Heart
Romery Luna A01749837
2025-03-01
Instalar paquetes y llamar librerías
#install.packages("e1071")
library(e1071)
#install.packages("caret")
library(caret)## Cargando paquete requerido: ggplot2## Cargando paquete requerido: latticeCargar la base
df <- read.csv("C:\\Users\\rylun\\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
# Partir la base de datos
set.seed(123)
renglones_entrenamiento <- createDataPartition(df$target, p=0.8, list=FALSE)
entrenamiento <- df[renglones_entrenamiento, ]
prueba <- df[-renglones_entrenamiento, ]Modelo SVM Linear
modelo <- svm(target ~ ., data = entrenamiento, kernel = "linear")
resultado_entrenamiento <- predict(modelo,entrenamiento)
resultado_prueba <- predict(modelo,prueba)Matriz de Confusión
mcre <- confusionMatrix(resultado_entrenamiento, entrenamiento$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
## 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 0.8480392Predicción
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"Conclusión
El uso de Máquinas de Vectores de Soporte (SVM) en el análisis de datos médicos ha demostrado ser una técnica efectiva para la clasificación de pacientes con enfermedad cardíaca.
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