Seguros R

Carga de archivo

file.choose() seguros <- read.csv(“C:\Users\lffr1\Downloads\seguros.csv”)

summary(seguros)

Entender la base de datos summary(bd)

install.packages(“dplyr”) library(dplyr)

Dplyr es una librería de manipulación de datos

count(bd, claimstatus, sort=TRUE) count(bd, ClaimID, sort=TRUE) count(bd, TotalPaid, sort=TRUE) count(bd, TotalReserves, sort=TRUE) count(bd, TotalRecovery , sort=TRUE) count(bd, IndemnityPaid, sort=TRUE) count(bd, OtherPaid, sort=TRUE) count(bd, TotalIncurredCost, sort=TRUE) count(bd, ClaimStatus, sort=TRUE) count(bd, IncidentDescription, sort=TRUE) count(bd, IsDenied, sort=TRUE) count(bd, Transaction_Time, sort=TRUE) count(bd, Procesing_Time, sort=TRUE) count(bd, ClaimantAge_at_DOI, sort=TRUE) count(bd, Gender, sort=TRUE) count(bd, ClaimantType, sort=TRUE) count(bd, InjuryNature, sort=TRUE) count(bd, BodyPartRegion, sort=TRUE) count(bd, BodyPart, sort=TRUE) count(bd, AverageWeeklyWage1, sort=TRUE) count(bd, BillReviewALE , sort=TRUE) count(bd, Hospital , sort=TRUE) count(bd, PhysicianOutpatientClaimID, sort=TRUE) count(bd, Rx, sort=TRUE)

regresion <- lm(TotalIncurredCost ~ Gender + ClaimantType + BodyPartRegion + BodyPart + AverageWeeklyWage1, data=seguros) summary(regresion)

regresion_ajustada <- lm(TotalIncurredCost ~ Gender + ClaimantType + BodyPartRegion + BodyPart + AverageWeeklyWage1, data=seguros) summary(regresion_ajustada)

datos_nuevos <- data.frame(ClaimantAge_at_DOI = c(20,30,40,50,60,70,80,90), Gender= “Male”, ClaimantType=“Medical Only”, BodyPartRegion=“Head”, BodyPart=“Brain”, AverageWeeklyWage1=550) predict(regresion_ajustada,datos_nuevos)