library(FactoMineR)
## Warning: package 'FactoMineR' was built under R version 4.0.3
library(factoextra)
## Loading required package: ggplot2
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
read.table("perros.txt",header=T,sep="",row.names=1)->perrosi
En este informe se realizará una aplicación del ACM utilizando el conjunto de datos “perros”. Este conjunto de datos presenta 27 razas de perros y 7 variables cualitativas. A continuación, se presenta el conjunto de datos.
knitr::kable(perrosi)
TAM | PES | VEL | INT | AFE | AGR | FUN | |
---|---|---|---|---|---|---|---|
bass | peq | liv | len | baj | baj | alt | caz |
beau | gra | med | alt | med | alt | alt | uti |
boxe | med | med | med | med | alt | alt | com |
buld | peq | liv | len | med | alt | baj | com |
bulm | gra | pes | len | alt | baj | alt | uti |
cani | peq | liv | med | alt | alt | baj | com |
chih | peq | liv | len | baj | alt | baj | com |
cock | med | liv | len | med | alt | alt | com |
coll | gra | med | alt | med | alt | baj | com |
dalm | med | med | med | med | alt | baj | com |
dobe | gra | med | alt | alt | baj | alt | uti |
dogo | gra | pes | alt | baj | baj | alt | uti |
foxh | gra | med | alt | baj | baj | alt | caz |
foxt | peq | liv | med | med | alt | alt | com |
galg | gra | med | alt | baj | baj | baj | caz |
gasc | gra | med | med | baj | baj | alt | caz |
labr | med | med | med | med | alt | baj | caz |
masa | gra | med | alt | alt | alt | alt | uti |
mast | gra | pes | len | baj | baj | alt | uti |
peki | peq | liv | len | baj | alt | baj | com |
podb | med | med | med | alt | alt | baj | caz |
podf | gra | med | med | med | baj | baj | caz |
poin | gra | med | alt | alt | baj | baj | caz |
sett | gra | med | alt | med | baj | baj | caz |
stbe | gra | pes | len | med | baj | alt | uti |
teck | peq | liv | len | med | alt | baj | com |
tern | gra | pes | len | med | baj | baj | uti |
par(mfrow=c(3,3))
barplot(table(perrosi$TAM),col=2)
barplot(table(perrosi$PES),col=3)
barplot(table(perrosi$VEL),col=4)
barplot(table(perrosi$INT),col=5)
barplot(table(perrosi$AFE),col=6)
barplot(table(perrosi$AGR),col=7)
barplot(table(perrosi$FUN),col=8)
chisq.test(table(perrosi$TAM,perrosi$PES))
## Warning in chisq.test(table(perrosi$TAM, perrosi$PES)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(perrosi$TAM, perrosi$PES)
## X-squared = 25.329, df = 4, p-value = 4.321e-05
chisq.test(table(perrosi$TAM,perrosi$VEL))
## Warning in chisq.test(table(perrosi$TAM, perrosi$VEL)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(perrosi$TAM, perrosi$VEL)
## X-squared = 15.891, df = 4, p-value = 0.003168
chisq.test(table(perrosi$TAM,perrosi$INT))
## Warning in chisq.test(table(perrosi$TAM, perrosi$INT)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(perrosi$TAM, perrosi$INT)
## X-squared = 3.6082, df = 4, p-value = 0.4616
chisq.test(table(perrosi$TAM,perrosi$AFE))
## Warning in chisq.test(table(perrosi$TAM, perrosi$AFE)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(perrosi$TAM, perrosi$AFE)
## X-squared = 13.954, df = 2, p-value = 0.0009333
chisq.test(table(perrosi$TAM,perrosi$AGR))
## Warning in chisq.test(table(perrosi$TAM, perrosi$AGR)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(perrosi$TAM, perrosi$AGR)
## X-squared = 2.0515, df = 2, p-value = 0.3585
chisq.test(table(perrosi$TAM,perrosi$FUN))
## Warning in chisq.test(table(perrosi$TAM, perrosi$FUN)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(perrosi$TAM, perrosi$FUN)
## X-squared = 16.354, df = 4, p-value = 0.002579
res.ACM.perros <- MCA(perrosi,quali.sup = 7,graph = TRUE)
fviz_mca_biplot(res.ACM.perros,repel=TRUE)
fviz_contrib(res.ACM.perros,choice="var",axes=1)
fviz_contrib(res.ACM.perros,choice="var",axes=2)
fviz_contrib(res.ACM.perros,choice="var",axes=3)
fviz_contrib(res.ACM.perros,choice="ind",axes=1)
fviz_contrib(res.ACM.perros,choice="ind",axes=2)
fviz_contrib(res.ACM.perros,choice="ind",axes=3)
#### COSENOS CUADRADOS
res.ACM.perros$var$cos2
## Dim 1 Dim 2 Dim 3 Dim 4 Dim 5
## TAM_gra 0.87503205 0.0005293413 0.003279033 0.036219310 1.586620e-02
## TAM_med 0.16462520 0.3448030588 0.234627550 0.026653716 2.184658e-02
## TAM_peq 0.49144201 0.2987546600 0.132809435 0.005052544 1.394894e-04
## PES_liv 0.57531341 0.2861238116 0.054196308 0.011447021 1.104688e-03
## PES_med 0.10044717 0.7221387844 0.057601141 0.015087719 3.895941e-02
## PES_pes 0.23420393 0.2155641859 0.339157541 0.001038734 8.582564e-02
## VEL_alt 0.39792110 0.0691296921 0.291151283 0.028763587 5.089122e-05
## VEL_len 0.06021292 0.6422447857 0.094932948 0.003795952 5.504701e-02
## VEL_med 0.15344741 0.3318791146 0.053456249 0.057717964 5.796523e-02
## INT_alt 0.03207684 0.0603213262 0.102831012 0.464645451 3.229645e-01
## INT_baj 0.05129787 0.2752677726 0.052025334 0.000247354 4.510944e-01
## INT_med 0.12673870 0.0756897524 0.225873819 0.338187895 1.986299e-02
## AFE_alt 0.64765585 0.0767360421 0.003980589 0.006420928 1.750915e-03
## AFE_baj 0.64765585 0.0767360421 0.003980589 0.006420928 1.750915e-03
## AGR_alt 0.17292377 0.0406368567 0.103307716 0.282075371 1.302074e-01
## AGR_baj 0.17292377 0.0406368567 0.103307716 0.282075371 1.302074e-01
fviz_cos2(res.ACM.perros,choice="var",axes=1)
fviz_cos2(res.ACM.perros,choice="var",axes=2)
fviz_cos2(res.ACM.perros,choice="var",axes=3)
cluster <- HCPC(res.ACM.perros,nb.clust=-1)
cluster$desc.var
##
## Link between the cluster variable and the categorical variables (chi-square test)
## =================================================================================
## p.value df
## TAM 7.377151e-10 6
## PES 5.258626e-09 6
## VEL 2.530335e-04 6
## FUN 2.691927e-04 6
## AFE 1.688726e-03 3
##
## Description of each cluster by the categories
## =============================================
## $`1`
## Cla/Mod Mod/Cla Global p.value v.test
## PES=PES_pes 100.00000 100 18.51852 1.238697e-05 4.370663
## FUN=uti 62.50000 100 29.62963 6.936703e-04 3.392069
## AFE=AFE_baj 38.46154 100 48.14815 1.594203e-02 2.410240
## TAM=TAM_gra 33.33333 100 55.55556 3.719807e-02 2.083584
## AFE=AFE_alt 0.00000 0 51.85185 1.594203e-02 -2.410240
## PES=PES_med 0.00000 0 51.85185 1.594203e-02 -2.410240
##
## $`2`
## Cla/Mod Mod/Cla Global p.value v.test
## PES=PES_med 71.42857 100 51.85185 0.0001186541 3.848890
## VEL=VEL_alt 88.88889 80 33.33333 0.0001674908 3.763591
## TAM=TAM_gra 66.66667 100 55.55556 0.0003559624 3.570749
## FUN=caz 66.66667 60 33.33333 0.0377633046 2.077415
## FUN=com 10.00000 10 37.03704 0.0334265616 -2.126922
## TAM=TAM_peq 0.00000 0 25.92593 0.0219001610 -2.292095
## PES=PES_liv 0.00000 0 29.62963 0.0109500805 -2.544288
## VEL=VEL_len 0.00000 0 37.03704 0.0023052801 -3.047794
##
## $`3`
## Cla/Mod Mod/Cla Global p.value v.test
## TAM=TAM_med 100.00000 100 18.51852 1.238697e-05 4.370663
## VEL=VEL_med 50.00000 80 29.62963 1.786201e-02 2.368466
## AFE=AFE_alt 35.71429 100 51.85185 2.479871e-02 2.244524
## AFE=AFE_baj 0.00000 0 48.14815 2.479871e-02 -2.244524
## TAM=TAM_gra 0.00000 0 55.55556 9.810479e-03 -2.582439
##
## $`4`
## Cla/Mod Mod/Cla Global p.value v.test
## TAM=TAM_peq 100.0 100.00000 25.92593 1.126088e-06 4.868218
## PES=PES_liv 87.5 100.00000 29.62963 9.008705e-06 4.439694
## FUN=com 60.0 85.71429 37.03704 4.290396e-03 2.855982
## VEL=VEL_len 50.0 71.42857 37.03704 4.690382e-02 1.987168
## VEL=VEL_alt 0.0 0.00000 33.33333 3.583663e-02 -2.098776
## PES=PES_med 0.0 0.00000 51.85185 1.932367e-03 -3.100435
## TAM=TAM_gra 0.0 0.00000 55.55556 8.918618e-04 -3.322589