1: Lattice
library(lattice)
library(datasets)
p <- xyplot(Ozone ~ Wind, data = airquality, pch = 20)
print(p)
##
## 5 6 7 8 9
## 31 30 31 31 30
airquality <- transform(airquality, Month = factor(Month))
xyplot(Ozone ~ Wind | Month, data = airquality, layout = c(5, 1))
# Panel function
set.seed(12) # remember 12 :)
x <- rnorm(100)
f <- rep(0:1, each = 50)
y <- x + f - f * x + rnorm(100, sd = 0.5)
f <- factor(f, labels = c("G1", "G2"))
xyplot(y ~ x | f, layout = c(2, 1), pch = 17)
## custome panel function
xyplot(y ~ x | f, panel = function(x, y, ...){
panel.xyplot(x, y, ...)
panel.abline(h = median(y), lty = 2)
})
xyplot(y ~ x | f, panel = function(x, y, ...){
panel.xyplot(x, y, ...)
panel.lmline(x, y, col = "red")
})
2:
# 1 --------------------------
# Base Plot
# In histograms, put a rug(variable) underline.
# This is just an example,
# library(help = "datasets")
data("airquality")
head(airquality)
## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 NA NA 14.3 56 5 5
## 6 28 NA 14.9 66 5 6
## Ozone Solar.R Wind Temp
## Min. : 1.00 Min. : 7.0 Min. : 1.700 Min. :56.00
## 1st Qu.: 18.00 1st Qu.:115.8 1st Qu.: 7.400 1st Qu.:72.00
## Median : 31.50 Median :205.0 Median : 9.700 Median :79.00
## Mean : 42.13 Mean :185.9 Mean : 9.958 Mean :77.88
## 3rd Qu.: 63.25 3rd Qu.:258.8 3rd Qu.:11.500 3rd Qu.:85.00
## Max. :168.00 Max. :334.0 Max. :20.700 Max. :97.00
## NA's :37 NA's :7
## Month Day
## Min. :5.000 Min. : 1.0
## 1st Qu.:6.000 1st Qu.: 8.0
## Median :7.000 Median :16.0
## Mean :6.993 Mean :15.8
## 3rd Qu.:8.000 3rd Qu.:23.0
## Max. :9.000 Max. :31.0
##
# View(airquality)
hist(airquality$Wind, col = "green")
rug(airquality$Wind)
hist(airquality$Wind, col = "green", breaks = 50)
rug(airquality$Wind)
abline(h = 7, col = "red")
abline(v = mean(airquality$Wind), col = "blue", lwd = 2)
# Boxplot
boxplot(airquality$Wind, col = "blue")
abline(h = 12, col = "red")
# Barplot
barplot(table(airquality$Month), col = "green")
# Multiple plots
attach(airquality)
boxplot(Solar.R ~ Month, data = airquality, col = "yellow")
abline(h = mean(Solar.R), col = "red") # why?
par(mfrow = c(5, 1), mar = c(4, 4, 2, 1))
hist(subset(airquality, Month == 5)$Solar.R, col = "red")
hist(subset(airquality, Month == 6)$Solar.R, col = "green")
hist(subset(airquality, Month == 7)$Solar.R, col = "blue")
hist(subset(airquality, Month == 8)$Solar.R, col = "yellow")
hist(subset(airquality, Month == 9)$Solar.R, col = "purple")
with(airquality, plot(x = Solar.R, y = Wind, col = Month))
abline(h = 12, lty = 2, lwd = 2)
plot(Ozone, Wind, col = Month)
abline(h = 12, lty = 2, lwd = 2)
par(mfrow = c(2, 2), mar = c(4, 4, 2, 1))
with(subset(airquality, Month == 5), plot(Solar.R, Wind, col = "red"))
with(subset(airquality, Month == 6), plot(Solar.R, Wind, col = "green"))
with(subset(airquality, Month == 7), plot(Solar.R, Wind, col = "blue"))
with(subset(airquality, Month == 8), plot(Solar.R, Wind, col = "black"))
detach(airquality)
# 2 --------------
# Lattice package
library(lattice)
library(datasets)
# library(help = "datasets")
head(mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
attach(mtcars)
table(cyl)
## cyl
## 4 6 8
## 11 7 14
xyplot(hp ~ mpg | cyl, data = mtcars, layour = c(3, 1))
detach(mtcars)
# 3 -------------
# ggplot
library(ggplot2)
data("mtcars")
str(mtcars)
## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
## $ am : num 1 1 1 0 0 0 0 0 0 0 ...
## $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
## The following object is masked from package:ggplot2:
##
## mpg
# ?ggplot
ggplot(data = mtcars, aes(x = mpg, y = hp, col = cyl)) +
geom_point()
ggplot(data = mtcars) + geom_boxplot(aes(x=factor(cyl),
y=mpg, fill=factor(cyl)),
position=position_dodge(1),
show.legend = FALSE)
ggplot(data = mtcars) + geom_boxplot(aes(x=factor(cyl),
y=hp, fill=factor(cyl)),
position=position_dodge(1),
show.legend = FALSE)
# Under-this is not working,
par(mfrow = c(2, 1), mar = c(4, 4, 2, 1))
ggplot(data = mtcars) + geom_boxplot(aes(x=factor(cyl),
y=mpg, fill=factor(cyl)),
position=position_dodge(1),
show.legend = FALSE)
ggplot(data = mtcars) + geom_boxplot(aes(x=factor(cyl),
y=hp, fill=factor(cyl)),
position=position_dodge(1),
show.legend = FALSE)
3:
set.seed(1234) # Remember 1234
x <- rnorm(12, mean = rep(1:3, each = 4), sd = 0.2)
y <- rnorm(12, mean = rep(c(1, 2, 1), each = 4), sd = 0.2)
plot(x, y, col = "blue", pch = 19, cex = 2)
text(x + 0.05, y + 0.05, labels = as.character(1:12))
d <- data.frame(x = x, y = y)
kmObj <- kmeans(d, centers = 3)
names(kmObj)
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"
## [1] 3 1 1 3 2 2 2 2 2 2 2 2
plot(x, y, col = kmObj$cluster, pch = 19, cex = 2)
points(kmObj$centers, col = 1:3, pch = 3, cex = 3, lwd = 3)
4:
set.seed(1234) # Remember 1234
x <- rnorm(12, mean = rep(1:3, each = 4), sd = 0.2)
y <- rnorm(12, mean = rep(c(1, 2, 1), each = 4), sd = 0.2)
plot(x, y, col = "blue", pch = 19, cex = 2)
text(x + 0.05, y + 0.05, labels = as.character(1:12))
d <- data.frame(x = x, y = y)
d
## x y
## 1 0.7585869 0.8447492
## 2 1.0554858 1.0128918
## 3 1.2168882 1.1918988
## 4 0.5308605 0.9779429
## 5 2.0858249 1.8977981
## 6 2.1012112 1.8177609
## 7 1.8850520 1.8325657
## 8 1.8906736 2.4831670
## 9 2.8871096 1.0268176
## 10 2.8219924 0.9018628
## 11 2.9045615 0.9118904
## 12 2.8003227 1.0919179
dist <- dist(d)
hClus <- hclust(dist)
hClus1 <- hclust(dist, method = "single")
hClus2 <- hclust(dist, method = "average")
hClus3 <- hclust(dist, method = "complete")
# Dendogram
plot(hClus)
heatmap(as.matrix(d)[sample(1:12), ])
5:
library(ggplot2)
data(mpg)
# 1. qplot()------------
str(mpg)
## tibble [234 x 11] (S3: tbl_df/tbl/data.frame)
## $ manufacturer: chr [1:234] "audi" "audi" "audi" "audi" ...
## $ model : chr [1:234] "a4" "a4" "a4" "a4" ...
## $ displ : num [1:234] 1.8 1.8 2 2 2.8 2.8 3.1 1.8 1.8 2 ...
## $ year : int [1:234] 1999 1999 2008 2008 1999 1999 2008 1999 1999 2008 ...
## $ cyl : int [1:234] 4 4 4 4 6 6 6 4 4 4 ...
## $ trans : chr [1:234] "auto(l5)" "manual(m5)" "manual(m6)" "auto(av)" ...
## $ drv : chr [1:234] "f" "f" "f" "f" ...
## $ cty : int [1:234] 18 21 20 21 16 18 18 18 16 20 ...
## $ hwy : int [1:234] 29 29 31 30 26 26 27 26 25 28 ...
## $ fl : chr [1:234] "p" "p" "p" "p" ...
## $ class : chr [1:234] "compact" "compact" "compact" "compact" ...
## [1] 234 11
## The following object is masked from mtcars:
##
## cyl
## [1] "manufacturer" "model" "displ" "year" "cyl"
## [6] "trans" "drv" "cty" "hwy" "fl"
## [11] "class"
qplot(displ, hwy, data = mpg)
qplot(displ, hwy, data = mpg, color = drv)
qplot(displ, hwy, data = mpg, geom = c("point", "smooth"))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
qplot(hwy, data = mpg, fill = drv, bins = 30)
qplot(displ, hwy, data = mpg, facets = . ~ drv)
qplot(hwy, data = mpg, facets = drv ~ ., binwidth = 2)
qplot(log(displ), data = mpg, bins = 30, fill = factor(cyl))
qplot(log(displ), data = mpg, geom = "density")
qplot(log(displ), data = mpg, geom = "density", color = factor(cyl),
fill = factor(cyl))
qplot(log(displ), log(hwy), data = mpg,
shape = factor(cyl), color = factor(drv))
qplot(log(displ), log(hwy), data = mpg, color = factor(fl))
qplot(log(displ), log(hwy), data = mpg,
color = factor(fl)) + geom_smooth(method = "lm")
## `geom_smooth()` using formula 'y ~ x'
# 2. ggplot()---------
library(ggplot2)
# library(help = "ggplot2")
str(mpg)
## tibble [234 x 11] (S3: tbl_df/tbl/data.frame)
## $ manufacturer: chr [1:234] "audi" "audi" "audi" "audi" ...
## $ model : chr [1:234] "a4" "a4" "a4" "a4" ...
## $ displ : num [1:234] 1.8 1.8 2 2 2.8 2.8 3.1 1.8 1.8 2 ...
## $ year : int [1:234] 1999 1999 2008 2008 1999 1999 2008 1999 1999 2008 ...
## $ cyl : int [1:234] 4 4 4 4 6 6 6 4 4 4 ...
## $ trans : chr [1:234] "auto(l5)" "manual(m5)" "manual(m6)" "auto(av)" ...
## $ drv : chr [1:234] "f" "f" "f" "f" ...
## $ cty : int [1:234] 18 21 20 21 16 18 18 18 16 20 ...
## $ hwy : int [1:234] 29 29 31 30 26 26 27 26 25 28 ...
## $ fl : chr [1:234] "p" "p" "p" "p" ...
## $ class : chr [1:234] "compact" "compact" "compact" "compact" ...
ggplot(data = mpg, aes(displ, hwy))
ggplot(data = mpg, aes(displ, hwy)) + geom_point()
ggplot(data = mpg, aes(displ, hwy)) + geom_point(col = factor(cyl))
ggplot(data = mpg, aes(displ, hwy, col = factor(cyl))) + geom_point()
ggplot(data = mpg, aes(displ, hwy)) + geom_point() + geom_smooth()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
ggplot(data = mpg, aes(displ, hwy)) + geom_point() + geom_smooth(method = "lm")
## `geom_smooth()` using formula 'y ~ x'
ggplot(data = mpg, aes(displ, hwy)) + geom_point() +
geom_smooth() + facet_grid(. ~ factor(cyl))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
ggplot(data = mpg, aes(displ, hwy, col = factor(cyl))) +
geom_point() + xlab("Engine displacement, in litres") +
ylab("Highway miles per gallon") +
ggtitle("Plot for displ vs hwv") +
labs(col = "No of Cylinder")
# 3. More ggplot()----------
library(ggplot2)
testdata <- data.frame(x = 1:100, y = rnorm(100))
str(testdata)
## 'data.frame': 100 obs. of 2 variables:
## $ x: int 1 2 3 4 5 6 7 8 9 10 ...
## $ y: num 1.102 -0.476 -0.709 -0.501 -1.629 ...
plot(testdata$x, testdata$y, type = "l")
## let's put a outlier to data
testdata[50, 2] <- 100 # Outlier
plot(testdata$x, testdata$y, type = "l")
plot(testdata$x, testdata$y, type = "l", ylim = c(-4, 4))
ggplot(testdata, aes(x, y)) + geom_line()
ggplot(testdata, aes(x, y)) + geom_line() + ylim(-4, 4)
ggplot(testdata, aes(x, y)) + geom_line() + coord_cartesian(ylim = c(-4, 4))
6:
# Here we see how colors works in R
x <- rnorm(1000)
y <- rnorm(1000)
# ?rgb
plot(x, y, pch = 19,
col = rgb(red = 0.75, green = 0.25, blue = 0))
plot(x, y, pch = 19,
col = rgb(red = 0, green = 0.5, blue = 0.5))
## if we want see more
plot(x, y, pch = 19,
col = rgb(red = 0, green = 0.5, blue = 0.5, alpha = 0.3))
# ?image
image(x = matrix(rnorm(100), 10, 10), col = c("blue", "green"))
require("grDevices") # for colours
x <- y <- seq(-4*pi, 4*pi, length.out = 27)
r <- sqrt(outer(x^2, y^2, "+"))
image(z = z <- cos(r^2)*exp(-r/6), col = gray.colors(33))
image(t(volcano)[ncol(volcano):1,])
# A prettier display of the volcano
x <- 10*(1:nrow(volcano))
y <- 10*(1:ncol(volcano))
image(x, y, volcano, col = hcl.colors(100, "terrain"), axes = FALSE)
contour(x, y, volcano, levels = seq(90, 200, by = 5),
add = TRUE, col = "brown")
axis(1, at = seq(100, 800, by = 100))
axis(2, at = seq(100, 600, by = 100))
box()
title(main = "Maunga Whau Volcano", font.main = 4)
# more search on,
# RColorBrewer
# colorRamp
x <- rnorm(10000)
y <- rnorm(10000)
smoothScatter(x, y)
