M4 Actividad Final

Contexto

1. Importar y juntar bases de datos

# file.choose()
bd1 <- read.csv("/Users/dannaleal/Downloads/ClaimsData2018.csv")
bd2 <- read.csv("/Users/dannaleal/Downloads/TransactionsSummary2018.csv")
bd <- merge(bd1, bd2, by="ClaimID",all=TRUE)

2. Crear nueva columna para Total Incurred Cost

# install.packages("dplyr")
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

bd <- bd %>% 
  mutate(Total_Incurred_Cost_Claim = TotalReserves + IndemnityPaid + OtherPaid - TotalRecovery)

3. Filtrar base de datos por sólo mujeres

bd_mujeres1 <- subset(bd, Gender == "Female")
# View(bd_mujeres1)

4. Eliminar columas de X

library(dplyr)
bd_mujeres1 <- bd_mujeres1 %>%
  select(-X:-X.22)

# View(bd_mujeres1)

5. Descargar base de datos limpia como CSV

write.csv(bd_mujeres1, "bd_mujeres limpia.csv", row.names = FALSE)