cluster final - comparacion 3-9 cluster sin variacion

Variables

merged2 <- merged %>% 
           remove_rownames %>% 
           column_to_rownames(var="Nom_Barri") %>% 
           select("n.tot","pc.esp","pc.ue27-esp","pc.20.34","2019-2014","n.esp.M1419",
                  "hotel2019","rest1614",
                  "RFD.2017",
                  "tot_ann","pmedio","pmedio.M1519","pm_ent.M1519","pm_priv.M1519",
                  "alq.num","alq.pm","alq.pm.M1519","alq.num.M1519",
                  "tot.comp","tot.eur","perc.nou.comp","perc.usat.comp","tot.comp.M1419",
                  "nou.eur.M1419","usat.eur.M1419",
                   )

Standardizar los datos

df <- scale(merged2)

Optimal K Elbow - elbow (1 option)

set.seed(123)
wss <- function(k) {
  kmeans(df, k, nstart = 100 )$tot.withinss
}

k.values <- 1:15

wss_values <- map_dbl(k.values, wss)

plot(k.values, wss_values,
       type="b", pch = 19, frame = FALSE, 
       xlab="Number of clusters K",
       ylab="Total within-clusters sum of squares")

##Optimal K Elbow - elbow (2 option)

set.seed(123)
fviz_nbclust(df, kmeans, method = "wss")

##Optimal K Average Silhouette Method 1

avg_sil <- function(k) {
  km.res <- kmeans(df, centers = k, nstart = 100)
  ss <- silhouette(km.res$cluster, dist(df))
  mean(ss[, 3])
}

k.values <- 2:15

avg_sil_values <- map_dbl(k.values, avg_sil)

plot(k.values, avg_sil_values,
       type = "b", pch = 19, frame = FALSE, 
       xlab = "Number of clusters K",
       ylab = "Average Silhouettes")

##Optimal K Average Silhouette Method 2

fviz_nbclust(df, kmeans, method = "silhouette")

##Optimal K Gap Statistic Method

set.seed(123)
gap_stat <- clusGap(df, FUN = kmeans, nstart = 100, K.max = 10, B = 50)

print(gap_stat, method = "firstmax")

## Clustering Gap statistic ["clusGap"] from call:
## clusGap(x = df, FUNcluster = kmeans, K.max = 10, B = 50, nstart = 100)
## B=50 simulated reference sets, k = 1..10; spaceH0="scaledPCA"
##  --> Number of clusters (method 'firstmax'): 3
##           logW   E.logW       gap     SE.sim
##  [1,] 4.768048 5.406652 0.6386030 0.02199320
##  [2,] 4.638512 5.282580 0.6440684 0.02170951
##  [3,] 4.564744 5.212277 0.6475336 0.02180143
##  [4,] 4.512625 5.154888 0.6422633 0.02169567
##  [5,] 4.463767 5.105600 0.6418335 0.02138685
##  [6,] 4.393140 5.062166 0.6690256 0.02085439
##  [7,] 4.337579 5.022726 0.6851467 0.02125951
##  [8,] 4.298579 4.985274 0.6866953 0.02108917
##  [9,] 4.258558 4.950904 0.6923459 0.02048023
## [10,] 4.214303 4.918371 0.7040686 0.02016710

##Optimal K Gap Statistic Method 2

fviz_gap_stat(gap_stat)

##Plot 3-9

final3 <- kmeans(df, centers = 3, nstart = 100)
final4 <- kmeans(df, centers = 4, nstart = 100)
final5 <- kmeans(df, centers = 5, nstart = 100)
final6 <- kmeans(df, centers = 6, nstart = 100)
final7 <- kmeans(df, centers = 7, nstart = 100)
final8 <- kmeans(df, centers = 8, nstart = 100)
final9 <- kmeans(df, centers = 9, nstart = 100)
fviz_cluster(final3, data = df)

fviz_cluster(final4, data = df)

fviz_cluster(final5, data = df)

fviz_cluster(final6, data = df)

fviz_cluster(final7, data = df)

fviz_cluster(final8, data = df)

fviz_cluster(final9, data = df)

##FIN

#Examinar a los numeros de cluster k3 <- kmeans(df, centers = 3, nstart = 100) k4 <- kmeans(df, centers = 4, nstart = 100) k5 <- kmeans(df, centers = 5, nstart = 100) k6 <- kmeans(df, centers = 6, nstart = 100) k7 <- kmeans(df, centers = 7, nstart = 100) k8 <- kmeans(df, centers = 8, nstart = 100) k9 <- kmeans(df, centers = 9, nstart = 100)

#plots to compare p3 <- fviz_cluster(k3, geom = “point”, data = df) + ggtitle(“k = 3”) p4 <- fviz_cluster(k4, geom = “point”, data = df) + ggtitle(“k = 4”) p5 <- fviz_cluster(k5, geom = “point”, data = df) + ggtitle(“k = 5”) p6 <- fviz_cluster(k6, geom = “point”, data = df) + ggtitle(“k = 6”) p7 <- fviz_cluster(k7, geom = “point”, data = df) + ggtitle(“k = 7”) p8 <- fviz_cluster(k8, geom = “point”, data = df) + ggtitle(“k = 8”) p9 <- fviz_cluster(k9, geom = “point”, data = df) + ggtitle(“k = 9”)

grid.arrange(p3, nrow = 1)

grid.arrange(p4, p5, nrow = 1)

grid.arrange(p6, p7, nrow = 1)

grid.arrange(p8, p9, nrow = 1)

K means

for (i in 3:5) { finalK <- kmeans(df, centers = i, nstart = 100) #print print(finalK) }

kkk <- merged2 %>% mutate(Cluster = final3$cluster) %>% group_by(Cluster) %>% summarise_all(“mean”)

z_cluster(finalK, data = df)

for (i in 3:9) { finalK <- kmeans(df, centers = i, nstart = 100) #plot x <- fviz_cluster(finalK, data = df) x }

Descriptive Statistic

kkk <- merged %>% mutate(Cluster = finalK$cluster) %>% group_by(Nom_Barri) #%>% #summarise_all(“mean”)

k.1 <- kkk %>% filter(Cluster == 1)

k.1$Nom_Barri

k.2 <- kkk %>% filter(Cluster == 2)

k.2$Nom_Barri

k.3 <- kkk %>% filter(Cluster == 3)

k.3$Nom_Barri