Thesis: “Reflexions methodologies autour du Napping: vers une integration du comportement du sujet dans l’analyse des donnees de Napping”
Chapter 1 - Napping and sorted Napping as a sensory profiling technique
Author: Tam Minh LE
Supervisor : Francois Husson & Sebastien Le
R version: 3.2.1 - Updated: 17.08.2015
rm(list=ls())
options(max.print=5.5E5) # max print
# Require package ---------------------------------------------------------
library(FactoMineR)
library(SensoMineR)
library(ggplot2)
library(reshape2)
library(stringr)
library(holos)
library(car)
library(cluster)
library(grDevices)
library(knitr)
# Set working directory ---------------------------------------------------
wd <- "C:/Users/LE Minh-Tam/Dropbox/00. Thesis/Data"
setwd(wd)
list.files(pattern=".rda")
## [1] "ba.qual.rda" "ba.sort.rda" "cards.fico.rda" "cards.rda"
## [5] "cards.tempo.rda" "emotion_fr.rda" "emotion_vn.rda" "videotablet.rda"
# Load data: (1) emotion data of French consumers & (2) Smoothies
load("emotion_fr.rda") # in the script of chapter 9, emotions = emotion_fr
emotions <- emotion_fr
# Figure 1.1: Tablecloth of s31
nappeplot(emotions[, c("X31","Y31")], numr=1, numc=1, lim=c(60,40), color = "black")
# Figure 1.2: Tablecloth of s96 -------------------------------------------
nappeplot(emotions[, c("X96","Y96")], numr=1, numc=1, lim=c(60,40), color = "black")
# Figure 1.3: representation provided by MFA
## MFA
njuge <- ncol(emotions)/2
namegroup <- c(paste("s", 1:100, sep=""))
res <- MFA(emotions, group = rep(2, njuge), ncp=Inf,
type = rep("c", njuge), graph=FALSE, name.group=namegroup)
round(res$ind$cos2["surprised",1:5],2) # cos2
## Dim.1 Dim.2 Dim.3 Dim.4 Dim.5
## 0.00 0.00 0.00 0.01 0.00
round(res$ind$contrib["surprised",1:5],2) # contribution
## Dim.1 Dim.2 Dim.3 Dim.4 Dim.5
## 0.04 0.03 0.20 6.15 1.04
## Plot
plot(res, axes = c(1, 2), choix = "ind", habillage = "ind",
palette=palette(c("black","black")),
xlim=c(-8,8), ylim=c(-10,10), cex=0.8,
title="Emotional space of French consumer", las=1)
# Figure 1.4: separate analysis of the group -----------------------------
palette.j = palette(c(rep("transparent",31), "blue",
rep("transparent",64), "blue",
rep("transparent", 5)))
plot(res, axes = c(1, 2), choix="axes", habillage="group",
palette=palette.j, lab.grpe=FALSE)
# Figure 1.5: representation of groups of variables ----------------------
plot(res, axes = c(1, 2), choix="group", col="black")
# Table 1.1: Decomposition of the total variance -------------------------
round(res$eig[1:10,],2)
## eigenvalue percentage of variance
## comp 1 49.43 37.36
## comp 2 8.85 6.69
## comp 3 5.58 4.22
## comp 4 4.85 3.67
## comp 5 4.03 3.05
## comp 6 3.79 2.86
## comp 7 3.66 2.76
## comp 8 3.36 2.54
## comp 9 3.23 2.44
## comp 10 2.71 2.05
## cumulative percentage of variance
## comp 1 37.36
## comp 2 44.05
## comp 3 48.27
## comp 4 51.94
## comp 5 54.98
## comp 6 57.85
## comp 7 60.61
## comp 8 63.15
## comp 9 65.59
## comp 10 67.64
# Part 2 - sorted Napping -------------------------------------------------
# load data smoothies
data(smoothies) # 24 subjects, 8 products
ncol(smoothies)/3 # number of subjects
## [1] 24
# Figure 1.6: an example of sorted napping --------------------------------
nappeplot(smoothies[, c("X5","Y5")], numr=1, numc=1,
lim=c(60,40), color = "black")
# Figure 1.7, 1.8, 1.9 ----------------------------------------------------
res.fasnt <- fasnt(smoothies, first = "nappe", sep.word = ";")
## Number of different words : 90
H.list <- list(rep(c(2,1),24), rep(2,24))
X11(); HMFA(smoothies, H = H.list, type = rep(c("c","n"), 24))
## **Results of the Hierarchical Multiple Factor Analysis (HMFA)**
##
## There are 8 individuals
##
## *Results are available in the following objects :
##
## name description
## 1 "$eig" "eigenvalues"
## 2 "$group" "results for all the groups"
## 3 "$ind" "results for the individuals"
## 4 "$partial" "partial coordinates for the individuals"
## 5 "$quanti.var" "results for the quantitative variables"
## 6 "$quali.var" "results for the categorical variables"
# Tab 1.2: sorted napping data of subject 5 -------------------------------
smoothies[,c("X5", "Y5", "C5")]
## X5 Y5 C5
## Immedia_MP 47.5 28 exotic fruits;acid
## Carrefour_MP 53.0 33 exotic fruits;acid
## Immedia_SRB 41.0 34 exotic fruits;acid
## Casino_SRB 40.5 25 exotic fruits;acid
## Innocent_PBC 45.0 8 banana flavor;heavy
## Casino_PBC 40.0 8 banana flavor;heavy
## Innocent_SB 14.0 22 unknown taste;heavy
## Carrefour_SB 19.0 16 unknown taste;heavy
# Table 1.3: An automatic description of fasnt() function -----------------
res.fasnt$textual
## $Carrefour_MP
## Intern % glob % Intern freq Glob freq p.value v.test
## acid 42.10526 15.66265 8 26 0.005900086 2.753283
##
## $Carrefour_SB
## NULL
##
## $Casino_PBC
## Intern % glob % Intern freq Glob freq p.value v.test
## acid 0 15.66265 0 26 0.01582659 -2.41289
##
## $Casino_SRB
## NULL
##
## $Immedia_MP
## NULL
##
## $Immedia_SRB
## Intern % glob % Intern freq Glob freq p.value v.test
## acid 34.78261 15.66265 8 26 0.02439432 2.250861
##
## $Innocent_PBC
## Intern % glob % Intern freq Glob freq p.value v.test
## acid 0 15.66265 0 26 0.01582659 -2.41289
##
## $Innocent_SB
## Intern % glob % Intern freq Glob freq p.value v.test
## strawberry 22.22222 6.626506 4 11 0.03997686 2.053988
##
## attr(,"class")
## [1] "descfreq" "list "
End of Chapter 1