Ordered and Sorted ggplot Bar Graph - r

I am trying to create a bar graph of an interaction between 'Treatment' and 'Day' from my data set. I want 'Treatment' to be sorted in the following order: 'Before', 'During', and 'After' and I would also like 'Day' 1 and 2 'Before', 'During', and 'After' next to each other, rather than having each 'Day' grouped together. Here is my data set:
structure(list(Name = structure(c(9L, 9L, 5L, 5L, 14L, 14L, 15L,
15L, 1L, 1L, 7L, 7L, 12L, 12L, 2L, 2L, 11L, 11L, 16L, 16L, 13L,
13L, 6L, 6L, 8L, 8L, 3L, 3L, 4L, 4L, 10L, 10L, 9L, 9L, 5L, 5L,
14L, 14L, 15L, 15L, 1L, 1L, 7L, 7L, 12L, 12L, 2L, 2L, 11L, 11L,
16L, 16L, 13L, 13L, 6L, 6L, 8L, 8L, 3L, 3L, 4L, 4L, 10L, 10L,
9L, 9L, 5L, 5L, 14L, 14L, 15L, 15L, 1L, 1L, 7L, 7L, 12L, 12L,
2L, 2L, 11L, 11L, 16L, 16L, 13L, 13L, 6L, 6L, 8L, 8L, 3L, 3L,
4L, 4L, 10L, 10L), .Label = c("DSGW", "DSOR", "DSYB", "GSWP",
"LSGL", "LSLL", "OSLL", "PSYP", "PSYR", "RSBB", "RSBP", "RSYY",
"WSGG", "WSPB", "WSRR", "WSRW"), class = "factor"), Day = c(1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L),
Treatment = structure(c(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, 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, 3L, 3L, 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), .Label = c("After",
"Before", "During"), class = "factor"), Behavior = c(3040L,
3219L, 2378L, 3529L, 3135L, 3702L, 2868L, 3035L, 1614L, 833L,
1255L, 1224L, 1569L, 1433L, 1567L, 1448L, 1197L, 1619L, 1543L,
1309L, 1738L, 1378L, 1362L, 1603L, 1109L, 1073L, 570L, 822L,
815L, 1166L, 0L, 835L, 3060L, 2815L, 2875L, 3394L, 3009L,
3274L, 2350L, 2455L, 972L, 815L, 983L, 1033L, 1520L, 1477L,
1461L, 1395L, 1242L, 1368L, 1637L, 1275L, 1646L, 1546L, 1064L,
971L, 596L, 1461L, 1276L, 1272L, 872L, 1026L, 1249L, 592L,
2277L, 3022L, 2997L, 3495L, 2591L, 3447L, 2479L, 2701L, 175L,
452L, 1287L, 1355L, 1252L, 1501L, 1371L, 1147L, 1465L, 1003L,
1510L, 0L, 1744L, 1026L, 959L, 898L, 1529L, 1092L, 417L,
289L, 40L, 762L, 1495L, 896L)), .Names = c("Name", "Day",
"Treatment", "Behavior"), class = "data.frame", row.names = c(NA,
-96L))
Here is the script I am using to produce my current figure:
ggplot(perch1, aes(x = interaction(Treatment,Day), y = Behavior, fill = factor(Day)))


An alternative would be to use facet wrap to plot each treatment in a separate panel.
ggplot(df, aes(x = factor(Day), y = Behavior, fill = factor(Day))) +
geom_bar(stat = 'identity') + facet_wrap(~Treatment, nrow = 1)
This won't label your interaction on the X-axis, but instead puts it in the panel title.


One option is to just add a new column to your data.frame and manually specify the order of the levels, rather than messing around with interaction:
library(ggplot2)
##
df$Group <- factor(
paste0(df$Day," : ",df$Treatment),
paste0(rep(1:2,3)," : ",
rep(c("Before","During","After"),each=2)))
##
R> ggplot(
df,
aes(x=Group,
y=Behavior,
fill=factor(Day)))+
geom_bar(stat='identity')+
scale_x_discrete(
labels=paste0("Day ",levels(df$Group)))

Related

ggalluvial assign different color for each node

I was following this post, but I do not get how can I manage it with my data.
My plot looks like:
And I would like that the "strings" were the same color as the 2nd column, i.e. for ESR1 I would like the orange string, and for PIK3CA green.
Any idea about how can I manage with scale_fill_manual or any other argument?
Thanks!
My code:
colorfill <- c("white", "white", "darkgreen", "orange", "white", "white", "white", "white", "white", "white", "white", "white", "white", "white", "white", "white", "white")
ggplot(data = Allu,
aes(axis1 = Gene_mut, axis2 = Metastasis_Location, y = Freq)) +
geom_alluvium(aes(fill = Gene_mut),
curve_type = "quintic") +
geom_stratum(width = 1/4, fill = colorfill) +
geom_text(stat = "stratum", size = 3,
aes(label = after_stat(stratum))) +
scale_x_discrete(limits = c("Metastasis_Location", "Gene_mut"),
expand = c(0.05, .05)) +
theme_void()
My data:
structure(list(Metastasis_Location = structure(c(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,
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, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 9L, 9L, 9L, 10L,
10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 11L, 11L, 11L, 11L, 11L,
11L, 11L), .Label = c("adrenal", "bone", "breast", "liver", "lung",
"muscle", "node", "pancreatic", "peritoneum", "pleural", "skin"
), class = "factor"), T0_T2_THERAPY_COD = structure(c(2L, 2L,
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, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 2L, 2L, 2L, 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, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("A",
"F"), class = "factor"), T0_T2_PD_event = structure(c(2L, 2L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 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, 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, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 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, 1L,
2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L), .Label = c("No Progression",
"Progression"), class = "factor"), Gene_mut = structure(c(4L,
5L, 1L, 3L, 4L, 1L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 5L, 5L, 5L, 6L, 3L, 6L, 6L, 6L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L,
5L, 6L, 2L, 3L, 4L, 4L, 3L, 3L, 3L, 4L, 5L, 6L, 3L, 6L, 3L, 3L,
3L, 3L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 3L, 4L, 4L, 5L, 6L,
1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L,
5L, 5L, 5L, 3L, 4L, 3L, 4L, 5L, 6L, 3L, 3L, 4L, 5L, 6L, 6L, 6L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 3L, 4L, 3L, 4L, 5L,
6L, 3L, 4L, 5L, 6L, 3L, 4L, 5L, 6L, 1L, 6L, 3L, 3L, 4L, 4L, 5L
), .Label = c("AKT1", "ERBB2", "ESR1", "PIK3CA", "TP53", "WT"
), class = "factor"), LABO_ID = structure(c(45L, 8L, 13L, 11L,
11L, 26L, 7L, 15L, 23L, 26L, 35L, 39L, 7L, 19L, 26L, 32L, 33L,
35L, 39L, 15L, 19L, 35L, 1L, 37L, 34L, 43L, 47L, 3L, 10L, 18L,
20L, 28L, 31L, 36L, 42L, 9L, 10L, 14L, 18L, 20L, 28L, 31L, 36L,
44L, 45L, 8L, 10L, 18L, 28L, 42L, 2L, 7L, 39L, 7L, 39L, 3L, 4L,
42L, 5L, 42L, 6L, 21L, 1L, 10L, 22L, 28L, 46L, 9L, 10L, 14L,
28L, 46L, 10L, 28L, 48L, 25L, 23L, 32L, 33L, 40L, 43L, 24L, 3L,
18L, 24L, 28L, 31L, 36L, 42L, 18L, 27L, 28L, 31L, 36L, 45L, 18L,
24L, 27L, 28L, 42L, 16L, 16L, 18L, 18L, 18L, 29L, 23L, 39L, 39L,
40L, 1L, 12L, 47L, 3L, 18L, 20L, 28L, 31L, 36L, 38L, 42L, 5L,
18L, 20L, 27L, 28L, 31L, 36L, 38L, 41L, 45L, 8L, 18L, 27L, 28L,
42L, 48L, 6L, 17L, 30L, 31L, 31L, 18L, 18L, 18L, 29L, 39L, 39L,
40L, 43L, 31L, 31L, 48L, 30L, 13L, 34L, 18L, 36L, 18L, 36L, 18L
), .Label = c("ER-11", "ER-19", "ER-21", "ER-22", "ER-29", "ER-30",
"ER-31", "ER-32", "ER-33", "ER-38", "ER-40", "ER-43", "ER-49",
"ER-8", "ER-AZ-04", "ER-AZ-05", "ER-AZ-06", "ER-AZ-07", "ER-AZ-08",
"ER-AZ-10", "ER-AZ-11", "ER-AZ-11=ER-47", "ER-AZ-13", "ER-AZ-14",
"ER-AZ-15", "ER-AZ-16", "ER-AZ-17", "ER-AZ-18", "ER-AZ-20", "ER-AZ-20=ER-27",
"ER-AZ-21", "ER-AZ-23", "ER-AZ-23=ER-52", "ER-AZ-24", "ER-AZ-29",
"ER-AZ-31", "ER-AZ-33", "ER-AZ-35", "ER-AZ-37", "ER-AZ-38", "ER-AZ-39",
"ER-AZ-40", "ER-AZ-43", "ER-AZ-44", "ER-AZ-45", "ER-AZ-49", "ER-AZ-51",
"ER-AZ-53"), class = "factor"), Freq = 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)), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"), row.names = c(NA, -161L), groups = structure(list(
Metastasis_Location = structure(c(1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 8L, 8L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 10L, 10L,
10L, 10L, 10L, 11L, 11L, 11L, 11L, 11L), .Label = c("adrenal",
"bone", "breast", "liver", "lung", "muscle", "node", "pancreatic",
"peritoneum", "pleural", "skin"), class = "factor"), T0_T2_THERAPY_COD = structure(c(2L,
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L), .Label = c("A",
"F"), class = "factor"), T0_T2_PD_event = structure(c(2L,
2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L,
2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L,
2L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L), .Label = c("No Progression",
"Progression"), class = "factor"), Gene_mut = structure(c(4L,
5L, 1L, 3L, 4L, 1L, 2L, 3L, 4L, 5L, 6L, 3L, 6L, 3L, 4L, 5L,
6L, 2L, 3L, 4L, 3L, 4L, 5L, 6L, 3L, 6L, 3L, 4L, 5L, 6L, 3L,
4L, 5L, 6L, 1L, 3L, 4L, 5L, 3L, 4L, 3L, 4L, 5L, 6L, 3L, 4L,
5L, 6L, 6L, 3L, 4L, 5L, 6L, 3L, 4L, 3L, 4L, 5L, 6L, 3L, 4L,
5L, 6L, 3L, 4L, 5L, 6L, 1L, 6L, 3L, 4L, 5L), .Label = c("AKT1",
"ERBB2", "ESR1", "PIK3CA", "TP53", "WT"), class = "factor"),
.rows = structure(list(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8:12,
13:19, 20:22, 23L, 24L, 25:27, 28:35, 36:45, 46:50, 51L,
52L, 53L, 54:55, 56:58, 59L, 60L, 61L, 62L, 63L, 64:67,
68:72, 73:75, 76L, 77L, 78:79, 80L, 81L, 82L, 83:89,
90:95, 96:100, 101L, 102L, 103L, 104L, 105L, 106L, 107:108,
109L, 110L, 111:112, 113L, 114:121, 122:131, 132:137,
138:140, 141L, 142L, 143L, 144L, 145L, 146L, 147L, 148L,
149L, 150L, 151L, 152L, 153L, 154L, 155L, 156L, 157:158,
159:160, 161L), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr", "list"))), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -72L), .drop = TRUE))

You're right to think of scale_fill_manual(). I think this is the more programmable alternative to passing a vector like colorfill to an aesthetic outside aes(). The following plot uses your data and color vector to control how the fill aesthetic is coded throughout the plot, and notice that fill is passed the same variable, Gene_mut, in both layers (alluvium and stratum):
ggplot(data = Allu,
aes(axis1 = Gene_mut, axis2 = Metastasis_Location, y = Freq)) +
geom_alluvium(aes(fill = Gene_mut),
curve_type = "quintic") +
geom_stratum(aes(fill = Gene_mut), width = 1/4) +
scale_fill_manual(values = colorfill) +
geom_text(stat = "stratum", size = 3,
aes(label = after_stat(stratum))) +
scale_x_discrete(limits = c("Metastasis_Location", "Gene_mut"),
expand = c(0.05, .05)) +
theme_void()
Since Metastasis_Location takes different values than Gene_mut, fill treats those strata as having missing values, which by default are colored grey. You can change that behavior by passing a color string to the na.value parameter of scale_fill_manual().

Group columns and fit in one plot

I have the following data-frame:
structure(list(inst = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("A8",
"b7", "X1"), class = "factor"), steps = structure(c(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, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("5",
"10", "20"), class = "factor"), family = structure(c(6L,
1L, 4L, 5L, 7L, 2L, 3L, 6L, 7L, 5L, 4L, 1L, 2L, 3L, 3L, 6L, 4L,
1L, 2L, 7L, 5L, 6L, 5L, 4L, 1L, 7L, 2L, 3L, 6L, 5L, 4L, 7L, 1L,
2L, 3L, 6L, 1L, 3L, 5L, 4L, 2L, 7L, 6L, 4L, 1L, 5L, 7L, 2L, 3L,
6L, 4L, 1L, 5L, 7L, 2L, 3L, 6L, 3L, 5L, 4L, 7L, 1L, 2L), .Label = c("Bay",
"Grad", "none", "Upp", "base", "new", "tuna"
), class = "factor"), mean_error = c(5.930259, 6.0611, 6.241703,
6.270109, 6.277435, 6.587473, 6.865757, 5.936106, 6.084044, 6.140153,
6.142072, 6.146425, 6.364658, 6.621481, 6.759502, 7.02175, 7.16422,
7.19518, 7.36932, 7.395606, 7.44191, 5.113961, 5.123312, 5.289946,
5.292267, 5.455671, 5.768393, 5.840368, 5.140513, 5.346728, 5.371491,
5.463127, 5.475944, 5.602034, 5.995647, 5.784786, 6.00454, 6.121524,
6.22509, 6.24901, 6.37396, 6.41903, 4.0439, 4.223119, 4.260518,
4.31062, 4.500065, 4.822419, 5.107085, 4.221596, 4.371242, 4.505292,
4.524415, 4.681877, 4.703846, 5.14499, 4.944005, 5.007325, 5.0561975,
5.1926225, 5.3353825, 5.34204, 5.63557)), row.names = c(64L,
3L, 38L, 55L, 73L, 12L, 21L, 67L, 76L, 58L, 41L, 6L, 15L, 24L,
27L, 70L, 44L, 9L, 18L, 79L, 61L, 63L, 54L, 37L, 2L, 72L, 11L,
20L, 66L, 57L, 40L, 75L, 5L, 14L, 23L, 69L, 8L, 26L, 60L, 43L,
17L, 78L, 62L, 36L, 1L, 53L, 71L, 10L, 19L, 65L, 39L, 4L, 56L,
74L, 13L, 22L, 68L, 25L, 59L, 42L, 77L, 7L, 16L), class = "data.frame")
I am trying to create groups of three steps per inst in the x-axis and fit everything in one plot. The outcome should resemble this
So far I tried:
df_bri %>% select(steps, inst, family, mean_error) %>%
ggplot(aes(x = steps, y = mean_error, fill = mean_error)) +
geom_boxplot()
and I get this:
I don't know how to separate the groups into 3 steps per inst.

fill=steps is what you need:
ggplot(df, aes(x = inst, y = mean_error, fill = steps)) +
geom_boxplot()

barchart - axis ticks are not adjusted according to the bars

I have to draw a bar chart in R ggplot2 with multiple variables (i.e each bar for BMI, weight, cholesterol, Blood pressure etc) in each group ( i.e. different populations ex: Indian, Korean, Philipinos etc.) But the bars are overflowing to the next group in the axis. for example: the bars of the Indian group is overflowing to Korean group. The axis marks are not adjusted accordingly. I have attached the figure .. can someone please help. Following is my code. dput(data) is also given.
p = ggplot(data = t,
aes(x = factor(Population, levels = names(sort(table(Population), increasing = TRUE))),
y = Snp_Count,
group = factor(Trait, levels = c("BMI", "DBP", "HDL", "Height", "LDL", "TC", "TG", "WC", "Weight"),
ordered = TRUE)))
p = p + geom_bar(aes(fill = Trait),
position = position_dodge(preserve = "single"),
stat = "identity") +
scale_fill_manual(values = c("#28559A", "#3EB650", "#E56B1F", "#A51890", "#FCC133", "#663300", "#6666ff", "#ff3300", "#ff66ff")) +
coord_flip()
structure(list(Trait = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L, 9L), .Label = c("BMI",
"DBP", "HDL", "HT", "LDL", "TC", "TG", "WC", "Weight"), class = "factor"),
Association = 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), .Label = "Direct", class = "factor"), TraitClass = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 1L, 1L, 1L, 1L, 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, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Anthropometric",
"BP", "Lipid"), class = "factor"), Population = structure(c(2L,
3L, 4L, 5L, 7L, 8L, 10L, 11L, 12L, 13L, 22L, 24L, 3L, 5L,
11L, 22L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L,
14L, 15L, 18L, 20L, 28L, 5L, 7L, 13L, 14L, 1L, 3L, 5L, 7L,
9L, 11L, 12L, 16L, 18L, 20L, 22L, 5L, 6L, 7L, 10L, 12L, 18L,
20L, 3L, 5L, 6L, 7L, 8L, 11L, 12L, 13L, 14L, 15L, 18L, 19L,
20L, 21L, 22L, 23L, 26L, 28L, 3L, 4L, 5L, 8L, 12L, 22L, 24L,
3L, 5L, 7L, 8L, 17L, 25L, 27L), .Label = c("ACB", "AFR",
"ASW", "ASW/ACB", "CEU", "CHB", "EAS", "Filipino", "FIN",
"GBR", "Hispanic", "Hispanic/Latinos", "JPT", "Korean", "Kuwaiti",
"Micronesian", "Moroccan", "MXL", "Mylopotamos", "Orcadian",
"Pomak", "SAS", "Saudi_Arabian", "Seychellois", "Surinamese",
"Taiwanese", "Turkish", "YRI"), class = "factor"), Snp_Count = c(3L,
12L, 6L, 17L, 2L, 10L, 1L, 6L, 3L, 3L, 10L, 6L, 1L, 1L, 1L,
1L, 2L, 1L, 10L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 3L, 1L, 1L,
2L, 1L, 2L, 20L, 5L, 4L, 1L, 1L, 2L, 7L, 2L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 8L, 2L, 4L, 3L, 1L, 2L, 1L, 4L, 20L, 5L,
11L, 2L, 4L, 3L, 4L, 2L, 3L, 4L, 1L, 1L, 1L, 2L, 2L, 1L,
2L, 3L, 2L, 4L, 4L, 1L, 4L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L
), Gene_Count = c(3L, 9L, 7L, 9L, 2L, 8L, 1L, 7L, 3L, 2L,
8L, 7L, 1L, 1L, 1L, 1L, 2L, 1L, 4L, 1L, 1L, 1L, 1L, 2L, 2L,
1L, 2L, 1L, 1L, 1L, 1L, 1L, 9L, 6L, 5L, 1L, 1L, 2L, 5L, 2L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 6L, 2L, 3L, 3L, 1L, 2L, 1L, 3L,
10L, 4L, 7L, 1L, 3L, 3L, 4L, 1L, 3L, 5L, 1L, 1L, 1L, 3L,
3L, 1L, 1L, 2L, 2L, 3L, 3L, 1L, 3L, 2L, 3L, 3L, 2L, 3L, 2L,
2L, 2L)), class = "data.frame", row.names = c(NA, -86L))

The total width of each group in your barchart is 0.9 by default, which means that 90% of the area is covered. When you increase the width of the individual bars to 3 they will overlap with other groups, the maximum value for with should thus be 1 and then it will touch the other groups.
I'd suggest in your situation to use facet_wrap instead of a dodged barchart.
Note: geom_col is the same as geom_bar(stat = "identity).
my.df$Trait <- factor(my.df$Trait, levels = c("BMI", "DBP", "HDL", "HT", "LDL", "TC", "TG", "WC", "Weight"))
my.df$Population <- factor(my.df$Population, levels = names(sort(table(my.df$Population), increasing = TRUE)))
ggplot(my.df, aes(x = Trait, y = Snp_Count, fill = Trait)) +
geom_col(width = 1) +
scale_fill_manual(values = c("#28559A", "#3EB650", "#E56B1F", "#A51890", "#FCC133", "#663300", "#6666ff", "#ff3300", "#ff66ff")) +
# Split the data by Population, allow flexible scales and spacing for y axis (Trait)
facet_grid(Population ~ ., scales = "free_y", space = "free_y", switch = "y") +
coord_flip() +
theme(axis.text.y = element_blank(), # Remove Trait labels (indicated by color)
axis.ticks.y = element_blank(), # Remove tick marks
strip.background = element_blank(),
strip.text.y = element_text(angle = 180, hjust = 1), # Rotate Population labels
panel.spacing.y = unit(3, "pt")) # Spacing between groups
Data
my.df <-
structure(list(Trait = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L, 9L),
.Label = c("BMI", "DBP", "HDL", "HT", "LDL", "TC", "TG", "WC", "Weight"), class = "factor"),
Population = structure(c(2L, 3L, 4L, 5L, 7L, 8L, 10L, 11L,
12L, 13L, 22L, 24L, 3L, 5L, 11L, 22L, 3L, 4L, 5L, 6L, 7L,
8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 18L, 20L, 28L, 5L,
7L, 13L, 14L, 1L, 3L, 5L, 7L, 9L, 11L, 12L, 16L, 18L, 20L,
22L, 5L, 6L, 7L, 10L, 12L, 18L, 20L, 3L, 5L, 6L, 7L, 8L,
11L, 12L, 13L, 14L, 15L, 18L, 19L, 20L, 21L, 22L, 23L, 26L,
28L, 3L, 4L, 5L, 8L, 12L, 22L, 24L, 3L, 5L, 7L, 8L, 17L,
25L, 27L),
.Label = c("ACB", "AFR", "ASW", "ASW/ACB", "CEU",
"CHB", "EAS", "Filipino", "FIN", "GBR", "Hispanic", "Hispanic/Latinos",
"JPT", "Korean", "Kuwaiti", "Micronesian", "Moroccan", "MXL",
"Mylopotamos", "Orcadian", "Pomak", "SAS", "Saudi_Arabian",
"Seychellois", "Surinamese", "Taiwanese", "Turkish", "YRI"), class = "factor"),
Snp_Count = c(3L, 12L, 6L, 17L, 2L,
10L, 1L, 6L, 3L, 3L, 10L, 6L, 1L, 1L, 1L, 1L, 2L, 1L, 10L,
1L, 1L, 2L, 1L, 2L, 1L, 1L, 3L, 1L, 1L, 2L, 1L, 2L, 20L,
5L, 4L, 1L, 1L, 2L, 7L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 8L,
2L, 4L, 3L, 1L, 2L, 1L, 4L, 20L, 5L, 11L, 2L, 4L, 3L, 4L,
2L, 3L, 4L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 3L, 2L, 4L, 4L, 1L,
4L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L)),
class = "data.frame", row.names = c(NA, -86L))

Weird results in ANOVA: the three-way interaction has a pvalue of exactly 1

I am running a three way interaction, predicting 'judgment' from 'factor_1' (between subject, two levels), 'factor_2' (between subject, two levels) and factor_3 (within subject, two levels). I have 120 participants (30 in each level of factor_1 and factor_2)
model <- aov(
judgment ~ factor_1*factor_2*factor_3 +
Error(participant/factor_3),
data = MyData)
summary(model)
I got a strange 3 way interaction result: the Sum Sq, Mean Sq, and F value have a value of (exactly) 0, and the p value is 1.
How is it possible?
Here are my data:
MyData = structure(list(participant = structure(c(1L, 1L, 2L, 2L, 3L,
3L, 4L, 4L, 5L, 5L, 6L, 6L, 7L, 7L, 8L, 8L, 9L, 9L, 10L, 10L,
11L, 11L, 12L, 12L, 13L, 13L, 14L, 14L, 15L, 15L, 16L, 16L, 17L,
17L, 18L, 18L, 19L, 19L, 20L, 20L, 21L, 21L, 22L, 22L, 23L, 23L,
24L, 24L, 25L, 25L, 26L, 26L, 27L, 27L, 28L, 28L, 29L, 29L, 30L,
30L, 31L, 31L, 32L, 32L, 33L, 33L, 34L, 34L, 35L, 35L, 36L, 36L,
37L, 37L, 38L, 38L, 39L, 39L, 40L, 40L, 41L, 41L, 42L, 42L, 43L,
43L, 44L, 44L, 45L, 45L, 46L, 46L, 47L, 47L, 48L, 48L, 49L, 49L,
50L, 50L, 51L, 51L, 52L, 52L, 53L, 53L, 54L, 54L, 55L, 55L, 56L,
56L, 57L, 57L, 58L, 58L, 59L, 59L, 60L, 60L, 61L, 61L, 62L, 62L,
63L, 63L, 64L, 64L, 65L, 65L, 66L, 66L, 67L, 67L, 68L, 68L, 69L,
69L, 70L, 70L, 71L, 71L, 72L, 72L, 73L, 73L, 74L, 74L, 75L, 75L,
76L, 76L, 77L, 77L, 78L, 78L, 79L, 79L, 80L, 80L, 81L, 81L, 82L,
82L, 83L, 83L, 84L, 84L, 85L, 85L, 86L, 86L, 87L, 87L, 88L, 88L,
89L, 89L, 90L, 90L, 91L, 91L, 92L, 92L, 93L, 93L, 94L, 94L, 95L,
95L, 96L, 96L, 97L, 97L, 98L, 98L, 99L, 99L, 100L, 100L, 101L,
101L, 102L, 102L, 103L, 103L, 104L, 104L, 105L, 105L, 106L, 106L,
107L, 107L, 108L, 108L, 109L, 109L, 110L, 110L, 111L, 111L, 112L,
112L, 113L, 113L, 114L, 114L, 115L, 115L, 116L, 116L, 117L, 117L,
118L, 118L, 119L, 119L, 120L, 120L), .Label = c("101", "102",
"103", "104", "105", "106", "107", "108", "109", "110", "111",
"112", "113", "114", "115", "116", "117", "118", "119", "120",
"121", "122", "123", "124", "125", "126", "127", "128", "129",
"130", "131", "132", "133", "134", "135", "136", "137", "138",
"139", "140", "141", "142", "143", "144", "145", "146", "147",
"148", "149", "150", "151", "152", "153", "154", "155", "156",
"157", "158", "159", "160", "161", "162", "163", "164", "165",
"166", "167", "168", "169", "170", "171", "172", "173", "174",
"175", "176", "177", "179", "180", "181", "182", "183", "184",
"185", "186", "187", "188", "189", "190", "191", "192", "193",
"194", "195", "196", "197", "198", "199", "200", "201", "202",
"203", "204", "205", "206", "207", "208", "209", "210", "211",
"212", "213", "214", "215", "216", "217", "218", "219", "220",
"221"), class = "factor"), factor_1 = structure(c(2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L), .Label = c("L",
"P"), class = "factor"), factor_2 = structure(c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L), .Label = c("1",
"2"), class = "factor"), factor_3 = structure(c(1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L), .Label = c("HighLoss",
"LowLoss"), class = "factor"), judgment = c(10L, 5L, 10L, 10L,
5L, 5L, 5L, 1L, 7L, 5L, 8L, 7L, 5L, 5L, 10L, 10L, 3L, 6L, 4L,
6L, 10L, 10L, 10L, 6L, 10L, 10L, 1L, 1L, 8L, 8L, 6L, 6L, 8L,
10L, 8L, 1L, 5L, 5L, 4L, 4L, 3L, 3L, 5L, 2L, 10L, 10L, 8L, 8L,
7L, 5L, 7L, 10L, 10L, 10L, 4L, 4L, 5L, 5L, 5L, 5L, 10L, 10L,
6L, 6L, 3L, 2L, 6L, 6L, 7L, 5L, 10L, 9L, 8L, 8L, 6L, 5L, 6L,
6L, 8L, 10L, 6L, 6L, 7L, 7L, 5L, 5L, 10L, 6L, 10L, 10L, 10L,
6L, 10L, 10L, 10L, 7L, 8L, 8L, 10L, 10L, 9L, 10L, 10L, 10L, 6L,
8L, 10L, 10L, 6L, 6L, 6L, 3L, 6L, 8L, 5L, 7L, 10L, 10L, 7L, 5L,
3L, 3L, 6L, 3L, 10L, 10L, 10L, 10L, 10L, 7L, 8L, 10L, 8L, 5L,
9L, 6L, 6L, 6L, 8L, 8L, 10L, 10L, 10L, 10L, 5L, 5L, 6L, 3L, 9L,
9L, 2L, 1L, 6L, 6L, 10L, 10L, 8L, 8L, 4L, 8L, 5L, 9L, 10L, 10L,
10L, 10L, 8L, 8L, 5L, 5L, 8L, 8L, 4L, 3L, 6L, 6L, 1L, 1L, 10L,
10L, 10L, 10L, 7L, 9L, 8L, 8L, 7L, 7L, 5L, 5L, 6L, 6L, 5L, 5L,
8L, 8L, 1L, 1L, 2L, 3L, 8L, 6L, 8L, 8L, 8L, 6L, 7L, 9L, 10L,
10L, 4L, 4L, 10L, 10L, 10L, 10L, 10L, 10L, 5L, 5L, 1L, 1L, 10L,
10L, 4L, 1L, 10L, 10L, 6L, 6L, 7L, 7L, 7L, 9L, 5L, 5L, 10L, 10L,
7L, 2L)), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA,
-240L), .Names = c("participant", "factor_1", "factor_2", "factor_3",
"judgment"))

drawing line segments connecting sets of points

I am trying to connect sets of (two) points at each level of x, in each facet. Here is a reproducible example:
datum <- structure(list(frequency = c(8L, 7L, 6L, 18L, 5L, 11L, 16L, 15L,
9L, 8L, 8L, 10L, 2L, 20L, 14L, 3L, 6L, 2L, 2L, 11L, 10L, 6L,
15L, 19L, 18L, 18L, 8L, 2L, 10L, 15L, 12L, 17L, 1L, 18L, 7L,
8L, 16L, 4L, 9L, 2L, 7L, 3L, 16L, 7L, 18L, 20L, 9L, 10L, 13L,
2L, 15L, 7L, 3L, 20L, 4L, 15L, 5L, 7L, 9L, 16L, 5L, 8L, 10L,
10L, 7L, 10L, 10L, 17L, 7L, 8L, 13L, 13L, 16L, 5L, 20L, 18L,
13L, 19L, 3L, 8L, 14L, 12L, 20L, 2L, 9L, 13L, 7L, 2L, 5L, 5L,
13L, 9L, 13L, 7L, 9L, 4L, 4L, 20L, 1L, 4L), band = structure(c(2L,
4L, 2L, 3L, 2L, 1L, 4L, 1L, 2L, 1L, 3L, 4L, 2L, 4L, 3L, 4L, 3L,
2L, 3L, 2L, 2L, 4L, 2L, 1L, 1L, 2L, 1L, 4L, 4L, 1L, 4L, 4L, 2L,
1L, 4L, 4L, 3L, 4L, 1L, 1L, 3L, 4L, 1L, 3L, 4L, 1L, 2L, 1L, 1L,
2L, 2L, 1L, 3L, 4L, 2L, 1L, 2L, 4L, 2L, 2L, 4L, 4L, 2L, 4L, 4L,
1L, 1L, 4L, 2L, 3L, 4L, 1L, 2L, 4L, 1L, 2L, 4L, 1L, 1L, 3L, 4L,
4L, 2L, 2L, 2L, 1L, 3L, 2L, 2L, 2L, 3L, 3L, 1L, 3L, 4L, 3L, 3L,
1L, 3L, 4L), .Label = c("1", "2", "3", "4"), class = "factor"),
test = structure(c(1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L,
2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
1L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L,
2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L
), .Label = c("1", "2"), class = "factor"), knowledge = structure(c(2L,
3L, 1L, 3L, 1L, 1L, 3L, 3L, 1L, 3L, 1L, 3L, 2L, 2L, 1L, 1L,
1L, 1L, 3L, 3L, 1L, 2L, 3L, 1L, 1L, 2L, 2L, 1L, 1L, 3L, 2L,
3L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 3L, 3L, 1L, 1L, 2L, 3L,
3L, 2L, 2L, 3L, 1L, 1L, 2L, 2L, 2L, 3L, 1L, 3L, 1L, 1L, 2L,
1L, 1L, 2L, 3L, 1L, 1L, 1L, 1L, 3L, 2L, 2L, 1L, 2L, 3L, 2L,
1L, 2L, 3L, 3L, 2L, 1L, 3L, 1L, 3L, 2L, 1L, 3L, 2L, 2L, 3L,
1L, 1L, 2L, 1L, 2L, 3L, 1L, 3L, 1L), .Label = c("1", "2",
"3"), class = "factor")), .Names = c("frequency", "band",
"test", "knowledge"), row.names = c(NA, -100L), class = "data.frame")
Here is the code I have so far:
ggplot(datum, aes(knowledge, frequency, color=test)) +
stat_summary(fun.y='mean', geom='point', position=position_dodge(width=.9), size=3) +
facet_grid(~band) +
labs(y='number of words (max = 20)', x='self-report knowledge') +
scale_x_discrete(labels=c('none', 'form', 'meaning'))
Looking at the left-most facet ('1') in the graph, I would like a line to connect the pretest to posttest in the none column, another line connecting pretest to posttest in the form column, and a line connecting the pretest to the posttest in the meaning column. I would like this done in each facet.
I hope that makes sense, and thanks!

I find relying on ggplot too much for data manipulation/summarizing can hurt more than it helps. I have no idea how to connect the position-dodged points with a line. Instead, I'd do something like this:
library(dplyr)
datsum = datum %>%
group_by(band, knowledge, test) %>%
summarize(mean = mean(frequency)) %>%
ungroup %>%
mutate(knowledge_fac = factor(knowledge, labels = c('none', 'form', 'meaning')))
ggplot(datsum, aes(x = test, y = mean)) +
geom_path(aes(group = band:knowledge)) +
geom_point(aes(color = factor(test))) +
facet_grid(band ~ knowledge_fac) +
labs(y='number of words (max = 20)', x='self-report knowledge')

Borrowing from Gregor's work in munging the data, I think this does what was requested. The mutate() chunk creates Test to be a numeric offset of -0.1 for test 1 and 0.1 for test 2. This is then added to the numeric value of knowledge. The result is the numeric x passed to ggplot2. Gregor correctly defined the groups, so the rest is straightforward.
library(dplyr)
datsum <- datum %>%
group_by(band, knowledge, test) %>%
summarize(mean = mean(frequency)) %>%
mutate(Test = 0.1 * (2 * (test == 2) - 1),
Knowledge = as.numeric(knowledge) + Test) %>%
ungroup
ggplot(datsum, aes(x = Knowledge, y = mean, color = test)) +
geom_path(aes(group = band:knowledge), color = "black") +
geom_point(size = 3) +
facet_wrap(~ band, nrow = 1) +
labs(y='number of words (max = 20)', x='self-report knowledge') +
scale_color_manual(values = c("orange", "blue")) +
scale_x_continuous(limits = c(0.5, 3.5), breaks = 1:3,
labels = c("none", "form", "meaning"))

Resources