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("/Users/sebastianfajardo/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.   :1.0000
str(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.   :3.000
str(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)

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          
##

Obtener predicción

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 = 52,
  sex = 1,
  cp = 0,
  trestbps = 125,
  chol = 212,
  fbs = 0,
  restecg = 1,
  thalach = 168,
  exang = 0,
  oldpeak = 1,
  slope = 2,
  ca = 0,
  thal = 3
)

prediccion <- predict(modelo, paciente)

if(prediccion == 1) {
  print("Tiene enfermedad cardíaca")
} else {
  print("No tiene enfermedad cardíaca")
}
## [1] "No tiene enfermedad cardíaca"

#Conclusión En conclusión , los bosques aleatorios es una herramienta robusta que combina distintos arboles de decisión para la prediccion de diagnostico en enfermedad cardiaca.

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