“Chap 6: CLARA- cluestering large application”
set.seed(1234)
df <- rbind(cbind(rnorm(200,0,8), rnorm(200,0,8)),
cbind(rnorm(300,50,8), rnorm(300,50,8)))
colnames(df) <- c("x", "y")
rownames(df) <- paste0("S", 1:nrow(df))
head(df, nrow = 6)
## x y
## S1 -9.656526 3.881815
## S2 2.219434 5.574150
## S3 8.675529 1.484111
## S4 -18.765582 5.605868
## S5 3.432998 2.493448
## S6 4.048447 6.083699
library(cluster)
## Warning: package 'cluster' was built under R version 4.3.3
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.3.3
library(factoextra)
## Warning: package 'factoextra' was built under R version 4.3.3
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
library(cluster)
library(factoextra)
fviz_nbclust(df, clara, method = "silhouette")+
theme_classic()
clara.res <- clara(df, 2, samples = 50, pamLike = TRUE)
print(clara.res)
## Call: clara(x = df, k = 2, samples = 50, pamLike = TRUE)
## Medoids:
## x y
## S121 -1.531137 1.145057
## S455 48.357304 50.233499
## Objective function: 9.87862
## Clustering vector: Named int [1:500] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 ...
## - attr(*, "names")= chr [1:500] "S1" "S2" "S3" "S4" "S5" "S6" "S7" ...
## Cluster sizes: 200 300
## Best sample:
## [1] S37 S49 S54 S63 S68 S71 S76 S80 S82 S101 S103 S108 S109 S118 S121
## [16] S128 S132 S138 S144 S162 S203 S210 S216 S231 S234 S249 S260 S261 S286 S299
## [31] S304 S305 S312 S315 S322 S350 S403 S450 S454 S455 S456 S465 S488 S497
##
## Available components:
## [1] "sample" "medoids" "i.med" "clustering" "objective"
## [6] "clusinfo" "diss" "call" "silinfo" "data"
dd <- cbind(df, cluster = clara.res$cluster)
head(dd, n = 4)
## x y cluster
## S1 -9.656526 3.881815 1
## S2 2.219434 5.574150 1
## S3 8.675529 1.484111 1
## S4 -18.765582 5.605868 1
clara.res$medoids
## x y
## S121 -1.531137 1.145057
## S455 48.357304 50.233499
head(clara.res$clustering, 10)
## S1 S2 S3 S4 S5 S6 S7 S8 S9 S10
## 1 1 1 1 1 1 1 1 1 1
dd <- cbind(df, cluster = clara.res$cluster)
head(dd, n = 4)
## x y cluster
## S1 -9.656526 3.881815 1
## S2 2.219434 5.574150 1
## S3 8.675529 1.484111 1
## S4 -18.765582 5.605868 1
clara.res$medoids
## x y
## S121 -1.531137 1.145057
## S455 48.357304 50.233499
head(clara.res$clustering, 10)
## S1 S2 S3 S4 S5 S6 S7 S8 S9 S10
## 1 1 1 1 1 1 1 1 1 1
fviz_cluster(clara.res,
palette = c("#00AFBB", "#FC4E07"), # color palette
ellipse.type = "t", # Concentration ellipse
geom = "point", pointsize = 1,
ggtheme = theme_classic()
)
CHAPTER 7
library("FactoMineR")
## Warning: package 'FactoMineR' was built under R version 4.3.3
library("factoextra")
library("FactoMineR")
data(wine)
colnames(wine)
## [1] "Label" "Soil"
## [3] "Odor.Intensity.before.shaking" "Aroma.quality.before.shaking"
## [5] "Fruity.before.shaking" "Flower.before.shaking"
## [7] "Spice.before.shaking" "Visual.intensity"
## [9] "Nuance" "Surface.feeling"
## [11] "Odor.Intensity" "Quality.of.odour"
## [13] "Fruity" "Flower"
## [15] "Spice" "Plante"
## [17] "Phenolic" "Aroma.intensity"
## [19] "Aroma.persistency" "Aroma.quality"
## [21] "Attack.intensity" "Acidity"
## [23] "Astringency" "Alcohol"
## [25] "Balance" "Smooth"
## [27] "Bitterness" "Intensity"
## [29] "Harmony" "Overall.quality"
## [31] "Typical"
data(wine)
res.mfa <- MFA(wine,
group = c(2, 5, 3, 10, 9, 2),
type = c("n", "s", "s", "s", "s", "s"),
name.group = c("origin","odor","visual", "odor.after.shaking", "taste", "overall"),
num.group.sup = c(1, 6),
graph = FALSE)
print(res.mfa)
## **Results of the Multiple Factor Analysis (MFA)**
## The analysis was performed on 21 individuals, described by 31 variables
## *Results are available in the following objects :
##
## name description
## 1 "$eig" "eigenvalues"
## 2 "$separate.analyses" "separate analyses for each group of variables"
## 3 "$group" "results for all the groups"
## 4 "$partial.axes" "results for the partial axes"
## 5 "$inertia.ratio" "inertia ratio"
## 6 "$ind" "results for the individuals"
## 7 "$quanti.var" "results for the quantitative variables"
## 8 "$quanti.var.sup" "results for the quantitative supplementary variables"
## 9 "$quali.var.sup" "results for the categorical supplementary variables"
## 10 "$summary.quanti" "summary for the quantitative variables"
## 11 "$summary.quali" "summary for the categorical variables"
## 12 "$global.pca" "results for the global PCA"
eig.val <- get_eigenvalue(res.mfa)
head(eig.val)
## eigenvalue variance.percent cumulative.variance.percent
## Dim.1 3.4619504 49.378382 49.37838
## Dim.2 1.3667683 19.494446 68.87283
## Dim.3 0.6154291 8.777969 77.65080
## Dim.4 0.3721997 5.308747 82.95954
## Dim.5 0.2703825 3.856511 86.81605
## Dim.6 0.2024033 2.886912 89.70297
fviz_screeplot(res.mfa)
group <- get_mfa_var(res.mfa, "group")
group
## Multiple Factor Analysis results for variable groups
## ===================================================
## Name Description
## 1 "$coord" "Coordinates"
## 2 "$cos2" "Cos2, quality of representation"
## 3 "$contrib" "Contributions"
## 4 "$correlation" "Correlation between groups and principal dimensions"
head(group$coord)
## Dim.1 Dim.2 Dim.3 Dim.4 Dim.5
## odor 0.7820738 0.61977283 0.37353451 0.17260092 0.08553276
## visual 0.8546846 0.04014481 0.01438360 0.04550736 0.02966750
## odor.after.shaking 0.9247734 0.46892047 0.18009116 0.10139051 0.11589439
## taste 0.9004187 0.23793016 0.04741982 0.05270088 0.03928784
head(group$cos2)
## Dim.1 Dim.2 Dim.3 Dim.4 Dim.5
## odor 0.3799491 0.238613517 0.0866745169 0.018506155 0.0045445922
## visual 0.7284016 0.001607007 0.0002062976 0.002065011 0.0008776492
## odor.after.shaking 0.6245535 0.160582210 0.0236855692 0.007507471 0.0098089810
## taste 0.7222292 0.050429542 0.0020031144 0.002474125 0.0013749986
head(group$contrib)
## Dim.1 Dim.2 Dim.3 Dim.4 Dim.5
## odor 22.59055 45.345861 60.694972 46.37321 31.63399
## visual 24.68795 2.937207 2.337166 12.22660 10.97242
## odor.after.shaking 26.71250 34.308703 29.262699 27.24089 42.86313
## taste 26.00900 17.408230 7.705163 14.15930 14.53047
fviz_mfa_var(res.mfa, "group")
fviz_contrib(res.mfa, "group", axes = 1)
fviz_contrib(res.mfa, "group", axes = 2)
quanti.var <- get_mfa_var(res.mfa, "quanti.var")
quanti.var
## Multiple Factor Analysis results for quantitative variables
## ===================================================
## Name Description
## 1 "$coord" "Coordinates"
## 2 "$cos2" "Cos2, quality of representation"
## 3 "$contrib" "Contributions"
head(quanti.var$coord)
## Dim.1 Dim.2 Dim.3 Dim.4
## Odor.Intensity.before.shaking 0.5908036 0.66723783 -0.02326175 0.3287015
## Aroma.quality.before.shaking 0.8352510 -0.07539908 -0.35417877 0.1414425
## Fruity.before.shaking 0.7160259 -0.15069626 -0.53748761 0.2517063
## Flower.before.shaking 0.4387181 -0.40937751 0.63731284 0.4029075
## Spice.before.shaking 0.0380525 0.86501993 0.12795122 -0.1822298
## Visual.intensity 0.8811873 0.23833245 0.14099033 -0.2128871
## Dim.5
## Odor.Intensity.before.shaking 0.05786231
## Aroma.quality.before.shaking 0.04992114
## Fruity.before.shaking 0.18981578
## Flower.before.shaking 0.12200773
## Spice.before.shaking 0.36741971
## Visual.intensity -0.17676282
head(quanti.var$cos2)
## Dim.1 Dim.2 Dim.3 Dim.4
## Odor.Intensity.before.shaking 0.349048863 0.445206325 0.000541109 0.10804466
## Aroma.quality.before.shaking 0.697644264 0.005685021 0.125442602 0.02000597
## Fruity.before.shaking 0.512693037 0.022709361 0.288892928 0.06335608
## Flower.before.shaking 0.192473567 0.167589944 0.406167661 0.16233443
## Spice.before.shaking 0.001447992 0.748259477 0.016371514 0.03320769
## Visual.intensity 0.776491025 0.056802358 0.019878273 0.04532093
## Dim.5
## Odor.Intensity.before.shaking 0.003348047
## Aroma.quality.before.shaking 0.002492121
## Fruity.before.shaking 0.036030029
## Flower.before.shaking 0.014885886
## Spice.before.shaking 0.134997242
## Visual.intensity 0.031245096
head(quanti.var$contrib)
## Dim.1 Dim.2 Dim.3 Dim.4
## Odor.Intensity.before.shaking 4.49733206 14.5296787 0.03921898 12.948424
## Aroma.quality.before.shaking 8.98882147 0.1855354 9.09194110 2.397581
## Fruity.before.shaking 6.60581103 0.7411389 20.93864000 7.592798
## Flower.before.shaking 2.47993227 5.4694372 29.43858302 19.454686
## Spice.before.shaking 0.01865671 24.4200703 1.18658923 3.979718
## Visual.intensity 7.91221841 1.4660681 1.13941864 4.295418
## Dim.5
## Odor.Intensity.before.shaking 0.5523351
## Aroma.quality.before.shaking 0.4111309
## Fruity.before.shaking 5.9439566
## Flower.before.shaking 2.4557588
## Spice.before.shaking 22.2708049
## Visual.intensity 4.0764862
fviz_mfa_var(res.mfa, "quanti.var", palette = "jco",
col.var.sup = "violet", repel = TRUE)
fviz_mfa_var(res.mfa, "quanti.var", palette = "jco",
col.var.sup = "violet", repel = TRUE,
geom = c("point", "text"), legend = "bottom")
fviz_contrib(res.mfa, choice = "quanti.var", axes = 1, top = 20,
palette = "jco")
fviz_contrib(res.mfa, choice = "quanti.var", axes = 2, top = 20,
palette = "jco")
fviz_mfa_var(res.mfa, "quanti.var", col.var = "contrib",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
col.var.sup = "violet", repel = TRUE,
geom = c("point", "text"))
fviz_mfa_var(res.mfa, col.var = "cos2",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
col.var.sup = "violet", repel = TRUE)
fviz_cos2(res.mfa, choice = "quanti.var", axes = 1)
ind <- get_mfa_ind(res.mfa)
ind
## Multiple Factor Analysis results for individuals
## ===================================================
## Name Description
## 1 "$coord" "Coordinates"
## 2 "$cos2" "Cos2, quality of representation"
## 3 "$contrib" "Contributions"
## 4 "$coord.partiel" "Partial coordinates"
## 5 "$within.inertia" "Within inertia"
## 6 "$within.partial.inertia" "Within partial inertia"
fviz_mfa_ind(res.mfa, col.ind = "cos2",
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
repel = TRUE)
fviz_mfa_ind(res.mfa,
habillage = "Label", # color by groups
palette = c("#00AFBB", "#E7B800", "#FC4E07"),
addEllipses = TRUE, ellipse.type = "confidence",
repel = TRUE # Avoid text overlapping
)
fviz_ellipses(res.mfa, c("Label", "Soil"), repel = TRUE)
## Warning: `gather_()` was deprecated in tidyr 1.2.0.
## ℹ Please use `gather()` instead.
## ℹ The deprecated feature was likely used in the factoextra package.
## Please report the issue at <https://github.com/kassambara/factoextra/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
fviz_mfa_ind(res.mfa, partial = "all")
fviz_mfa_ind(res.mfa, partial = c("1DAM", "1VAU", "2ING"))
fviz_mfa_axes(res.mfa)
