multivariado
laura maria ardila muñoz
library(FactoMineR)## Warning: package 'FactoMineR' was built under R version 4.4.3library(factoextra)## Warning: package 'factoextra' was built under R version 4.4.3## Cargando paquete requerido: ggplot2## Warning: package 'ggplot2' was built under R version 4.4.3## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBalibrary(readxl)## Warning: package 'readxl' was built under R version 4.4.3library(readxl)
Datos1 <- read_excel("C:/Users/User/Downloads/Datos1.xlsx")
View(Datos1)
Datos1_pca <- Datos1[, -which(names(Datos1) == "id")]
Datos1_pca$diagnosis <- as.factor(Datos1_pca$diagnosis)
res.pca <- PCA(Datos1_pca, quali.sup = 1, graph = FALSE)
summary(res.pca)##
## Call:
## PCA(X = Datos1_pca, quali.sup = 1, graph = FALSE)
##
##
## Eigenvalues
## Dim.1 Dim.2 Dim.3 Dim.4 Dim.5 Dim.6 Dim.7
## Variance 13.282 5.691 2.818 1.981 1.649 1.207 0.675
## % of var. 44.272 18.971 9.393 6.602 5.496 4.025 2.251
## Cumulative % of var. 44.272 63.243 72.636 79.239 84.734 88.759 91.010
## Dim.8 Dim.9 Dim.10 Dim.11 Dim.12 Dim.13 Dim.14
## Variance 0.477 0.417 0.351 0.294 0.261 0.241 0.157
## % of var. 1.589 1.390 1.169 0.980 0.871 0.805 0.523
## Cumulative % of var. 92.598 93.988 95.157 96.137 97.007 97.812 98.335
## Dim.15 Dim.16 Dim.17 Dim.18 Dim.19 Dim.20 Dim.21
## Variance 0.094 0.080 0.059 0.053 0.049 0.031 0.030
## % of var. 0.314 0.266 0.198 0.175 0.165 0.104 0.100
## Cumulative % of var. 98.649 98.915 99.113 99.288 99.453 99.557 99.657
## Dim.22 Dim.23 Dim.24 Dim.25 Dim.26 Dim.27 Dim.28
## Variance 0.027 0.024 0.018 0.015 0.008 0.007 0.002
## % of var. 0.091 0.081 0.060 0.052 0.027 0.023 0.005
## Cumulative % of var. 99.749 99.830 99.890 99.942 99.969 99.992 99.997
## Dim.29 Dim.30
## Variance 0.001 0.000
## % of var. 0.002 0.000
## Cumulative % of var. 100.000 100.000
##
## Individuals (the 10 first)
## Dist Dim.1 ctr cos2 Dim.2 ctr cos2
## 1 | 10.710 | 9.193 1.118 0.737 | 1.949 0.117 0.033
## 2 | 5.132 | 2.388 0.075 0.216 | -3.768 0.438 0.539
## 3 | 6.119 | 5.734 0.435 0.878 | -1.075 0.036 0.031
## 4 | 13.986 | 7.123 0.671 0.259 | 10.276 3.261 0.540
## 5 | 5.868 | 3.935 0.205 0.450 | -1.948 0.117 0.110
## 6 | 5.735 | 2.380 0.075 0.172 | 3.950 0.482 0.474
## 7 | 3.970 | 2.239 0.066 0.318 | -2.690 0.223 0.459
## 8 | 4.195 | 2.143 0.061 0.261 | 2.340 0.169 0.311
## 9 | 6.017 | 3.175 0.133 0.278 | 3.392 0.355 0.318
## 10 | 12.163 | 6.352 0.534 0.273 | 7.727 1.844 0.404
## Dim.3 ctr cos2
## 1 | -1.123 0.079 0.011 |
## 2 | -0.529 0.017 0.011 |
## 3 | -0.552 0.019 0.008 |
## 4 | -3.233 0.652 0.053 |
## 5 | 1.390 0.120 0.056 |
## 6 | -2.935 0.537 0.262 |
## 7 | -1.640 0.168 0.171 |
## 8 | -0.872 0.047 0.043 |
## 9 | -3.120 0.607 0.269 |
## 10 | -4.342 1.176 0.127 |
##
## Variables (the 10 first)
## Dim.1 ctr cos2 Dim.2 ctr cos2 Dim.3
## radius_mean | 0.798 4.792 0.636 | -0.558 5.469 0.311 | -0.014
## texture_mean | 0.378 1.076 0.143 | -0.142 0.356 0.020 | 0.108
## perimeter_mean | 0.829 5.177 0.688 | -0.513 4.630 0.264 | -0.016
## area_mean | 0.805 4.884 0.649 | -0.551 5.340 0.304 | 0.048
## smoothness_mean | 0.520 2.033 0.270 | 0.444 3.464 0.197 | -0.175
## compactness_mean | 0.872 5.726 0.760 | 0.362 2.307 0.131 | -0.124
## concavity_mean | 0.942 6.677 0.887 | 0.144 0.362 0.021 | 0.005
## concave points_mean | 0.951 6.804 0.904 | -0.083 0.121 0.007 | -0.043
## symmetry_mean | 0.504 1.909 0.254 | 0.454 3.623 0.206 | -0.068
## fractal_dimension_mean | 0.235 0.414 0.055 | 0.875 13.438 0.765 | -0.038
## ctr cos2
## radius_mean 0.007 0.000 |
## texture_mean 0.417 0.012 |
## perimeter_mean 0.009 0.000 |
## area_mean 0.082 0.002 |
## smoothness_mean 1.088 0.031 |
## compactness_mean 0.549 0.015 |
## concavity_mean 0.001 0.000 |
## concave points_mean 0.065 0.002 |
## symmetry_mean 0.162 0.005 |
## fractal_dimension_mean 0.051 0.001 |
##
## Supplementary categories
## Dist Dim.1 cos2 v.test Dim.2 cos2
## B | 2.251 | -2.206 0.960 -18.720 | 0.346 0.024
## M | 3.791 | 3.715 0.960 18.720 | -0.583 0.024
## v.test Dim.3 cos2 v.test
## B 4.489 | 0.213 0.009 3.927 |
## M -4.489 | -0.359 0.009 -3.927 |fviz_pca_ind(res.pca,
habillage = 1,
addEllipses = TRUE,
palette = c("#00AFBB", "#FC4E07"),
repel = TRUE,
title = "Individuos según diagnóstico")
fviz_pca_var(res.pca,
col.var = "cos2",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
title = "Variables activas en el PCA")
fviz_screeplot(res.pca, addlabels = TRUE, ylim = c(0, 50))
pc1 <- res.pca$ind$coord[, 1]
Datos1_pca$PC1 <- pc1#Descripcion: La variable diagnosis se trató como variable ilustrativa porque no participa en el cálculo del PCA, pero permite interpretar los componentes.y Se conservaron las 30 variables numéricas que describen propiedades morfológicas de los tumores.
Se aplicó PCA indicando que diagnosis es una variable cualitativa ilustrativa. El PCA transforma las variables originales en nuevos componentes no correlacionados que explican la variabilidad total.o