library(pacman)
p_load(rmdformats, readr, readxl, ggplot2, plotly, DT, xfun, gridExtra, leaflet, GGally, psych, corrplot, cluster)
pMiel = read_csv("EstadoProdMiel.csv")
## Rows: 51 Columns: 3
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (1): Estado
## dbl (2): ProduccionMiel, Year
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
ggplot(pMiel,aes(Year,ProduccionMiel,color = Estado) ) +geom_line()+ geom_point(size=4)
set.seed(101)
mielCluster = kmeans(pMiel[,2],center=3,nstart = 20)
mielCluster
## K-means clustering with 3 clusters of sizes 14, 17, 20
##
## Cluster means:
## ProduccionMiel
## 1 9485.879
## 2 2698.033
## 3 5860.918
##
## Clustering vector:
## [1] 1 1 3 1 1 1 1 1 1 1 1 1 1 3 3 1 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 2 2 2 2
## [39] 2 2 2 2 2 2 2 2 2 2 2 2 2
##
## Within cluster sum of squares by cluster:
## [1] 19545446 4938183 10719279
## (between_SS / total_SS = 91.0 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"
table(mielCluster$cluster, pMiel$Estado)
##
## JALISCO QUINTANA_ROO YUCATAN
## 1 0 0 14
## 2 0 17 0
## 3 17 0 3
clusplot(pMiel, mielCluster$cluster, color= TRUE, shade= TRUE, lines=0)
tot.withinss <- vector(mode="character", length=15)
for (i in 1:15){
mielCluster <- kmeans(pMiel[2], center=i, nstart=20)
tot.withinss[i] <- mielCluster$tot.withinss
}
plot(1:15, tot.withinss, type = "b", pch=19)
