## ----setup, include=FALSE---------------------------------------------
## Global options
knitr::opts_chunk$set(cache = TRUE)


## ---------------------------------------------------------------------
a <- 10
b <- 3 / 10
d <- "star"
e <- "10"
f <- T|F 
g <- T|NA 


## ---------------------------------------------------------------------
is.integer(a) ; is.double(a)
is.character(e)
is.logical(f)


## ---------------------------------------------------------------------
as.character(a)
as.integer(e)
as.numeric(f)
as.numeric(d)


## ---------------------------------------------------------------------
a==10L
identical(a, 10L)
identical(as.integer(a), 10L)


## ---------------------------------------------------------------------
(v_num <- c(2, 3.6, 1e2))
(v_cha <- c("hi", "goodbye", "farewell"))


## ---------------------------------------------------------------------
(v_le0 <- vector())
length(v_le0)
(v_log <- vector(, length=2))


## ---------------------------------------------------------------------
v_mix_1 <- c(v_log, v_num)
v_mix_2 <- c(v_num, v_cha)
v_mix_3 <- c(v_log, v_cha)


## ----include=F--------------------------------------------------------
typeof(v_mix_1) ; typeof(v_mix_2 <- c(v_num, v_cha)) ;
typeof(v_mix_3 <- c(v_log, v_cha))


## ---------------------------------------------------------------------
1:10


## ---------------------------------------------------------------------
seq(1, 10) 


## ---------------------------------------------------------------------
seq(10, 1)


## ---------------------------------------------------------------------
seq(1, 10, 2)
seq(1, 10, length=5)
seq(1, 10, 10)
seq(1, 10, length=1)
seq(1, 10, 2.5)
seq(1, 10, le=2.5)  # length is rounded up


## ---------------------------------------------------------------------
rep(2, 5)
rep(c(2,5), 2)
rep(c(2, 5), c(2, 5))


## ---------------------------------------------------------------------
x <- c(1, 2, 5)
x[1]
x[1:2]
x[c(1,3)]
x[-2]
x[-(1:2)]


## ---------------------------------------------------------------------
y <- c(x, -1.2, 0, 10, 6.2, 3, -3, 9, 12, sqrt(2))


## ---------------------------------------------------------------------
x <- c(1:2,4,5,7,8,10,11)
x[x<5 | x>7]


## ---------------------------------------------------------------------
which(x<5 | x>7)


## ---------------------------------------------------------------------
 x <- 1:10
 
 x*2
 
 x > 5


## ---------------------------------------------------------------------
x <- rep(10,8)
y <- c(1,2)
x*y   
x+y


## ---------------------------------------------------------------------
paste(1:3)  # same as as.character(1:3)
paste(1:3, 2)
paste0(1:3, 2)
paste(1:3, 2, sep=".")
paste("day", 1:5)


## ---------------------------------------------------------------------
x <- 0:7
# Are all the x values bigger than 0?
all(x>0)
# Are any of the x values negative?
any(x<0)
# then, it must be True that
any(x>0)


## ---------------------------------------------------------------------
x <- c(16.5, 16, 17, 12)
length(x)
sort(x)
order(x)
sort(x, decreasing=T)
sum(x)/length(x)
mean(x)
min(x); max(x); range(x)


## ---------------------------------------------------------------------
x <- c(1,0,5)
str(x)
attributes(x)

x <- c(a=1, b=0, c=5)
# or
x <- c(1,0,5) ; names(x) <- c("a", "b", "c")
# or
setNames(c(1,0,5), c("a", "b", "c"))

names(x)
attributes(x)


## ---------------------------------------------------------------------
x <- c(T, T, F, T)


## ----eval=F-----------------------------------------------------------
# sum(x) ; mean(x)


## ----eval=F-----------------------------------------------------------
# x[c(TRUE, TRUE, NA, FALSE)]


## ---------------------------------------------------------------------
(x <- matrix(c(2,3,5,7,11,13), nrow=3))
(x <- matrix(c(2,3,5,7,11,13), ncol=3))


## ---------------------------------------------------------------------
(x <- scan("data/ex.data", skip = 1, quiet = TRUE))
(mx <- matrix(x, ncol=3, byrow=TRUE))


## ---------------------------------------------------------------------
nrow(mx) ; ncol(mx) ; dim(mx)


## ---------------------------------------------------------------------
rownames(mx) <- paste0("r", 1:2)
colnames(mx) <- c("a", "b", "c")
mx


## ---------------------------------------------------------------------
x <- 1:20
(ax <- array(x, dim=c(5,2,2)))
dim(ax)


## ---------------------------------------------------------------------
str(2:4)
y <- matrix(2:4, nrow = 1)    # row vector
str(y) 

y <- matrix(2:4, ncol = 1)    # column vector
str(y) 

y <- array(2:4, 3)           # 1d array 
str(y)


## ---------------------------------------------------------------------
mx[2,1]     # select the element in the cell (2,1)
mx[2, ]      # select the second row  
mx["r2", ]
mx[ ,3]      # select the third column 
mx[ ,"c"]


## ---------------------------------------------------------------------
x <- matrix(1:16, ncol=4)
(y <- x[c(1,4),c(3,4)])


## ---------------------------------------------------------------------
ax[3,2,1]
ax[ ,2, ]
ax[-1, ,1]


## ----include=F--------------------------------------------------------
a <- matrix(1:6, 2)
a
b <- a[,2]
b
is.vector(b)
is.matrix(b)
b <- as.matrix(b)
b
d <- array(1:12, c(2,3,2))
d
length(d)
d_copy <- d
d_copy[,,1] <- b
d ; d_copy


## ---------------------------------------------------------------------
(x <- vector("list", length = 3))


## ---------------------------------------------------------------------
x1 <- 1:3
x2 <- c("A", "B", "C", "D", "E")
x3 <- matrix(1:12, nrow=3)

x[[1]] <- x1; x[[2]] <- x2; x[[3]] <- x3
x

mylist <- list(x1, x2, x3)  # define the list 'mylist'
str(mylist)


## ---------------------------------------------------------------------
(mylist2 <- list(comp1 = x1, comp2 = x2, comp3 = x3))


## ---------------------------------------------------------------------
names(mylist)
names(mylist2)


## ---------------------------------------------------------------------
newlist <- c(mylist, mylist2)
is.list(newlist)
str(newlist)


## ---------------------------------------------------------------------
newlist <- list(mylist, mylist2)
str(newlist)


## ---------------------------------------------------------------------
mylist[1]
mylist[[1]]
mylist2$comp1


## ---------------------------------------------------------------------
mylist[[3]][,4]


## ---------------------------------------------------------------------
dim(ax)
dimnames(ax)
dimnames(ax) <- list(letters[1:5], LETTERS[1:2], paste0("m", 1:2))
ax
ax['a',,'m1']


## ----echo=1:2---------------------------------------------------------
x <- list(list(1, 2), c(3, 4))
y <- c(list(1, 2), c(3, 4))


## ---------------------------------------------------------------------
b <- array(1:16, c(4, 2, 2))


## ----include=F--------------------------------------------------------
str(x) ; str(y)
x[[2]][2]
y[[4]]

dimnames(b) <- list(c("R1", "R2", "R3", "R4"), c("C1", "C2"), c("A", "B"))


## ---------------------------------------------------------------------
country <- c("Italy","Germany","France","Germany","Germany","Germany",
              "France","Italy","Italy","France")


## ---------------------------------------------------------------------
countryf <- factor(country)
str(countryf)

class(countryf)
typeof(countryf)


## ---------------------------------------------------------------------
countryf <- factor(country, levels=c("Italy", "France", "Germany"))
str(countryf)


## ---------------------------------------------------------------------
table(country)
table(countryf)


## ---------------------------------------------------------------------
age <- c(47,44,44,40,38,36,42,34,34,44)
gender <- c(1,1,2,1,1,2,1,2,2,2)


## ---------------------------------------------------------------------
tapply(age, countryf, mean)


## ---------------------------------------------------------------------
genderf <- factor(gender)
levels(genderf) <- c("F","M")
str(genderf)


## ---------------------------------------------------------------------
unclass(genderf)
as.integer(genderf)


## ----eval=F-----------------------------------------------------------
# sum(as.integer(c("1", "1", "0", "1", "1", "0")))
# sum(as.integer(fs))
# sum(as.integer(levels(fs)[fs]))


## ---------------------------------------------------------------------
v1 <- factor(letters[1:5])
levels(v1) <- rev(levels(v1))
v2 <- factor(letters[1:5], levels = rev(letters[1:5]))


## ----include=F--------------------------------------------------------
x<-c(5, 12, 13, 12)
y<-factor(x)
str(y)
unclass(y) ; as.integer(y)

fs<-factor(c("1", "1", "0", "1", "1", "0"))
fs
str(fs)
sum(as.integer(c("1", "1", "0", "1", "1", "0")))
sum(as.integer(fs))
sum(as.integer(levels(fs)[fs]))

levels(fs)<-c("m", "f")
table(fs)


## ----include=T--------------------------------------------------------
#What does this code do? How does v2 differ from v1?
v1 <- factor(letters[1:5])
levels(v1) <- rev(levels(v1))
v1
str(v1)
v2 <- factor(letters[1:5], levels = rev(letters[1:5]))
v2
str(v2)


## ---------------------------------------------------------------------
under40 <- age < 40
dat <- data.frame(country=countryf, age=age, sex=genderf, under40=under40)


## ---------------------------------------------------------------------
str(dat)
dplyr::glimpse(dat)

class(dat)
is.data.frame(dat)


## ---------------------------------------------------------------------
head(dat)
tail(dat)


## ----eval=F-----------------------------------------------------------
# View(dat)
# edit(dat)


## ---------------------------------------------------------------------
dat[3,2]
dat[1:3, 2:4]
dat[3, ]


## ---------------------------------------------------------------------
x <- dat[, 2]
str(x)


## ---------------------------------------------------------------------
dat[ , c("age", "sex")]


## ---------------------------------------------------------------------
dat["age"] 
str(dat["age"]) 


## ---------------------------------------------------------------------
dat$sex


## ---------------------------------------------------------------------
dat$under40 <- NULL
head(dat)


## ----message=F--------------------------------------------------------
attach(dat)


## ---------------------------------------------------------------------
age


## ---------------------------------------------------------------------
detach(dat)


## ---------------------------------------------------------------------
x <- runif(8)
y <- letters[1:8]
z <- sample(c(rep(T,5),rep(F,3)))


## ----include=F--------------------------------------------------------
newdf <- data.frame(x,y,z)
head(newdf)

data.frame(nome=c("Andrea", "Biagio", "Caterina", "Daria", "Enrico"), anni=as.integer(c(19, 35, 23, 45, 30)))


## ---------------------------------------------------------------------
library(readxl)
fav_food <- read_excel("data/favourite-food.xlsx")
fav_food
str(fav_food)


## ----include=F--------------------------------------------------------
str(as.data.frame(fav_food))