Actividad 1

Teoría

# 1. Crear base de datos. 

df<-data.frame(x=c(2,2,8,5,7,6,1,4),y=c(10,5,4,8,5,4,2,9))

# 2. Numero de grupos 

grupos <- 3 

# 3. Clasificacion

segmentos <- kmeans(df,grupos)
segmentos

## K-means clustering with 3 clusters of sizes 3, 3, 2
## 
## Cluster means:
##          x        y
## 1 7.000000 4.333333
## 2 3.666667 9.000000
## 3 1.500000 3.500000
## 
## Clustering vector:
## [1] 2 3 1 2 1 1 3 2
## 
## Within cluster sum of squares by cluster:
## [1] 2.666667 6.666667 5.000000
##  (between_SS / total_SS =  85.8 %)
## 
## Available components:
## 
## [1] "cluster"      "centers"      "totss"        "withinss"     "tot.withinss"
## [6] "betweenss"    "size"         "iter"         "ifault"

# 4. Asignacion de grupos

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

##   x  y cluster
## 1 2 10       2
## 2 2  5       3
## 3 8  4       1
## 4 5  8       2
## 5 7  5       1
## 6 6  4       1
## 7 1  2       3
## 8 4  9       2

# 5. Graficar resultados 

# install.packages("ggplot2")
# install.packages("factoextra")

library(ggplot2)
library(factoextra)

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

fviz_cluster(segmentos, data=df,
             palette=c("gray","lightblue","darkgreen"),
             ellipse.type = "euclid",
             star.plot = T,
             repel= T,
             ggtheme = theme()
             )

## Too few points to calculate an ellipse

## Too few points to calculate an ellipse
## Too few points to calculate an ellipse

# Optimizar 

library(cluster)
library(data.table)
set.seed(123)
optimizacion <-clusGap(df,FUN = kmeans, nstart=1,K.max = 7)
plot(optimizacion, xlab= "numero de clusters k")

#El punto mas alto de la grafica indica la cantidad de grupos optimos