23L, 24L, 21L, 22L, 22L, 22L, 27L, 26L,
63L, 23L, 22L, 32L, 24L, 22L, 23L, 31L, 40L, 24L, 24L, 22L,
23L, 38L, 22L, 27L, 29L, 24L, 22L, 25L, 32L, 24L, 24L, 23L,
23L, 23L, 56L, 48L, 27L, 25L, 23L, 24L, 21L, 25L, 23L, 27L,
31L, 26L, 26L, 24L, 30L, 23L, 25L, 25L, 26L, 26L, 25L, 35L,
28L, 30L, 21L, 25L, 23L, 37L, 21L, 44L), label = "Age"),
sex = structure(c(2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L,
1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L
), .Label = c("Female", "Male"), class = "factor", label = "Sex"),
q1 = structure(c(0L, 11L, 18L, 0L, 18L, 19L, 9L, 13L, 36L,
41L, 29L, 34L, 33L, 53L, 27L, 35L, NA, 40L, 49L, 34L, 38L,
48L, 35L, 29L, 23L, 47L, 35L, 69L, 50L, 45L, 60L, 49L, 34L,
NA, 43L, 44L, 51L, 20L, 37L, 69L, 36L, 41L, 45L, 60L, 47L,
62L, 58L, 47L, 18L, 30L, 52L, 48L, 60L, 51L, 53L, 54L, 42L,
52L, 47L, 51L, 56L, NA, 54L, 51L, 47L, 57L, 47L, 66L, 53L,
54L, NA, 54L, 57L, 49L, 67L, 80L, 49L, 36L, 58L, 57L, 50L,
87L, 51L, 55L, 59L, 70L, 65L, 59L, 61L, 67L, 50L, 63L, 60L,
73L, 70L, 88L, 88L, 83L, 100L, 100L), label = "Question 1"),
q2 = c(0L, 13L, 12L, 22L, 23L, 19L, 31L, 11L, 71L, 13L, 36L,
12L, 33L, 24L, 37L, 37L, 37L, 41L, 50L, 35L, 58L, 39L, 42L,
37L, 64L, 48L, 44L, NA, 40L, 57L, 46L, 49L, 37L, 42L, 67L,
53L, 51L, 35L, 49L, 65L, 49L, 58L, 51L, 49L, 46L, 59L, 40L,
47L, NA, 51L, 53L, 47L, 60L, 51L, 53L, NA, 63L, 52L, 41L,
49L, 50L, NA, 53L, 52L, 64L, 54L, 57L, 50L, 57L, 54L, 55L,
64L, 62L, 27L, 65L, 70L, 53L, 68L, 65L, 54L, 59L, 53L, 61L,
56L, 58L, 69L, 74L, 62L, 56L, 67L, 62L, 58L, 60L, 72L, 78L,
100L, 84L, 96L, 100L, 99L), q3 = c(0L, 14L, 18L, NA, 19L,
16L, 53L, 66L, 81L, 35L, 36L, 65L, 32L, 73L, 75L, 30L, 64L,
44L, 13L, 51L, 62L, 50L, 42L, 51L, 47L, 12L, 60L, 62L, 66L,
77L, 55L, 43L, 69L, 70L, 85L, 68L, 50L, 56L, 46L, 97L, 67L,
80L, 59L, 63L, 46L, 60L, 35L, 47L, 35L, 52L, 48L, 58L, 62L,
51L, 65L, 67L, 65L, 61L, 71L, 58L, 56L, 57L, 54L, 73L, 60L,
62L, 57L, 63L, 53L, 54L, 79L, 87L, 59L, 61L, 78L, 16L, 43L,
81L, 69L, 69L, 58L, 47L, 49L, 56L, 58L, 51L, 77L, 65L, 61L,
67L, 83L, 90L, 81L, 83L, 78L, 66L, 98L, 9L, 71L, 100L), q4 = c(0L,
10L, 23L, 33L, 20L, 17L, 7L, 20L, 3L, 41L, 29L, 17L, 32L,
0L, 39L, 50L, 22L, 42L, 52L, 43L, 18L, 24L, 46L, 53L, 31L,
14L, 31L, 43L, 24L, 41L, 19L, 42L, 38L, 42L, 37L, 69L, 33L,
57L, 51L, 7L, 49L, 10L, 44L, 29L, 50L, 24L, 59L, 48L, 63L,
46L, 9L, 49L, 44L, 51L, 44L, 43L, 38L, 45L, 12L, 52L, 49L,
NA, 53L, 42L, 40L, 46L, 68L, 46L, 53L, 54L, 33L, 41L, 39L,
42L, 32L, 41L, 66L, 36L, 21L, 55L, 44L, 61L, 47L, 56L, 61L,
57L, 68L, 41L, 39L, 67L, 23L, 47L, 68L, 34L, 61L, 25L, 68L,
92L, 70L, 100L), q5 = c(5L, 7L, 15L, 0L, 19L, 17L, 31L, 19L,
23L, 19L, 26L, 34L, 35L, 52L, 46L, 44L, NA, 42L, 34L, 18L,
34L, 47L, 51L, 34L, 47L, 39L, 57L, 46L, 48L, 43L, 49L, 41L,
41L, 42L, 48L, 43L, 50L, 49L, 68L, 43L, 38L, 46L, 46L, 48L,
61L, 57L, 50L, 49L, 47L, 51L, NA, 48L, 34L, 51L, 52L, 52L,
46L, 54L, 48L, 55L, 57L, NA, 53L, 51L, 58L, 48L, 50L, 64L,
57L, 54L, 52L, 53L, 61L, 79L, 58L, 78L, 51L, 64L, 68L, 58L,
55L, 59L, 64L, 62L, 60L, 58L, 67L, 63L, 66L, 68L, 72L, 65L,
72L, 69L, 75L, 27L, 70L, 95L, 100L, 100L), q6 = c(3L, 13L,
14L, 43L, 17L, 23L, 0L, 20L, 11L, 33L, 38L, 3L, 44L, 0L,
6L, 50L, 0L, 46L, 34L, 53L, 34L, 19L, 50L, 43L, 47L, 63L,
46L, 27L, 18L, 42L, 42L, 41L, 51L, 32L, 43L, 24L, 50L, 52L,
11L, 4L, 49L, 31L, 59L, 28L, 61L, 46L, 56L, 50L, 40L, 51L,
30L, 47L, 57L, 46L, 46L, 44L, 43L, 42L, 53L, 50L, 50L, 53L,
53L, 66L, 30L, 40L, 52L, 39L, 52L, 54L, 51L, 32L, 32L, 64L,
43L, 7L, 58L, 31L, 39L, 51L, 57L, 44L, 59L, 62L, 61L, 57L,
32L, 39L, 68L, 58L, 83L, 62L, 43L, 32L, 61L, 65L, 60L, 94L,
86L, 100L), q7 = c(40L, 20L, 31L, 67L, 18L, 27L, 50L, 49L,
29L, 38L, 45L, 53L, 53L, 53L, 53L, 56L, 70L, 45L, 43L, 53L,
42L, 69L, 53L, 47L, 47L, 48L, 53L, 48L, 80L, 66L, 46L, 48L,
61L, 62L, 37L, 69L, 49L, 61L, 69L, 86L, 50L, 68L, 49L, 50L,
35L, 44L, 43L, 50L, 62L, 51L, 53L, 50L, 46L, 51L, 53L, 51L,
71L, 53L, 87L, 57L, 56L, 54L, 53L, 42L, 69L, 61L, 45L, 47L,
53L, 54L, 68L, 73L, 66L, 65L, 56L, 72L, 69L, 71L, 71L, 60L,
57L, 63L, 75L, 58L, 61L, 52L, 24L, 69L, 71L, 53L, 94L, 81L,
43L, 91L, 61L, 57L, 46L, 95L, 84L, 100L), q8 = c(3L, 25L,
13L, 0L, 18L, 27L, 15L, 17L, 13L, 38L, 31L, 29L, 26L, 53L,
11L, 36L, 23L, 30L, 46L, 43L, 57L, 39L, 25L, 42L, 63L, 69L,
30L, 64L, 47L, 41L, 54L, 42L, 37L, 38L, 39L, 21L, 50L, 47L,
50L, 24L, 49L, 45L, 45L, 55L, 47L, 43L, 46L, 49L, 62L, 51L,
43L, 47L, 63L, 51L, 48L, 49L, 40L, 54L, 46L, 49L, 58L, 49L,
53L, 52L, 41L, 50L, 45L, 47L, 53L, 54L, 50L, 56L, 64L, 39L,
57L, 38L, 49L, 43L, 48L, 52L, 58L, 55L, 68L, 62L, 59L, 58L,
64L, 68L, 46L, 56L, 31L, 63L, 67L, 71L, 62L, 99L, 82L, 98L,
100L, 100L), q9 = c(0L, 13L, 5L, 0L, 18L, 25L, 0L, 19L, 0L,
15L, 22L, 64L, 26L, 0L, 51L, 37L, 60L, 43L, 43L, 50L, 17L,
38L, 51L, 49L, 28L, 32L, 40L, 13L, 16L, 19L, 36L, 51L, 55L,
46L, 35L, 26L, 41L, 48L, 31L, 21L, 43L, 61L, 39L, 40L, 46L,
49L, 50L, 50L, 52L, 53L, 87L, 55L, 36L, 51L, 48L, 52L, 42L,
53L, 59L, 50L, 41L, 53L, 53L, 52L, 66L, 60L, 56L, 54L, 53L,
54L, 25L, 34L, 37L, 50L, 38L, 73L, 46L, 72L, 56L, 52L, 59L,
53L, 40L, 62L, 60L, 58L, 64L, 63L, 67L, 59L, 79L, 63L, 95L,
39L, 66L, 75L, 72L, 91L, 79L, 100L), q10 = c(0L, 2L, 3L,
0L, 18L, 25L, 21L, 17L, 22L, 31L, 24L, 16L, 26L, 53L, 37L,
16L, 53L, 40L, 50L, 40L, 61L, 49L, 34L, 44L, 34L, 69L, 47L,
37L, 66L, 24L, 49L, 50L, 35L, 42L, 37L, 56L, 50L, 52L, 66L,
65L, 51L, 41L, 45L, 62L, 46L, 42L, 49L, 50L, 61L, 53L, 69L,
48L, 38L, 51L, 48L, 50L, 69L, 53L, 65L, 58L, 58L, 53L, 53L,
51L, 58L, 57L, 59L, 60L, 53L, 54L, 74L, 48L, 68L, 69L, 52L,
74L, 65L, 47L, 59L, 56L, 67L, 57L, 70L, 61L, 59L, 67L, 63L,
70L, 66L, 53L, 75L, 65L, 72L, 100L, 67L, 100L, 78L, 98L,
100L, 100L), score = structure(c(5.1, 12.8, 15.2, 18.33,
18.8, 21.5, 21.7, 25.1, 28.9, 30.4, 31.6, 32.7, 34, 36.1,
38.2, 39.1, 41.13, 41.3, 41.4, 42, 42.1, 42.2, 42.9, 42.9,
43.1, 44.1, 44.3, 45.44, 45.5, 45.5, 45.6, 45.6, 45.8, 46.22,
47.1, 47.3, 47.5, 47.7, 47.8, 48.1, 48.1, 48.1, 48.2, 48.4,
48.5, 48.6, 48.6, 48.7, 48.89, 48.9, 49.33, 49.7, 50, 50.5,
51, 51.33, 51.9, 51.9, 52.9, 52.9, 53.1, 53.17, 53.2, 53.2,
53.3, 53.5, 53.6, 53.6, 53.7, 54, 54.11, 54.2, 54.5, 54.5,
54.6, 54.9, 54.9, 54.9, 55.4, 56.4, 56.4, 57.9, 58.4, 59,
59.6, 59.7, 59.8, 59.9, 60.1, 61.5, 65.2, 65.7, 66.1, 66.4,
67.9, 70.2, 74.6, 85.1, 89, 99.9), label = "Evaluation Score")), row.names = c(NA,
-100L), class = "data.frame")
I created a basic violin plot with a boxplot, and I want to add an error box. Here is some code:
dplyr::summarize(mean=mean(score), se=sd(score)/sqrt(n()),
upper=mean+(2*se), lower=mean-(2*se))
p <- ggplot() +
geom_violin(data=dt, aes(x=together, y=score, fill=second, color=second)) +
geom_point(data=errbar_lims, aes(x=together, y=mean), size=3) +
geom_errorbar(aes(x=errbar_lims$together, ymax=errbar_lims$upper,
ymin=errbar_lims$lower), stat='identity', width=.25) +
theme_minimal()
print(p)
This is what I get:
The errors are only shown for the two groups.
How can I add define the errors and display an error box to all four violins? I there a way to overlay the error box on the violins? like those:
Any help would be appreciated!

You have a total of four violins on your plot, because you have placed the factor level together along the x axis, and used the column second for your fill aesthetic. Each value of together therefore has two violins: one for "Negative Second" and one for "Positive Second".
The problem is that when you made the data frame errbar_lims, you only grouped by together, so if we examine it we will see it does not contain any information about second. It only has two rows, so can only produce two error bars:
errbar_lims
#> # A tibble: 2 x 5
#> together mean se upper lower
#> <fct> <dbl> <dbl> <dbl> <dbl>
#> 1 Shared Negative 53.3 1.92 57.1 49.4
#> 2 Shared Positive 45.3 2.00 49.3 41.3
What you are looking for is a data frame with four rows to cover all 4 possible combinations of together and second. You could achieve that by doing this:
errbar_lims <- group_by(dt, together, second) %>%
summarize(mean = mean(score),
se = sd(score) / sqrt(n()),
upper = mean + (2 * se),
lower = mean - (2 * se))
If we examine this, we will see it has the four rows that we need for our four error bars:
errbar_lims
#> # A tibble: 4 x 6
#> # Groups: together [2]
#> together second mean se upper lower
#> <fct> <fct> <dbl> <dbl> <dbl> <dbl>
#> 1 Shared Negative Negative Second 55.7 3.35 62.4 49.0
#> 2 Shared Negative Positive Second 50.9 1.91 54.8 47.1
#> 3 Shared Positive Negative Second 45.0 3.02 51.1 39.0
#> 4 Shared Positive Positive Second 45.5 2.69 50.9 40.2
Now we can plot, but we need to remember to tell geom_point and geom_errorbar that they should be grouped according to the second column. We also need to tell them we want the geoms to be dodged so that they are not all plotted between the violins:
ggplot(dt, aes(x = together, fill = second)) +
geom_violin(aes(y = score, color = second)) +
geom_point(data = errbar_lims, aes(x = together, y = mean, group = second),
size = 3,
position = position_dodge(width = 0.9)) +
geom_errorbar(data = errbar_lims,
aes(ymax = upper, ymin = lower, group = second),
stat = 'identity',
position = position_dodge(width = 0.9),
width = 0.25) +
theme_minimal()

Merging error in R

For two example dataframes:
gp <- structure(list(gp.code = structure(c(1L, 3L, 5L, 13L, 6L, 20L,
10L, 19L, 17L, 12L, 2L, 18L, 7L, 16L, 15L, 4L, 8L, 143L, 14L,
9L, 11L, 33L, 23L, 113L, 102L, 97L, 83L, 122L, 77L, 111L, 29L,
68L, 142L, 56L, 118L, 115L, 78L, 58L, 104L, 71L, 43L, 121L, 32L,
110L, 53L, 70L, 123L, 61L, 87L, 48L, 73L, 100L, 37L, 141L, 114L,
34L, 89L, 81L, 98L, 92L, 63L, 50L, 60L, 47L, 125L, 145L, 145L,
93L, 93L, 99L, 99L, 138L, 138L, 137L, 86L, 139L, 91L, 146L, 79L,
103L, 31L, 124L, 22L, 76L, 26L, 108L, 105L, 116L, 84L, 136L,
67L, 106L, 52L, 95L, 51L, 27L, 82L, 130L, 101L, 107L, 133L, 62L,
42L, 117L, 112L, 85L, 69L, 49L, 46L, 45L, 120L, 38L, 39L, 55L,
96L, 80L, 75L, 44L, 35L, 109L, 41L, 24L, 59L, 54L, 144L, 65L,
28L, 25L, 119L, 66L, 74L, 36L, 57L, 21L, 135L, 134L, 132L, 140L,
64L, 127L, 129L, 128L, 131L, 72L, 88L, 40L, 30L, 94L, 90L, 126L
), .Label = c("E82002", "E82014", "E82018", "E82019", "E82023",
"E82031", "E82037", "E82040", "E82041", "E82055", "E82058", "E82059",
"E82060", "E82062", "E82071", "E82077", "E82084", "E82095", "E82107",
"E82113", "M85001", "M85002", "M85005", "M85007", "M85008", "M85009",
"M85011", "M85013", "M85015", "M85019", "M85020", "M85021", "M85024",
"M85025", "M85030", "M85031", "M85037", "M85041", "M85042", "M85043",
"M85047", "M85048", "M85051", "M85052", "M85055", "M85056", "M85058",
"M85059", "M85062", "M85064", "M85065", "M85070", "M85074", "M85076",
"M85077", "M85078", "M85079", "M85084", "M85086", "M85088", "M85092",
"M85097", "M85098", "M85107", "M85111", "M85113", "M85115", "M85116",
"M85118", "M85127", "M85128", "M85134", "M85136", "M85141", "M85142",
"M85145", "M85146", "M85153", "M85154", "M85156", "M85167", "M85171",
"M85174", "M85176", "M85177", "M85178", "M85179", "M85600", "M85611",
"M85624", "M85634", "M85642", "M85652", "M85655", "M85669", "M85671",
"M85679", "M85684", "M85686", "M85693", "M85694", "M85699", "M85701",
"M85713", "M85715", "M85716", "M85717", "M85721", "M85730", "M85733",
"M85735", "M85736", "M85749", "M85753", "M85756", "M85757", "M85770",
"M85774", "M85776", "M85782", "M85783", "M85794", "M85797", "M85801",
"M88020", "M88021", "M89001", "M89002", "M89008", "M89009", "M89012",
"M89013", "M89021", "M89026", "M89027", "Y00412", "Y00471", "Y00492",
"Y01680", "Y02567", "Y02571", "Y02620", "Y02639", "Y02893", "Y02961",
"Y02963"), class = "factor"), cqc.rating = structure(c(1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 5L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 2L, 1L, 1L, 1L, 1L,
5L, 1L, 5L, 1L, 5L, 1L, 5L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 5L, 1L, 1L, 1L, 5L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 1L,
1L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L), .Label = c("good", "inadequate", "not rated",
"oustanding", "requires improvement"), class = "factor")), .Names = c("gp.code",
"cqc.rating"), row.names = c(NA, 150L), class = "data.frame")
df <- structure(list(gp.code = structure(c(1L, 4L, 6L, 14L, 7L, 2L,
21L, 11L, 20L, 18L, 13L, 3L, 19L, 22L, 8L, 17L, 16L, 5L, 9L,
148L, 15L, 10L, 12L, 37L, 25L, 127L, 114L, 109L, 77L, 135L, 98L,
87L, 125L, 79L, 32L, 147L, 64L, 132L, 129L, 88L, 67L, 118L, 68L,
93L, 49L, 82L, 134L, 26L, 35L, 124L, 61L, 81L, 136L, 33L, 71L,
54L, 102L, 46L, 84L, 112L, 43L, 146L, 128L, 24L, 38L, 103L, 95L,
110L, 105L, 74L, 57L, 70L, 53L, 138L, 117L, 39L, 94L, 116L, 149L,
111L, 144L, 106L, 143L, 145L, 101L, 104L, 150L, 89L, 115L, 34L,
137L, 23L, 29L, 86L, 28L, 75L, 83L, 122L, 60L, 66L, 119L, 99L,
130L, 142L, 65L, 78L, 59L, 107L, 120L, 56L, 31L, 58L, 30L, 72L,
96L, 139L, 113L, 121L, 140L, 73L, 48L, 131L, 126L, 42L, 100L,
76L, 80L, 141L, 55L, 52L, 36L, 51L, 133L, 44L, 45L, 63L, 40L,
92L, 108L, 90L, 85L, 50L, 41L, 123L, 91L, 47L, 27L, 69L, 62L,
97L), .Label = c("E82002", "E82004", "E82014", "E82018", "E82019",
"E82023", "E82031", "E82037", "E82040", "E82041", "E82055", "E82058",
"E82059", "E82060", "E82062", "E82071", "E82077", "E82084", "E82095",
"E82107", "E82113", "E82663", "M85002", "M85003", "M85005", "M85006",
"M85007", "M85009", "M85010", "M85011", "M85014", "M85015", "M85018",
"M85020", "M85021", "M85023", "M85024", "M85025", "M85028", "M85029",
"M85030", "M85036", "M85037", "M85041", "M85042", "M85045", "M85047",
"M85048", "M85051", "M85052", "M85055", "M85056", "M85058", "M85059",
"M85062", "M85063", "M85064", "M85065", "M85070", "M85072", "M85074",
"M85076", "M85077", "M85078", "M85081", "M85082", "M85084", "M85085",
"M85086", "M85088", "M85092", "M85094", "M85097", "M85098", "M85100",
"M85105", "M85108", "M85115", "M85116", "M85118", "M85127", "M85128",
"M85133", "M85136", "M85142", "M85145", "M85146", "M85153", "M85154",
"M85156", "M85159", "M85163", "M85164", "M85166", "M85167", "M85171",
"M85172", "M85174", "M85176", "M85177", "M85178", "M85179", "M85611",
"M85634", "M85642", "M85652", "M85669", "M85671", "M85679", "M85684",
"M85686", "M85693", "M85694", "M85699", "M85701", "M85706", "M85711",
"M85713", "M85715", "M85716", "M85717", "M85721", "M85730", "M85733",
"M85735", "M85736", "M85749", "M85753", "M85756", "M85757", "M85770",
"M85774", "M85782", "M85783", "M85794", "M85797", "M85801", "M88020",
"M89009", "M89021", "Y00159", "Y00412", "Y00471", "Y00492", "Y01680",
"Y02571", "Y02620", "Y02639", "Y02961", "Y02963"), class = "factor"),
antibiotic = c(1.23248149651249, 1.19804465710497, 0.753794802511325,
0.85669917849255, 0.806766970145873, 1.2944351625755, 0.79749081458912,
0.949915803767271, 1.28676136005656, 0.861894948337942, 0.98944777231592,
0.77976175611218, 1.0802092104795, 1.18992427754597, 0.922230847446508,
1.00968448247105, 1.00925275017575, 1.13856339619023, 1.29658868391219,
3.43992412181159, 0.9405259515181, 1.04536664449872, 0.857195681526592,
1.36040902899291, 1.1555007762595, 1.23099411388522, 1.2921619764172,
1.20896911806371, 0.90601414991211, 1.48026866615811, 0.865283503864064,
1.34285564503446, 0.919419926661631, 1.41915312988514, 1.2330635342805,
3.66834851140276, 1.2803964023984, 0.777309332259057, 1.16760007845018,
0.903108177347766, 1.07415817045842, 1.76503145582347, 0.662906258393768,
1.11922205065869, 1.45743378132416, 1.40338387936522, 1.56356764856955,
1.21554707497369, 0.765459254266153, 1.02985290952772, 0.747988215118069,
1.28199535302764, 0.791630491986821, 1.45457105212014, 1.5360908424018,
1.36219759497743, 1.2823181822961, 1.16445352400409, 0.867251210987798,
0.93449947713661, 0.972235945064716, 0.952976072770419, 1.01713285255742,
1.0094222885861, 0.875833539680039, 0.618892154842347, 0.472595751806604,
0.496879988390655, 1.50731245234776, 1.04907441178441, 0.894164623526121,
0.658261298693029, 0.726078998206472, 1.02776752877325, 1.19666179452119,
0.97476267236602, 0.0127648710748021, 1.17439331625073, 5.8393330107237,
1.59645232815965, 0.487542408650236, 1.14865894544346, 0.729495610858418,
0.475652186678803, 0.810665743225695, 1.55727483921682, 0.509032628956674,
1.08248967413256, 0.829656197645062, 0.883813971368163, 1.1606344950849,
0.643888106444113, 0.658542420310134, 0.788100265873058,
0.999993653251755, 0.549776366766276, 1.00900222339709, 0.759174545084884,
0.732601429257463, 0.811032584239922, 0.992078825347759,
0.916336303170667, 0.924425842068231, 0.833487920775124,
1.2048401786876, 1.0710312446967, 1.15996384388112, 0.802575397465166,
0.827940641127218, 0.988964351312201, 0.810501627167164,
0.972188732451928, 1.21663117141513, 0.648182525899754, 1.24597821683072,
1.25013278566623, 1.16685772173495, 0.878810966942241, 1.21188990166584,
1.05209718360933, 0.928089616209815, 1.51726626492982, 0.955522092040987,
1.14598540145985, 0.992072220256482, 1.17856657930143, 0.487420516416757,
1.12018266962542, 0.999491890919433, 1.10449907263643, 1.38308178076077,
1.0848078324396, 0.735665641476272, 0.815600508556523, 1.04175344119065,
1.63317262657807, 0.941009543029732, 0.945643608300648, 0.785026349264038,
1.11186113789778, 0.931541465655869, 0.950426305389678, 1.12222589692599,
1.75509240895922, 1.39836663546273, 1.11387374264761, 1.42177823010633,
0.957155370021804, 1.48242155040868, 1.1388984391116)), .Names = c("gp.code",
"antibiotic"), row.names = c(NA, 150L), class = "data.frame")
I wish to merge the data in gp to df. This is a sample of my data, the full version is about 8000 records.
I normally use the code:
new <- merge(df, gp, by=c("gp.code"), all.x=T)
But when I run this, you can see it retrieves 154 records in the 'new' dataframe. As I understand it, the all.x=TRUE refers to all of the records in the df dataframe - why is it picking up more rows of data? If I change it to all.y=TRUE it gets 150 records. When I run this on my full dataset, I cannot back to the number of rows in df (using all.x or all.y = T), just with the additional merged column.
What am I doing wrong? Is there another function which is more appropriate?

ggplot2: Inconsistent color from alpha

I am making several plots that have different x-axis limits, and I want to highlight a region of interest by adding a grey box. Even though I use the same geom_rect() command with the same alpha value in ggplot2, I get results with very different grey colors. I have looked here and here but so far have not figured out how to make these boxes the same level of transparency. Below is a reproducible example (with fake data) and the figures that it produces. Notice the different color of the grey rectangles. I want the grey to be the same across plots.
Data<-structure(list(X = c(34L, 27L, 28L, 47L, 26L, 3L, 13L, 31L, 39L,
16L, 45L, 5L, 49L, 17L, 29L, 43L, 1L, 35L, 41L, 10L, 48L, 24L,
12L, 11L, 30L, 40L, 8L, 4L, 20L, 25L, 50L, 22L, 9L, 21L, 18L,
7L, 15L, 44L, 6L, 36L, 46L, 33L, 2L, 37L, 23L, 14L, 42L, 38L,
19L, 32L, 34L, 27L, 28L, 47L, 26L, 3L, 13L, 31L, 39L, 16L, 45L,
5L, 49L, 17L, 29L, 43L, 1L, 35L, 41L, 10L, 48L, 24L, 12L, 11L,
30L, 40L, 8L, 4L, 20L, 25L, 50L, 22L, 9L, 21L, 18L, 7L, 15L,
44L, 6L, 36L, 46L, 33L, 2L, 37L, 23L, 14L, 42L, 38L, 19L, 32L
), Y = c(130L, 146L, 58L, 110L, 117L, 135L, 133L, 108L, 97L,
61L, 71L, 64L, 103L, 142L, 125L, 104L, 100L, 147L, 111L, 78L,
56L, 145L, 62L, 69L, 70L, 116L, 137L, 79L, 150L, 94L, 91L, 81L,
65L, 118L, 129L, 83L, 98L, 84L, 85L, 148L, 93L, 73L, 59L, 87L,
134L, 88L, 136L, 90L, 140L, 55L, 89L, 115L, 123L, 51L, 132L,
126L, 66L, 80L, 60L, 120L, 109L, 76L, 74L, 57L, 149L, 121L, 138L,
128L, 114L, 127L, 68L, 107L, 67L, 112L, 144L, 119L, 53L, 52L,
54L, 96L, 131L, 106L, 113L, 72L, 95L, 63L, 92L, 86L, 75L, 105L,
82L, 101L, 139L, 143L, 122L, 77L, 99L, 141L, 124L, 102L), B = structure(c(2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 1L, 1L), class = "factor", .Label = c("no", "yes"))), .Names = c("X",
"Y", "B"), row.names = c(NA, -100L), class = "data.frame")
Data2<-structure(list(variable = c(2.49676547444708, 0.67359598601097,
0.674751772966082, 0.0317590441796792, 0.485143583939748, 1.08231639527806,
0.0732344181040914, 1.62357048819912, 0.146833215667032, 0.823157103468943,
0.240761579418538, 1.37540376416553), DOY_mid_month = c(15, 46,
75, 106, 136, 167, 197, 228, 259, 289, 320, 350)), .Names = c("variable",
"DOY_mid_month"), row.names = c(NA, -12L), class = "data.frame")
test<-ggplot(data=Data) +
geom_rect(aes(xmin=5, xmax=30, ymin=1, ymax=40), alpha = 0.02) +
geom_point(aes(x = X, y = X, colour= B), data =Data, size=2) +
theme_bw()
test2 <-ggplot(data=Data2) +
geom_rect(aes(xmin=5, xmax=30, ymin=-Inf, ymax=Inf), alpha = 0.02) +
geom_point(aes(x = DOY_mid_month, y = variable), color="black", size=4) +
scale_x_continuous("Day of Year", limits = c(0, 366)) + # Use this to add back X-axis label for the bottom plot in panel
scale_y_continuous(expression(paste("Variable", sep=""))) +
theme_bw()
Plot result from first example:
Plot result from second example:

You are currently drawing one rectangle for each row of the dataset. The more rectangles you overlap, the darker they get, which is why the longer dataset has a darker rectangle. Use annotate instead of geom_rect to draw a single rectangle.
annotate(geom = "rect", xmin=5, xmax=30, ymin=-Inf, ymax=Inf, alpha = 0.2)
If you want to stick with geom_rect you can give a one row data.frame to that layer so that each rectangle is only drawn one time. Here I use a fake dataset, although you could put your rectangle limits in the data.frame, as well.
geom_rect(data = data.frame(fake = 1),
aes(xmin = 5, xmax= 30, ymin = -Inf, ymax = Inf), alpha = 0.2)

Internal ordering of facets ggplot2

I'm trying to plot a facets in ggplot2 but I struggle to get the internal ordering of the different facets right. The data looks like this:
head(THAT_EXT)
ID FILE GENRE NODE
1 CKC_1823_01 CKC Novels better
2 CKC_1824_01 CKC Novels better
3 EW9_192_03 EW9 Popular Science better
4 H0B_265_01 H0B Popular Science sad
5 CS2_231_03 CS2 Academic Prose desirable
6 FED_8_05 FED Academic Prose certain
str(THAT_EXT)
'data.frame': 851 obs. of 4 variables:
$ ID : Factor w/ 851 levels "A05_122_01","A05_277_07",..: 345 346 439 608 402 484 319 395 228 5 ...
$ FILE : Factor w/ 241 levels "A05","A06","A0K",..: 110 110 127 169 120 135 105 119 79 2 ...
$ GENRE: Factor w/ 5 levels "Academic Prose",..: 4 4 5 5 1 1 1 5 1 5 ...
$ NODE : Factor w/ 115 levels "absurd","accepted",..: 14 14 14 89 23 16 59 59 18 66 ...
Part of the problem is that can't get the sorting right. Here is the code for the sorting of NODE that I use:
THAT_EXT <- within(THAT_EXT,
NODE <- factor(NODE,
levels=names(sort(table(NODE),
decreasing=TRUE))))
When I plot this with the code below I get a graphs in which the NODE is not correctly sorted in the individual GENREs since different NODEs are more frequent in different GENREs:
p1 <-
ggplot(THAT_EXT, aes(x=NODE)) +
geom_bar() +
scale_x_discrete("THAT_EXT", breaks=NULL) + # supress tick marks on x axis
facet_wrap(~GENRE)
What I want is for every facet to have NODE sorted in decreasing order for that particular GENRE. Can anyone help with this?
structure(list(ID = structure(c(1L, 2L, 3L, 4L, 10L, 133L, 137L,
138L, 139L, 140L, 141L, 142L, 143L, 144L, 145L, 146L, 147L, 148L,
149L, 150L, 151L, 152L, 153L, 154L, 155L, 156L, 157L, 158L, 159L,
160L, 161L, 162L, 163L, 164L, 165L, 166L, 167L, 168L, 169L, 170L,
171L, 172L, 173L, 174L, 175L, 176L, 177L, 178L, 179L, 180L, 181L,
182L, 183L, 184L, 185L, 186L, 187L, 188L, 189L, 190L, 191L, 192L,
193L, 194L, 195L, 196L, 197L, 198L, 199L, 200L, 201L, 202L, 203L,
204L, 205L, 206L, 207L, 208L, 212L, 213L, 214L, 215L, 216L, 217L,
218L, 219L, 220L, 221L, 222L, 223L, 224L, 225L, 226L, 227L, 228L,
229L, 230L, 231L, 232L, 233L, 234L, 235L, 236L, 237L, 238L, 239L,
240L, 241L, 267L, 268L, 269L, 270L, 271L, 272L, 273L, 274L, 275L,
276L, 277L, 278L, 279L, 280L, 281L, 282L, 283L, 284L, 290L, 291L,
298L, 299L, 300L, 303L, 304L, 305L, 306L, 307L, 308L, 309L, 310L,
313L, 314L, 315L, 316L, 317L, 318L, 319L, 327L, 328L, 329L, 330L,
331L, 332L, 333L, 334L, 335L, 336L, 337L, 338L, 339L, 340L, 341L,
342L, 343L, 344L, 345L, 346L, 347L, 348L, 352L, 353L, 354L, 355L,
356L, 357L, 358L, 359L, 360L, 349L, 350L, 351L, 361L, 362L, 363L,
364L, 365L, 366L, 367L, 368L, 369L, 370L, 371L, 372L, 373L, 374L,
375L, 376L, 377L, 378L, 379L, 380L, 381L, 12L, 13L, 14L, 15L,
16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L, 27L, 28L,
29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 41L, 42L, 43L, 44L, 45L,
46L, 50L, 54L, 72L, 73L, 74L, 75L, 76L, 90L, 91L, 92L, 97L, 98L,
102L, 115L, 125L, 126L, 127L, 128L, 129L, 130L, 131L, 132L, 209L,
210L, 211L, 242L, 243L, 244L, 245L, 246L, 289L, 292L, 293L, 294L,
295L, 296L, 297L, 301L, 302L, 311L, 312L, 320L, 321L, 322L, 323L,
324L, 325L, 326L, 382L, 383L, 384L, 385L, 386L, 387L, 388L, 5L,
6L, 7L, 8L, 9L, 11L, 37L, 38L, 39L, 40L, 47L, 48L, 49L, 51L,
52L, 53L, 55L, 56L, 57L, 58L, 59L, 60L, 61L, 62L, 63L, 64L, 65L,
66L, 67L, 68L, 69L, 70L, 71L, 77L, 78L, 79L, 80L, 81L, 82L, 83L,
84L, 85L, 86L, 87L, 88L, 89L, 93L, 94L, 95L, 96L, 99L, 100L,
101L, 103L, 104L, 105L, 106L, 107L, 108L, 109L, 110L, 111L, 112L,
113L, 114L, 116L, 117L, 118L, 119L, 120L, 121L, 122L, 123L, 124L,
134L, 135L, 136L, 247L, 248L, 249L, 250L, 251L, 252L, 253L, 254L,
255L, 256L, 257L, 258L, 259L, 260L, 261L, 262L, 263L, 264L, 265L,
266L, 285L, 286L, 287L, 288L), .Label = c("A05_122_01", "A05_277_07",
"A05_400_01", "A05_99_01", "A06_1283_02", "A06_1389_01", "A06_1390_01",
"A06_1441_02", "A06_884_03", "A0K_1190_03", "A77_1684_01", "A8K_525_03",
"A8K_582_01", "A8K_645_01", "A8K_799_01", "A90_341_02", "A90_496_01",
"A94_217_01", "A94_472_01", "A94_477_03", "A9M_164_01", "A9M_259_03",
"A9N_199_01", "A9N_489_01", "A9N_591_01", "A9R_173_01", "A9R_425_02",
"A9W_536_02", "AA5_121_01", "AAE_203_01", "AAE_243_01", "AAE_412_01",
"AAW_14_03", "AAW_244_02", "AAW_297_04", "AAW_365_04", "ADG_1398_01",
"ADG_1500_01", "ADG_1507_01", "ADG_1516_01", "AHB_336_01", "AHB_421_01",
"AHJ_1090_02", "AHJ_619_01", "AR3_340_01", "AR3_91_03", "ARF_879_01",
"ARF_985_01", "ARF_991_02", "ARK_1891_01", "ASL_33_04", "ASL_43_01",
"ASL_9_01", "AT7_1031_01", "B09_1162_01", "B09_1475_01", "B09_1493_01",
"B09_1539_01", "B0G_197_01", "B0G_320_01", "B0N_1037_01", "B0N_624_01",
"B0N_645_02", "B0N_683_01", "B3G_313_04", "B3G_320_03", "B3G_398_02",
"B7M_1630_01", "B7M_1913_01", "BNN_746_02", "BNN_895_01", "BP7_2426_01",
"BP7_2777_01", "BP7_2898_01", "BP9_410_01", "BP9_599_01", "BPK_829_01",
"C93_1407_02", "C9A_181_01", "C9A_196_01", "C9A_365_01", "C9A_82_02",
"C9A_9_01", "CB9_306_02", "CB9_63_04", "CB9_86_01", "CBJ_439_01",
"CBJ_702_02", "CBJ_705_01", "CCM_320_01", "CCM_665_01", "CCM_669_02",
"CCN_1036_02", "CCN_1078_01", "CCN_1119_01", "CCN_784_01", "CCW_2284_02",
"CCW_2349_03", "CE7_242_02", "CE7_284_01", "CE7_39_01", "CEB_1675_01",
"CER_145_03", "CER_23_01", "CER_235_02", "CER_378_10", "CET_1056_02",
"CET_680_01", "CET_705_01", "CET_797_01", "CET_838_01", "CET_879_05",
"CET_946_03", "CET_986_01", "CEY_2977_01", "CJ3_107_02", "CJ3_114_03",
"CJ3_20_01", "CJ3_81_01", "CK2_112_01", "CK2_22_01", "CK2_392_01",
"CK2_42_01", "CK2_75_01", "CKC_1776_01", "CKC_1777_01", "CKC_1823_01",
"CKC_1824_01", "CKC_1860_01", "CKC_1883_01", "CKC_1883_02", "CKC_2127_01",
"CMN_1439_02", "CRM_5767_01", "CRM_5770_03", "CRM_5789_01", "CS2_110_01",
"CS2_131_01", "CS2_139_01", "CS2_187_01", "CS2_187_03", "CS2_231_03",
"CS2_249_02", "CS2_301_01", "CS2_35_01", "CS2_58_02", "EV6_16_01",
"EV6_206_02", "EV6_240_01", "EV6_244_02", "EV6_28_01", "EV6_30_01",
"EV6_32_01", "EV6_450_01", "EV6_69_01", "EV6_80_01", "EV6_91_01",
"FAC_1019_01", "FAC_1026_01", "FAC_1027_01", "FAC_1235_01", "FAC_1269_05",
"FAC_1270_05", "FAC_1393_01", "FAC_1406_03", "FAC_933_01", "FAC_950_01",
"FAC_960_01", "FED_105_01", "FED_120_02", "FED_21_02", "FED_281_02",
"FED_302_02", "FED_53_01", "FED_8_05", "FEF_498_03", "FEF_674_03",
"FR2_410_01", "FR2_557_02", "FR2_593_01", "FR2_691_01", "FR4_232_01",
"FR4_331_01", "FR4_346_01", "FS7_818_01", "FS7_919_01", "FU0_368_02",
"FYT_1138_01", "FYT_1183_01", "FYT_901_05", "G08_1336_01", "G1E_385_01",
"G1N_824_01", "G1N_860_01", "G1N_868_01", "G1N_975_01", "GU5_854_01",
"GUJ_423_01", "GUJ_501_01", "GUJ_611_01", "GUJ_629_03", "GUJ_700_01",
"GV0_10_01", "GV0_104_01", "GV0_111_01", "GV0_122_01", "GV0_160_01",
"GV0_232_02", "GV2_1465_01", "GV2_1899_01", "GV6_2683_01", "GW6_297_01",
"GW6_306_05", "GW6_307_01", "GW6_322_01", "GW6_330_02", "GW6_335_01",
"GW6_338_01", "GW6_367_02", "GW6_373_01", "GW6_407_01", "GW6_411_01",
"GW6_413_01", "GW6_421_01", "GW6_423_01", "GW6_424_01", "GW6_428_01",
"GW6_447_01", "GWM_480_01", "GWM_533_02", "GWM_554_02", "GWM_554_03",
"GWM_609_01", "GWM_609_04", "GWM_610_01", "GWM_730_01", "GWM_731_01",
"GWM_738_01", "GWM_804_06", "GWM_815_01", "GWM_832_03", "GVP_179_01",
"GVP_211_01", "GVP_393_02", "GVP_443_02", "GVP_710_01", "H0B_171_04",
"H0B_216_01", "H0B_265_01", "H0B_32_01", "H0B_361_03", "H0B_365_01",
"H0B_369_01", "H0B_74_01", "H0B_93_01", "H10_1002_01", "H10_1032_04",
"H10_653_01", "H10_803_01", "H10_824_01", "H10_825_03", "H10_881_01",
"H10_986_01", "H78_851_04", "H78_891_01", "H78_946_04", "H79_1959_19",
"H7S_110_05", "H7S_130_06", "H7S_131_03", "H7S_131_04", "H7S_146_01",
"H7S_148_01", "H7S_164_01", "H7S_179_01", "H7S_54_01", "H7S_56_05",
"H7S_62_03", "H7S_79_01", "H7S_8_01", "H7S_81_01", "H7S_83_01",
"H7S_87_01", "H7S_92_03", "H7X_1028_02", "H7X_1091_01", "H7X_691_01",
"H7X_695_01", "H8H_2917_01", "H8K_153_01", "H8K_55_01", "H8M_1897_01",
"H8M_2104_02", "H8T_3316_03", "H98_3204_01", "H98_3410_01", "H98_3490_02",
"H9R_130_02", "H9R_39_01", "H9S_1297_01", "HA2_3107_02", "HA2_3284_01",
"HPY_754_04", "HPY_785_09", "HPY_799_03", "HPY_807_04", "HPY_830_04",
"HPY_838_02", "HPY_843_01", "HPY_869_11", "HR7_190_01", "HR7_440_01",
"HTP_540_01", "HTP_585_01", "HTP_588_05", "HTP_593_01", "HTP_601_01",
"HTP_613_01", "HTP_648_02", "HTW_197_01", "HTW_494_01", "HTW_750_01",
"HWL_2770_01", "HWL_2919_01", "HWM_45_01", "HWM_45_02", "HXY_1047_03",
"HXY_701_01", "HXY_781_01", "HXY_783_01", "HXY_784_01", "HXY_836_01",
"HXY_931_01", "HXY_963_01", "HXY_972_01", "HXY_985_03", "HY6_1024_01",
"HY6_1025_01", "HY6_1164_01", "HY6_1223_01", "HY6_988_03", "HY6_989_01",
"HY8_160_01", "HY8_164_01", "HY8_292_03", "HY8_316_01", "HY9_778_03",
"HY9_845_02", "HYX_235_08", "HYX_245_01", "HYX_88_01", "J12_1474_02",
"J12_1492_01", "J12_1571_01", "J12_1845_01", "J14_341_01", "J18_597_04",
"J18_698_02", "J18_759_01", "J18_828_01", "J3R_197_01", "J3R_219_02",
"J3R_277_04", "J3T_267_01", "J3T_269_02", "J3T_57_02", "J41_41_02",
"J41_58_03", "J9B_133_03", "J9B_341_02", "J9B_341_03", "J9D_147_05",
"J9D_218_01", "J9D_411_01", "J9D_616_01", "J9D_616_02", "JNB_563_02",
"JT7_118_01", "JT7_129_02", "JT7_218_02", "JT7_344_02", "JXS_3663_01",
"JXU_407_01", "JXU_468_02", "JXU_559_01", "JXV_1439_04", "JXV_1592_01",
"JY1_100_01"), class = "factor"), GENRE = structure(c(1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L), .Label = c("Academic Prose", "Conversation", "News",
"Novels", "Popular Science"), class = "factor"), NODE = structure(c(9L,
10L, 10L, 10L, 4L, 10L, 71L, 35L, 49L, 6L, 5L, 15L, 28L, 44L,
64L, 64L, 28L, 28L, 18L, 18L, 32L, 18L, 58L, 10L, 72L, 28L, 18L,
10L, 64L, 10L, 35L, 64L, 64L, 69L, 8L, 10L, 50L, 69L, 49L, 49L,
15L, 69L, 10L, 49L, 8L, 64L, 49L, 10L, 69L, 18L, 61L, 67L, 67L,
61L, 57L, 69L, 11L, 10L, 64L, 10L, 59L, 61L, 49L, 10L, 59L, 1L,
61L, 35L, 54L, 54L, 39L, 44L, 61L, 64L, 69L, 1L, 23L, 49L, 49L,
8L, 69L, 49L, 69L, 49L, 49L, 69L, 35L, 49L, 49L, 49L, 35L, 10L,
49L, 48L, 10L, 49L, 11L, 44L, 50L, 11L, 50L, 69L, 49L, 10L, 59L,
68L, 47L, 69L, 49L, 35L, 29L, 8L, 49L, 50L, 35L, 10L, 35L, 8L,
35L, 8L, 10L, 35L, 10L, 10L, 10L, 35L, 44L, 61L, 35L, 44L, 28L,
47L, 39L, 39L, 49L, 61L, 43L, 60L, 19L, 10L, 10L, 10L, 44L, 44L,
62L, 44L, 10L, 59L, 10L, 61L, 1L, 53L, 33L, 10L, 8L, 8L, 64L,
64L, 10L, 57L, 61L, 64L, 66L, 19L, 61L, 64L, 10L, 10L, 8L, 19L,
35L, 28L, 10L, 61L, 35L, 42L, 35L, 28L, 32L, 64L, 10L, 18L, 28L,
25L, 35L, 35L, 10L, 18L, 10L, 22L, 55L, 28L, 10L, 1L, 55L, 51L,
1L, 38L, 28L, 28L, 33L, 10L, 44L, 29L, 16L, 8L, 28L, 69L, 32L,
10L, 61L, 20L, 35L, 10L, 28L, 10L, 32L, 10L, 46L, 59L, 64L, 35L,
66L, 2L, 35L, 28L, 30L, 18L, 69L, 32L, 10L, 28L, 17L, 36L, 64L,
61L, 10L, 64L, 33L, 3L, 37L, 26L, 28L, 64L, 44L, 28L, 64L, 64L,
6L, 6L, 64L, 50L, 32L, 8L, 64L, 50L, 28L, 24L, 18L, 47L, 35L,
40L, 24L, 55L, 44L, 22L, 1L, 49L, 44L, 18L, 45L, 63L, 64L, 35L,
12L, 35L, 10L, 35L, 10L, 10L, 10L, 44L, 44L, 44L, 65L, 44L, 55L,
32L, 49L, 64L, 39L, 69L, 1L, 60L, 7L, 14L, 44L, 33L, 10L, 19L,
10L, 70L, 53L, 8L, 61L, 61L, 44L, 61L, 65L, 28L, 68L, 69L, 27L,
61L, 28L, 72L, 34L, 61L, 32L, 10L, 49L, 35L, 49L, 10L, 10L, 69L,
39L, 40L, 19L, 59L, 53L, 49L, 49L, 44L, 49L, 35L, 49L, 61L, 61L,
1L, 10L, 28L, 49L, 35L, 49L, 61L, 50L, 69L, 35L, 61L, 35L, 50L,
10L, 28L, 69L, 61L, 21L, 69L, 29L, 35L, 35L, 35L, 11L, 69L, 8L,
41L, 56L, 35L, 61L, 69L, 49L, 49L, 49L, 1L, 13L, 64L, 64L, 52L,
44L, 64L, 64L, 50L, 49L, 69L, 11L, 59L, 49L, 31L), .Label = c("apparent",
"appropriate", "awful", "axiomatic", "best", "better", "breathtaking",
"certain", "characteristic", "clear", "conceivable", "convenient",
"crucial", "cruel", "desirable", "disappointing", "emphatic",
"essential", "evident", "expected", "extraordinary", "fair",
"fortunate", "Funny", "good", "great", "imperative", "important",
"impossible", "incredible", "inescapable", "inevitable", "interesting",
"ironic", "likely", "Likely", "lucky", "ludicrous", "natural",
"necessary", "needful", "notable", "noteworthy", "obvious", "odd",
"paradoxical", "plain", "plausible", "possible", "probable",
"proper", "relevant", "remarkable", "revealing", "right", "Sad",
"self-evident", "sensible", "significant", "striking", "surprising",
"symptomatic", "terrible", "true", "typical", "understandable",
"unexpected", "unfortunate", "unlikely", "unreasonable", "untrue",
"vital"), class = "factor")), .Names = c("ID", "GENRE", "NODE"
), class = "data.frame", row.names = c(NA, -388L))

As I mentioned already: facet_wrap is not intended for having individual scales. At least I didn't find a solution. Hence, setting the labels in scale_x_discrete did not bring the desired result.
But this my workaround:
library(plyr)
library(ggplot2)
nodeCount <- ddply( df, c("GENRE", "NODE"), nrow )
nodeCount$factors <- paste( nodeCount$GENRE, nodeCount$NODE, sep ="." )
nodeCount <- nodeCount[ order( nodeCount$GENRE, nodeCount$V1, decreasing=TRUE ), ]
nodeCount$factors <- factor( nodeCount$factors, levels=nodeCount$factors )
head(nodeCount)
GENRE NODE V1 factors
121 Popular Science possible 14 Popular Science.possible
128 Popular Science surprising 11 Popular Science.surprising
116 Popular Science likely 9 Popular Science.likely
132 Popular Science unlikely 9 Popular Science.unlikely
103 Popular Science clear 7 Popular Science.clear
129 Popular Science true 5 Popular Science.true
g <- ggplot( nodeCount, aes( y=V1, x = factors ) ) +
geom_bar() +
scale_x_discrete( breaks=NULL ) + # supress tick marks on x axis
facet_wrap( ~GENRE, scale="free_x" ) +
geom_text( aes( label = NODE, y = V1+2 ), angle = 45, vjust = 0, hjust=0, size=3 )
Which gives:

Resources