March Workshop for R Novices
R-Ladies Coding Club (London)
23 Mar ’16
This is the CODE-ONLY cribsheet for the Novice workshop. Full document to be provided during & after workshop.
Schedule
– 6.30-6.35pm: A. RStudio - Basics
– 6.35-6.40pm: B. Pre-loaded data - Examine
– 6:40-6:50pm: C. Make your own data - Geo Chart
– 6:50-6:55pm: D. ggplot2 - Set-up
– 6:55-7:15pm: E. ggplot2 - Data Viz + Extensions
– 7:15-7.30pm: BREAK
– 7.30-8.15pm: F. Machine Learning technique - Clustering + Extension
A. RStudio - Basics
(i) Open & Save new R Script
(ii) Running code
(iii) Creating R Objects
object <- 3 + 5
object## [1] 8B. Pre-loaded Data - Examine
data()data("iris")
data("mtcars")
data("longley")
data("USArrests")
data("VADeaths")class()
dim()
str()
summary()
head()
tail()
View()
?<name of data set>C. Make your own data - Geo Chart
(i)
Country <- c("United Kingdom", "France", "Spain", "Germany", "US", "Australia", "Thailand" )
Popularity <- c()
geodata <- data.frame(Country, Popularity)
View(geodata)
class(geodata)(ii)
install.packages("googleVis")
library(googleVis)(iii)
?gvisGeoChart
args(gvisGeoChart)(iv)
geochart <- gvisGeoChart(geodata,
locationvar = "Country",
colorvar = "Popularity")
plot(geochart)D. ggplot2
(i)
install.packages("ggplot2")(ii)
library(ggplot2)(iii)
?ggplotdata("diamonds", "economics")E. ggplot2 - Data Viz
(i) Line Chart
line.graph <- ggplot(data = economics, aes(x = date, y = pop)) + geom_line()
plot(line.graph)
(ii) Bar Chart
bar.chart <- ggplot(data = diamonds, aes(x = cut)) + geom_bar()
plot(bar.chart)
(iii) Box Plot
box.plot <- ggplot(data = diamonds, aes(x = cut, y = price)) + geom_boxplot()
plot(box.plot)
(iv) Scatterplot
scatterplot <- ggplot(data = diamonds, aes(x = price, y = carat)) + geom_point()
plot(scatterplot)
Extensions!!
–
+ ggtitle("insert title here")
+ xlab("insert x-axis label here")
+ ylab("insert y-axis label here")–
+ geom_line(colour = "tomato")
+ geom_bar(colour = "slategrey", fill = "peachpuff")
+ geom_boxplot(colour = "navy", fill = "oldlace")–
bar.chart.subset <- ggplot(data = diamonds, aes(x = cut)) + geom_bar(aes(fill = clarity))
plot(bar.chart.subset)
scatterplot.subset <- ggplot(data = diamonds, aes(x = price, y = carat)) + geom_point(aes(colour = cut))
plot(scatterplot.subset)
–
bar.chart.facet <- ggplot(data = diamonds, aes(x = cut)) + geom_bar() + facet_grid(color~.)bar.chart.facet <- ggplot(data = diamonds, aes(x = cut)) + geom_bar(aes(fill = color)) + facet_grid(color~.)
plot(bar.chart.facet)
F. Machine Learning technique - Clustering
Intro + Steps
Steps:
(i) Load & Explore data
(ii) Clean data
(iii) Standardise data
(iv) Calculate Euclidean Distance Matrix
(v) Calculate Clusters
(vi) Make Dendrogram data viz
(vii) Define appropriate no. of Clusters
(viii) Variable combinations determining Cluster Membership
(ix) Create final Cluster Membership data
(i) Load & Explore data
data(mtcars)
View(mtcars)
?mtcars(ii) Clean data
mtcars1 <- mtcars[, -c(8, 9)]
View(mtcars1)(iii) Standardise data
medians <- apply(mtcars1, 2, median)
mads <- apply(mtcars1, 2, mad)
mtcars2 <- scale(mtcars1, center = medians, scale = mads)print(mtcars2, digits=2)## mpg cyl disp hp drat wt qsec gear carb
## Mazda RX4 0.333 0.00 -0.26 -0.17 0.29 -0.92 -0.88 0.00 1.35
## Mazda RX4 Wag 0.333 0.00 -0.26 -0.17 0.29 -0.59 -0.49 0.00 1.35
## Datsun 710 0.665 -0.67 -0.63 -0.39 0.22 -1.31 0.64 0.00 -0.67
## Hornet 4 Drive 0.407 0.00 0.44 -0.17 -0.87 -0.14 1.22 -0.67 -0.67
## Hornet Sportabout -0.092 0.67 1.17 0.67 -0.77 0.15 -0.49 -0.67 0.00(iv) Calculate Euclidean Distance Matrix
mtcars3 <- dist(mtcars2, method = "euclidean")print(mtcars3, digits=2)(v) Calculate Clusters
clusters <- hclust(mtcars3, method = "ward.D2")(vi) Make Dendrogram data viz
plot(clusters)plot(clusters, hang = -1)
(vii) Define appropriate no. of Clusters
rect.hclust(clusters, 6)
clusters.6 <- cutree(clusters, 6)(viii) Variable combinations determining Cluster Membership
means <- aggregate(mtcars2, list(clusters.6), mean)
options(digits = 2)
means## Group.1 mpg cyl disp hp drat wt qsec gear carb
## 1 1 0.10 0.00 -0.26 0.067 0.223 -0.39 -0.335 0.13 1.62
## 2 2 0.48 -0.48 -0.26 -0.352 -0.153 -0.50 1.595 -0.29 -0.39
## 3 3 -0.45 0.67 0.85 0.610 -0.916 0.47 -0.275 -0.67 0.29
## 4 4 -0.85 0.67 1.03 1.936 -0.028 0.28 -1.852 0.00 2.02
## 5 5 -1.36 0.67 1.86 1.215 -0.911 2.63 0.021 -0.67 1.35
## 6 6 2.01 -0.67 -0.78 -0.616 0.790 -1.89 0.486 0.22 -0.34means2 <- aggregate(mtcars[,-c(8,9)], list(clusters.6), mean)
means2## Group.1 mpg cyl disp hp drat wt qsec gear carb
## 1 1 20 6.0 160 128 3.9 3.0 17 4.2 4.4
## 2 2 22 4.6 160 96 3.6 2.9 20 3.6 1.4
## 3 3 17 8.0 316 170 3.0 3.7 17 3.0 2.4
## 4 4 15 8.0 340 272 3.7 3.5 15 4.0 5.0
## 5 5 12 8.0 457 217 3.1 5.3 18 3.0 4.0
## 6 6 30 4.0 87 76 4.3 1.9 18 4.3 1.5(ix) Create final Cluster Membership data
mtcars.membership <- cbind(clusters.6, mtcars)mtcars.membership## clusters.6 mpg cyl disp hp drat wt qsec vs am gear
## Mazda RX4 1 21 6 160 110 3.9 2.6 16 0 1 4
## Mazda RX4 Wag 1 21 6 160 110 3.9 2.9 17 0 1 4
## Datsun 710 2 23 4 108 93 3.9 2.3 19 1 1 4
## Hornet 4 Drive 2 21 6 258 110 3.1 3.2 19 1 0 3
## Hornet Sportabout 3 19 8 360 175 3.1 3.4 17 0 0 3
## Valiant 2 18 6 225 105 2.8 3.5 20 1 0 3Extension!!
install.packages("sparcl")library(sparcl)
ColorDendrogram(clusters, y = clusters.6, labels = names(clusters.6), branchlength = 5)