Actividad 4.2

Titanic

1. Importar

#file.choose()
titanic <- read.csv("/Users/roygomez/Desktop/titanic.csv")

2. Enteder

summary(titanic)

##      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

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

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

Observaciones: 1. Existen NA’s. 2. Algunos nombres se repiten.

3. Limpiar base de datos

# Cambiar nombre a la variable pclass
colnames(titanic)[1] <- "class"

# Extraer las variables de interés
ttnc <- titanic[,c("class","age","sex", "survived")]

# ¿Cuántos NA tengo por variable?
sapply(ttnc, function(x) sum(is.na(x)))

##    class      age      sex survived 
##        1      264        0        1

# Eliminar NA
ttnc <- na.omit(ttnc)
#str(ttnc)

# Convertir las variables categóricas en factores
ttnc$class <- as.factor(ttnc$class)
ttnc$sex <- as.factor(ttnc$sex)
ttnc$survived <- as.factor(ttnc$survived)

str(ttnc)

## 'data.frame':    1046 obs. of  4 variables:
##  $ class   : 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 "0","1": 2 2 1 1 1 2 2 1 2 1 ...
##  - attr(*, "na.action")= 'omit' Named int [1:264] 16 38 41 47 60 70 71 75 81 107 ...
##   ..- attr(*, "names")= chr [1:264] "16" "38" "41" "47" ...

4. Crear árbol de decisión

library(rpart)
library(rpart.plot)

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

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

rpart.plot(arbol)