Arbol de Decisión
Paulina Badillo González
2023-09-19
Titanic
1. Importar la base de datos
titanic <- read.csv("~/Downloads/titanic.csv")2. 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 :1189library(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. Tenemos 2 registros de Nombre repetidos. 2. Tenemos NA en la base de datos.
3. Limpiar la base de datos
#Extraer las variables de interés
Titanic <- titanic[,c("pclass","age", "sex", "survived")]
#¿Cuántos NA tengo en la base de datos?
sum(is.na(Titanic))## [1] 266#¿Cuántos NA tengo por variable?
sapply(Titanic, function(x) sum(is.na(x)))## pclass age sex survived
## 1 264 0 1#ELiminar renglón blanco
Titanic <- Titanic[-1310,]
#Convertir las variables categóricas en factores
Titanic$pclass <- as.factor(Titanic$pclass)
Titanic$sex <- as.factor(Titanic$sex)
Titanic$survived <- as.factor(ifelse(Titanic$survived==0, "Murio", "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 "Murio","Sobrevivió": 2 2 1 1 1 2 2 1 2 1 ...#¿Cuántos NA tengo por variable?
sapply(Titanic, function(x) sum(is.na(x)))## pclass age sex survived
## 0 263 0 04. Crear el árbol de decisión
#install.packages("raprt")
library(rpart)
#install.packages("raprt.plot")
library(rpart.plot)
arbol <- rpart(formula = survived ~ ., data = Titanic)
arbol## n= 1309
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 1309 500 Murio (0.6180290 0.3819710)
## 2) sex=male 843 161 Murio (0.8090154 0.1909846)
## 4) age>=9.5 800 136 Murio (0.8300000 0.1700000) *
## 5) age< 9.5 43 18 Sobrevivió (0.4186047 0.5813953)
## 10) pclass=3 29 11 Murio (0.6206897 0.3793103) *
## 11) pclass=1,2 14 0 Sobrevivió (0.0000000 1.0000000) *
## 3) sex=female 466 127 Sobrevivió (0.2725322 0.7274678) *rpart.plot(arbol)
prp(arbol,extra = 7)
Cáncer de Mama
1. Importar la base de datos
cancer_de_mama <- read.csv("~/Downloads/cancer_de_mama.csv")2. Entender la base de datos
summary(cancer_de_mama)## diagnosis radius_mean texture_mean perimeter_mean
## Length:569 Min. : 6.981 Min. : 9.71 Min. : 43.79
## Class :character 1st Qu.:11.700 1st Qu.:16.17 1st Qu.: 75.17
## Mode :character Median :13.370 Median :18.84 Median : 86.24
## Mean :14.127 Mean :19.29 Mean : 91.97
## 3rd Qu.:15.780 3rd Qu.:21.80 3rd Qu.:104.10
## Max. :28.110 Max. :39.28 Max. :188.50
## area_mean smoothness_mean compactness_mean concavity_mean
## Min. : 143.5 Min. :0.05263 Min. :0.01938 Min. :0.00000
## 1st Qu.: 420.3 1st Qu.:0.08637 1st Qu.:0.06492 1st Qu.:0.02956
## Median : 551.1 Median :0.09587 Median :0.09263 Median :0.06154
## Mean : 654.9 Mean :0.09636 Mean :0.10434 Mean :0.08880
## 3rd Qu.: 782.7 3rd Qu.:0.10530 3rd Qu.:0.13040 3rd Qu.:0.13070
## Max. :2501.0 Max. :0.16340 Max. :0.34540 Max. :0.42680
## concave.points_mean symmetry_mean fractal_dimension_mean radius_se
## Min. :0.00000 Min. :0.1060 Min. :0.04996 Min. :0.1115
## 1st Qu.:0.02031 1st Qu.:0.1619 1st Qu.:0.05770 1st Qu.:0.2324
## Median :0.03350 Median :0.1792 Median :0.06154 Median :0.3242
## Mean :0.04892 Mean :0.1812 Mean :0.06280 Mean :0.4052
## 3rd Qu.:0.07400 3rd Qu.:0.1957 3rd Qu.:0.06612 3rd Qu.:0.4789
## Max. :0.20120 Max. :0.3040 Max. :0.09744 Max. :2.8730
## texture_se perimeter_se area_se smoothness_se
## Min. :0.3602 Min. : 0.757 Min. : 6.802 Min. :0.001713
## 1st Qu.:0.8339 1st Qu.: 1.606 1st Qu.: 17.850 1st Qu.:0.005169
## Median :1.1080 Median : 2.287 Median : 24.530 Median :0.006380
## Mean :1.2169 Mean : 2.866 Mean : 40.337 Mean :0.007041
## 3rd Qu.:1.4740 3rd Qu.: 3.357 3rd Qu.: 45.190 3rd Qu.:0.008146
## Max. :4.8850 Max. :21.980 Max. :542.200 Max. :0.031130
## compactness_se concavity_se concave.points_se symmetry_se
## Min. :0.002252 Min. :0.00000 Min. :0.000000 Min. :0.007882
## 1st Qu.:0.013080 1st Qu.:0.01509 1st Qu.:0.007638 1st Qu.:0.015160
## Median :0.020450 Median :0.02589 Median :0.010930 Median :0.018730
## Mean :0.025478 Mean :0.03189 Mean :0.011796 Mean :0.020542
## 3rd Qu.:0.032450 3rd Qu.:0.04205 3rd Qu.:0.014710 3rd Qu.:0.023480
## Max. :0.135400 Max. :0.39600 Max. :0.052790 Max. :0.078950
## fractal_dimension_se radius_worst texture_worst perimeter_worst
## Min. :0.0008948 Min. : 7.93 Min. :12.02 Min. : 50.41
## 1st Qu.:0.0022480 1st Qu.:13.01 1st Qu.:21.08 1st Qu.: 84.11
## Median :0.0031870 Median :14.97 Median :25.41 Median : 97.66
## Mean :0.0037949 Mean :16.27 Mean :25.68 Mean :107.26
## 3rd Qu.:0.0045580 3rd Qu.:18.79 3rd Qu.:29.72 3rd Qu.:125.40
## Max. :0.0298400 Max. :36.04 Max. :49.54 Max. :251.20
## area_worst smoothness_worst compactness_worst concavity_worst
## Min. : 185.2 Min. :0.07117 Min. :0.02729 Min. :0.0000
## 1st Qu.: 515.3 1st Qu.:0.11660 1st Qu.:0.14720 1st Qu.:0.1145
## Median : 686.5 Median :0.13130 Median :0.21190 Median :0.2267
## Mean : 880.6 Mean :0.13237 Mean :0.25427 Mean :0.2722
## 3rd Qu.:1084.0 3rd Qu.:0.14600 3rd Qu.:0.33910 3rd Qu.:0.3829
## Max. :4254.0 Max. :0.22260 Max. :1.05800 Max. :1.2520
## concave.points_worst symmetry_worst fractal_dimension_worst
## Min. :0.00000 Min. :0.1565 Min. :0.05504
## 1st Qu.:0.06493 1st Qu.:0.2504 1st Qu.:0.07146
## Median :0.09993 Median :0.2822 Median :0.08004
## Mean :0.11461 Mean :0.2901 Mean :0.08395
## 3rd Qu.:0.16140 3rd Qu.:0.3179 3rd Qu.:0.09208
## Max. :0.29100 Max. :0.6638 Max. :0.20750library(dplyr)
count(cancer_de_mama, diagnosis, sort=TRUE)## diagnosis n
## 1 B 357
## 2 M 2123. Crear el árbol de decisión
library(rpart)
library(rpart.plot)
arbol <- rpart(formula = diagnosis ~ ., data=cancer_de_mama)
arbol## n= 569
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 569 212 B (0.62741652 0.37258348)
## 2) radius_worst< 16.795 379 33 B (0.91292876 0.08707124)
## 4) concave.points_worst< 0.1358 333 5 B (0.98498498 0.01501502) *
## 5) concave.points_worst>=0.1358 46 18 M (0.39130435 0.60869565)
## 10) texture_worst< 25.67 19 4 B (0.78947368 0.21052632) *
## 11) texture_worst>=25.67 27 3 M (0.11111111 0.88888889) *
## 3) radius_worst>=16.795 190 11 M (0.05789474 0.94210526) *rpart.plot(arbol)
prp(arbol, extra = 7)