USAarrests

Contexto

La base de datos USArrests contiene estadísticas en arrestos por cada 100,000 residentes por agresión, asesinato y violación en cada uno de los 50 estados de EE.UU. en 1973.

Instalar paquetes y llamar librería

#install.packages("caret") #Algoritmos de aprendizaje automático
library(caret)

## Loading required package: ggplot2

## Loading required package: lattice

#install.packages("datasets") #Para usar la base de datos "Iris"
library(datasets)
#install.packages("lattice") #Crear gráficos
library(lattice)
#install.packages("DataExplorer") #Análisis Descriptivo"
library(DataExplorer)
#install.packages("kernlab")
library(kernlab)

## 
## Attaching package: 'kernlab'

## The following object is masked from 'package:ggplot2':
## 
##     alpha

#install.packages("dplyr") # Manipulación de datos
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

#install.packages("cluster")
library(cluster)
#install.packages("factoextra")
library(factoextra)

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

#install.packages("data.table")
library(data.table)

## 
## Attaching package: 'data.table'

## The following objects are masked from 'package:dplyr':
## 
##     between, first, last

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

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ lubridate 1.9.4     ✔ tibble    3.2.1
## ✔ purrr     1.0.4     ✔ tidyr     1.3.1
## ✔ readr     2.1.5

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ kernlab::alpha()      masks ggplot2::alpha()
## ✖ data.table::between() masks dplyr::between()
## ✖ purrr::cross()        masks kernlab::cross()
## ✖ dplyr::filter()       masks stats::filter()
## ✖ data.table::first()   masks dplyr::first()
## ✖ lubridate::hour()     masks data.table::hour()
## ✖ lubridate::isoweek()  masks data.table::isoweek()
## ✖ dplyr::lag()          masks stats::lag()
## ✖ data.table::last()    masks dplyr::last()
## ✖ purrr::lift()         masks caret::lift()
## ✖ lubridate::mday()     masks data.table::mday()
## ✖ lubridate::minute()   masks data.table::minute()
## ✖ lubridate::month()    masks data.table::month()
## ✖ lubridate::quarter()  masks data.table::quarter()
## ✖ lubridate::second()   masks data.table::second()
## ✖ purrr::transpose()    masks data.table::transpose()
## ✖ lubridate::wday()     masks data.table::wday()
## ✖ lubridate::week()     masks data.table::week()
## ✖ lubridate::yday()     masks data.table::yday()
## ✖ lubridate::year()     masks data.table::year()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Importar base de datos

df <- USArrests

Análisis Descriptivo

#create_report(df)
plot_missing(df)

plot_histogram(df)

plot_correlation(df)

summary(df)

##      Murder          Assault         UrbanPop          Rape      
##  Min.   : 0.800   Min.   : 45.0   Min.   :32.00   Min.   : 7.30  
##  1st Qu.: 4.075   1st Qu.:109.0   1st Qu.:54.50   1st Qu.:15.07  
##  Median : 7.250   Median :159.0   Median :66.00   Median :20.10  
##  Mean   : 7.788   Mean   :170.8   Mean   :65.54   Mean   :21.23  
##  3rd Qu.:11.250   3rd Qu.:249.0   3rd Qu.:77.75   3rd Qu.:26.18  
##  Max.   :17.400   Max.   :337.0   Max.   :91.00   Max.   :46.00

Scalar la base de datos

df <- df[, c("Murder", "Assault", "Rape")]
datos_escalados <- scale(df)

grupos <- 3 #Número de clusters inicial
segmentos <- kmeans(datos_escalados, grupos)

df$Cluster <- as.factor(segmentos$cluster)

df$Promedio_Score <- rowMeans(df[, c("Murder", "Assault", "Rape")])

df$Seguridad <- cut(df$Promedio_Score, breaks = quantile(df$Promedio_Score, probs = c(0, 0.25, 0.5, 0.75, 1)),
                    labels = c("Muy Seguro", "Seguro", "Inseguro", "Muy Inseguro"),
                    include.lowest = TRUE)

Graficar cluster

fviz_cluster(segmentos, data=datos_escalados)

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

promedio <- aggregate(df[,-ncol(df)], by=list(df$Cluster), FUN=mean)

## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA

promedio

##   Group.1    Murder   Assault     Rape Cluster Promedio_Score
## 1       1 12.331579 259.31579 29.21579      NA      100.28772
## 2       2  3.078571  80.92857 11.80000      NA       31.93571
## 3       3  6.588235 145.76471 20.07647      NA       57.47647

table(df$Cluster)

## 
##  1  2  3 
## 19 14 17