Árbol de decisión

Titanic

1. Importar la base 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

#file.choose()
titanic_db <- read.csv("/Users/marianaguevara/Downloads/titanic.csv")

2. Entender la base de datos

summary(titanic_db)

##      pclass         survived         name               sex           
##  Min.   :1.000   Min.   :0.000   Length:1310        Length:1310       
##  1st Qu.:2.000   1st Qu.:0.000   Class :character   Class :character  
##  Median :3.000   Median :0.000   Mode  :character   Mode  :character  
##  Mean   :2.295   Mean   :0.382                                        
##  3rd Qu.:3.000   3rd Qu.:1.000                                        
##  Max.   :3.000   Max.   :1.000                                        
##  NA's   :1       NA's   :1                                            
##       age              sibsp            parch          ticket         
##  Min.   : 0.1667   Min.   :0.0000   Min.   :0.000   Length:1310       
##  1st Qu.:21.0000   1st Qu.:0.0000   1st Qu.:0.000   Class :character  
##  Median :28.0000   Median :0.0000   Median :0.000   Mode  :character  
##  Mean   :29.8811   Mean   :0.4989   Mean   :0.385                     
##  3rd Qu.:39.0000   3rd Qu.:1.0000   3rd Qu.:0.000                     
##  Max.   :80.0000   Max.   :8.0000   Max.   :9.000                     
##  NA's   :264       NA's   :1        NA's   :1                         
##       fare            cabin             embarked             boat          
##  Min.   :  0.000   Length:1310        Length:1310        Length:1310       
##  1st Qu.:  7.896   Class :character   Class :character   Class :character  
##  Median : 14.454   Mode  :character   Mode  :character   Mode  :character  
##  Mean   : 33.295                                                           
##  3rd Qu.: 31.275                                                           
##  Max.   :512.329                                                           
##  NA's   :2                                                                 
##       body        home.dest        
##  Min.   :  1.0   Length:1310       
##  1st Qu.: 72.0   Class :character  
##  Median :155.0   Mode  :character  
##  Mean   :160.8                     
##  3rd Qu.:256.0                     
##  Max.   :328.0                     
##  NA's   :1189

#count(titanic_db, name, sort = TRUE)
#count(titanic_db, sex, sort = TRUE)
#count(titanic_db, ticket, sort = TRUE)
#count(titanic_db, cabin, sort = TRUE)
#count(titanic_db, embarked, sort = TRUE)
#count(titanic_db, boat, sort = TRUE)
#count(titanic_db, home.dest, sort = TRUE)

Observaciones: 1. Tenemos 2 registros de Nombre repetidos. 2. Tenemos NA’s en la base de datos

3. Modificar la base de datos

#Extraer las variables de interes
Titanic <- titanic_db[,c("pclass", "age", "sex", "survived")]
View(Titanic)

# Cuantos NA's tengo en la base de datos
sum(is.na(Titanic))

## [1] 266

#Cuantos NA's tengo por variable
sapply(Titanic, function(x) sum(is.na(x)))

##   pclass      age      sex survived 
##        1      264        0        1

#Elimanr renglon blanco
Titanic <- Titanic[-1310,]

#Convertir las variables catégoricas en factores
Titanic$pclass <- as.factor(Titanic$pclass)
Titanic$sex <- as.factor(Titanic$sex)
Titanic$survived <- as.factor(ifelse(Titanic$survived==0, "Murió", "Sobrevivió"))
str(Titanic)

## 'data.frame':    1309 obs. of  4 variables:
##  $ pclass  : Factor w/ 3 levels "1","2","3": 1 1 1 1 1 1 1 1 1 1 ...
##  $ age     : num  29 0.917 2 30 25 ...
##  $ sex     : Factor w/ 2 levels "female","male": 1 2 1 2 1 2 1 2 1 2 ...
##  $ survived: Factor w/ 2 levels "Murió","Sobrevivió": 2 2 1 1 1 2 2 1 2 1 ...

#Cuantos NA's tengo por variable
sapply(Titanic, function(x) sum(is.na(x)))

##   pclass      age      sex survived 
##        0      263        0        0

#Eliminar NA's
Titanic <- na.omit(Titanic)

#Cuantos NA's tengo por variable
sapply(Titanic, function(x) sum(is.na(x)))

##   pclass      age      sex survived 
##        0        0        0        0

4. Crear el árbol de decisión

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

#install.packages("rpart.plot")
library(rpart.plot)


arbol <- rpart(formula = survived ~ ., data = Titanic)
arbol 

## n= 1046 
## 
## node), split, n, loss, yval, (yprob)
##       * denotes terminal node
## 
##  1) root 1046 427 Murió (0.59177820 0.40822180)  
##    2) sex=male 658 135 Murió (0.79483283 0.20516717)  
##      4) age>=9.5 615 110 Murió (0.82113821 0.17886179) *
##      5) age< 9.5 43  18 Sobrevivió (0.41860465 0.58139535)  
##       10) pclass=3 29  11 Murió (0.62068966 0.37931034) *
##       11) pclass=1,2 14   0 Sobrevivió (0.00000000 1.00000000) *
##    3) sex=female 388  96 Sobrevivió (0.24742268 0.75257732)  
##      6) pclass=3 152  72 Murió (0.52631579 0.47368421)  
##       12) age>=1.5 145  66 Murió (0.54482759 0.45517241) *
##       13) age< 1.5 7   1 Sobrevivió (0.14285714 0.85714286) *
##      7) pclass=1,2 236  16 Sobrevivió (0.06779661 0.93220339) *

rpart.plot(arbol)

prp(arbol, extra = 7)