# file.choose()

Instalar paquetes y llamar librerías

# install.packages("randomForest")
library(e1071)
# install.packages("caret") 
library(caret)
## Cargando paquete requerido: ggplot2
## Cargando paquete requerido: lattice

Crear la base de datos

df <- read.csv("C:\\Users\\sebas\\OneDrive\\Escritorio\\Inteligencia de Negocios\\Modulo 2\\22 08 2024\\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 SVM Lineal

modelo <- svm(target ~ ., data = entrenamiento, kernel= "linear")
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
##          0 301  37
##          1  99 384
##                                           
##                Accuracy : 0.8343          
##                  95% CI : (0.8071, 0.8592)
##     No Information Rate : 0.5128          
##     P-Value [Acc > NIR] : < 2.2e-16       
##                                           
##                   Kappa : 0.6672          
##                                           
##  Mcnemar's Test P-Value : 1.689e-07       
##                                           
##             Sensitivity : 0.7525          
##             Specificity : 0.9121          
##          Pos Pred Value : 0.8905          
##          Neg Pred Value : 0.7950          
##              Prevalence : 0.4872          
##          Detection Rate : 0.3666          
##    Detection Prevalence : 0.4117          
##       Balanced Accuracy : 0.8323          
##                                           
##        'Positive' Class : 0               
##

Matriz de Confusión

mcrp <- confusionMatrix(resultado_prueba,prueba$target) # matriz de confusión del resultado de la prueba
mcrp
## Confusion Matrix and Statistics
## 
##           Reference
## Prediction  0  1
##          0 78 10
##          1 21 95
##                                           
##                Accuracy : 0.848           
##                  95% CI : (0.7913, 0.8944)
##     No Information Rate : 0.5147          
##     P-Value [Acc > NIR] : < 2e-16         
##                                           
##                   Kappa : 0.6948          
##                                           
##  Mcnemar's Test P-Value : 0.07249         
##                                           
##             Sensitivity : 0.7879          
##             Specificity : 0.9048          
##          Pos Pred Value : 0.8864          
##          Neg Pred Value : 0.8190          
##              Prevalence : 0.4853          
##          Detection Rate : 0.3824          
##    Detection Prevalence : 0.4314          
##       Balanced Accuracy : 0.8463          
##                                           
##        'Positive' Class : 0               
## 
resultados <- data.frame("SVM Lineal" = c(mcre$overall["Accuracy"], mcrp$overall["Accuracy"]))
rownames(resultados) <- c("Precision de entrenamiento", "Precision de prueba")
resultados
##                            SVM.Lineal
## Precision de entrenamiento  0.8343484
## Precision de prueba         0.8480392

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
)
prediccion <- predict(modelo, paciente)

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

En conclusión, la maquina de vectores de soporte funciona para la herramientas cardiacas

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