Titanic
Iker Villafaña - A00573756
2025-02-27
Importar la base de datos
# file.choose()
titanic <- read.csv("C:\\Users\\Usuario\\Documents\\IAConcentración\\M2\\Titanic\\titanic.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 :1189str(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] 266sapply(Titanic, function(x) sum(is.na(x)))## pclass age sex survived
## 1 264 0 1Titanic <- 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 más altas probabilidades de sobrevivir en el
Titanic son niño varón menor de 9.5 años de 1° y 2° clase (100%), y
mujeres en 1° y 2° clase (93%). 2. Las más bajas probabilidades de
sobrevivir en el Titanic son los hombres mayores de 9.5 años (18%), y
los hombres menores de 9.5 años en 3° clase (38%)