ejercicio vinos

#install.packages("cluster")
library(cluster)
#install.packages("ggplot2")
library(ggplot2)
#install.packages("data.table")
library(data.table)
#install.packages("factoextra")
library(factoextra)

## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa

#install.packages("maps")
library(maps)

## 
## Attaching package: 'maps'

## The following object is masked from 'package:cluster':
## 
##     votes.repub

df <- USArrests

codo<-df

# Escalar las variables numéricas
datos_escalados <- scale(codo)

# Método del codo para definir clusters
set.seed(123) 
wcss <- vector() 
max_k <- 10 
for (k in 1:max_k) {
  kmeans_model <- kmeans(datos_escalados, centers = k, nstart = 25)
  wcss[k] <- kmeans_model$tot.withinss
}

# Gráfica
par(mar = c(4, 4, 1, 1)) 
plot(1:max_k, wcss, type = "b", xlab = "Numero de Clusters", ylab = "WCSS", main = "Metodo del Codo", pch = 19, frame = FALSE)

set.seed(123)
optimizacion <- clusGap(datos_escalados, FUN=kmeans, nstart=1, K.max = 10)
plot(optimizacion, xlab="numero de clusters k") 

grupos <- 3
segmentos <- kmeans(datos_escalados,grupos)
segmentos

## K-means clustering with 3 clusters of sizes 29, 13, 8
## 
## Cluster means:
##       Murder    Assault    UrbanPop        Rape
## 1 -0.7010700 -0.7071522 -0.09924526 -0.57773737
## 2  0.6950701  1.0394414  0.72263703  1.27693964
## 3  1.4118898  0.8743346 -0.81452109  0.01927104
## 
## Clustering vector:
##        Alabama         Alaska        Arizona       Arkansas     California 
##              3              2              2              3              2 
##       Colorado    Connecticut       Delaware        Florida        Georgia 
##              2              1              1              2              3 
##         Hawaii          Idaho       Illinois        Indiana           Iowa 
##              1              1              2              1              1 
##         Kansas       Kentucky      Louisiana          Maine       Maryland 
##              1              1              3              1              2 
##  Massachusetts       Michigan      Minnesota    Mississippi       Missouri 
##              1              2              1              3              2 
##        Montana       Nebraska         Nevada  New Hampshire     New Jersey 
##              1              1              2              1              1 
##     New Mexico       New York North Carolina   North Dakota           Ohio 
##              2              2              3              1              1 
##       Oklahoma         Oregon   Pennsylvania   Rhode Island South Carolina 
##              1              1              1              1              3 
##   South Dakota      Tennessee          Texas           Utah        Vermont 
##              1              3              2              1              1 
##       Virginia     Washington  West Virginia      Wisconsin        Wyoming 
##              1              1              1              1              1 
## 
## Within cluster sum of squares by cluster:
## [1] 53.354791 19.922437  8.316061
##  (between_SS / total_SS =  58.4 %)
## 
## Available components:
## 
## [1] "cluster"      "centers"      "totss"        "withinss"     "tot.withinss"
## [6] "betweenss"    "size"         "iter"         "ifault"

Asignación <- cbind(df, cluster = segmentos$cluster)
Asignación

##                Murder Assault UrbanPop Rape cluster
## Alabama          13.2     236       58 21.2       3
## Alaska           10.0     263       48 44.5       2
## Arizona           8.1     294       80 31.0       2
## Arkansas          8.8     190       50 19.5       3
## California        9.0     276       91 40.6       2
## Colorado          7.9     204       78 38.7       2
## Connecticut       3.3     110       77 11.1       1
## Delaware          5.9     238       72 15.8       1
## Florida          15.4     335       80 31.9       2
## Georgia          17.4     211       60 25.8       3
## Hawaii            5.3      46       83 20.2       1
## Idaho             2.6     120       54 14.2       1
## Illinois         10.4     249       83 24.0       2
## Indiana           7.2     113       65 21.0       1
## Iowa              2.2      56       57 11.3       1
## Kansas            6.0     115       66 18.0       1
## Kentucky          9.7     109       52 16.3       1
## Louisiana        15.4     249       66 22.2       3
## Maine             2.1      83       51  7.8       1
## Maryland         11.3     300       67 27.8       2
## Massachusetts     4.4     149       85 16.3       1
## Michigan         12.1     255       74 35.1       2
## Minnesota         2.7      72       66 14.9       1
## Mississippi      16.1     259       44 17.1       3
## Missouri          9.0     178       70 28.2       2
## Montana           6.0     109       53 16.4       1
## Nebraska          4.3     102       62 16.5       1
## Nevada           12.2     252       81 46.0       2
## New Hampshire     2.1      57       56  9.5       1
## New Jersey        7.4     159       89 18.8       1
## New Mexico       11.4     285       70 32.1       2
## New York         11.1     254       86 26.1       2
## North Carolina   13.0     337       45 16.1       3
## North Dakota      0.8      45       44  7.3       1
## Ohio              7.3     120       75 21.4       1
## Oklahoma          6.6     151       68 20.0       1
## Oregon            4.9     159       67 29.3       1
## Pennsylvania      6.3     106       72 14.9       1
## Rhode Island      3.4     174       87  8.3       1
## South Carolina   14.4     279       48 22.5       3
## South Dakota      3.8      86       45 12.8       1
## Tennessee        13.2     188       59 26.9       3
## Texas            12.7     201       80 25.5       2
## Utah              3.2     120       80 22.9       1
## Vermont           2.2      48       32 11.2       1
## Virginia          8.5     156       63 20.7       1
## Washington        4.0     145       73 26.2       1
## West Virginia     5.7      81       39  9.3       1
## Wisconsin         2.6      53       66 10.8       1
## Wyoming           6.8     161       60 15.6       1

fviz_cluster(segmentos, data=datos_escalados)

promedio <- aggregate(Asignación, by=list(Asignación$cluster), FUN=mean)
promedio

##   Group.1    Murder  Assault UrbanPop     Rape cluster
## 1       1  4.734483 111.8276 64.10345 15.82069       1
## 2       2 10.815385 257.3846 76.00000 33.19231       2
## 3       3 13.937500 243.6250 53.75000 21.41250       3

c=c("Mississippi","North Carolina","South Carolina","Georgia","Alabama","Arkansas","Louisiana","Tennessee")
d=c("Alaska","Maryland","New Mexico","Michigan","Florida","Nevada","California","Colorado","Texas","Illinois","Arizona","New York","Missouri")
e=c("New Jersey","Washington","Connecticut","Delaware","Hawaii","Idaho","Indiana","Iowa","Kansas","Kentucky","Maine","Massachusetts","Minnesota","Montana","Nebraska","New Hampshire","North Dakota","Ohio","Oklahoma","Oregon","Pennsylvania","Rhode Island","South Dakota","Utah","Vermont","Virginia","West Virginia","Wisconsin","Wyoming")
map(database = "state")
map(database = "state",regions = c,col = "red",fill = T,add = TRUE)
map(database = "state",regions = d,col = "orange",fill = T,add = TRUE)
map(database = "state",regions = e,col = "green",fill = T,add = TRUE)

#conclusiones