Version de R

R.version

               _                           
platform       x86_64-pc-linux-gnu         
arch           x86_64                      
os             linux-gnu                   
system         x86_64, linux-gnu           
status                                     
major          4                           
minor          4.3                         
year           2025                        
month          02                          
day            28                          
svn rev        87843                       
language       R                           
version.string R version 4.4.3 (2025-02-28)
nickname       Trophy Case                 

Importation et inspection des données

#importation des données
library(readxl)
D <- readxl::read_excel("/content/habitudes_de_vie.xlsx")
str(D)

tibble [360 × 6] (S3: tbl_df/tbl/data.frame)
 $ TYPELAIT     : chr [1:360] "2%MILK" "SKIM" "NOMILK" "NOMILK" ...
 $ SELALIMENT   : chr [1:360] "MODERATE" "MODERATE" "NONE" "NONE" ...
 $ SELCONSO     : chr [1:360] "MODERATE" "LOW" "???" "LOW" ...
 $ ACTIVITESPORT: chr [1:360] "DAILY" "DAILY" "DAILY" "DAILY" ...
 $ FUMER        : chr [1:360] "REGULAR" "NEVER" "FORMER" "OCCASIONAL" ...
 $ HAB_BOISSON  : chr [1:360] "OCCASIONAL" "NEVER" "NEVER" "REGULAR" ...

#transformer en dataframe de factor
#sinon warning de "arules" (booléen ou factor acceptés)
D <- as.data.frame(lapply(D,factor))
str(D)

'data.frame':	360 obs. of  6 variables:
 $ TYPELAIT     : Factor w/ 5 levels "2%MILK","NOMILK",..: 1 4 2 2 1 1 5 2 1 1 ...
 $ SELALIMENT   : Factor w/ 5 levels "???","ALOT","MODERATE",..: 3 3 4 4 4 4 2 5 4 4 ...
 $ SELCONSO     : Factor w/ 6 levels "???","HIGH","LOW",..: 4 3 1 3 3 6 4 2 3 6 ...
 $ ACTIVITESPORT: Factor w/ 6 levels "???","DAILY",..: 2 2 2 2 3 2 3 3 2 2 ...
 $ FUMER        : Factor w/ 5 levels "????","FORMER",..: 5 3 2 4 5 3 5 5 3 5 ...
 $ HAB_BOISSON  : Factor w/ 4 levels "FORMER","NEVER",..: 3 2 2 4 3 3 3 4 2 4 ...

#premières lignes
head(D)

A data.frame: 6 × 6

	TYPELAIT	SELALIMENT	SELCONSO	ACTIVITESPORT	FUMER	HAB_BOISSON
	<fct>	<fct>	<fct>	<fct>	<fct>	<fct>
1	2%MILK	MODERATE	MODERATE	DAILY	REGULAR	OCCASIONAL
2	SKIM	MODERATE	LOW	DAILY	NEVER	NEVER
3	NOMILK	NONE	???	DAILY	FORMER	NEVER
4	NOMILK	NONE	LOW	DAILY	OCCASIONAL	REGULAR
5	2%MILK	NONE	LOW	NEVER	REGULAR	OCCASIONAL
6	2%MILK	NONE	VERYLOW	DAILY	NEVER	OCCASIONAL

Extraction des itemsets fréquents

#installer le package à la volée
#install.packages("arules")

Installing package into ‘/usr/local/lib/R/site-library’
(as ‘lib’ is unspecified)

#chargement et version du package "arules"
library(arules)
packageVersion("arules")

Loading required package: Matrix


Attaching package: ‘arules’


The following objects are masked from ‘package:base’:

    abbreviate, write

[1] ‘1.7.9’

#paramétrage et extraction des itemsets (cf. l'option target)
#singletons ou paires d'items fréquents (support >= 0.3)
params <- list(supp=0.3, minlen=1, maxlen=2, target="frequent itemsets")
freq <- apriori(D, parameter=params)

Apriori

Parameter specification:
 confidence minval smax arem  aval originalSupport maxtime support minlen
         NA    0.1    1 none FALSE            TRUE       5     0.3      1
 maxlen            target  ext
      2 frequent itemsets TRUE

Algorithmic control:
 filter tree heap memopt load sort verbose
    0.1 TRUE TRUE  FALSE TRUE    2    TRUE

Absolute minimum support count: 108 

set item appearances ...[0 item(s)] done [0.00s].
set transactions ...[31 item(s), 360 transaction(s)] done [0.00s].
sorting and recoding items ... [9 item(s)] done [0.00s].
creating transaction tree ... done [0.00s].
checking subsets of size 1 2

Warning message in apriori(D, parameter = params):
“Mining stopped (maxlen reached). Only patterns up to a length of 2 returned!”

 done [0.01s].
sorting transactions ... done [0.00s].
writing ... [10 set(s)] done [0.00s].
creating S4 object  ... done [0.00s].

#affichage des itemsets
inspect(freq)

     items                                  support   count
[1]  {FUMER=REGULAR}                        0.3166667 114  
[2]  {SELALIMENT=NONE}                      0.3166667 114  
[3]  {SELCONSO=LOW}                         0.3416667 123  
[4]  {ACTIVITESPORT=DAILY}                  0.3500000 126  
[5]  {SELALIMENT=VERYLITTLE}                0.3666667 132  
[6]  {FUMER=FORMER}                         0.3888889 140  
[7]  {ACTIVITESPORT=NEVER}                  0.4777778 172  
[8]  {HAB_BOISSON=REGULAR}                  0.5916667 213  
[9]  {TYPELAIT=2%MILK}                      0.6416667 231  
[10] {TYPELAIT=2%MILK, HAB_BOISSON=REGULAR} 0.4027778 145  

#tri selon support décroissant
inspect(sort(freq,by="support"))

     items                                  support   count
[1]  {TYPELAIT=2%MILK}                      0.6416667 231  
[2]  {HAB_BOISSON=REGULAR}                  0.5916667 213  
[3]  {ACTIVITESPORT=NEVER}                  0.4777778 172  
[4]  {TYPELAIT=2%MILK, HAB_BOISSON=REGULAR} 0.4027778 145  
[5]  {FUMER=FORMER}                         0.3888889 140  
[6]  {SELALIMENT=VERYLITTLE}                0.3666667 132  
[7]  {ACTIVITESPORT=DAILY}                  0.3500000 126  
[8]  {SELCONSO=LOW}                         0.3416667 123  
[9]  {FUMER=REGULAR}                        0.3166667 114  
[10] {SELALIMENT=NONE}                      0.3166667 114  

#récupération dans un data frame
#toutes post-opérations compatibles avec des dataframe
#possibles dès lors
res <- DATAFRAME(freq)
res

A data.frame: 10 × 3

	items	support	count
	<fct>	<dbl>	<int>
1	{FUMER=REGULAR}	0.3166667	114
2	{SELALIMENT=NONE}	0.3166667	114
3	{SELCONSO=LOW}	0.3416667	123
4	{ACTIVITESPORT=DAILY}	0.3500000	126
5	{SELALIMENT=VERYLITTLE}	0.3666667	132
6	{FUMER=FORMER}	0.3888889	140
7	{ACTIVITESPORT=NEVER}	0.4777778	172
8	{HAB_BOISSON=REGULAR}	0.5916667	213
9	{TYPELAIT=2%MILK}	0.6416667	231
10	{TYPELAIT=2%MILK,HAB_BOISSON=REGULAR}	0.4027778	145

#vérification 1 - support
prop.table(table(D$FUMER))

       ????      FORMER       NEVER  OCCASIONAL     REGULAR 
0.002777778 0.388888889 0.261111111 0.030555556 0.316666667 

#vérification 2 - support
prop.table(table(D$TYPELAIT,D$HAB_BOISSON))

           
                 FORMER       NEVER  OCCASIONAL     REGULAR
  2%MILK    0.016666667 0.161111111 0.061111111 0.402777778
  NOMILK    0.005555556 0.011111111 0.005555556 0.041666667
  POWDER    0.000000000 0.002777778 0.000000000 0.002777778
  SKIM      0.000000000 0.019444444 0.005555556 0.027777778
  WHOLEMILK 0.008333333 0.063888889 0.047222222 0.116666667

#filtrage des itemsets
#rechercher qui concernent HAB_BOISSON
res[grep("HAB_BOISSON",res$items),]

A data.frame: 2 × 3

	items	support	count
	<fct>	<dbl>	<int>
8	{HAB_BOISSON=REGULAR}	0.5916667	213
10	{TYPELAIT=2%MILK,HAB_BOISSON=REGULAR}	0.4027778	145

Extraction des règles

#paramétrage et extraction
#cf. notamment l'option target
params.regles <- list(supp=0.1, conf=0.7, minlen=2, maxlen=4, target="rules")
regles <- apriori(D,parameter=params.regles)

Apriori

Parameter specification:
 confidence minval smax arem  aval originalSupport maxtime support minlen
        0.7    0.1    1 none FALSE            TRUE       5     0.1      2
 maxlen target  ext
      4  rules TRUE

Algorithmic control:
 filter tree heap memopt load sort verbose
    0.1 TRUE TRUE  FALSE TRUE    2    TRUE

Absolute minimum support count: 36 

set item appearances ...[0 item(s)] done [0.00s].
set transactions ...[31 item(s), 360 transaction(s)] done [0.00s].
sorting and recoding items ... [17 item(s)] done [0.00s].
creating transaction tree ... done [0.00s].
checking subsets of size 1 2 3 4

Warning message in apriori(D, parameter = params.regles):
“Mining stopped (maxlen reached). Only patterns up to a length of 4 returned!”

 done [0.01s].
writing ... [11 rule(s)] done [0.00s].
creating S4 object  ... done [0.00s].

#affichage
inspect(regles)

     lhs                         rhs                     support confidence  coverage     lift count
[1]  {SELALIMENT=MODERATE,                                                                          
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1250000  0.7142857 0.1750000 1.113173    45
[2]  {TYPELAIT=2%MILK,                                                                              
      SELALIMENT=MODERATE}    => {HAB_BOISSON=REGULAR} 0.1250000  0.7258065 0.1722222 1.226715    45
[3]  {SELCONSO=MODERATE,                                                                            
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1305556  0.7014925 0.1861111 1.093235    47
[4]  {SELALIMENT=NONE,                                                                              
      SELCONSO=VERYLOW}       => {TYPELAIT=2%MILK}     0.1361111  0.7777778 0.1750000 1.212121    49
[5]  {SELCONSO=VERYLOW,                                                                             
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1027778  0.7400000 0.1388889 1.153247    37
[6]  {SELALIMENT=NONE,                                                                              
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1250000  0.7142857 0.1750000 1.113173    45
[7]  {ACTIVITESPORT=DAILY,                                                                          
      FUMER=FORMER}           => {HAB_BOISSON=REGULAR} 0.1194444  0.8269231 0.1444444 1.397616    43
[8]  {ACTIVITESPORT=DAILY,                                                                          
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1694444  0.7261905 0.2333333 1.131725    61
[9]  {TYPELAIT=2%MILK,                                                                              
      ACTIVITESPORT=DAILY}    => {HAB_BOISSON=REGULAR} 0.1694444  0.7349398 0.2305556 1.242152    61
[10] {SELALIMENT=VERYLITTLE,                                                                        
      FUMER=FORMER}           => {HAB_BOISSON=REGULAR} 0.1083333  0.7090909 0.1527778 1.198464    39
[11] {SELALIMENT=VERYLITTLE,                                                                        
      ACTIVITESPORT=NEVER}    => {TYPELAIT=2%MILK}     0.1166667  0.7000000 0.1666667 1.090909    42

#trier selon le lift décroissant
inspect(sort(regles,by="lift"))

     lhs                         rhs                     support confidence  coverage     lift count
[1]  {ACTIVITESPORT=DAILY,                                                                          
      FUMER=FORMER}           => {HAB_BOISSON=REGULAR} 0.1194444  0.8269231 0.1444444 1.397616    43
[2]  {TYPELAIT=2%MILK,                                                                              
      ACTIVITESPORT=DAILY}    => {HAB_BOISSON=REGULAR} 0.1694444  0.7349398 0.2305556 1.242152    61
[3]  {TYPELAIT=2%MILK,                                                                              
      SELALIMENT=MODERATE}    => {HAB_BOISSON=REGULAR} 0.1250000  0.7258065 0.1722222 1.226715    45
[4]  {SELALIMENT=NONE,                                                                              
      SELCONSO=VERYLOW}       => {TYPELAIT=2%MILK}     0.1361111  0.7777778 0.1750000 1.212121    49
[5]  {SELALIMENT=VERYLITTLE,                                                                        
      FUMER=FORMER}           => {HAB_BOISSON=REGULAR} 0.1083333  0.7090909 0.1527778 1.198464    39
[6]  {SELCONSO=VERYLOW,                                                                             
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1027778  0.7400000 0.1388889 1.153247    37
[7]  {ACTIVITESPORT=DAILY,                                                                          
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1694444  0.7261905 0.2333333 1.131725    61
[8]  {SELALIMENT=MODERATE,                                                                          
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1250000  0.7142857 0.1750000 1.113173    45
[9]  {SELALIMENT=NONE,                                                                              
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1250000  0.7142857 0.1750000 1.113173    45
[10] {SELCONSO=MODERATE,                                                                            
      HAB_BOISSON=REGULAR}    => {TYPELAIT=2%MILK}     0.1305556  0.7014925 0.1861111 1.093235    47
[11] {SELALIMENT=VERYLITTLE,                                                                        
      ACTIVITESPORT=NEVER}    => {TYPELAIT=2%MILK}     0.1166667  0.7000000 0.1666667 1.090909    42

#récupération dans un data.frame
dfRegles <- DATAFRAME(regles)
dfRegles

A data.frame: 11 × 7

	LHS	RHS	support	confidence	coverage	lift	count
	<fct>	<fct>	<dbl>	<dbl>	<dbl>	<dbl>	<int>
1	{SELALIMENT=MODERATE,HAB_BOISSON=REGULAR}	{TYPELAIT=2%MILK}	0.1250000	0.7142857	0.1750000	1.113173	45
2	{TYPELAIT=2%MILK,SELALIMENT=MODERATE}	{HAB_BOISSON=REGULAR}	0.1250000	0.7258065	0.1722222	1.226715	45
3	{SELCONSO=MODERATE,HAB_BOISSON=REGULAR}	{TYPELAIT=2%MILK}	0.1305556	0.7014925	0.1861111	1.093235	47
4	{SELALIMENT=NONE,SELCONSO=VERYLOW}	{TYPELAIT=2%MILK}	0.1361111	0.7777778	0.1750000	1.212121	49
5	{SELCONSO=VERYLOW,HAB_BOISSON=REGULAR}	{TYPELAIT=2%MILK}	0.1027778	0.7400000	0.1388889	1.153247	37
6	{SELALIMENT=NONE,HAB_BOISSON=REGULAR}	{TYPELAIT=2%MILK}	0.1250000	0.7142857	0.1750000	1.113173	45
7	{ACTIVITESPORT=DAILY,FUMER=FORMER}	{HAB_BOISSON=REGULAR}	0.1194444	0.8269231	0.1444444	1.397616	43
8	{ACTIVITESPORT=DAILY,HAB_BOISSON=REGULAR}	{TYPELAIT=2%MILK}	0.1694444	0.7261905	0.2333333	1.131725	61
9	{TYPELAIT=2%MILK,ACTIVITESPORT=DAILY}	{HAB_BOISSON=REGULAR}	0.1694444	0.7349398	0.2305556	1.242152	61
10	{SELALIMENT=VERYLITTLE,FUMER=FORMER}	{HAB_BOISSON=REGULAR}	0.1083333	0.7090909	0.1527778	1.198464	39
11	{SELALIMENT=VERYLITTLE,ACTIVITESPORT=NEVER}	{TYPELAIT=2%MILK}	0.1166667	0.7000000	0.1666667	1.090909	42

#avec possibilité de filtrage toujours
#ex. règles avec HAB_BOISSON dans le conséquent
dfRegles[grep("HAB_BOISSON",dfRegles$RHS),]

A data.frame: 4 × 7

	LHS	RHS	support	confidence	coverage	lift	count
	<fct>	<fct>	<dbl>	<dbl>	<dbl>	<dbl>	<int>
2	{TYPELAIT=2%MILK,SELALIMENT=MODERATE}	{HAB_BOISSON=REGULAR}	0.1250000	0.7258065	0.1722222	1.226715	45
7	{ACTIVITESPORT=DAILY,FUMER=FORMER}	{HAB_BOISSON=REGULAR}	0.1194444	0.8269231	0.1444444	1.397616	43
9	{TYPELAIT=2%MILK,ACTIVITESPORT=DAILY}	{HAB_BOISSON=REGULAR}	0.1694444	0.7349398	0.2305556	1.242152	61
10	{SELALIMENT=VERYLITTLE,FUMER=FORMER}	{HAB_BOISSON=REGULAR}	0.1083333	0.7090909	0.1527778	1.198464	39