Regresion Lineal. Titanic

Importar la base de datos

# file.choose()
titanic <- read.csv("C:\\Users\\rylun\\Downloads\\titanic(1).csv")

Entender la base de datos

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

str(titanic)

## 'data.frame':    1310 obs. of  14 variables:
##  $ pclass   : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ survived : int  1 1 0 0 0 1 1 0 1 0 ...
##  $ name     : chr  "Allen, Miss. Elisabeth Walton" "Allison, Master. Hudson Trevor" "Allison, Miss. Helen Loraine" "Allison, Mr. Hudson Joshua Creighton" ...
##  $ sex      : chr  "female" "male" "female" "male" ...
##  $ age      : num  29 0.917 2 30 25 ...
##  $ sibsp    : int  0 1 1 1 1 0 1 0 2 0 ...
##  $ parch    : int  0 2 2 2 2 0 0 0 0 0 ...
##  $ ticket   : chr  "24160" "113781" "113781" "113781" ...
##  $ fare     : num  211 152 152 152 152 ...
##  $ cabin    : chr  "B5" "C22 C26" "C22 C26" "C22 C26" ...
##  $ embarked : chr  "S" "S" "S" "S" ...
##  $ boat     : chr  "2" "11" "" "" ...
##  $ body     : int  NA NA NA 135 NA NA NA NA NA 22 ...
##  $ home.dest: chr  "St Louis, MO" "Montreal, PQ / Chesterville, ON" "Montreal, PQ / Chesterville, ON" "Montreal, PQ / Chesterville, ON" ...

Filtrar base de datos

Titanic <- titanic[,c("pclass","age","sex","survived")]
Titanic$survived <- as.factor(ifelse(Titanic$survived==0, "Murio", "Sobrevive"))
Titanic$pclass <- as.factor(Titanic$pclass)
Titanic$sex <- as.factor(Titanic$sex)
str(Titanic)

## 'data.frame':    1310 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/ 3 levels "","female","male": 2 3 2 3 2 3 2 3 2 3 ...
##  $ survived: Factor w/ 2 levels "Murio","Sobrevive": 2 2 1 1 1 2 2 1 2 1 ...

sum(is.na(Titanic))

## [1] 266

sapply(Titanic, function(x) sum(is.na(x)))

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

Titanic <- na.omit(Titanic)

Crear arbol de decisión

#install.packages("rpart")
library(rpart)
arbol <- rpart(formula=survived ~ ., data = Titanic)
arbol

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

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

prp(arbol,extra = 7,prefix = "fraccion")

## Conclusiones 1. Las mujeres tienen una tasa de supervivencia mucho mayor (0,75 en la raíz del segundo árbol). 2. Si un hombre tenía más de 9,5 años y estaba en tercera clase, la probabilidad de morir era muy alta 3. Aunque estar en tercera clase reducía las posibilidades de sobrevivir, las mujeres tenían una mayor tasa de supervivencia incluso en esta categoría