Caroline Patenaude
Bibliothécaire - Bibliothèque des lettres et sciences humaines
# Chargement des modules nécessaires
library(questionr)
library(car)
library(ggplot2)
# Ajouter la fonction de téléchargement si nécessaire:
# install.packages("questionr", dependencies=TRUE)
# install.packages("car", dependencies=TRUE)
# install.packages("ggplot2", dependencies=TRUE)
#
# Téléchargement de la base de données hdv2003 du module questionr
# (Extrait de l'enquête "Histoire de vie" de l'Insee - https://www.insee.fr/fr/statistiques/2532244)
data(hdv2003)
# Copie de la base de données dans un objet (datatable) nommé bd
bd <- hdv2003
Fonctions de base s’accompagnent de nombreux arguments dont plusieurs peuvent être utilisés pour tous les graphiques
plot(table(bd$freres.soeurs),
col="red", # col= couleur des barres
main = "Nombre de frères et soeurs", # main= titre du grahique
ylab = "Effectif", # ylab= titre de l'axe y
xlab="Nombre de frères et soeurs", # xlab= titre de l'axe x
ylim=c(1, 500), # ylim= graduation de l'axe y
xlim=c(0, 25), # xlim= graduation de l'axe x
type="b") # type= style de lignes ("h", "p", "l", "o", "s", "b)
# Modifications possibles parmi tant d'autres: faire varier les points selon les valeurs d'une autre variable
# par l'ajout de fonctions superposées
plot(bd$age, bd$heures.tv) # var quanti/quanti
points(bd$age[bd$sexe=="Homme"], bd$heures.tv[bd$sexe=="Homme"], pch=16, col="steelblue")
points(bd$age[bd$sexe=="Femme"], bd$heures.tv[bd$sexe=="Femme"], pch=16, col="orange")
legend("topright", legend=c("Homme","Femme"), col=c("steelblue","orange"), pch=c(16))
# plot() nuage de points
# points() création d'une séquence de points colorés superposés en fonction de valeurs de variables sélectionnées par condition
# pch= style de points
# col= couleur des points
# legend() ajout d'une légende et ses arguments de paramétrage
## [1] "white" "aliceblue" "antiquewhite"
## [4] "antiquewhite1" "antiquewhite2" "antiquewhite3"
## [7] "antiquewhite4" "aquamarine" "aquamarine1"
## [10] "aquamarine2" "aquamarine3" "aquamarine4"
## [13] "azure" "azure1" "azure2"
## [16] "azure3" "azure4" "beige"
## [19] "bisque" "bisque1" "bisque2"
## [22] "bisque3" "bisque4" "black"
## [25] "blanchedalmond" "blue" "blue1"
## [28] "blue2" "blue3" "blue4"
## [31] "blueviolet" "brown" "brown1"
## [34] "brown2" "brown3" "brown4"
## [37] "burlywood" "burlywood1" "burlywood2"
## [40] "burlywood3" "burlywood4" "cadetblue"
## [43] "cadetblue1" "cadetblue2" "cadetblue3"
## [46] "cadetblue4" "chartreuse" "chartreuse1"
## [49] "chartreuse2" "chartreuse3" "chartreuse4"
## [52] "chocolate" "chocolate1" "chocolate2"
## [55] "chocolate3" "chocolate4" "coral"
## [58] "coral1" "coral2" "coral3"
## [61] "coral4" "cornflowerblue" "cornsilk"
## [64] "cornsilk1" "cornsilk2" "cornsilk3"
## [67] "cornsilk4" "cyan" "cyan1"
## [70] "cyan2" "cyan3" "cyan4"
## [73] "darkblue" "darkcyan" "darkgoldenrod"
## [76] "darkgoldenrod1" "darkgoldenrod2" "darkgoldenrod3"
## [79] "darkgoldenrod4" "darkgray" "darkgreen"
## [82] "darkgrey" "darkkhaki" "darkmagenta"
## [85] "darkolivegreen" "darkolivegreen1" "darkolivegreen2"
## [88] "darkolivegreen3" "darkolivegreen4" "darkorange"
## [91] "darkorange1" "darkorange2" "darkorange3"
## [94] "darkorange4" "darkorchid" "darkorchid1"
## [97] "darkorchid2" "darkorchid3" "darkorchid4"
## [100] "darkred" "darksalmon" "darkseagreen"
## [103] "darkseagreen1" "darkseagreen2" "darkseagreen3"
## [106] "darkseagreen4" "darkslateblue" "darkslategray"
## [109] "darkslategray1" "darkslategray2" "darkslategray3"
## [112] "darkslategray4" "darkslategrey" "darkturquoise"
## [115] "darkviolet" "deeppink" "deeppink1"
## [118] "deeppink2" "deeppink3" "deeppink4"
## [121] "deepskyblue" "deepskyblue1" "deepskyblue2"
## [124] "deepskyblue3" "deepskyblue4" "dimgray"
## [127] "dimgrey" "dodgerblue" "dodgerblue1"
## [130] "dodgerblue2" "dodgerblue3" "dodgerblue4"
## [133] "firebrick" "firebrick1" "firebrick2"
## [136] "firebrick3" "firebrick4" "floralwhite"
## [139] "forestgreen" "gainsboro" "ghostwhite"
## [142] "gold" "gold1" "gold2"
## [145] "gold3" "gold4" "goldenrod"
## [148] "goldenrod1" "goldenrod2" "goldenrod3"
## [151] "goldenrod4" "gray" "gray0"
## [154] "gray1" "gray2" "gray3"
## [157] "gray4" "gray5" "gray6"
## [160] "gray7" "gray8" "gray9"
## [163] "gray10" "gray11" "gray12"
## [166] "gray13" "gray14" "gray15"
## [169] "gray16" "gray17" "gray18"
## [172] "gray19" "gray20" "gray21"
## [175] "gray22" "gray23" "gray24"
## [178] "gray25" "gray26" "gray27"
## [181] "gray28" "gray29" "gray30"
## [184] "gray31" "gray32" "gray33"
## [187] "gray34" "gray35" "gray36"
## [190] "gray37" "gray38" "gray39"
## [193] "gray40" "gray41" "gray42"
## [196] "gray43" "gray44" "gray45"
## [199] "gray46" "gray47" "gray48"
## [202] "gray49" "gray50" "gray51"
## [205] "gray52" "gray53" "gray54"
## [208] "gray55" "gray56" "gray57"
## [211] "gray58" "gray59" "gray60"
## [214] "gray61" "gray62" "gray63"
## [217] "gray64" "gray65" "gray66"
## [220] "gray67" "gray68" "gray69"
## [223] "gray70" "gray71" "gray72"
## [226] "gray73" "gray74" "gray75"
## [229] "gray76" "gray77" "gray78"
## [232] "gray79" "gray80" "gray81"
## [235] "gray82" "gray83" "gray84"
## [238] "gray85" "gray86" "gray87"
## [241] "gray88" "gray89" "gray90"
## [244] "gray91" "gray92" "gray93"
## [247] "gray94" "gray95" "gray96"
## [250] "gray97" "gray98" "gray99"
## [253] "gray100" "green" "green1"
## [256] "green2" "green3" "green4"
## [259] "greenyellow" "grey" "grey0"
## [262] "grey1" "grey2" "grey3"
## [265] "grey4" "grey5" "grey6"
## [268] "grey7" "grey8" "grey9"
## [271] "grey10" "grey11" "grey12"
## [274] "grey13" "grey14" "grey15"
## [277] "grey16" "grey17" "grey18"
## [280] "grey19" "grey20" "grey21"
## [283] "grey22" "grey23" "grey24"
## [286] "grey25" "grey26" "grey27"
## [289] "grey28" "grey29" "grey30"
## [292] "grey31" "grey32" "grey33"
## [295] "grey34" "grey35" "grey36"
## [298] "grey37" "grey38" "grey39"
## [301] "grey40" "grey41" "grey42"
## [304] "grey43" "grey44" "grey45"
## [307] "grey46" "grey47" "grey48"
## [310] "grey49" "grey50" "grey51"
## [313] "grey52" "grey53" "grey54"
## [316] "grey55" "grey56" "grey57"
## [319] "grey58" "grey59" "grey60"
## [322] "grey61" "grey62" "grey63"
## [325] "grey64" "grey65" "grey66"
## [328] "grey67" "grey68" "grey69"
## [331] "grey70" "grey71" "grey72"
## [334] "grey73" "grey74" "grey75"
## [337] "grey76" "grey77" "grey78"
## [340] "grey79" "grey80" "grey81"
## [343] "grey82" "grey83" "grey84"
## [346] "grey85" "grey86" "grey87"
## [349] "grey88" "grey89" "grey90"
## [352] "grey91" "grey92" "grey93"
## [355] "grey94" "grey95" "grey96"
## [358] "grey97" "grey98" "grey99"
## [361] "grey100" "honeydew" "honeydew1"
## [364] "honeydew2" "honeydew3" "honeydew4"
## [367] "hotpink" "hotpink1" "hotpink2"
## [370] "hotpink3" "hotpink4" "indianred"
## [373] "indianred1" "indianred2" "indianred3"
## [376] "indianred4" "ivory" "ivory1"
## [379] "ivory2" "ivory3" "ivory4"
## [382] "khaki" "khaki1" "khaki2"
## [385] "khaki3" "khaki4" "lavender"
## [388] "lavenderblush" "lavenderblush1" "lavenderblush2"
## [391] "lavenderblush3" "lavenderblush4" "lawngreen"
## [394] "lemonchiffon" "lemonchiffon1" "lemonchiffon2"
## [397] "lemonchiffon3" "lemonchiffon4" "lightblue"
## [400] "lightblue1" "lightblue2" "lightblue3"
## [403] "lightblue4" "lightcoral" "lightcyan"
## [406] "lightcyan1" "lightcyan2" "lightcyan3"
## [409] "lightcyan4" "lightgoldenrod" "lightgoldenrod1"
## [412] "lightgoldenrod2" "lightgoldenrod3" "lightgoldenrod4"
## [415] "lightgoldenrodyellow" "lightgray" "lightgreen"
## [418] "lightgrey" "lightpink" "lightpink1"
## [421] "lightpink2" "lightpink3" "lightpink4"
## [424] "lightsalmon" "lightsalmon1" "lightsalmon2"
## [427] "lightsalmon3" "lightsalmon4" "lightseagreen"
## [430] "lightskyblue" "lightskyblue1" "lightskyblue2"
## [433] "lightskyblue3" "lightskyblue4" "lightslateblue"
## [436] "lightslategray" "lightslategrey" "lightsteelblue"
## [439] "lightsteelblue1" "lightsteelblue2" "lightsteelblue3"
## [442] "lightsteelblue4" "lightyellow" "lightyellow1"
## [445] "lightyellow2" "lightyellow3" "lightyellow4"
## [448] "limegreen" "linen" "magenta"
## [451] "magenta1" "magenta2" "magenta3"
## [454] "magenta4" "maroon" "maroon1"
## [457] "maroon2" "maroon3" "maroon4"
## [460] "mediumaquamarine" "mediumblue" "mediumorchid"
## [463] "mediumorchid1" "mediumorchid2" "mediumorchid3"
## [466] "mediumorchid4" "mediumpurple" "mediumpurple1"
## [469] "mediumpurple2" "mediumpurple3" "mediumpurple4"
## [472] "mediumseagreen" "mediumslateblue" "mediumspringgreen"
## [475] "mediumturquoise" "mediumvioletred" "midnightblue"
## [478] "mintcream" "mistyrose" "mistyrose1"
## [481] "mistyrose2" "mistyrose3" "mistyrose4"
## [484] "moccasin" "navajowhite" "navajowhite1"
## [487] "navajowhite2" "navajowhite3" "navajowhite4"
## [490] "navy" "navyblue" "oldlace"
## [493] "olivedrab" "olivedrab1" "olivedrab2"
## [496] "olivedrab3" "olivedrab4" "orange"
## [499] "orange1" "orange2" "orange3"
## [502] "orange4" "orangered" "orangered1"
## [505] "orangered2" "orangered3" "orangered4"
## [508] "orchid" "orchid1" "orchid2"
## [511] "orchid3" "orchid4" "palegoldenrod"
## [514] "palegreen" "palegreen1" "palegreen2"
## [517] "palegreen3" "palegreen4" "paleturquoise"
## [520] "paleturquoise1" "paleturquoise2" "paleturquoise3"
## [523] "paleturquoise4" "palevioletred" "palevioletred1"
## [526] "palevioletred2" "palevioletred3" "palevioletred4"
## [529] "papayawhip" "peachpuff" "peachpuff1"
## [532] "peachpuff2" "peachpuff3" "peachpuff4"
## [535] "peru" "pink" "pink1"
## [538] "pink2" "pink3" "pink4"
## [541] "plum" "plum1" "plum2"
## [544] "plum3" "plum4" "powderblue"
## [547] "purple" "purple1" "purple2"
## [550] "purple3" "purple4" "red"
## [553] "red1" "red2" "red3"
## [556] "red4" "rosybrown" "rosybrown1"
## [559] "rosybrown2" "rosybrown3" "rosybrown4"
## [562] "royalblue" "royalblue1" "royalblue2"
## [565] "royalblue3" "royalblue4" "saddlebrown"
## [568] "salmon" "salmon1" "salmon2"
## [571] "salmon3" "salmon4" "sandybrown"
## [574] "seagreen" "seagreen1" "seagreen2"
## [577] "seagreen3" "seagreen4" "seashell"
## [580] "seashell1" "seashell2" "seashell3"
## [583] "seashell4" "sienna" "sienna1"
## [586] "sienna2" "sienna3" "sienna4"
## [589] "skyblue" "skyblue1" "skyblue2"
## [592] "skyblue3" "skyblue4" "slateblue"
## [595] "slateblue1" "slateblue2" "slateblue3"
## [598] "slateblue4" "slategray" "slategray1"
## [601] "slategray2" "slategray3" "slategray4"
## [604] "slategrey" "snow" "snow1"
## [607] "snow2" "snow3" "snow4"
## [610] "springgreen" "springgreen1" "springgreen2"
## [613] "springgreen3" "springgreen4" "steelblue"
## [616] "steelblue1" "steelblue2" "steelblue3"
## [619] "steelblue4" "tan" "tan1"
## [622] "tan2" "tan3" "tan4"
## [625] "thistle" "thistle1" "thistle2"
## [628] "thistle3" "thistle4" "tomato"
## [631] "tomato1" "tomato2" "tomato3"
## [634] "tomato4" "turquoise" "turquoise1"
## [637] "turquoise2" "turquoise3" "turquoise4"
## [640] "violet" "violetred" "violetred1"
## [643] "violetred2" "violetred3" "violetred4"
## [646] "wheat" "wheat1" "wheat2"
## [649] "wheat3" "wheat4" "whitesmoke"
## [652] "yellow" "yellow1" "yellow2"
## [655] "yellow3" "yellow4" "yellowgreen"
# variable indépendante à gauche (x), dépendante à droite (y)
# Notation formule: les formules passent la variable y en premier,
# donc la notation formule de la fonction générique plot(x, y) est plot(y ~ x)
# Ajout de la fonction de densité à la fonction plot()
plot(density(bd$heures.tv, na.rm = TRUE), main = "Heures d'écoute de télé")
# Ajout de la fonction lines() qui permet de superposer plusieurs éléments graphiques
# lwd= largeur des lignes
plot(density(bd$age[bd$sexe == "Femme"]), lwd = 3, col = "red", main = "Titre du graphique")
lines(density(bd$age[bd$sexe == "Homme"]), lwd = 3, col = "blue")
tb.eff <- table(bd$trav.satis, bd$sexe) # tableau d'effectifs
tb.prop <- cprop(tb.eff, total = FALSE) # tableau de proportions
# Graphique à barres avec table d'effectifs superposés
# legend = levels pour faire apparaitre les catégories de la variable choisie
barplot(tb.eff , legend = levels(bd$trav.satis))
# Graphique à barres avec table de proportions
barplot(tb.prop, beside = TRUE, xlab = "Satisfaction", ylab = "pourcentages", las=2, ylim=c(0, 100),
col = c("blue", "green", "orange"), legend = levels(bd$trav.satis))
# Histogramme avec quelques arguments
hist(bd$age, main = "Age", col="violetred2", breaks = 8, xlab = "Age", ylab = "Effectif", labels = TRUE)
# main= titre du grahique
# col= couleur des barres
# breaks= nombre de "barres"
# xlab= titre de l'axe x
# ylab= titre de l'axe y
# labels= affichage des valeurs
# Pour ajouter une ligne de densité:
## argument prob = TRUE affichage de la ligne de densité
## fonction lines(density(bd$age, na.rm = TRUE), lwd = 4, col = "green")
par(mfrow = c(1, 2), bg="gray", col.axis="green", mar=c(5, 5, 5, 5))
hist(bd$age[bd$sport == "Oui"], main = "Sportif", col = "chartreuse2")
hist(bd$age[bd$sport == "Non"], main = "Non sportif", col = "cyan4")
# par() disposition des graphiques
# bg= couleur du "background"
# col.axis= couleur de la numérotation des axes
# mar= grosseur des marges
# Graphique mosaique
mosaicplot(sport ~ sexe, bd, las = 1, shade = TRUE, main="Niveau de qualification selon le sexe")
# Chaque boite correspond à une cellule
# largeur: pourcentages en colonnes
# hauteur: pourcentages en lignes
# Couleurs: résidus du chi2
# diagramme Q-Q (Module car)
qqPlot(bd$heures.tv, col=colors()[9], col.lines=colors()[30], lwd=4, pch=1)
## [1] 288 391
# Compare à une distribution normale, quantile par quantile
# Trace en pointillé l'intervalle de confiance à 95%
# Identifie les points les plus éloignés de leur quantile normal
# col= sélection de couleurs des points par position dans la palette colors()
# col.lines= sélection de couleurs des lignes par position dans la palette colors()
# lwd= largeur des lignes
# pch= type de points
# Nuage de points + ligne de régression non paramétrique et boites à moustache sur les axes (Module car)
scatterplot(heures.tv ~ age, data=bd)
https://ggplot2.tidyverse.org/reference/ https://www.r-graph-gallery.com/ggplot2-package.html
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ggplot(bd) +
geom_histogram(aes(x = age), fill="orchid1", colour = "white", binwidth = 5) + # arguments de couleurs et largeur des barres
ggtitle("Age des répondants") + # titre du graphique
xlab("Age") + # titre axe x
ylab("Effectifs") # titre axe y
# Le faceting permet d’effectuer plusieurs fois le même graphique selon les valeurs d’une ou plusieurs
# variables qualitatives, içi facet_grid(~sexe).
ggplot(bd) +
geom_histogram(aes(x = age), fill="orchid1", colour = "white", breaks = c(0, 20, 40, 60, 80, 100)) + # breaks= limites des catégories d'âge
ggtitle("Age des répondants") + # titre du graphique
xlab("Age") + # titre axe x
facet_grid(~sexe) # variable de groupes
ggplot(bd) +
geom_bar(aes(x = trav.satisf), fill = "thistle3", width = .7) +
xlab("Satisfaction") +
ylab("Effectifs") +
ggtitle("Satisfaction au travail")
# Pour faire varier la couleur en fonction des valeurs prises par d'une autre variable, on réalise un "mappage"
# on doit alors placer l’attribut graphique (ici fill=) à l’intérieur de la parenthèse aes()
ggplot(bd) +
geom_bar(aes(x = occup, fill = sexe)) # position = "stack" - effectifs de groupes superposés par défaut
ggplot(bd) +
geom_bar(aes(x = occup, fill = sexe), position = "dodge") # position = "dodge" - effectifs de groupes côte à côte
ggplot(bd) +
geom_bar(aes(x = occup, fill = sexe), position = "fill") # position = "fill" - proportions superposées des groupes
ggplot(bd) +
geom_point(aes(x = age, y = freres.soeurs, color = sexe), size=3, pch=19) +
scale_color_brewer("sexe", palette = "Accent") +
theme(legend.position = "bottom", legend.box = "vertical") # ou appliquer des thèmes prédéfinis comme theme_dark()
# color= à l'intérieur de aes() permet de faire varier la couleur des points en fonction des valeurs d’une troisième variable
# Modier la grosseur des points avec size= et le type avec pch=
# Autre répertoire de couleurs scale_color_brewer: RColorBrewer::display.brewer.all()
# theme() fonction permettant de personnaliser l'apparence des graphiques:
## permet d'appliquer des thèmes complets (ex: theme_dark()) ou des composantes spécifiques - voir aide ?theme
ggplot(bd) +
geom_point(aes(x = age, y = heures.tv, color=sexe, size=heures.tv), alpha=0.2) +
scale_size("Heures de télé", range = c(1,10)) +
scale_x_continuous("Age", limits = c(15,100)) +
scale_y_continuous("Heures de télé", limits = c(0,15))
## Warning: Removed 5 rows containing missing values (geom_point).
# size= déplacé à l'intérieur de eas permet de faire varier la grosseur des points selon une variable quantitative
# alpha= modifier la transparence
# scale() permet de définir les limites des échelles x et y et leur légende respective
# ajouter une droite de régression + lignes de densité
ggplot(bd, aes(x=age, y=freres.soeurs)) +
geom_point(col="steelblue2") +
geom_smooth(method="lm", col="thistle3") +
geom_density2d(color = "orange") +
scale_x_log10()
## `geom_smooth()` using formula 'y ~ x'
# On passe en y la variable quanti et en x la variable quali
ggplot(bd) +
geom_boxplot(aes(x = trav.satisf, y =age), varwidth = TRUE, fill = "midnightblue", color = "chartreuse1") +
ggtitle("Pratique de la religion")
# on fait varier la couleur selon une variable et on "flip" le tout
ggplot(bd, aes(x = sexe, y = freres.soeurs, color = sexe)) + geom_boxplot() + coord_flip()
# Distribution de l'âge selon le sexe (densité superposée avec transparence)
ggplot(bd, aes(x = age, color = sexe, fill=sexe)) +
geom_density(alpha=0.55)