# Instalar paquetes y llamar librerías
#install.packages("randomForest")
library(randomForest)## randomForest 4.7-1.1## Type rfNews() to see new features/changes/bug fixes.#install.packages("caret")
library(caret)## Loading required package: ggplot2##
## Attaching package: 'ggplot2'## The following object is masked from 'package:randomForest':
##
## margin## Loading required package: lattice# Crear la base de datos
df <- read.csv("~/Downloads/heart.csv")# Análisis exploratorio
summary(df)## age sex cp trestbps
## Min. :29.00 Min. :0.0000 Min. :0.0000 Min. : 94.0
## 1st Qu.:48.00 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:120.0
## Median :56.00 Median :1.0000 Median :1.0000 Median :130.0
## Mean :54.43 Mean :0.6956 Mean :0.9424 Mean :131.6
## 3rd Qu.:61.00 3rd Qu.:1.0000 3rd Qu.:2.0000 3rd Qu.:140.0
## Max. :77.00 Max. :1.0000 Max. :3.0000 Max. :200.0
## chol fbs restecg thalach
## Min. :126 Min. :0.0000 Min. :0.0000 Min. : 71.0
## 1st Qu.:211 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:132.0
## Median :240 Median :0.0000 Median :1.0000 Median :152.0
## Mean :246 Mean :0.1493 Mean :0.5298 Mean :149.1
## 3rd Qu.:275 3rd Qu.:0.0000 3rd Qu.:1.0000 3rd Qu.:166.0
## Max. :564 Max. :1.0000 Max. :2.0000 Max. :202.0
## exang oldpeak slope ca
## Min. :0.0000 Min. :0.000 Min. :0.000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.000 1st Qu.:1.000 1st Qu.:0.0000
## Median :0.0000 Median :0.800 Median :1.000 Median :0.0000
## Mean :0.3366 Mean :1.072 Mean :1.385 Mean :0.7541
## 3rd Qu.:1.0000 3rd Qu.:1.800 3rd Qu.:2.000 3rd Qu.:1.0000
## Max. :1.0000 Max. :6.200 Max. :2.000 Max. :4.0000
## thal target
## Min. :0.000 Min. :0.0000
## 1st Qu.:2.000 1st Qu.:0.0000
## Median :2.000 Median :1.0000
## Mean :2.324 Mean :0.5132
## 3rd Qu.:3.000 3rd Qu.:1.0000
## Max. :3.000 Max. :1.0000str(df)## 'data.frame': 1025 obs. of 14 variables:
## $ age : int 52 53 70 61 62 58 58 55 46 54 ...
## $ sex : int 1 1 1 1 0 0 1 1 1 1 ...
## $ cp : int 0 0 0 0 0 0 0 0 0 0 ...
## $ trestbps: int 125 140 145 148 138 100 114 160 120 122 ...
## $ chol : int 212 203 174 203 294 248 318 289 249 286 ...
## $ fbs : int 0 1 0 0 1 0 0 0 0 0 ...
## $ restecg : int 1 0 1 1 1 0 2 0 0 0 ...
## $ thalach : int 168 155 125 161 106 122 140 145 144 116 ...
## $ exang : int 0 1 1 0 0 0 0 1 0 1 ...
## $ oldpeak : num 1 3.1 2.6 0 1.9 1 4.4 0.8 0.8 3.2 ...
## $ slope : int 2 0 0 2 1 1 0 1 2 1 ...
## $ ca : int 2 0 0 1 3 0 3 1 0 2 ...
## $ thal : int 3 3 3 3 2 2 1 3 3 2 ...
## $ target : int 0 0 0 0 0 1 0 0 0 0 ...df$target <- as.factor(df$target)
summary(df)## age sex cp trestbps
## Min. :29.00 Min. :0.0000 Min. :0.0000 Min. : 94.0
## 1st Qu.:48.00 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:120.0
## Median :56.00 Median :1.0000 Median :1.0000 Median :130.0
## Mean :54.43 Mean :0.6956 Mean :0.9424 Mean :131.6
## 3rd Qu.:61.00 3rd Qu.:1.0000 3rd Qu.:2.0000 3rd Qu.:140.0
## Max. :77.00 Max. :1.0000 Max. :3.0000 Max. :200.0
## chol fbs restecg thalach
## Min. :126 Min. :0.0000 Min. :0.0000 Min. : 71.0
## 1st Qu.:211 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:132.0
## Median :240 Median :0.0000 Median :1.0000 Median :152.0
## Mean :246 Mean :0.1493 Mean :0.5298 Mean :149.1
## 3rd Qu.:275 3rd Qu.:0.0000 3rd Qu.:1.0000 3rd Qu.:166.0
## Max. :564 Max. :1.0000 Max. :2.0000 Max. :202.0
## exang oldpeak slope ca
## Min. :0.0000 Min. :0.000 Min. :0.000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.000 1st Qu.:1.000 1st Qu.:0.0000
## Median :0.0000 Median :0.800 Median :1.000 Median :0.0000
## Mean :0.3366 Mean :1.072 Mean :1.385 Mean :0.7541
## 3rd Qu.:1.0000 3rd Qu.:1.800 3rd Qu.:2.000 3rd Qu.:1.0000
## Max. :1.0000 Max. :6.200 Max. :2.000 Max. :4.0000
## thal target
## Min. :0.000 0:499
## 1st Qu.:2.000 1:526
## Median :2.000
## Mean :2.324
## 3rd Qu.:3.000
## Max. :3.000str(df)## 'data.frame': 1025 obs. of 14 variables:
## $ age : int 52 53 70 61 62 58 58 55 46 54 ...
## $ sex : int 1 1 1 1 0 0 1 1 1 1 ...
## $ cp : int 0 0 0 0 0 0 0 0 0 0 ...
## $ trestbps: int 125 140 145 148 138 100 114 160 120 122 ...
## $ chol : int 212 203 174 203 294 248 318 289 249 286 ...
## $ fbs : int 0 1 0 0 1 0 0 0 0 0 ...
## $ restecg : int 1 0 1 1 1 0 2 0 0 0 ...
## $ thalach : int 168 155 125 161 106 122 140 145 144 116 ...
## $ exang : int 0 1 1 0 0 0 0 1 0 1 ...
## $ oldpeak : num 1 3.1 2.6 0 1.9 1 4.4 0.8 0.8 3.2 ...
## $ slope : int 2 0 0 2 1 1 0 1 2 1 ...
## $ ca : int 2 0 0 1 3 0 3 1 0 2 ...
## $ thal : int 3 3 3 3 2 2 1 3 3 2 ...
## $ target : Factor w/ 2 levels "0","1": 1 1 1 1 1 2 1 1 1 1 ...# Partir la base de datos
set.seed(123)
renglones_entrenamiento <- createDataPartition(df$target, p=0.8, list=FALSE)
entrenamiento <- df[renglones_entrenamiento, ]
prueba <- df[-renglones_entrenamiento, ]# Construir el modelo Random Forest
modelo <- randomForest(target ~ ., data = entrenamiento)
resultado_entrenamiento <- predict(modelo,entrenamiento)
resultado_prueba <- predict(modelo,prueba)
resultado_prueba## 1 6 13 20 26 27 29 31 38 47 52 57 58 61 64 67
## 0 1 1 1 0 1 0 0 1 1 0 1 1 1 1 1
## 70 71 77 81 83 88 90 92 104 108 110 113 115 118 125 142
## 0 0 1 0 0 0 0 1 1 0 0 0 0 0 0 0
## 161 170 177 187 194 195 196 200 202 205 223 229 233 246 251 253
## 0 1 0 0 1 0 1 0 1 1 1 1 0 1 0 0
## 255 260 269 274 278 281 283 286 287 289 296 304 305 309 313 317
## 0 1 0 0 1 1 1 1 1 1 0 0 1 0 0 1
## 323 333 341 350 358 360 365 369 379 385 388 390 391 396 399 407
## 0 1 1 0 0 1 0 1 0 0 0 1 0 1 1 1
## 410 420 431 432 439 444 446 462 464 465 466 471 473 479 491 492
## 0 1 0 0 1 1 1 1 1 1 1 1 1 1 1 1
## 493 497 509 512 521 525 537 542 543 549 558 559 561 563 584 588
## 0 0 0 0 0 0 1 1 1 1 1 1 1 1 0 0
## 590 598 627 631 633 640 645 648 654 666 668 674 680 690 693 694
## 0 1 0 0 1 1 1 1 0 1 0 1 0 1 0 1
## 696 698 699 708 711 717 720 723 724 727 731 738 744 753 755 756
## 0 0 0 1 1 0 1 1 1 0 1 0 1 1 1 1
## 757 758 759 767 780 789 791 801 804 806 809 817 828 837 838 840
## 0 1 1 0 1 0 0 0 0 1 1 1 0 1 1 1
## 845 848 860 863 864 869 877 889 894 895 897 910 916 917 920 922
## 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 0
## 928 932 934 935 937 938 939 941 943 946 953 958 959 967 975 977
## 1 0 0 1 1 0 1 0 1 1 1 0 1 0 1 0
## 985 990 995 997 1005 1006 1009 1013 1021 1022 1024 1025
## 1 1 0 0 1 0 1 0 1 0 1 0
## Levels: 0 1# Matriz de Confusión
mcre <- confusionMatrix(resultado_entrenamiento, entrenamiento$target) # matriz de confusión del resultado del entrenamiento
mcre## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 400 0
## 1 0 421
##
## Accuracy : 1
## 95% CI : (0.9955, 1)
## No Information Rate : 0.5128
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Sensitivity : 1.0000
## Specificity : 1.0000
## Pos Pred Value : 1.0000
## Neg Pred Value : 1.0000
## Prevalence : 0.4872
## Detection Rate : 0.4872
## Detection Prevalence : 0.4872
## Balanced Accuracy : 1.0000
##
## 'Positive' Class : 0
## mcrp <- confusionMatrix(resultado_prueba,prueba$target) # matriz de confusión del resultado de la prueba
mcrp## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 99 0
## 1 0 105
##
## Accuracy : 1
## 95% CI : (0.9821, 1)
## No Information Rate : 0.5147
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Sensitivity : 1.0000
## Specificity : 1.0000
## Pos Pred Value : 1.0000
## Neg Pred Value : 1.0000
## Prevalence : 0.4853
## Detection Rate : 0.4853
## Detection Prevalence : 0.4853
## Balanced Accuracy : 1.0000
##
## 'Positive' Class : 0
## resultados <- data.frame("rf" = c(mcre$overall["Accuracy"], mcrp$overall["Accuracy"]))
rownames(resultados) <- c("Precision de entrenamiento", "Precision de prueba")
resultados## rf
## Precision de entrenamiento 1
## Precision de prueba 1# Obtener predicción
paciente <- data.frame(
age = 58,
sex = 0,
cp = 0,
trestbps = 100,
chol = 248,
fbs = 0,
restecg = 0,
thalach = 122,
exang = 0,
oldpeak = 1,
slope = 1,
ca = 0,
thal = 2
)# Hacer la predicción
prediccion <- predict(modelo, paciente)
if(prediccion == 1) {
print("Tiene enfermedad cardíaca")
} else {
print("No tiene enfermedad cardíaca")
}## [1] "Tiene enfermedad cardíaca"#Conclusión: en conclusion los bosques aleatorios son una herramienta robusta que combina distintos arboles de decision para la prediccion de diagnostico en enfermedades cardiacas