Related
Change secondary line axis color changes send color for ggplot, but I chose to go with base R, and would like to be able to select the second y axis color.
I have the following data:
df = structure(list(A = c("Q4-17", "Q1-18", "Q2-18", "Q3-18", "Q4-18",
"Q1-19", "Q2-19", "Q3-19", "Q4-19", "Q1-20", "Q2-20", "Q3-20",
"Q4-20", "Q1-21", "Q2-21", "Q3-21", "Q4-21", "Q1-22", "Q2-22",
"Q3-22"), B = c(69.45, 71.1, 74.94, 73.87, 93.61, 91.83,
95.38, 109.8, 133.75, 125.26, 118.22, 145.65, 144.9757185, 155.3464032,
184.367033, 179.8121721, 187.235487, 189.1684376, 184.3864519,
161.5300056), C = c(70.73, 71.73, 74.33, 73.27,
95.94, 94.38, 95.38, 109.8, 115.32, 116.92, 115.9, 113.87, 106.108147,
96.84273563, 111.5150869, 110.1228567, 110.7448835, 194.9684376,
187.7241152, 167.7665553), D = c(260.3, 216.02, 203.72,
203.52, 300.96, 320.77, 330.5, 413.52, 436.7, 474.96, 463.6,
501.87, 493.8865461, 497.1760767, 514.9903459, 503.7601267, 510.8362938,
614.9915546, 603.5761107, 593.660831), E = c(NA,
NA, NA, NA, NA, NA, NA, NA, 39.237, 35.621, 32.964, NA, 152.137,
140.743023, 167.809, 170.877, 117.517, 102.691723, 88.8, 76.2445528
)), class = "data.frame", row.names = c(NA, -20L))
df = df %>%
rowwise() %>%
mutate(sums = sum(D,E, na.rm = TRUE))
df = df[8:nrow(df),]
and this to generate my plot
x <- seq(1,nrow(df),1)
y1 <- df$B
y2 <- df$D
par(mar = c(5, 4, 4, 4) + 0.3)
plot(x, y1, col = "#000000",
type = "l",
main = "title",
ylim = c(0, max(df[,2:3])),
ylab = "Y1",
xlab = "",
xaxt = "n")
axis(1,
at = seq(from = 13, by = -4, length.out = 4),
labels = df$A[seq(from = 13, by = -4, length.out = 4)])
lines(x, df$C, lty = "dashed", col = "#adadad", lwd = 2)
par(new = TRUE)
plot(x, df$sums, col = "#ffa500",
axes = FALSE, xlab = "", ylab = "", type = "l")
axis(side = 4, at = pretty(range(y2)),
ylim = c(0,max(df[,3:5], na.rm = TRUE)),
col = "#00aa00") # Add colour selection of 2nd axis
par(new = TRUE)
plot(x, df$D , col = "#0000ff",
axes = FALSE, xlab = "", ylab = "", type = "l", lwd = 1)
mtext("y2", side = 4, line = 3)
but this does not colour my complete second y axis, nor labels, nor title
does any one have any suggestions to be able to set entire y2 axis to be #00AA00 - ticks, labels, and title?
Plotting an xts should be really easy, but I can't seem to get the xlab, and ylab to work..
ylab="Price"
xlab="Date"
plot(x = basket[, 1], lty="dotted", xlab = xlab, ylab = ylab, col = "mediumblue", lwd = 2)
title("Cumulative")
This will plot the figure, but without any labels on the x- and y-axis.
There must be an easy solution to this. The plot looks as it should besides that issue. I have tried with xts.plot, zoo.plot, xyplot but none seem to do the trick.
Data sample
structure(c(1, 1.01463414634146, 0.926829268292683, 0.970731707317073,
0.953658536585366, 1, 0.998263888888889, 1.01159722222222, 1.05076388888889,
1.05034722222222, 1, 1.00178890876565, 0.985688729874776, 1.04293381037567,
1.04651162790698, 1, 0.976675478152698, 0.990359197636448, 1.06515316436013,
1.04571606282071), class = c("xts", "zoo"), index = structure(c(946944000,
947030400, 947116800, 947203200, 947462400), tzone = "UTC", tclass = "Date"), .Dim = 5:4, .Dimnames = list(
NULL, c("new.close", "new.close.1", "new.close.2", "new.close.3"
)))
It is plot.zoo, not zoo.plot. These all work for me:
library(xts)
plot(as.zoo(basket[, 1]), xlab = "X", ylab = "Y")
plot.zoo(basket[, 1], xlab = "X", ylab = "Y")
library(lattice)
xyplot(basket[, 1], xlab = "X", ylab = "Y")
library(ggplot2)
autoplot(basket[, 1]) + xlab("X") + ylab("Y")
Note
basket <-
structure(c(1, 1.01463414634146, 0.926829268292683, 0.970731707317073,
0.953658536585366, 1, 0.998263888888889, 1.01159722222222, 1.05076388888889,
1.05034722222222, 1, 1.00178890876565, 0.985688729874776, 1.04293381037567,
1.04651162790698, 1, 0.976675478152698, 0.990359197636448, 1.06515316436013,
1.04571606282071), class = c("xts", "zoo"), index = structure(c(946944000,
947030400, 947116800, 947203200, 947462400), tzone = "UTC", tclass = "Date"), .Dim = 5:4, .Dimnames = list(
NULL, c("new.close", "new.close.1", "new.close.2", "new.close.3"
)))
I know this might not be exactly what you had in mind, but it gets the job done. Plus, you get to work with ggplot2 which way better than the standard plotting system. In addition, I am using ggfortify which extends ggplot() capabilities to handle time series.
library(xts)
library(zoo)
library(ggfortify)
library(ggplot2)
myts = structure(
c(1, 1.01463414634146, 0.926829268292683, 0.970731707317073,
0.953658536585366, 1, 0.998263888888889, 1.01159722222222, 1.05076388888889,
1.05034722222222, 1, 1.00178890876565, 0.985688729874776, 1.04293381037567,
1.04651162790698, 1, 0.976675478152698, 0.990359197636448, 1.06515316436013,
1.04571606282071),
class = c("xts", "zoo"),
index = structure(c(946944000, 947030400,
947116800, 947203200,
947462400),
tzone = "UTC",
tclass = "Date"),
.Dim = 5:4, .Dimnames = list(NULL,
c("new.close",
"new.close.1",
"new.close.2",
"new.close.3" ) )
)
autoplot( myts[ , 1], xlab = "Date", ylab = "Price" )
Created on 2020-05-05 by the reprex package (v0.3.0)
I have the following toy data
Xeafield (1999) (PER) ,1,0.5745375408
Lancelot et al. (1989),0.9394939494,0.4733405876
LemLM Xeafield (1997) (TER) ,0.6265126513,0.2959738847
Almore and Flemin (2001) (KER),0.4218921892,0.5745375408
Malek et al. (2006) (HER) ,0.4125412541,1
Charles and Osborne (2003),0.0308030803,0.1414581066
And trying a simple 2D plot in R with points labeled using the 1st column.
pdf('data.pdf', width = 7, height = 8)
d1 <- read.csv("data.csv", header=F, dec=".",sep = ",")
plot(as.matrix(d1[,2]), as.matrix(d1[,3]), col= "blue", pch = 19, cex = 1, lty = "solid", lwd = 2, ylim=c(0,1), xaxt = "n",yaxt = "n")
text(as.matrix(d1[,2]), as.matrix(d1[,3]), labels=as.matrix(d1[,1]), cex= 0.7, pos=3)
x_axis_range <- c(0,1)
x_axis_labels <- c("Small","Large")
axis(1,at = x_axis_range, labels = x_axis_labels)
y_axis_range <- c(0,1)
y_axis_labels <- c("Slow","Fast")
axis(2,at = y_axis_range, labels = y_axis_labels)
title(xlab="Memory", ylab="Speed",cex.lab=1)
dev.off()
But the plot doesn't come out right. A few issues I have: the axis label are messed up (it shows as.matrix ..., instead of the label I specified), and the margin of the plot is to small that node labels are cutoff. I am new to using R and plot, appreciate your help.
A simple solution for your problem is to define axis labels and axis ranges in the plot function.
d1 <- structure(list(V1 = structure(c(6L, 3L, 4L, 1L, 5L, 2L), .Label = c("Almore and Flemin (2001) (KER)",
"Charles and Osborne (2003)", "Lancelot et al. (1989)", "LemLM Xeafield (1997) (TER) ",
"Malek et al. (2006) (HER) ", "Xeafield (1999) (PER) "), class = "factor"),
V2 = c(1, 0.9394939494, 0.6265126513, 0.4218921892, 0.4125412541,
0.0308030803), V3 = c(0.5745375408, 0.4733405876, 0.2959738847,
0.5745375408, 1, 0.1414581066)), .Names = c("V1", "V2", "V3"
), class = "data.frame", row.names = c(NA, -6L))
# Use xlab and ylab for axis labels and
# and xlim and ylim for setting axis ranges
plot(as.matrix(d1[,2]), as.matrix(d1[,3]), col= "blue", pch = 19,
cex = 1, lty = "solid", lwd = 2, ylim=c(-0.1,1.1), xaxt = "n",yaxt = "n",
xlab="Memory", ylab="Speed",cex.lab=1, xlim=c(-0.1,1.1))
text(as.matrix(d1[,2]), as.matrix(d1[,3]),
labels=as.matrix(d1[,1]), cex= 0.7, pos=3)
x_axis_range <- c(0,1)
x_axis_labels <- c("Small","Large")
axis(1,at = x_axis_range, labels = x_axis_labels)
y_axis_range <- c(0,1)
y_axis_labels <- c("Slow","Fast")
axis(2,at = y_axis_range, labels = y_axis_labels)
I have a table (below) showing the percentage of tree species (categorical variable) present in a group experiment. My objective is to plot the percentage of tree species on the y-axis and 'Species' on the x-axis within a barplot.
Issue
My problem is that I am experiencing problems with formatting the x-axis correctly. My objective is to ensure that the x-axis labels for**'Species'** are:-
Positioned directly underneath their bar at the tick mark
Do not overlap onto the plotting area
If anyone can help solve this issue, I would be incredibly grateful.
R code
df <- leaf.percent[order(leaf.percent$Leaf.Percentge, decreasing = TRUE),]
Tree.labels<-c("Quercus robar", "Quercus Patraea",
"Deciduous", "Oak",
"Plant", "Shrub")
par(mar=c(6, 6, 3, 3))
Tree<-barplot(df$Leaf.Percentge, names.arg = df$Species,
xaxt = "n",
ylab="Percentage %",
xlab="Tree Species",
col="lightblue",
ylim = c(0, 60))
axis(1, at=Tree, labels=FALSE)
text(seq(1, 6, by=1), par("usr")[3] - 0.2,
labels=unique(Tree.labels),
srt = 25, pos = 1,
xpd = TRUE, cex=0.7)
DATA
structure(list(Species = structure(1:6, .Label = c("Deciduous",
"Oak", "Plant", "Quercus_petraea", "Quercus_robur", "Shrub"), class = "factor"),
Frequency = c(48L, 29L, 6L, 70L, 206L, 4L), Leaf.Percentge = c(13.2231404958678,
7.98898071625344, 1.65289256198347, 19.2837465564738, 56.7493112947658,
1.10192837465565)), .Names = c("Species", "Frequency", "Leaf.Percentge"
), row.names = c(NA, -6L), class = "data.frame")
Load sample data frame
df <- structure(list(ID = c(1,1,1,2,2,2,3,3,3),
time = c(0L,1L,2L,0L,1L,2L,0L,1L,2L),
M1a = c(0, 0.2, 0.3, 0, 1.5, 2.9,0, 2.4, 3.9),
M2a = c(0, 0.4, 0.6,0,0.9, 0.9,0,0.5, 0.7),
M3a = c(0,0.3, 0.4, 0, 0.6, 0.9,0, 0.5, 0.8),
M4a = c(0,0.6, 0.6,0, 0.4, 0.6,0, 0.2, 0.9),
M1b = c(0L, 200L, 300L,0L, 300L, 900L,0L, 900L, 1000L),
M2b = c(0L, 400L, 600L,0L, 600L, 900L,0L, 600L, 1000L),
M3b = c(0L, 300L, 400L,0L, 200L, 800L,0L, 200L, 900L),
M4b = c(0L, 600L, 600L,0L, 800L, 1000L,0L, 400L, 1100L)),
.Names = c("ID", "time", "M1a", "M2a", "M3a", "M4a","M1b", "M2b","M3b", "M4b"), class = "data.frame", row.names = c(NA, -9L))
Now plot two y-axis scatter plot
par(mar=c(5,4,4,5)+.1)
plot(df$time,df$M1a,type="p",col="red", main="M1", cex=0.5, cex.main=2, cex.lab=1.0, cex.axis=0.7)
par(new = TRUE)
plot(df$time,df$M1b,type="p",col="blue",xaxt="n",yaxt="n",xlab="",ylab="")
mtext("Relative change (%)",side=4,line=3)
axis(4)
legend("topleft",col=c("red","blue"),lty=1,legend=c("Absolute Change","Relative Change"))
What I am stuck with?
1.Median trend line
I was able to add regression line, but I want to have a median trend line connecting M1a and M1b medians for three time points.
2.Adding p-values to the plot, repeated one-way anova test
fit1=aov(df$M1a~df$time + Error(ID/time),na.action=na.exclude,data=df);
sig1= summary(fit1)$"Error: Within"$"Pr(>F)"
if (sig<0.001) star='**' else if (sig>=0.001&sig<0.05) star='*' else star='';
if (sig1<0.001) star='**' else star='';
I was planning to add use above code for adding p-value in my 2-y axis plot. Here, I get sig1 as NULL, however, sig1 should print out 0.153.
The final results should include * mark on the main title of plot (M1), if results are significant.
Any tips? Thanks in advance!
To answer #2 first, one needs to look at the inner structures of a summary.aov object:
dput(summary(fit1))
structure(list(`Error: ID` = structure(list(structure(list(Df = 1,
`Sum Sq` = 5.60666666666667, `Mean Sq` = 5.60666666666667,
`F value` = NA_real_, `Pr(>F)` = NA_real_), .Names = c("Df",
"Sum Sq", "Mean Sq", "F value", "Pr(>F)"), class = c("anova",
"data.frame"), row.names = "Residuals")), class = c("summary.aov",
"listof")), `Error: ID:time` = structure(list(structure(list(
Df = 1, `Sum Sq` = 11.3157142857143, `Mean Sq` = 11.3157142857143), .Names = c("Df",
"Sum Sq", "Mean Sq"), class = c("anova", "data.frame"), row.names = "df$time")), class = c("summary.aov",
"listof")), `Error: Within` = structure(list(structure(list(Df = c(1,
5), `Sum Sq` = c(0.325952380952381, 0.573888888888889), `Mean Sq` = c(0.325952380952381,
0.114777777777778), `F value` = c(2.83985617480293, NA), `Pr(>F)` = c(0.152766396924706,
NA)), .Names = c("Df", "Sum Sq", "Mean Sq", "F value", "Pr(>F)"
), class = c("anova", "data.frame"), row.names = c("df$time ",
"Residuals"))), class = c("summary.aov", "listof"))), .Names = c("Error: ID",
"Error: ID:time", "Error: Within"), class = "summary.aovlist")
And note that the values within summary(fit1)$"Error: Within" are actually buried one level deeper (and don't have names so need numeric index. Do this:
summary(fit1)$"Error: Within"[[1]]$`Pr(>F)`
[1] 0.1527664 NA
Now to see if I can figure out the two-0rdinate plot issue. Pretty sure one would need to do any median plotting before the par(new=TRUE) operation because that changes the user coordinate system based on the new data.
Adding a title with extracted value to your plot augmented by the helpful comment by #VincentBonhomme:
plot(df$time,df$M1a,type="p",col="red", cex=0.5, cex.main=2, cex.lab=1.0, cex.axis=0.7)
lines(unique(df$time),
tapply(df$M1a, df$time, median))
par(new = TRUE)
plot( df$time, df$M1b,type="p", col="blue", xaxt="n", yaxt="n", xlab="",ylab="")
lines(unique(df$time),
tapply(df$M1b, df$time, median))
mtext("Relative change (%)",side=4,line=3)
axis(4)
legend("topleft",col=c("red","blue"), lty=1,legend=c("Absolute Change","Relative Change"))
title(main=bquote("P-value for M1 (absolute scale)"==
.(round(summary(fit1)$"Error: Within"[[1]]$`Pr(>F)`, 3) ) ) )