SVM
Constantino Millet Xacur
2024-08-22
# Instalar paquetes y llamar librerías
# install.packages("e1071")
library(e1071)
# install.packages("caret")
library(caret)## Loading required package: ggplot2## Loading required package: lattice# Crear la base de datos
df <- read.csv("/Users/constantinomilletxacur/Desktop/Concentracion/Modulo 2/heart.csv")# file.choose()# 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$target, p=0.8, list=FALSE)
entrenamiento <- df[renglones_entrenamiento, ]
prueba <- df[-renglones_entrenamiento, ]# Construir el modelo Random Forest
modelo <- svm(target ~ ., data = entrenamiento, kerner = "lineal")
resultado_entrenamiento <- predict(modelo,entrenamiento)
resultado_prueba <- predict(modelo,prueba)# Matriz de Confusión
mcre <- confusionMatrix(resultado_entrenamiento, entrenamiento$target) # matriz de confusión del resultado del entrenamiento
mcre## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 376 9
## 1 24 412
##
## Accuracy : 0.9598
## 95% CI : (0.944, 0.9722)
## No Information Rate : 0.5128
## P-Value [Acc > NIR] : < 2e-16
##
## Kappa : 0.9195
##
## Mcnemar's Test P-Value : 0.01481
##
## Sensitivity : 0.9400
## Specificity : 0.9786
## Pos Pred Value : 0.9766
## Neg Pred Value : 0.9450
## Prevalence : 0.4872
## Detection Rate : 0.4580
## Detection Prevalence : 0.4689
## Balanced Accuracy : 0.9593
##
## 'Positive' Class : 0
## mcrp <- confusionMatrix(resultado_prueba,prueba$target) # matriz de confusión del resultado de la prueba
mcrp## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 93 3
## 1 6 102
##
## Accuracy : 0.9559
## 95% CI : (0.9179, 0.9796)
## No Information Rate : 0.5147
## P-Value [Acc > NIR] : <2e-16
##
## Kappa : 0.9116
##
## Mcnemar's Test P-Value : 0.505
##
## Sensitivity : 0.9394
## Specificity : 0.9714
## Pos Pred Value : 0.9688
## Neg Pred Value : 0.9444
## Prevalence : 0.4853
## Detection Rate : 0.4559
## Detection Prevalence : 0.4706
## Balanced Accuracy : 0.9554
##
## 'Positive' Class : 0
## resultados <- data.frame("SVM Lineal" = c(mcre$overall["Accuracy"], mcrp$overall["Accuracy"]))
rownames(resultados) <- c("Precision de entrenamiento", "Precision de prueba")
resultados## SVM.Lineal
## Precision de entrenamiento 0.9598051
## Precision de prueba 0.9558824# 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"Conclusion
En conclusion, la Maquina de Vectores de Soporte es una herramienta robusta para la pediccion de diagnostico en enfermedad cardiaca.
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