Change x axis labels to hours (time) on geom_tile() - r

Here is a geom_tile displaying hours and days of the week, how can it made to display each hour (i.e. 00:00 through to 23:00 on the x axis)?
library(tidyverse)
df %>%
ggplot(aes(hour, day, fill = value)) +
geom_tile(colour = "ivory")
Currently it displays every fifth hour:
I have tried a bunch of different things, and would prefer a 'best practice' way (i.e. without manually generating labels), but in case labels are needed, here's one way to produce them hour_labs <- 0:23 %>% { ifelse(nchar(.) == 1, paste0("0", .), .) } %>% paste0(., ":00")
Data for reproducible example
df <- structure(list(day = structure(c(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, 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, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L), .Label = c("Sunday",
"Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"
), class = c("ordered", "factor")), hour = c(0L, 2L, 3L, 5L,
6L, 7L, 8L, 10L, 11L, 12L, 13L, 18L, 21L, 22L, 23L, 0L, 1L, 2L,
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 20L, 21L, 22L,
23L, 0L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L,
20L, 21L, 22L, 23L, 0L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
11L, 13L, 14L, 20L, 21L, 22L, 23L, 0L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 9L, 10L, 11L, 12L, 13L, 15L, 20L, 21L, 22L, 23L, 0L,
1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 11L, 13L, 14L, 15L, 16L,
19L, 21L, 0L, 1L, 2L, 3L, 7L, 8L, 10L, 13L, 14L, 22L, 23L), value = c(1L,
1L, 1L, 2L, 1L, 3L, 1L, 1L, 2L, 1L, 3L, 1L, 2L, 13L, 13L, 24L,
39L, 21L, 17L, 25L, 22L, 27L, 28L, 19L, 6L, 2L, 2L, 1L, 2L, 2L,
7L, 23L, 38L, 18L, 26L, 21L, 20L, 31L, 40L, 35L, 22L, 5L, 3L,
2L, 7L, 4L, 3L, 3L, 3L, 17L, 13L, 23L, 24L, 19L, 31L, 13L, 35L,
50L, 22L, 13L, 7L, 2L, 1L, 1L, 1L, 1L, 3L, 14L, 17L, 33L, 32L,
32L, 25L, 29L, 27L, 38L, 26L, 11L, 8L, 4L, 5L, 5L, 3L, 1L, 1L,
3L, 14L, 21L, 24L, 22L, 25L, 26L, 23L, 58L, 36L, 26L, 6L, 3L,
1L, 5L, 3L, 1L, 1L, 3L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L,
1L, 1L)), row.names = c(NA, -116L), groups = structure(list(day = structure(1:7, .Label = c("Sunday",
"Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"
), class = c("ordered", "factor")), .rows = structure(list(1:15,
16:33, 34:51, 52:69, 70:88, 89:105, 106:116), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr"))), row.names = c(NA, 7L), class = c("tbl_df", "tbl",
"data.frame"), .drop = TRUE), class = c("grouped_df", "tbl_df",
"tbl", "data.frame"))

Here's one way using sprintf to construct labels.
library(dplyr)
library(ggplot2)
df %>%
mutate(lab = sprintf('%02d:00', hour)) %>%
ggplot() + aes(lab, day, fill = value) +
geom_tile(colour = "ivory") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
To complete the missing times apart from #Eric Watt's suggestion we can also use complete.
df %>%
mutate(lab = sprintf('%02d:00', hour)) %>%
tidyr::complete(lab = sprintf('%02d:00', 0:23)) %>%
ggplot() + aes(lab, day, fill = value) +
geom_tile(colour = "ivory") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))

I would suggest making sure your data type is correctly representing your data. If your hour column is representing time in hours, then it should be a time based structure. For example:
df$hour <- as.POSIXct(as.character(df$hour), format = "%H", tz = "UTC")
Then you can tell ggplot that the x axis is a datetime variable using scale_x_datetime.
ggplot(df, aes(hour, day, fill = value)) +
geom_tile(colour = "ivory") +
scale_x_datetime(labels = date_format("%H:%M")) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
If you want a break for every hour, you can input that as breaks:
ggplot(df, aes(hour, day, fill = value)) +
geom_tile(colour = "ivory") +
scale_x_datetime(breaks = as.POSIXct(as.character(0:23), format = "%H", tz = "UTC"),
labels = date_format("%H:%M")) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
You can also use the scales package which has handy formatting options such as date_breaks:
library(scales)
ggplot(df, aes(hour, day, fill = value)) +
geom_tile(colour = "ivory") +
scale_x_datetime(breaks = date_breaks("1 hour"),
labels = date_format("%H:%M")) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))

Related

Re-assemble dataframe by index

What I'm trying to do is getting a dataframe where the repeated rows in the first column act as an index to copy the corresponding rows of other columns. I know this sound messy, and my inability to accurately state the issue is one of the reasons I'm having so many problems with this.
I'll provide a reproducible example below.
structure(list(Var1 = structure(c(1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L,
16L, 17L), .Label = c("2016-01", "2016-02", "2016-03", "2016-04",
"2016-05", "2016-06", "2016-07", "2016-08", "2016-09", "2016-10",
"2016-11", "2016-12", "2017-01", "2017-02", "2017-03", "2017-04",
"2017-05"), class = "factor"), Var2 = structure(c(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, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L
), .Label = c("B2B", "B2C", "B2K"), class = "factor"), Freq = c(5L,
13L, 8L, 13L, 36L, 5L, 18L, 1L, 12L, 24L, 22L, 6L, 24L, 15L,
11L, 26L, 1L, 338L, 285L, 291L, 232L, 142L, 42L, 92L, 9L, 46L,
34L, 45L, 35L, 30L, 31L, 36L, 56L, 9L, 0L, 1L, 0L, 0L, 0L, 0L,
7L, 0L, 13L, 0L, 1L, 0L, 0L, 0L, 0L, 2L, 0L)), .Names = c("Var1",
"Var2", "Freq"), class = "data.frame", row.names = c(NA, -51L
))
basically what I want is:
On Var1 no repeated dates
On the row where the date is repeated, take the value of Var2 and Freq and copy them in two new columns to the index of the unique date
This must be done for every distinct level of Var2
Thank you in advance!
I think what your trying to explain is a dcast. Does this end up how you want it?
library(reshape2)
dcast(x,Var1~Var2,value.var="Freq")
A base R option would be
xtabs(Freq~Var1 + Var2, df1)

plot group and category means with group_by

I am new to R and trying to figure out a way to plot means for individual samples as well as group means with ggplot.
I am following this articles on R-bloggers (last paragraph):
https://www.r-bloggers.com/plotting-individual-observations-and-group-means-with-ggplot2/
This is my code:
gd <- meanplot1 %>%
group_by(treatment, value) %>%
summarise(measurement = mean(measurement))
ggplot(meanplot1, aes(x=value, y=measurement, color=treatment)) +
geom_line(aes(group=sample), alpha=0.3) +
geom_line(data=gd, size=3, alpha=0.9) +
theme_bw()
Whilst the sample means are being shown, the group means arenĀ“t. I get the error
geom_path: Each group consists of only one observation. Do you need
to adjust the group aesthetic?
Upon adding group=1, I get a weirdly mixed category mean, but not what I am looking for..
I scrolled through a lot of articles already, but couldnt find an answer - I would be so happy if somebody could help me out here!! :)
My data (meanplot1) is formatted like this:
treatment sample value measurement
1 control, control 1, initial, 20,
2 control, control 1, 26, NA,
3 control, control 1, 26', 28,
12 control, control 2, initial, 22,
13 control control 2, 26, NA,
14 control control 2, 26', 36,
15 control control 2, 28, 45,
67 stressed, stress 1, initial, 37,
68 stressed, stress 1, 26, NA,
69 stressed, stress 1, 26', 17,
78 stressed, stress 2, initial, 36,
79 stressed, stress 2, 26, NA,
80 stressed, stress 2, 26', 25,
I am hoping to see 6 lines, one mean for stress 1, stress 2, control 1 and control 2, and one mean for all treatment=control, and one for all treatment=stressed
output dput(gd):
structure(list(treatment = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L
), .Label = c("control", "stressed"), class = "factor"), value = structure(c(1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 1L, 2L, 3L, 4L, 5L,
6L, 7L, 8L, 9L, 10L, 11L), .Label = c("26", "26'", "28", "28'",
"30", "30'", "32", "32'", "34", "34'", "initial"), class = "factor"),
measurement = c(NA, 32.3333333333333, 39.5, 30.3333333333333,
31.8333333333333, 31.8333333333333, NA, 36, 34.6666666666667,
36, 24.6666666666667, NA, 25.3333333333333, 33.3333333333333,
32, 50.1666666666667, 39.1666666666667, NA, 33.5, 24.3333333333333,
27.3333333333333, 36)), class = c("grouped_df", "tbl_df",
"tbl", "data.frame"), row.names = c(NA, -22L), vars = list(treatment), drop = TRUE, .Names = c("treatment",
"value", "measurement"))
output dput(meanplot1):
structure(list(treatment = 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, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("control",
"stressed"), class = "factor"), sample = structure(c(1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 11L,
11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L), .Label = c("control 1",
"control 2", "control 3", "control 4", "control 5", "control 6",
"stress 1", "stress 2", "stress 3", "stress 4", "stress 5", "stress 6"
), class = "factor"), value = structure(c(11L, 1L, 2L,
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 9L, 10L, 11L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
11L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 1L, 2L, 3L,
4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 9L, 10L, 11L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L,
1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L, 11L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L,
9L, 10L, 11L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L), .Label = c("26", "26'",
"28", "28'", "30", "30'", "32", "32'", "34", "34'", "initial"
), class = "factor"), measurement = c(20L, NA, 28L, 18L, 17L,
19L, 34L, NA, 23L, 29L, 27L, 22L, NA, 36L, 45L, 31L, 40L, 44L,
NA, 49L, 40L, 39L, 32L, NA, 35L, 57L, 30L, 37L, 29L, NA, 44L,
37L, 46L, 20L, NA, 39L, 27L, 30L, 40L, 25L, NA, 29L, 50L, 30L,
26L, NA, 28L, 45L, 47L, 27L, 35L, NA, 24L, 22L, 35L, 28L, NA,
28L, 45L, 27L, 28L, 24L, NA, 47L, 30L, 39L, 37L, NA, 17L, 29L,
29L, 31L, 29L, NA, 37L, 21L, 27L, 36L, NA, 25L, 41L, 51L, 66L,
50L, NA, 33L, 25L, 22L, 36L, NA, 33L, 45L, 26L, 72L, 59L, NA,
33L, 26L, 25L, 33L, NA, 21L, 33L, 25L, 29L, 21L, NA, 26L, 20L,
16L, 22L, NA, 30L, 27L, 28L, 57L, 41L, NA, 28L, 23L, 17L, 52L,
NA, 26L, 25L, 33L, 46L, 35L, NA, 44L, 31L, 57L)), .Names = c("treatment",
"sample", "value", "measurement"), class = "data.frame", row.names = c(NA,
-132L))
I suppose you are aiming to plot the treatment means.
By default, since you are using a categorical x-axis, the grouping is set to the interaction between x and color. You only want to group by treatment, however. So we'll add the correct grouping to the call.
ggplot(meanplot1, aes(x = value, y = measurement, color=treatment)) +
geom_line(aes(group=sample), alpha=0.3) +
geom_line(aes(group = treatment), gd, size=3, alpha=0.9) +
theme_bw()
Also note that
ggplot(meanplot1, aes(x=value, y=measurement, color=treatment)) +
geom_line(aes(group=sample), alpha=0.3) +
stat_summary(aes(group = treatment), fun.y = mean, geom = 'line', size=3, alpha=0.9) +
theme_bw()
Gives the same plot, without the interruption.

How to read multiple line formula for systemfit in R

I am using systemfit to run system of equations using SUR method. I need to read long (multiple line) formula.My simple reproducible dataset can be accessed using following codes.
dat<-structure(list(Time = structure(c(9L, 7L, 15L, 1L, 17L, 13L,
11L, 3L, 23L, 21L, 19L, 5L, 10L, 8L, 16L, 2L, 18L, 14L, 12L,
4L, 24L, 22L, 20L, 6L), .Label = c("Apr-00", "Apr-01", "Aug-00",
"Aug-01", "Dec-00", "Dec-01", "Feb-00", "Feb-01", "Jan-00", "Jan-01",
"Jul-00", "Jul-01", "Jun-00", "Jun-01", "Mar-00", "Mar-01", "May-00",
"May-01", "Nov-00", "Nov-01", "Oct-00", "Oct-01", "Sep-00", "Sep-01"
), class = "factor"), ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), .Label = c("A", "B"), class = "factor"), y1 = c(25L,
14L, 45L, 15L, 24L, 17L, 18L, 19L, 14L, 15L, 25L, 14L, 45L, 15L,
24L, 17L, 18L, 19L, 14L, 15L, 25L, 14L, 45L, 15L), y2 = c(4L,
3L, 4L, 5L, 1L, 4L, 5L, 3L, 6L, 4L, 2L, 5L, 4L, 3L, 4L, 5L, 1L,
4L, 5L, 3L, 6L, 4L, 2L, 5L), x1 = c(3L, 4L, 1L, 8L, 6L, 7L, 9L,
7L, 3L, 1L, 2L, 5L, 6L, 3L, 4L, 1L, 8L, 6L, 7L, 9L, 7L, 3L, 1L,
2L), x2 = c(4L, 3L, 4L, 5L, 1L, 4L, 5L, 3L, 6L, 4L, 2L, 5L, 4L,
3L, 4L, 5L, 1L, 4L, 5L, 3L, 6L, 4L, 2L, 5L), x3 = c(3L, 4L, 2L,
8L, 6L, 7L, 9L, 7L, 3L, 1L, 2L, 5L, 6L, 3L, 4L, 2L, 8L, 6L, 7L,
9L, 7L, 3L, 1L, 2L), x4 = c(4L, 3L, 4L, 5L, 1L, 4L, 5L, 3L, 6L,
4L, 2L, 5L, 4L, 3L, 4L, 5L, 1L, 4L, 5L, 3L, 6L, 4L, 2L, 5L),
x5 = c(3L, 4L, 3L, 8L, 6L, 7L, 9L, 7L, 3L, 1L, 2L, 5L, 6L,
3L, 4L, 3L, 8L, 6L, 7L, 9L, 7L, 3L, 1L, 2L)), .Names = c("Time",
"ID", "y1", "y2", "x1", "x2", "x3", "x4", "x5"), class = "data.frame", row.names = c(NA,
-24L))
My example formula is like this,
model1<- y1 ~ x1 + x2 + x3
+ x4 +x5
eqSystem <- list(model1)
library(systemfit)
fit_prod_SUR <- systemfit(eqSystem, method= "SUR", data=dat)
print(fit_prod_SUR)
I have to include several very long formulas into eqSystem. But my problem is since my formula (e.g. model1) are very long it has got multiple lines. When I run the eqSystem with systemfit, it reads only the variables in the very first line of each formula. I tried with following code, but it does not work.
model1<- (get(paste("y1 ~ x1 + x2 + x3",
" + x4 + x5", sep="")))
But it does not take as a formula. Please could anyone help me to how to read all variables (in multiple lines) of formula in R.

Use dplyr to find genotype frequency across SNPs

To find genotype frequency across SNPs I need to find the proportion of a certain genotype (XX, YX, or YY) in the total number of samples (XX, YX, and YY). I think I would need to start my dplyr statement with
dat %>% group_by(Assay) %>%
but I don't know how to finish it. The data, dat, provided below and dput at the bottom.
Source: local data frame [143 x 3]
Groups: Assay
Assay Final n
1 One_apoe-83 Invalid 2
2 One_apoe-83 No Call 9
3 One_apoe-83 NTC 2
4 One_apoe-83 XX 4
5 One_apoe-83 YX 41
6 One_apoe-83 YY 134
7 One_CD9-269 Invalid 2
8 One_CD9-269 No Call 5
9 One_CD9-269 NTC 2
10 One_CD9-269 XX 99
.. ... ... ...
I could use a for loop across SNPs to get what I'm looking for with boolean patterning for each genotype but that would be very verbose.
for(i in seq(levels(dat$Assay))) {
storage_df[i,1] <- dat[dat$Assay == levels(dat$Assay)[i],]$XX / (dat[dat$Assay == levels(dat$Assay)[i],]$XX + dat[dat$Assay == levels(dat$Assay)[i],]$YX + dat[dat$Assay == levels(dat$Assay)[i],]$XY) ...
You get the point. How would I do this in dplyr? The whole object is below.
dat <- structure(list(Assay = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L,
5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L,
7L, 7L, 8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L, 10L,
10L, 10L, 10L, 10L, 10L, 11L, 11L, 11L, 11L, 11L, 11L, 12L, 12L,
12L, 12L, 12L, 12L, 13L, 13L, 13L, 13L, 13L, 13L, 14L, 14L, 14L,
14L, 14L, 14L, 15L, 15L, 15L, 15L, 15L, 15L, 16L, 16L, 16L, 16L,
16L, 16L, 17L, 17L, 17L, 17L, 17L, 17L, 18L, 18L, 18L, 18L, 18L,
18L, 19L, 19L, 19L, 19L, 19L, 19L, 20L, 20L, 20L, 20L, 20L, 20L,
21L, 21L, 21L, 21L, 21L, 21L, 22L, 22L, 22L, 22L, 22L, 22L, 23L,
23L, 23L, 23L, 23L, 23L, 24L, 24L, 24L, 24L, 24L, 24L), .Label = c("One_apoe-83",
"One_CD9-269", "One_Cytb_26", "One_E2", "One_ghsR-66", "One_IL8r-362",
"One_KPNA-422", "One_lpp1-44", "One_MHC2_190", "One_MHC2_251",
"One_Prl2", "One_redd1-414", "One_STC-410", "One_STR07", "One_sys1-230",
"One_U1004-183", "One_U1105", "One_U1201-492", "One_U1203-175",
"One_U1209-111", "One_U1212-106", "One_U401-224", "One_vamp5-255",
"One_ZNF-61"), class = "factor"), Final = structure(c(1L, 2L,
3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 6L, 1L,
2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L,
6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L,
2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L,
6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L,
2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L,
6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L), .Label = c("Invalid",
"No Call", "NTC", "XX", "YX", "YY"), class = "factor"), n = c(2L,
9L, 2L, 4L, 41L, 134L, 2L, 5L, 2L, 99L, 75L, 9L, 2L, 7L, 2L,
110L, 71L, 2L, 8L, 2L, 110L, 59L, 11L, 2L, 6L, 2L, 67L, 86L,
29L, 2L, 3L, 2L, 152L, 28L, 5L, 2L, 4L, 2L, 78L, 81L, 25L, 2L,
4L, 2L, 115L, 62L, 7L, 2L, 17L, 2L, 80L, 62L, 29L, 2L, 13L, 2L,
59L, 68L, 48L, 2L, 7L, 2L, 48L, 86L, 47L, 2L, 7L, 2L, 42L, 87L,
52L, 2L, 3L, 2L, 47L, 81L, 57L, 2L, 9L, 2L, 40L, 85L, 54L, 2L,
8L, 2L, 52L, 86L, 42L, 2L, 7L, 2L, 9L, 39L, 133L, 2L, 8L, 2L,
101L, 71L, 8L, 2L, 13L, 2L, 20L, 82L, 73L, 2L, 11L, 2L, 27L,
75L, 75L, 2L, 6L, 2L, 3L, 40L, 139L, 2L, 13L, 2L, 59L, 82L, 34L,
2L, 19L, 2L, 20L, 84L, 65L, 2L, 11L, 2L, 119L, 47L, 11L, 2L,
8L, 2L, 51L, 100L, 29L)), class = "data.frame", .Names = c("Assay",
"Final", "n"), row.names = c(NA, -143L))
Hope I am not misunderstanding. Are you looking for below:
Assume the data structure is:
df <- structure(list(Assay = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L), .Label = c("One_apoe-83", "One_CD9-269"), class = "factor"),
Final = structure(c(1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L
), .Label = c("Invalid", "No Call", "NTC", "XX", "YX", "YY"
), class = "factor"), n = c(2L, 9L, 2L, 4L, 41L, 134L, 2L,
5L, 2L, 99L)), .Names = c("Assay", "Final", "n"), class = "data.frame", row.names = c("1",
"2", "3", "4", "5", "6", "7", "8", "9", "10"))
Code
df %>% group_by(Assay) %>% mutate(n_percent = n/sum(n)*100)
# Assay Final n n_percent
# 1 One_apoe-83 Invalid 2 1.041667
# 2 One_apoe-83 No Call 9 4.687500
# 3 One_apoe-83 NTC 2 1.041667
# 4 One_apoe-83 XX 4 2.083333
# 5 One_apoe-83 YX 41 21.354167
# 6 One_apoe-83 YY 134 69.791667
# 7 One_CD9-269 Invalid 2 1.851852
# 8 One_CD9-269 No Call 5 4.629630
# 9 One_CD9-269 NTC 2 1.851852
# 10 One_CD9-269 XX 99 91.666667
Option 2
Here is the code based on the comment. A line is added to filter out the elements you don't want.
df %>%
filter(! Final %in% c("Invalid", "No Call", "NTC")) %>%
group_by(Assay) %>%
mutate(n_percent = n/sum(n)*100)
# Source: local data frame [4 x 4]
# Groups: Assay
#
# Assay Final n n_percent
# 1 One_apoe-83 XX 4 2.234637
# 2 One_apoe-83 YX 41 22.905028
# 3 One_apoe-83 YY 134 74.860335
# 4 One_CD9-269 XX 99 100.000000

Showing data.frame as table or matrix in R

I want to show the following data.frame
df <- structure(list(Variety = structure(c(2L, 3L, 4L, 5L, 6L, 7L,
1L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L,
3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 1L), .Label = c("F2022",
"F9917", "Hegari", "JS2002", "JS263", "PC1", "Sadabahar"), class = "factor"),
Priming = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 1L), .Label = c("CaCl2",
"Dry", "Hydro", "KCL", "KNO3", "NaCl", "Onfarm"), class = "factor"),
Letters = structure(c(1L, 3L, 10L, 11L, 10L, 19L, 27L, 5L,
28L, 11L, 18L, 20L, 9L, 1L, 22L, 14L, 30L, 26L, 24L, 3L,
22L, 9L, 16L, 10L, 15L, 25L, 6L, 7L, 17L, 30L, 18L, 13L,
20L, 27L, 19L, 29L, 23L, 2L, 8L, 12L, 6L, 31L, 8L, 22L, 4L,
32L, 21L, 33L, 2L), .Label = c("a", "at", "bcd", "bclq",
"bcq", "bd", "bds", "chlq", "ds", "e", "efg", "efgmnor",
"efgnor", "efgnr", "efgr", "eg", "fgmnor", "fmnor", "hijkl",
"hijkp", "hikl", "hklq", "ijkmp", "ijmop", "jmop", "mno",
"mnop", "mnor", "su", "t", "uv", "v", "w"), class = "factor")), .Names = c("Variety",
"Priming", "Letters"), row.names = c(NA, -49L), class = "data.frame")
as Table or matrix with Ordered Variety names along rows and Ordered Priming names along columns and showing Letter column in the main body of the table in R.
I could not figure out how to do this. Any help will be highly appreciated. Thanks in advance.
This should do it.
d <- d[order(d$Variety,d$Priming),]
dw <- reshape(data = d, idvar = 'Variety', timevar = 'Priming', direction = 'wide')
dw
You might want to edit the column names.
names(dw) <- gsub('Letters.', '', names(dw), fixed = TRUE)
Simple one
library(reshape2)
acast(data=df, formula=Variety~Priming)
CaCl2 Dry Hydro KCL KNO3 NaCl Onfarm
F2022 at mnop a hklq bds hijkl uv
F9917 a bcq hklq ds fgmnor su chlq
Hegari bcd mnor efgnr eg t ijkmp hklq
JS2002 e efg t e fmnor at bclq
JS263 efg fmnor mno efgr efgnor chlq v
PC1 e hijkp ijmop jmop hijkp efgmnor hikl
Sadabahar hijkl ds bcd bd mnop bd w

Resources