1.5.4 Les vecteurs

x <- c(5.6,-2,78,42.3) # vecteur de numériques à 4 éléments
x
x <- c(x,3,c(12,8)) # vecteur à 7 éléments
x
x <- 2 # vecteur de longueur 1
x
1:6
seq(1,6,by=0.5)
seq(1,6,length=5)
rep(1,4)
rep(c(1,2),each=3)

A = rep(1,1000) # création d’un vecteur de 1
typeof(A)

[1] "double"

object.size(A)

8048 bytes

object.size(as.integer(A))

4048 bytes

typeof(as.integer(A)+1)

[1] "double"

object.size(as.integer(A)+1)

8048 bytes

typeof(as.integer(A)+1L)

[1] "integer"

object.size(as.integer(A)+1L)

4048 bytes

A = rep(1L,1000) # vecteur de 1 stocké en entiers
object.size(A)

4048 bytes

x <- c("A","BB","C1")
x

[1] "A"  "BB" "C1"

x <- rep('A',5)
x

[1] "A" "A" "A" "A" "A"

paste("X",1:5,sep="-")

[1] "X-1" "X-2" "X-3" "X-4" "X-5"

paste(c("X","Y"),1:5,"txt",sep=".")

[1] "X.1.txt" "Y.2.txt" "X.3.txt" "Y.4.txt" "X.5.txt"

paste(c("X","Y"),1:5,sep=".",collapse="+")

[1] "X.1+Y.2+X.3+Y.4+X.5"

substr("livre",2,5)

[1] "ivre"

txtvec <- c("arm","foot","lefroo", "bafoobar")
grep("foo", txtvec)

[1] 2 4

gsub("foo", txtvec, replacement = "DON")

[1] "arm"      "DONt"     "lefroo"   "baDONbar"

1>0

[1] TRUE

x>13

[1] TRUE TRUE TRUE TRUE TRUE

x <- c(-1,0,2)
test <- x>1
(1+x^2)*test

[1] 0 0 5

all(x>1)

[1] FALSE

any(x>1)

[1] TRUE

v <- 1:100
v[6] # donne le sixième élément de v

[1] 6

v[6:8] # donne les 6ème, 7ème et 8ème éléments de v

[1] 6 7 8

v[c(6,6,1:2)] # donne les 6ème, 6ème, 1er et 2ème éléments de v

[1] 6 6 1 2

v[10:1] # donne les 10ème, 9ème, ..., 1er éléments de v

 [1] 10  9  8  7  6  5  4  3  2  1

v[-(1:5)] # donne v sans ses 5 premiers éléments

 [1]   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21  22  23  24  25  26  27  28  29  30  31  32  33  34
[30]  35  36  37  38  39  40  41  42  43  44  45  46  47  48  49  50  51  52  53  54  55  56  57  58  59  60  61  62  63
[59]  64  65  66  67  68  69  70  71  72  73  74  75  76  77  78  79  80  81  82  83  84  85  86  87  88  89  90  91  92
[88]  93  94  95  96  97  98  99 100

v[-c(1,5)] # donne v sans le premier et le cinquième élément

 [1]   2   3   4   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21  22  23  24  25  26  27  28  29  30  31
[30]  32  33  34  35  36  37  38  39  40  41  42  43  44  45  46  47  48  49  50  51  52  53  54  55  56  57  58  59  60
[59]  61  62  63  64  65  66  67  68  69  70  71  72  73  74  75  76  77  78  79  80  81  82  83  84  85  86  87  88  89
[88]  90  91  92  93  94  95  96  97  98  99 100

v <- 1:15
print(v)

 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15

v[(v<5)]

[1] 1 2 3 4

v[(v<5)&(v>=12)] # & signifie "et"

integer(0)

v[(v<5)|(v>=12)] # | signifie "ou"

[1]  1  2  3  4 12 13 14 15

T <- c(23, 28, 24, 32)
O3 <- c(80, 102, 87, 124)
O3[T>25]

[1] 102 124

x[is.na(x)] <- 0 # les éléments NA de x reçoivent la valeur 0
y[y<0]<- -y[y<0]
y <- abs(y)

which.min(x)

[1] 1

which(x==min(x))

[1] 1

1.5.5 Les matrices

m <- matrix(c(1,17,12,3,6,0),ncol=2)
m

     [,1] [,2]
[1,]    1    3
[2,]   17    6
[3,]   12    0

m <- matrix(1:8,nrow=2,byrow=TRUE)
m

     [,1] [,2] [,3] [,4]
[1,]    1    2    3    4
[2,]    5    6    7    8

m <- matrix(1:4,nrow=3,ncol=3)

data length [4] is not a sub-multiple or multiple of the number of rows [3]

m

     [,1] [,2] [,3]
[1,]    1    4    3
[2,]    2    1    4
[3,]    3    2    1

un <- matrix(1,nrow=2,ncol=4)
un

     [,1] [,2] [,3] [,4]
[1,]    1    1    1    1
[2,]    1    1    1    1

x <- seq(1,10,by=2)
x

[1] 1 3 5 7 9

as.matrix(x)

     [,1]
[1,]    1
[2,]    3
[3,]    5
[4,]    7
[5,]    9

m[1,]

[1] 1 4 3

m[1,,drop=FALSE]

     [,1] [,2] [,3]
[1,]    1    4    3

m[,c(2,2,1)]

     [,1] [,2] [,3]
[1,]    4    4    1
[2,]    1    1    2
[3,]    2    2    3

m[-1,] # matrice m sans sa première ligne

     [,1] [,2] [,3]
[1,]    2    1    4
[2,]    3    2    1

m[1:2,-1] # 2 premières lignes de m privée de sa 1ère colonne

     [,1] [,2]
[1,]    4    3
[2,]    1    4

m <- matrix(1:8,ncol=4,byrow=TRUE)
m

     [,1] [,2] [,3] [,4]
[1,]    1    2    3    4
[2,]    5    6    7    8

m[,m[1,]>2]

     [,1] [,2]
[1,]    3    4
[2,]    7    8

m[m>2]

[1] 5 6 3 7 4 8

m[m>2] <- NA
m

     [,1] [,2] [,3] [,4]
[1,]    1    2   NA   NA
[2,]   NA   NA   NA   NA

m <- matrix(1:4,ncol=2)
m

     [,1] [,2]
[1,]    1    3
[2,]    2    4

n <- matrix(3:6,ncol=2,byrow=T)
n

     [,1] [,2]
[1,]    3    4
[2,]    5    6

m+n

     [,1] [,2]
[1,]    4    7
[2,]    7   10

m*n # produit élément par élément

     [,1] [,2]
[1,]    3   12
[2,]   10   24

sin(m) # sinus élément par élément

          [,1]       [,2]
[1,] 0.8414710  0.1411200
[2,] 0.9092974 -0.7568025

exp(m) # exponentielle élément par élément

         [,1]     [,2]
[1,] 2.718282 20.08554
[2,] 7.389056 54.59815

m^4 # puissance quatrième élément par élément

     [,1] [,2]
[1,]    1   81
[2,]   16  256

A <- matrix(1:4,ncol=2)
B <- matrix(c(5,7,6,8),ncol=2)
D <- A%*%t(B)
D

     [,1] [,2]
[1,]   23   31
[2,]   34   46

eig <- eigen(D)
eig

eigen() decomposition
$`values`
[1] 68.9419802  0.0580198

$vectors
           [,1]       [,2]
[1,] -0.5593385 -0.8038173
[2,] -0.8289393  0.5948762

eig$vectors[,1]

[1] -0.5593385 -0.8289393

V <- c(1,2)
solve(D,V)

[1] -4  3

X <- matrix(1:6,ncol=3)
X

     [,1] [,2] [,3]
[1,]    1    3    5
[2,]    2    4    6

ncol(X)

[1] 3

nrow(X)

[1] 2

dim(X)

[1] 2 3

cbind(c(1,2),c(3,4))

     [,1] [,2]
[1,]    1    3
[2,]    2    4

apply(X,MARGIN=2,sum) # sommes par colonne

[1]  3  7 11

apply(X,1,mean) # moyennes par ligne

[1] 3 4

1.5.6 Les facteurs

sexe <- factor(c("M","M","F","M","F","M","M","M"))
sexe

[1] M M F M F M M M
Levels: F M

sexe <- factor(c(2,2,1,2,1,2,1),labels=c("femme","homme"))
sexe

[1] homme homme femme homme femme homme femme
Levels: femme homme

niveau <- ordered(c("débutant","débutant","champion","champion",
"moyen","moyen","moyen","champion"),
levels=c("débutant","moyen","champion"))
niveau

[1] débutant débutant champion champion moyen    moyen    moyen    champion
Levels: débutant < moyen < champion

salto <- c(1:5,5:1)
salto

 [1] 1 2 3 4 5 5 4 3 2 1

salto.f <- as.factor(salto)
salto.f

 [1] 1 2 3 4 5 5 4 3 2 1
Levels: 1 2 3 4 5

levels(salto.f)

[1] "1" "2" "3" "4" "5"

nlevels(salto.f)

[1] 5

table(salto.f)

salto.f
1 2 3 4 5 
2 2 2 2 2 

x <- factor(c(10,11,13))
as.numeric(x)

[1] 1 2 3

as.numeric(as.character(x))

[1] 10 11 13

1.5.7 Les listes

vecteur <- seq(2,10,by=3)
matrice <- matrix(1:8,ncol=2)
facteur <- factor(c("M","M","F","M","F","M","M","M"))
ordonne <- ordered(c("débutant","débutant","champion",
                     "champion","moyen","moyen","moyen","champion"),
                   levels=c("débutant","moyen","champion"))
maliste <- list(vecteur,matrice,facteur,ordonne)
length(maliste)

[1] 4

mode(maliste)

[1] "list"

names(maliste)

NULL

names(maliste) <- c("vec","mat","sexe","ski")
names(maliste)

[1] "vec"  "mat"  "sexe" "ski" 

maliste[[3]]

[1] M M F M F M M M
Levels: F M

maliste[[1]]

[1] 2 5 8

maliste$sexe

[1] M M F M F M M M
Levels: F M

maliste[["sexe"]]

[1] M M F M F M M M
Levels: F M

maliste[c(1,3)]

$`vec`
[1] 2 5 8

$sexe
[1] M M F M F M M M
Levels: F M

X <- matrix(1:12,nrow=4,ncol=3)
nomligne <- c("ligne1","ligne2","ligne3","ligne4")
nomcol <- c("col1","col2","col3")
dimnames(X) <- list(nomligne,nomcol)
X

       col1 col2 col3
ligne1    1    5    9
ligne2    2    6   10
ligne3    3    7   11
ligne4    4    8   12

X[c("ligne4","ligne1"),c("col3","col2")]

       col3 col2
ligne4   12    8
ligne1    9    5

dimnames(X) <- list(NULL,dimnames(X)[[2]])
X

     col1 col2 col3
[1,]    1    5    9
[2,]    2    6   10
[3,]    3    7   11
[4,]    4    8   12

1.5.8 Les data-frames

vec1 <- 1:5
vec2 <- c("a","b","c","c","b")
df <- data.frame(nom.var1 = vec1, nom.var2 = vec2)

1.5.9 La classe d’un objet

df <- data.frame(x = 1:2, y = c(3, 5))
print(df)

  x y
1 1 3
2 2 5

print.default(df)

$`x`
[1] 1 2

$y
[1] 3 5

attr(,"class")
[1] "data.frame"

library(data.table)
dt <- data.table::data.table(df)
dt

   x y
1: 1 3
2: 2 5

class(dt)

[1] "data.table" "data.frame"

1.6 Les fonctions

set.seed(13) # fixe la graine du générateur
rnorm(n=3)

[1]  0.5543269 -0.2802719  1.7751634

set.seed(13) # fixe la graine du générateur
rnorm(n=4,mean=5,sd=0.5)

[1] 5.277163 4.859864 5.887582 5.093660

args(rnorm)

function (n, mean = 0, sd = 1) 
NULL

args(plot)

function (x, y, ...) 
NULL

1.7 Les packages

set.seed(45) # fixe la graine du générateur aléatoire
require(MASS) # ou library(MASS)
mvrnorm(3,mu=c(0,1),Sigma=matrix(c(1,0.5,0.5,1),2,2))

           [,1]        [,2]
[1,]  0.6681649  0.92211747
[2,] -0.1600569 -0.05816423
[3,] -0.1612923  0.50391363

set.seed(45) # fixe la graine du générateur aléatoire
MASS::mvrnorm(3,mu=c(0,1),Sigma=matrix(c(1,0.5,0.5,1),2,2))

           [,1]        [,2]
[1,]  0.6681649  0.92211747
[2,] -0.1600569 -0.05816423
[3,] -0.1612923  0.50391363

if (!require(rpart)) install.packages("rpart") # installe rpart si besoin
require(rpart)

update.packages(ask=FALSE)
packs = as.data.frame(installed.packages(.libPaths()[1]), stringsAsFactors = F)
install.packages(packs$Package) ## réinstallation des packages