Related
I'm trying to fix an issue with my GGBalloonPlot graph with regards to how R processes the axis labels.
By default R plots the data using the labels ranked in reverse alphabetical order but to reveal the pattern of the data, the data need to be plotted in a specific order. The only way I've been able to do trick the software is by manually adding a prefix to each label in my .csv table so that R would rank them properly in my output. This is time consuming since I need to manually order the data first before adding the prefix and then plotting.
I would like to input a character vector (or something like that) which would essentially specify the order in which I want to have the data plotted which would reveal the pattern without the need for a prefix in the label name.
I have made some attempts with "scale_y_discrete" without success. I would also like to do the same thing for the X axis since I've had to use the same "trick" to display the columns in the proper non-alphabetical order which offsets the position of the labels. Any idea on how to get GGplot to display my values as seen in the graph without having to "trick" the software since this is quite time consuming ?
Data + Code
#Assign data to "Stack_Overflow_DummyData"
Stack_Overflow_DummyData <- structure(list(Species = structure(c(8L, 3L, 1L, 5L, 6L, 2L,
7L, 4L, 8L, 3L, 1L, 5L, 6L, 2L, 7L, 4L, 8L, 3L, 1L, 5L, 6L, 2L,
7L, 4L, 8L, 3L, 1L, 5L, 6L, 2L, 7L, 4L), .Label = c("Ani", "Cal",
"Can", "Cau", "Fis", "Ort", "Sem", "Zan"), class = "factor"),
Species_prefix = structure(c(8L, 7L, 6L, 5L, 4L, 3L, 2L,
1L, 8L, 7L, 6L, 5L, 4L, 3L, 2L, 1L, 8L, 7L, 6L, 5L, 4L, 3L,
2L, 1L, 8L, 7L, 6L, 5L, 4L, 3L, 2L, 1L), .Label = c("ac.Cau",
"ad.Sem", "af.Cal", "ag.Ort", "as.Fis", "at.Ani", "be.Can",
"bf.Zan"), class = "factor"), Dist = structure(c(2L, 3L,
5L, 2L, 1L, 1L, 4L, 5L, 2L, 3L, 5L, 2L, 1L, 1L, 4L, 5L, 2L,
3L, 5L, 2L, 1L, 1L, 4L, 5L, 2L, 3L, 5L, 2L, 1L, 1L, 4L, 5L
), .Label = c("End", "Ind", "Pan", "Per", "Wid"), class = "factor"),
Region = structure(c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Cen", "Col",
"Far", "Nor"), class = "factor"), Region_prefix = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L), .Label = c("a.Far", "b.Nor", "c.Cen", "d.Col"), class = "factor"),
Frequency = c(75, 50, 25, 50, 0, 0, 0, 0, 11.1, 22.2, 55.6,
55.6, 11.1, 0, 5.6, 0, 0, 2.7, 36.9, 27.9, 65.8, 54.1, 37.8,
28.8, 0, 0, 0, 3.1, 34.4, 21.9, 78.1, 81.3)), class = "data.frame", row.names = c(NA,
-32L))
# Plot Data With Prefix Trick
library(ggplot2)
library(ggpubr)
# make color base on Dist, size and alpha dependent on Frequency
ggballoonplot(Stack_Overflow_DummyData, x = "Region_prefix", y = "Species_prefix",
size = "Frequency", size.range = c(1, 9), fill = "Dist") +
theme_set(theme_gray() +
theme(legend.key=element_blank())) +
# Sets Grey Theme and removes grey background from legend panel
theme(axis.title = element_blank()) +
# Removes X axis title (Region)
geom_text(aes(label=Frequency), alpha=1.0, size=3, nudge_x = 0.4)
# Add Frequency Values Next to the circles
# Plot Data Without Prefix Trick
library(ggplot2)
library(ggpubr)
# make color base on Dist, size and alpha dependent on Frequency
ggballoonplot(Stack_Overflow_DummyData, x = "Region", y = "Species",
size = "Frequency", size.range = c(1, 9), fill = "Dist") +
theme_set(theme_gray() +
theme(legend.key=element_blank())) +
# Sets Grey Theme and removes grey background from legend panel
theme(axis.title = element_blank()) +
# Removes X axis title (Region)
geom_text(aes(label=Frequency), alpha=1.0, size=3, nudge_x = 0.4)
# Add Frequency Values Next to the circles
Here below are the graphs
Good Graph.
Using the label prefix trick with the visible pattern in the data:
Wrong Graph (R default).
Without the prefix trick when GGplot automatically orders the data/labels and the graph makes no sense:
To sum up, I would like the Good graph output without having to have to previously add a prefix in my labels.
Many Thanks in advance for your help.
For the axis labels I would define a previous function to override the breaks:
shlab <- function(lbl_brk){
sub("^[a-z]+\\.","",lbl_brk) # removes the starts of strings as a. or ab.
}
Then, to change the labels you just have to use scale_x,y_discrete with labels = shlab (if you look at the help of scale_x_discrete you will see that one of the options for labels is A function that takes the breaks as input and returns labels as output).
For the colours would be enough to change them (values) in scale_fill_manual and for the sizes, using guides so:
library(ggplot2)
library(ggpubr)
shlab <- function(lbl_brk){
sub("^[a-z]+\\.","",lbl_brk)
}
ggballoonplot(Stack_Overflow_DummyData, x = "Region_prefix", y = "Species_prefix", size = "Frequency", size.range = c(1, 9), fill = "Dist") +
scale_x_discrete(labels = shlab) +
scale_y_discrete(labels = shlab) +
scale_fill_manual(values = c("green", "blue", "red", "black", "white")) +
guides(fill = guide_legend(override.aes = list(size=8))) +
theme_set(theme_gray() + theme(legend.key=element_blank())) + # Sets Grey Theme and removes grey background from legend panel
theme(axis.title = element_blank()) + # Removes X axis title (Region)
geom_text(aes(label=Frequency), alpha=1.0, size=3, nudge_x = 0.4) # Add Frequency Values Next to the circles
UPDATE:
With the new dataset and vector labels:
library(ggplot2)
library(ggpubr)
# make color base on Dist, size and alpha dependent on Frequency
ggballoonplot(Stack_Overflow_DummyData, x = "Region", y = "Species",
size = "Frequency", size.range = c(1, 9), fill = "Dist") +
scale_y_discrete(limits = c("Cau", "Sem", "Cal", "Ort", "Fis", "Ani", "Can", "Zan")) +
scale_x_discrete(limits = c("Far", "Nor", "Cen", "Col")) +
theme_set(theme_gray() +
theme(legend.key=element_blank())) +
# Sets Grey Theme and removes grey background from legend panel
theme(axis.title = element_blank()) +
# Removes X axis title (Region)
geom_text(aes(label=Frequency), alpha=1.0, size=3, nudge_x = 0.4)
First of all, thanks^13 to tidyverse. I want the bars in the chart below to follow the same factor levels reordered by forcats::fct_reorder (). Surprisingly, I see different order of levels in the data set when View ()ed as when they are displayed in the chart (see below). The chart should illustrate the number of failed students before and after the bonus marks (I want to sort the bars based on the number of failed students before the bonus).
MWE
ggplot (df) +
geom_bar (aes (forcats::fct_reorder (subject, FailNo, .desc= TRUE), FailNo, fill = forcats::fct_rev (Bonus)), position = 'dodge', stat = 'identity') +
theme (axis.text.x=element_text(angle=45, vjust=1.5, hjust=1.5, size = rel (1.2)))
Data output of dput (df)
structure(list(subject = structure(c(1L, 2L, 5L, 6L, 3L, 7L,
4L, 9L, 10L, 8L, 12L, 11L, 1L, 2L, 5L, 6L, 3L, 7L, 4L, 9L, 10L,
8L, 12L, 11L), .Label = c("CAB_1", "DEM_1", "SSR_2", "RRG_1",
"TTP_1", "TTP_2", "IMM_1", "RRG_2", "DEM_2", "VRR_2", "PRS_2",
"COM_2", "MEB_2", "PHH_1", "PHH_2"), class = "factor"), Bonus = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("After", "Before"), class = "factor"),
FailNo = c(29, 28, 20, 18, 15, 13, 12, 8, 5, 4, 4, 2, 21,
16, 16, 14, 7, 10, 10, 5, 3, 4, 4, 1)), .Names = c("subject",
"Bonus", "FailNo"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA,
-24L))
Bar chart
The issue
According to the table above, SSR_2 var should come in the fifth rank and IMM_1 in the sixth, however in the chart we see these two variables swapping their positions. How to sort it right after tidyverse in this case?
Use factor with unique levels for your x -axis.
ggplot (df) +
geom_bar (aes(factor(forcats::fct_reorder
(subject, FailNo, .desc= TRUE),
levels=unique(subject)),
FailNo,
fill = forcats::fct_rev (Bonus)),
position = 'dodge', stat = 'identity') +
theme(axis.text.x=element_text(angle=45, vjust=1.5, hjust=1.5, size = rel (1.2)))
Edited: #dotorate comment
Sort failNo before the bonus
library(dplyr)
df_before_bonus <- df %>% filter(Bonus == "Before") %>% arrange(desc(FailNo))
Use FailNo before the bonus to create the factor
df$subject <- factor(df$subject, levels = df_before_bonus$subject, ordered = TRUE)
Updated plot
ggplot(df) +
geom_bar(aes (x = subject, y = FailNo, fill = as.factor(Bonus)),
position = 'dodge', stat = 'identity') +
theme (axis.text.x=element_text(angle=45, vjust=1.5, hjust=1.5, size = rel (1.2)))
This question already has answers here:
How to increase size of the points in ggplot2, similar to cex in base plots?
(2 answers)
Closed 8 years ago.
I want to increase the scale of circles in ggplot2. I tried something like this aes(size=100*n) but it did not work for me.
df <-
structure(list(Logit = c(-2.9842723737754, 1.49511606166294,
-2.41756623714116, -2.96160412831003, -2.12996384688938, -1.61751836789074,
-0.454353048358851, 0.9284099250287, -0.144082412641708, -2.30422500981431,
-0.658367257547178, 0.082600042011989, -0.318343575566633, -0.717447827238429,
-1.0508122312565, -2.82559465551781, 0.361703788394458, -1.85086010050691,
-0.0916611209129359, -0.740116072703798, 0.0599317965466193,
-0.370764867295404, -0.703703748477917, -0.749040239408657, -2.7575899191217,
-2.51532401980067, 1.38177483433609, 1.47244781619757, -0.205002348239784,
0.135021333740761), PRes = c(-0.661648371860934, 1.63444424896772,
-0.30348016008728, -0.230651042355737, 1.07487559116003, -0.460143991337599,
-0.823052248365889, -0.999903730870253, -0.959022180953211, -0.321344960297977,
-1.40881799070885, -0.674754839222841, 0.239931843185434, -1.81660411888874,
0.830318780187542, -0.24702802619469, 0.692695708496924, -0.40412065378683,
-0.977640032689132, -0.715192962242284, -1.06270128658429, -0.856103053117159,
-0.731162073769824, 1.51334938767359, 4.02946801536109, 3.56902361409375,
0.505952430753934, 0.483660641952208, 1.13712619443209, 0.951889504154342
), n = c(7L, 38L, 1L, 1L, 11L, 1L, 1L, 4L, 1L, 1L, 3L, 9L, 2L,
8L, 2L, 1L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L)), .Names = c("Logit", "PRes", "n"), row.names = c(NA, -30L
), class = "data.frame")
library(ggplot2)
ggplot(data=df, mapping=aes(x=Logit, y=PRes, label=rownames(df))) +
geom_point(aes(size=n), shape=1, color="black") +
geom_text() +
theme_bw() +
theme(legend.position="none")
Simply add a scale for size:
+ scale_size_continuous(range = c(10, 15))
I don't know what I'm missing but I cannot figure out a very simple task. This is a small piece of my dataframe:
dput(df)
structure(list(ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), .Label = "SOU55", class = "factor"), Depth = c(2L, 4L,
6L, 8L, 10L, 12L, 14L, 16L, 18L, 20L), Value = c(211.8329815,
278.9603866, 255.6111086, 212.6163368, 193.7281895, 200.9584658,
160.9289157, 192.0664419, 174.5951019, 7.162682425)), .Names = c("ID",
"Depth", "Value"), class = "data.frame", row.names = c(NA, -10L
))
What I'm trying to do is simply plotting Depth versus Value with ggplot, this is the simple code:
ggplot(df, aes(Value, Depth))+
geom_point()+
geom_line()
and this the result:
But it is pretty different from what I really want. This is the plot made with Libreoffice:
It seems that ggplot doesn't link correctly the values. What am I doing wrong?
Thanks to all!
You need geom_path() to connect the observations in the original order. geom_line() sorts the data according to the x-aesthetic before plotting:
ggplot(df, aes(Value, Depth))+
geom_point()+
geom_path()
Hopefully someone here will be able to help me with a problem that I'm having with a ggplot script I'm trying to get right. The script will be used many times with different data, so it needs to be relatively flexible. I've got it almost where I want it, but I've come across a problem I haven't been able to solve.
The script is for a line graph with labels for each line in the right hand margin. Sometimes the graph is faceted, other times it is not.
The piece I'm having trouble with is that I would like to color code the labels in the right margin as black if there was no significant change over time, green if there was positive change, and red if there was negative change. I've got a script that works to carry this out when I only have a single facet, but as soon as I have multiple facets in the graph, the color coding of the labels gives the following error
Error: Incompatible lengths for set aesthetics:
Below is the script with data with multiple facets. The problem seems to be in the way that I'm specifying color in the geom_text line. If I delete the color call in the geom_text line in the script, then I get the attributes printed in the correct place, just not colored. I'm really at a loss on this one. This is my first post here, so let me know if I've done anything wrong with my post.
WITH MULTIPLE FACETS (DOES NOT WORK)
require(ggplot2)
require(grid)
require(zoo)
require(reshape)
require(reshape2)
require(directlabels)
time.data<-structure(list(Attribute = structure(c(1L, 1L, 2L, 2L, 3L, 3L,
4L, 4L, 5L, 5L, 6L, 6L), .Label = c("Taste 1", "Taste 2", "Taste 3",
"Use 1", "Use 2", "Use 3"), class = "factor"), Attribute.Category = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Nutritional/Usage",
"Taste/Quality"), class = "factor"), Attribute.Order = c(1L,
1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L, 6L, 6L), Category.Order = c(1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L), Color = structure(c(1L,
1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L, 6L, 6L), .Label = c("#084594",
"#2171B5", "#4292C6", "#6A51A3", "#807DBA", "#9E9AC8"), class = "factor"),
value = c(75L, 78L, 90L, 95L, 82L, 80L, 43L, 40L, 25L, 31L,
84L, 84L), Date2 = structure(c(2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L), .Label = c("1/1/2013", "9/1/2012"), class = "factor")), .Names = c("Attribute",
"Attribute.Category", "Attribute.Order", "Category.Order", "Color",
"value", "Date2"), class = "data.frame", row.names = c(NA, -12L
))
label.data<-structure(list(7:12, Attribute = structure(1:6, .Label = c("Taste 1",
"Taste 2", "Taste 3", "Use 1", "Use 2", "Use 3"), class = "factor"),
Attribute.Category = structure(c(2L, 2L, 2L, 1L, 1L, 1L), .Label = c("Nutritional/Usage",
"Taste/Quality"), class = "factor"), Attribute.Order = 1:6,
Category.Order = c(1L, 1L, 1L, 2L, 2L, 2L), Color = structure(1:6, .Label = c("#084594",
"#2171B5", "#4292C6", "#6A51A3", "#807DBA", "#9E9AC8"), class = "factor"),
Significance = structure(c(2L, 3L, 1L, 1L, 3L, 2L), .Label = c("neg",
"neu", "pos"), class = "factor"), variable = structure(c(1L,
1L, 1L, 1L, 1L, 1L), .Label = "1/1/2013", class = "factor"),
value = c(78L, 95L, 80L, 40L, 31L, 84L), Date2 = structure(c(1L,
1L, 1L, 1L, 1L, 1L), .Label = "2013-01-01", class = "factor"),
label.color = structure(c(1L, 2L, 3L, 3L, 2L, 1L), .Label = c("black",
"forestgreen", "red"), class = "factor")), .Names = c("",
"Attribute", "Attribute.Category", "Attribute.Order", "Category.Order",
"Color", "Significance", "variable", "value", "Date2", "label.color"
), class = "data.frame", row.names = c(NA, -6L))
color.palette<-as.character(unique(time.data$Color))
time.data$Date2<-as.Date(time.data$Date2,format="%m/%d/%Y")
plot<-ggplot()+
geom_line(data=time.data,aes(as.numeric(time.data$Date2),time.data$value,group=time.data$Attribute,color=time.data$Color),size=1)+
geom_text(data=label.data,aes(x=Inf, y=label.data$value, label=paste(" ",label.data$Attribute)),
color=label.data$label.color,
size=4,vjust=0, hjust=0,na.rm=T)+
facet_grid(Attribute.Category~.,space="free")+
theme_bw()+
scale_x_continuous(breaks=as.numeric(unique(time.data$Date2)),labels=format(unique(time.data$Date2),format = "%b %Y"))+
theme(strip.background=element_blank(),
strip.text.y=element_blank(),
legend.text=element_blank(),
legend.title=element_blank(),
plot.margin=unit(c(1,5,1,1),"cm"),
legend.position="none")+
scale_colour_manual(values=color.palette)
gt3 <- ggplot_gtable(ggplot_build(plot))
gt3$layout$clip[gt3$layout$name == "panel"] <- "off"
grid.draw(gt3)
Some problems:
Inside your aesthetic declarations, you should not be referencing the data columns as time.data$Date2, but just as Date2. The data argument specifies where to look for that information (which needs to all be in the same data.frame for a given layer, but, as you take advantage of, can vary layer to layer).
In the geom_text call, color was not inside the aes call; if you are mapping it to data which is in the data.frame, you have to have it inside the aes call. This would throw a different error after fixing the first part because then it would not be able to find label.color anywhere because it would not know to look inside label.data.
Fixing those, then the scale_colour_manual complains that there are 9 colors and you have only supplied 6. That is because there are 6 colors from the lines and 3 from the text. Since you specified these as actual color names, you can just use scale_colour_identity.
Putting this all together:
plot <- ggplot()+
geom_line(data=time.data, aes(as.numeric(Date2), value,
group=Attribute, color=Color),
size=1)+
geom_text(data=label.data, aes(x=Inf, y=value,
label=paste(" ",Attribute),
color=label.color),
size=4,vjust=0, hjust=0)+
facet_grid(Attribute.Category~.,space="free") +
scale_x_continuous(breaks=as.numeric(unique(time.data$Date2)),
labels=format(unique(time.data$Date2),format = "%b %Y")) +
scale_colour_identity() +
theme_bw()+
theme(strip.background=element_blank(),
strip.text.y=element_blank(),
legend.text=element_blank(),
legend.title=element_blank(),
plot.margin=unit(c(1,5,1,1),"cm"),
legend.position="none")
gt3 <- ggplot_gtable(ggplot_build(plot))
gt3$layout$clip[gt3$layout$name == "panel"] <- "off"
grid.draw(gt3)
To get an idea how much you can strip down your example, this is much closer to minimal:
time.data <-
structure(list(Attribute = structure(c(1L, 1L, 2L, 2L, 3L, 3L,
4L, 4L), .Label = c("Taste 1", "Taste 2", "Use 1", "Use 2"), class = "factor"),
Attribute.Category = structure(c(2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L), .Label = c("Nutritional/Usage", "Taste/Quality"), class = "factor"),
Color = c("#084594", "#084594", "#2171B5", "#2171B5", "#6A51A3",
"#6A51A3", "#807DBA", "#807DBA"), value = c(75L, 78L, 90L,
95L, 43L, 40L, 25L, 31L), Date2 = structure(c(15584, 15706,
15584, 15706, 15584, 15706, 15584, 15706), class = "Date")), .Names = c("Attribute",
"Attribute.Category", "Color", "value", "Date2"), row.names = c(NA,
-8L), class = "data.frame")
label.data <-
structure(list(value = c(78L, 95L, 40L, 31L), Attribute = structure(1:4, .Label = c("Taste 1",
"Taste 2", "Use 1", "Use 2"), class = "factor"), label.color = c("black",
"forestgreen", "red", "forestgreen"), Attribute.Category = structure(c(2L,
2L, 1L, 1L), .Label = c("Nutritional/Usage", "Taste/Quality"), class = "factor"),
Date2 = structure(c(15706, 15706, 15706, 15706), class = "Date")), .Names = c("value",
"Attribute", "label.color", "Attribute.Category", "Date2"), row.names = c(NA,
-4L), class = "data.frame")
ggplot() +
geom_line(data = time.data,
aes(x=Date2, y=value, group=Attribute, colour=Color)) +
geom_text(data = label.data,
aes(x=Date2, y=value, label=Attribute, colour=label.color),
hjust = 1) +
facet_grid(Attribute.Category~.) +
scale_colour_identity()
The theme stuff (and the making the labels visible outside the plot) isn't relevant to the question, nor is the x-axis conversions from Date to numeric to handle having Inf. I also trimmed the data to just the needed columns, and reduced categorical variable to only two categories.