#Chapitre 3 : solution des exercices
#Complement en ligne
#Exercice 3.1
d_hotels <- read.csv("https://tinyurl.com/y3rxbxoo")
head(d_hotels)
## NOM PAYS ETOILE CONFORT CHAMBRE CUISINE SPORT PLAGE PRIX
## 1 Appolpon Grèce 1 4 56 2 0 8 390
## 2 Caravel Grèce 4 7 471 7 6 5 468
## 3 Christina Grèce 2 7 93 3 0 5 427
## 4 Economy Grèce 1 3 56 1 0 8 369
## 5 Eden Beach Grèce 1 4 286 3 4 7 499
## 6 Hanikian Beach Grèce 3 6 282 5 10 10 526
library(GGally)
## Loading required package: ggplot2
## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2
ggparcoord(d_hotels, columns = 3:ncol(d_hotels), groupColumn=2,
scale = "std", boxplot = TRUE, alphaLines = 0.5)+ facet_grid(
rows=vars(PAYS))+ theme(axis.text.x=element_text(angle=45,hjust=1,
vjust=1),legend.position="")
#Exercice 3.2
d_pres2002<-read.csv("https://tinyurl.com/yyoowvkl",row.names=1)
head(d_pres2002[,1:3])
## Arlette.Laguiller Dominique.Voynet François.Bayrou
## MIDI PYRENEES 18613 25267 341641
## ALSACE 13821 20382 214339
## BRETAGNE 25663 39026 451986
## RHONE ALPES 38095 62997 689671
## PACA 26407 38339 419162
## NORD PDC 52668 31382 340694
mosaicplot(d_pres2002, type = "pearson", shade = TRUE, las = 2,
main = "Associations et r\u00e9sidus du test du chi2")
d_pres2007 <- read.csv("https://tinyurl.com/yyolq665",row.names=1)
head(d_pres2007[,1:8])
## Sarkozy Bayrou Royal Le.Pen Besanc. Villiers Voynet Laguiller
## Alsace 362391 214259 171282 135730 33310 22492 20382 13821
## Aquitaine 532127 417546 557300 168664 78230 34028 28285 22046
## Auvergne 238152 169395 225477 78704 41522 18730 12090 12936
## Bourgogne 297544 175213 241094 119041 42246 24971 13690 14440
## Bretagne 557507 451988 564100 143926 94205 41212 39026 25662
## Centre 460425 278175 345352 168912 65347 45720 22655 22279
mosaicplot(d_pres2007, type = "pearson", shade = TRUE, las = 2,
main = "Associations et r\u00e9sidus du test du chi2")
#q1
data(UCBAdmissions)
str(UCBAdmissions)
## 'table' num [1:2, 1:2, 1:6] 512 313 89 19 353 207 17 8 120 205 ...
## - attr(*, "dimnames")=List of 3
## ..$ Admit : chr [1:2] "Admitted" "Rejected"
## ..$ Gender: chr [1:2] "Male" "Female"
## ..$ Dept : chr [1:6] "A" "B" "C" "D" ...
mosaicplot(UCBAdmissions)
library(vcd)
## Loading required package: grid
assoc(UCBAdmissions)
#q2
library(FactoMineR)
try(MCA(UCBAdmissions))
## Error in dimnames(res) <- list(attributes(tab)$row.names, listModa) :
## la longueur de 'dimnames' [2] n'est pas égale à l'étendue du tableau
?MCA
#q3
library(DescTools)
UCBA.df <- Untable(UCBAdmissions)
head(UCBA.df)
## Admit Gender Dept
## 1 Admitted Male A
## 2 Admitted Male A
## 3 Admitted Male A
## 4 Admitted Male A
## 5 Admitted Male A
## 6 Admitted Male A
str(UCBA.df)
## 'data.frame': 4526 obs. of 3 variables:
## $ Admit : Factor w/ 2 levels "Admitted","Rejected": 1 1 1 1 1 1 1 1 1 1 ...
## $ Gender: Factor w/ 2 levels "Male","Female": 1 1 1 1 1 1 1 1 1 1 ...
## $ Dept : Factor w/ 6 levels "A","B","C","D",..: 1 1 1 1 1 1 1 1 1 1 ...
## - attr(*, "out.attrs")=List of 2
## ..$ dim : Named int 2 2 6
## .. ..- attr(*, "names")= chr "Admit" "Gender" "Dept"
## ..$ dimnames:List of 3
## .. ..$ Admit : chr "Admit=Admitted" "Admit=Rejected"
## .. ..$ Gender: chr "Gender=Male" "Gender=Female"
## .. ..$ Dept : chr "Dept=A" "Dept=B" "Dept=C" "Dept=D" ...
MCA(UCBA.df, graph=FALSE)
## **Results of the Multiple Correspondence Analysis (MCA)**
## The analysis was performed on 4526 individuals, described by 3 variables
## *The results are available in the following objects:
##
## name description
## 1 "$eig" "eigenvalues"
## 2 "$var" "results for the variables"
## 3 "$var$coord" "coord. of the categories"
## 4 "$var$cos2" "cos2 for the categories"
## 5 "$var$contrib" "contributions of the categories"
## 6 "$var$v.test" "v-test for the categories"
## 7 "$ind" "results for the individuals"
## 8 "$ind$coord" "coord. for the individuals"
## 9 "$ind$cos2" "cos2 for the individuals"
## 10 "$ind$contrib" "contributions of the individuals"
## 11 "$call" "intermediate results"
## 12 "$call$marge.col" "weights of columns"
## 13 "$call$marge.li" "weights of rows"
#Exercice 3.4
d_wow <- read.csv("https://tinyurl.com/y5gffvsb", row.names =1)
head(d_wow[,1:3])
## Continent Area
## Durotar Kalimdor Central Kalimdor
## The Barrens Kalimdor Central Kalimdor
## Silverpine Forest Eastern Kingdoms Lordaeron
## Stonetalon Mountains Kalimdor Central Kalimdor
## Thunder Bluff Kalimdor Central Kalimdor
## Dustwallow Marsh Kalimdor Central Kalimdor
## Zone
## Durotar Durotar
## The Barrens The Barrens
## Silverpine Forest Silverpine Forest
## Stonetalon Mountains Stonetalon Mountains
## Thunder Bluff Thunder Bluff
## Dustwallow Marsh Dustwallow Marsh
d.d_wow <- dist(d_wow[,8:12])
wow.cah.ward <- hclust(d.d_wow, method="ward.D2")
library(ggdendro)
ggdendrogram(wow.cah.ward, labels = FALSE)
#Exercice 3.5
d_hotels <- read.csv("https://tinyurl.com/y3rxbxoo", row.names=1)
head(d_hotels)
## PAYS ETOILE CONFORT CHAMBRE CUISINE SPORT PLAGE PRIX
## Appolpon Grèce 1 4 56 2 0 8 390
## Caravel Grèce 4 7 471 7 6 5 468
## Christina Grèce 2 7 93 3 0 5 427
## Economy Grèce 1 3 56 1 0 8 369
## Eden Beach Grèce 1 4 286 3 4 7 499
## Hanikian Beach Grèce 3 6 282 5 10 10 526
d.d_hotels <- dist(d_hotels[,2:7])
hotels.cah.ward <- hclust(d.d_hotels, method="ward.D2")
ggdendrogram(hotels.cah.ward)
