SVM
Agustín Gómez Perez A01732897
2024-08-22
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: latticelibrary(e1071)Crear la base de datos
df <- read.csv("/Users/agustingomezperez/Desktop/Inteligencia Artificial/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$target, p=0.8, list=FALSE)
entrenamiento <- df[renglones_entrenamiento, ]
prueba <- df[-renglones_entrenamiento, ]Construir el modelo SVM linear
modelo <- svm(target ~ ., data = entrenamiento, kernel = "linear")
resultado_entrenamiento <- predict(modelo,entrenamiento)
resultado_prueba <- predict(modelo,prueba)Matriz de Confusión
mcre <- confusionMatrix(resultado_entrenamiento, entrenamiento$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$target) # matriz de confusión del resultado de la prueba
mcrp## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 78 10
## 1 21 95
##
## Accuracy : 0.848
## 95% CI : (0.7913, 0.8944)
## No Information Rate : 0.5147
## P-Value [Acc > NIR] : < 2e-16
##
## Kappa : 0.6948
##
## Mcnemar's Test P-Value : 0.07249
##
## Sensitivity : 0.7879
## Specificity : 0.9048
## Pos Pred Value : 0.8864
## Neg Pred Value : 0.8190
## Prevalence : 0.4853
## Detection Rate : 0.3824
## Detection Prevalence : 0.4314
## Balanced Accuracy : 0.8463
##
## 'Positive' Class : 0
## #Resultados
resultados <- data.frame("SVM linear" = c(mcre$overall["Accuracy"], mcrp$overall["Accuracy"]))
rownames(resultados) <- c("Precision de entrenamiento", "Precision de prueba")
resultados## SVM.linear
## Precision de entrenamiento 0.8343484
## Precision de prueba 0.8480392Obtener 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"#Conclusiones
La maquina de vectores de soporte es una herramienta robusta para la predicción de diagnostico en enfermedad cardiaca.
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