"To some people R is just the 18th letter of the alphabet. [...] R is also the name of a popular programming language used by a growing number of data analysts inside corporations and academia. It is becoming their lingua franca partly because data mining has entered a golden age, whether being used to set ad prices, find new drugs more quickly or fine-tune financial models. Companies as diverse as Google, Pfizer, Merck, Bank of America, the InterContinental Hotels Group and Shell use it."
[The New York Times]
introduzione a R
G.Bonafè
Arpa ER
R
Se scrivo 3+4 ottengo come risultato 7. [NB nel primo riquadro mostro il comando, nel secondo il risultato di quel comando]
3 + 4
## [1] 7
Il risultato lo posso assegnare a un oggetto.
a <- 3 + 4
b <- 11
c <- a + b
print(c)
## [1] 18
sequenze, vettori
a <- 50:4
print(a)
## [1] 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32 31 30 29 28
## [24] 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10 9 8 7 6 5
## [47] 4
b <- seq(from = 0.4, to = 18, length.out = 20)
print(b)
## [1] 0.400 1.326 2.253 3.179 4.105 5.032 5.958 6.884 7.811 8.737
## [11] 9.663 10.589 11.516 12.442 13.368 14.295 15.221 16.147 17.074 18.000
matrici (1)
riga1 <- c(1, 3:10)
riga2 <- c(2:5, 6, 11:8)
riga3 <- riga1/2
matrice <- rbind(riga1, riga2, riga3)
print(matrice)
## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
## riga1 1.0 3.0 4 5.0 6 7.0 8 9.0 10
## riga2 2.0 3.0 4 5.0 6 11.0 10 9.0 8
## riga3 0.5 1.5 2 2.5 3 3.5 4 4.5 5
matrici (2)
summary(matrice)
## V1 V2 V3 V4 V5
## Min. :0.50 Min. :1.50 Min. :2.00 Min. :2.50 Min. :3.0
## 1st Qu.:0.75 1st Qu.:2.25 1st Qu.:3.00 1st Qu.:3.75 1st Qu.:4.5
## Median :1.00 Median :3.00 Median :4.00 Median :5.00 Median :6.0
## Mean :1.17 Mean :2.50 Mean :3.33 Mean :4.17 Mean :5.0
## 3rd Qu.:1.50 3rd Qu.:3.00 3rd Qu.:4.00 3rd Qu.:5.00 3rd Qu.:6.0
## Max. :2.00 Max. :3.00 Max. :4.00 Max. :5.00 Max. :6.0
## V6 V7 V8 V9
## Min. : 3.50 Min. : 4.00 Min. :4.50 Min. : 5.00
## 1st Qu.: 5.25 1st Qu.: 6.00 1st Qu.:6.75 1st Qu.: 6.50
## Median : 7.00 Median : 8.00 Median :9.00 Median : 8.00
## Mean : 7.17 Mean : 7.33 Mean :7.50 Mean : 7.67
## 3rd Qu.: 9.00 3rd Qu.: 9.00 3rd Qu.:9.00 3rd Qu.: 9.00
## Max. :11.00 Max. :10.00 Max. :9.00 Max. :10.00
grafici (1)
Un grafico spartano.
plot(riga1, type = "h")
lines(riga2, col = "red")
points(riga3, col = "green")
grafici (2)
Complichiamo un po' le cose...
# convert factor to numeric for convenience
Orange$Tree <- as.numeric(Orange$Tree)
ntrees <- max(Orange$Tree)
# get the range for the x and y axis
xrange <- range(Orange$age)
yrange <- range(Orange$circumference)
# set up the plot
plot(xrange, yrange, type = "n", xlab = "Age (days)", ylab = "Circumference (mm)")
colors <- rainbow(ntrees)
linetype <- c(1:ntrees)
plotchar <- seq(18, 18 + ntrees, 1)
grafici (3)
... aggiungendo anche titolo, sottotitolo, legenda
# add lines
for (i in 1:ntrees) {
tree <- subset(Orange, Tree == i)
lines(tree$age, tree$circumference, type = "b", lwd = 1.5, lty = linetype[i],
col = colors[i], pch = plotchar[i])
}
# add a title and subtitle
title("Tree Growth", "example of line plot")
# add a legend
legend(xrange[1], yrange[2], 1:ntrees, cex = 0.8, col = colors, pch = plotchar,
lty = linetype, title = "Tree")
grafici (4)
Ecco.
accesso a dati remoti
url <- "http://www.sr.bham.ac.uk/~ajrs"
file <- "R/datasets/a85_extended_NEDsearch.txt"
A <- read.table(paste(url, file, sep = "/"), sep = "|", skip = 20, header = TRUE)
close(url(paste(url, file, sep = "/"))) # close connection after use
dim(A) # Show dimensions of data frame: rows columns
## [1] 5077 16
grafico a barre
colnames(A)[5] <- "type"
barplot(sort(table(A$type), decreasing = TRUE), log = "y")
boxplot
plot(Redshift ~ type, data = A, log = "y")
abline(h = 0.055, col = "red") # Show redshift of the cluster Abell 85
