SVM
Karla López A00839790
2026-02-27
Teoria
El paquete CARET (Classification And REgression Training) es un paquete integral con una amplia variedad de algoritmos para el aprendizaje automC!tico.
Instalar paquetes y llamar librerias
# install.packages("ggplot2") # GrC!ficas
library(ggplot2)
# install.packages("lattice") # Crear grC!ficos
library(lattice)
# install.packages("caret") # Algoritmos de aprendizaje automC!tico
library(caret)
# install.packages("datasets") # Usar bases de datos, en este caso Iris
library(datasets)
# install.packages("DataExplorer") # AnC!lisis Exploratorio
library(DataExplorer)Crear la base de datos
df <- data.frame(iris)Entender la base de datos
summary(df)## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
## str(df)## 'data.frame': 150 obs. of 5 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...# create_report(df)
plot_missing(df)## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## ℹ The deprecated feature was likely used in the DataExplorer package.
## Please report the issue at
## <https://github.com/boxuancui/DataExplorer/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
plot_histogram(df)
plot_correlation(df)
NOTA: La variable que queremos predecir debe tener formato de FACTOR
Partir la base de datos
# Normalmente 80-20
set.seed(123)
renglones_entrenamiento <- createDataPartition(df$Species, p=0.8, list=FALSE)
entrenamiento <- df[renglones_entrenamiento, ]
prueba <- df[-renglones_entrenamiento, ]Distintos tipos de MC)todos para Modelar
Los mC)todos mC!s utilizados para modelar aprendizaje automC!tico son:
- SVM: Support Vector Machine o MC!quina de
Vectores de Soporte. Hay varios subtipos: Lineal (svmLinear), Radial
(svmRadial), PolinC3mico (svmPoly), etc.
- Crbol de DecisiC3n: rpart
- Redes Neuronales: nnet
- Random Forest o Bosques Aleatorios: rf
Modelo 1. SVM Lineal
modelo1 <- train(Species ~ ., data=entrenamiento,
method = "svmLinear", #Cambiar
preProcess = c("scale", "center"),
trControl = trainControl(method="cv", number=10),
tuneGride = data.frame(C=1) #Cambiar
)
resultado_entrenamiento1 <- predict(modelo1, entrenamiento)
resultado_prueba1 <- predict(modelo1, prueba)
# Matriz de ConfusiC3n
# Es una tabla de evaluaciC3n que desglosa el rendimiento del modelo de clasificaciC3n.
# Matriz de ConfusiC3n del Resultado del Entrenamiento
mcre1 <- confusionMatrix(resultado_entrenamiento1, entrenamiento$Species)
mcre1## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 40 0 0
## versicolor 0 39 0
## virginica 0 1 40
##
## Overall Statistics
##
## Accuracy : 0.9917
## 95% CI : (0.9544, 0.9998)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.9875
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.9750 1.0000
## Specificity 1.0000 1.0000 0.9875
## Pos Pred Value 1.0000 1.0000 0.9756
## Neg Pred Value 1.0000 0.9877 1.0000
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3250 0.3333
## Detection Prevalence 0.3333 0.3250 0.3417
## Balanced Accuracy 1.0000 0.9875 0.9938# Matriz de ConfusiC3n del Resultado de la Prueba
mcrp1 <- confusionMatrix(resultado_prueba1, prueba$Species)
mcrp1## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 10 1
## virginica 0 0 9
##
## Overall Statistics
##
## Accuracy : 0.9667
## 95% CI : (0.8278, 0.9992)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : 2.963e-13
##
## Kappa : 0.95
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 0.9000
## Specificity 1.0000 0.9500 1.0000
## Pos Pred Value 1.0000 0.9091 1.0000
## Neg Pred Value 1.0000 1.0000 0.9524
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.3000
## Detection Prevalence 0.3333 0.3667 0.3000
## Balanced Accuracy 1.0000 0.9750 0.9500Modelo 2. SVM Radial
modelo2 <- train(Species ~ ., data=entrenamiento,
method = "svmRadial", #Cambiar
preProcess = c("scale", "center"),
trControl = trainControl(method="cv", number=10),
tuneGride = data.frame(sigma=1, C=1) #Cambiar
)
resultado_entrenamiento2 <- predict(modelo2, entrenamiento)
resultado_prueba2 <- predict(modelo2, prueba)
# Matriz de ConfusiC3n
# Es una tabla de evaluaciC3n que desglosa el rendimiento del modelo de clasificaciC3n.
# Matriz de ConfusiC3n del Resultado del Entrenamiento
mcre2 <- confusionMatrix(resultado_entrenamiento2, entrenamiento$Species)
mcre2## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 40 0 0
## versicolor 0 39 0
## virginica 0 1 40
##
## Overall Statistics
##
## Accuracy : 0.9917
## 95% CI : (0.9544, 0.9998)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.9875
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.9750 1.0000
## Specificity 1.0000 1.0000 0.9875
## Pos Pred Value 1.0000 1.0000 0.9756
## Neg Pred Value 1.0000 0.9877 1.0000
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3250 0.3333
## Detection Prevalence 0.3333 0.3250 0.3417
## Balanced Accuracy 1.0000 0.9875 0.9938# Matriz de ConfusiC3n del Resultado de la Prueba
mcrp2 <- confusionMatrix(resultado_prueba2, prueba$Species)
mcrp2## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 10 2
## virginica 0 0 8
##
## Overall Statistics
##
## Accuracy : 0.9333
## 95% CI : (0.7793, 0.9918)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : 8.747e-12
##
## Kappa : 0.9
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 0.8000
## Specificity 1.0000 0.9000 1.0000
## Pos Pred Value 1.0000 0.8333 1.0000
## Neg Pred Value 1.0000 1.0000 0.9091
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.2667
## Detection Prevalence 0.3333 0.4000 0.2667
## Balanced Accuracy 1.0000 0.9500 0.9000Modelo 3. SVM Polinomico
modelo3 <- train(Species ~ ., data=entrenamiento,
method = "svmPoly", #Cambiar
preProcess = c("scale", "center"),
trControl = trainControl(method="cv", number=10),
tuneGride = data.frame(degree=1, scale=1, C=1) #Cambiar
)
resultado_entrenamiento3 <- predict(modelo3, entrenamiento)
resultado_prueba3 <- predict(modelo3, prueba)
# Matriz de ConfusiC3n
# Es una tabla de evaluaciC3n que desglosa el rendimiento del modelo de clasificaciC3n.
# Matriz de ConfusiC3n del Resultado del Entrenamiento
mcre3 <- confusionMatrix(resultado_entrenamiento3, entrenamiento$Species)
mcre3## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 40 0 0
## versicolor 0 40 4
## virginica 0 0 36
##
## Overall Statistics
##
## Accuracy : 0.9667
## 95% CI : (0.9169, 0.9908)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.95
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 0.9000
## Specificity 1.0000 0.9500 1.0000
## Pos Pred Value 1.0000 0.9091 1.0000
## Neg Pred Value 1.0000 1.0000 0.9524
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.3000
## Detection Prevalence 0.3333 0.3667 0.3000
## Balanced Accuracy 1.0000 0.9750 0.9500# Matriz de ConfusiC3n del Resultado de la Prueba
mcrp3 <- confusionMatrix(resultado_prueba3, prueba$Species)
mcrp3## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 10 2
## virginica 0 0 8
##
## Overall Statistics
##
## Accuracy : 0.9333
## 95% CI : (0.7793, 0.9918)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : 8.747e-12
##
## Kappa : 0.9
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 0.8000
## Specificity 1.0000 0.9000 1.0000
## Pos Pred Value 1.0000 0.8333 1.0000
## Neg Pred Value 1.0000 1.0000 0.9091
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.2667
## Detection Prevalence 0.3333 0.4000 0.2667
## Balanced Accuracy 1.0000 0.9500 0.9000Modelo 4. Arbol de Decisicion
modelo4 <- train(Species ~ ., data=entrenamiento,
method = "rpart", #Cambiar
preProcess = c("scale", "center"),
trControl = trainControl(method="cv", number=10),
tuneLength = 10 #Cambiar
)
resultado_entrenamiento4 <- predict(modelo4, entrenamiento)
resultado_prueba4 <- predict(modelo4, prueba)
# Matriz de ConfusiC3n
# Es una tabla de evaluaciC3n que desglosa el rendimiento del modelo de clasificaciC3n.
# Matriz de ConfusiC3n del Resultado del Entrenamiento
mcre4 <- confusionMatrix(resultado_entrenamiento4, entrenamiento$Species)
mcre4## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 40 0 0
## versicolor 0 39 3
## virginica 0 1 37
##
## Overall Statistics
##
## Accuracy : 0.9667
## 95% CI : (0.9169, 0.9908)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.95
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.9750 0.9250
## Specificity 1.0000 0.9625 0.9875
## Pos Pred Value 1.0000 0.9286 0.9737
## Neg Pred Value 1.0000 0.9872 0.9634
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3250 0.3083
## Detection Prevalence 0.3333 0.3500 0.3167
## Balanced Accuracy 1.0000 0.9688 0.9563# Matriz de ConfusiC3n del Resultado de la Prueba
mcrp4 <- confusionMatrix(resultado_prueba4, prueba$Species)
mcrp4## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 10 2
## virginica 0 0 8
##
## Overall Statistics
##
## Accuracy : 0.9333
## 95% CI : (0.7793, 0.9918)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : 8.747e-12
##
## Kappa : 0.9
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 0.8000
## Specificity 1.0000 0.9000 1.0000
## Pos Pred Value 1.0000 0.8333 1.0000
## Neg Pred Value 1.0000 1.0000 0.9091
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.2667
## Detection Prevalence 0.3333 0.4000 0.2667
## Balanced Accuracy 1.0000 0.9500 0.9000Modelo 5. Redes Neuronales
modelo5 <- train(Species ~ ., data=entrenamiento,
method = "nnet", #Cambiar
preProcess = c("scale", "center"),
trControl = trainControl(method="cv", number=10)
#Cambiar
)## # weights: 11
## initial value 117.009298
## iter 10 value 30.693062
## iter 20 value 4.480530
## iter 30 value 2.124646
## iter 40 value 1.724334
## iter 50 value 1.558463
## iter 60 value 1.384759
## iter 70 value 1.194959
## iter 80 value 1.157489
## iter 90 value 1.037588
## iter 100 value 1.021675
## final value 1.021675
## stopped after 100 iterations
## # weights: 27
## initial value 144.555680
## iter 10 value 7.295675
## iter 20 value 0.951236
## iter 30 value 0.019779
## iter 40 value 0.001778
## final value 0.000054
## converged
## # weights: 43
## initial value 159.941630
## iter 10 value 29.130468
## iter 20 value 2.433214
## iter 30 value 0.203630
## iter 40 value 0.008716
## final value 0.000085
## converged
## # weights: 11
## initial value 122.779692
## iter 10 value 57.486922
## iter 20 value 43.651900
## iter 30 value 43.557151
## final value 43.557011
## converged
## # weights: 27
## initial value 125.993185
## iter 10 value 26.004322
## iter 20 value 19.109050
## iter 30 value 18.927620
## iter 40 value 18.923505
## final value 18.923489
## converged
## # weights: 43
## initial value 162.888687
## iter 10 value 20.938843
## iter 20 value 18.031113
## iter 30 value 17.715120
## iter 40 value 17.596630
## iter 50 value 17.399696
## iter 60 value 17.368518
## iter 70 value 17.368513
## iter 70 value 17.368513
## iter 70 value 17.368513
## final value 17.368513
## converged
## # weights: 11
## initial value 118.505234
## iter 10 value 40.039271
## iter 20 value 5.135436
## iter 30 value 3.734191
## iter 40 value 3.277615
## iter 50 value 3.145069
## iter 60 value 2.954089
## iter 70 value 2.904871
## iter 80 value 2.904015
## iter 90 value 2.903149
## iter 100 value 2.902252
## final value 2.902252
## stopped after 100 iterations
## # weights: 27
## initial value 122.899975
## iter 10 value 7.401054
## iter 20 value 0.334446
## iter 30 value 0.315600
## iter 40 value 0.297078
## iter 50 value 0.290032
## iter 60 value 0.266801
## iter 70 value 0.252113
## iter 80 value 0.242813
## iter 90 value 0.232748
## iter 100 value 0.223962
## final value 0.223962
## stopped after 100 iterations
## # weights: 43
## initial value 130.368788
## iter 10 value 6.085146
## iter 20 value 0.541576
## iter 30 value 0.324721
## iter 40 value 0.310666
## iter 50 value 0.288764
## iter 60 value 0.261876
## iter 70 value 0.241344
## iter 80 value 0.232620
## iter 90 value 0.221434
## iter 100 value 0.211098
## final value 0.211098
## stopped after 100 iterations
## # weights: 11
## initial value 114.821771
## iter 10 value 44.055072
## iter 20 value 11.932704
## iter 30 value 3.206457
## iter 40 value 2.877159
## iter 50 value 2.634047
## iter 60 value 2.327700
## iter 70 value 2.138623
## iter 80 value 1.010075
## iter 90 value 0.852535
## iter 100 value 0.693471
## final value 0.693471
## stopped after 100 iterations
## # weights: 27
## initial value 121.119589
## iter 10 value 4.241406
## iter 20 value 0.011919
## final value 0.000059
## converged
## # weights: 43
## initial value 146.114510
## iter 10 value 5.225415
## iter 20 value 0.151541
## iter 30 value 0.000108
## iter 30 value 0.000056
## iter 30 value 0.000055
## final value 0.000055
## converged
## # weights: 11
## initial value 117.838276
## iter 10 value 43.963261
## iter 20 value 42.933568
## iter 20 value 42.933567
## iter 20 value 42.933567
## final value 42.933567
## converged
## # weights: 27
## initial value 150.828476
## iter 10 value 24.131661
## iter 20 value 19.605948
## iter 30 value 19.530553
## iter 40 value 19.527242
## final value 19.527057
## converged
## # weights: 43
## initial value 125.354310
## iter 10 value 21.660478
## iter 20 value 17.958628
## iter 30 value 17.736044
## iter 40 value 17.719752
## iter 50 value 17.719581
## iter 50 value 17.719581
## iter 50 value 17.719581
## final value 17.719581
## converged
## # weights: 11
## initial value 118.990031
## iter 10 value 46.484314
## iter 20 value 39.225686
## iter 30 value 9.650620
## iter 40 value 4.514044
## iter 50 value 3.865438
## iter 60 value 3.508071
## iter 70 value 3.041838
## iter 80 value 2.965815
## iter 90 value 2.953655
## iter 100 value 2.950243
## final value 2.950243
## stopped after 100 iterations
## # weights: 27
## initial value 122.010199
## iter 10 value 10.036298
## iter 20 value 0.341101
## iter 30 value 0.272783
## iter 40 value 0.249672
## iter 50 value 0.228956
## iter 60 value 0.219568
## iter 70 value 0.215171
## iter 80 value 0.210042
## iter 90 value 0.197683
## iter 100 value 0.188999
## final value 0.188999
## stopped after 100 iterations
## # weights: 43
## initial value 129.722314
## iter 10 value 4.282782
## iter 20 value 0.309622
## iter 30 value 0.272824
## iter 40 value 0.255595
## iter 50 value 0.245836
## iter 60 value 0.226164
## iter 70 value 0.216460
## iter 80 value 0.208423
## iter 90 value 0.204559
## iter 100 value 0.200969
## final value 0.200969
## stopped after 100 iterations
## # weights: 11
## initial value 129.077732
## iter 10 value 50.893757
## iter 20 value 49.341214
## iter 30 value 47.711365
## iter 40 value 45.883507
## iter 50 value 45.433657
## iter 60 value 44.762037
## iter 70 value 20.639842
## iter 80 value 5.307883
## iter 90 value 4.186131
## iter 100 value 3.928824
## final value 3.928824
## stopped after 100 iterations
## # weights: 27
## initial value 129.835217
## iter 10 value 9.829857
## iter 20 value 1.817620
## iter 30 value 0.001192
## final value 0.000064
## converged
## # weights: 43
## initial value 157.390266
## iter 10 value 8.338611
## iter 20 value 1.541313
## iter 30 value 0.005079
## final value 0.000075
## converged
## # weights: 11
## initial value 129.818872
## iter 10 value 75.525777
## iter 20 value 57.964228
## iter 30 value 43.875992
## final value 43.827214
## converged
## # weights: 27
## initial value 130.968358
## iter 10 value 45.968354
## iter 20 value 22.634991
## iter 30 value 21.409538
## iter 40 value 21.358119
## iter 50 value 21.351406
## iter 60 value 21.351186
## final value 21.351182
## converged
## # weights: 43
## initial value 213.775591
## iter 10 value 21.725412
## iter 20 value 18.822673
## iter 30 value 18.513150
## iter 40 value 18.456837
## iter 50 value 18.449317
## final value 18.449280
## converged
## # weights: 11
## initial value 118.962754
## iter 10 value 26.053147
## iter 20 value 6.333793
## iter 30 value 4.570285
## iter 40 value 4.297908
## iter 50 value 4.105559
## iter 60 value 3.903061
## iter 70 value 3.826761
## iter 80 value 3.823960
## iter 90 value 3.823294
## iter 100 value 3.822242
## final value 3.822242
## stopped after 100 iterations
## # weights: 27
## initial value 132.606102
## iter 10 value 22.897922
## iter 20 value 1.809082
## iter 30 value 0.796543
## iter 40 value 0.759424
## iter 50 value 0.614426
## iter 60 value 0.580862
## iter 70 value 0.550861
## iter 80 value 0.541313
## iter 90 value 0.484870
## iter 100 value 0.476444
## final value 0.476444
## stopped after 100 iterations
## # weights: 43
## initial value 108.487853
## iter 10 value 9.006639
## iter 20 value 1.563172
## iter 30 value 0.682425
## iter 40 value 0.633490
## iter 50 value 0.545956
## iter 60 value 0.496924
## iter 70 value 0.473405
## iter 80 value 0.439298
## iter 90 value 0.395353
## iter 100 value 0.365287
## final value 0.365287
## stopped after 100 iterations
## # weights: 11
## initial value 119.337907
## iter 10 value 53.721540
## iter 20 value 51.519354
## iter 30 value 50.670578
## iter 40 value 49.482013
## iter 50 value 40.619548
## iter 60 value 14.073622
## iter 70 value 5.816424
## iter 80 value 4.847922
## iter 90 value 3.451476
## iter 100 value 2.080745
## final value 2.080745
## stopped after 100 iterations
## # weights: 27
## initial value 140.648336
## iter 10 value 49.133514
## iter 20 value 34.297381
## iter 30 value 33.313181
## iter 40 value 17.096108
## iter 50 value 9.985887
## iter 60 value 1.717089
## iter 70 value 0.288081
## iter 80 value 0.001470
## final value 0.000094
## converged
## # weights: 43
## initial value 125.329208
## iter 10 value 4.485921
## iter 20 value 0.228080
## iter 30 value 0.006659
## final value 0.000088
## converged
## # weights: 11
## initial value 124.049774
## iter 10 value 57.031473
## iter 20 value 44.512638
## iter 30 value 44.385507
## final value 44.384992
## converged
## # weights: 27
## initial value 126.045603
## iter 10 value 39.049105
## iter 20 value 22.776253
## iter 30 value 20.135451
## iter 40 value 19.958468
## iter 50 value 19.949415
## iter 60 value 19.949154
## final value 19.949153
## converged
## # weights: 43
## initial value 131.415649
## iter 10 value 23.127808
## iter 20 value 19.282709
## iter 30 value 19.178237
## iter 40 value 19.174237
## iter 50 value 19.173870
## iter 60 value 19.173657
## final value 19.173655
## converged
## # weights: 11
## initial value 121.517667
## iter 10 value 70.104915
## iter 20 value 51.842884
## iter 30 value 37.560847
## iter 40 value 17.174634
## iter 50 value 7.825111
## iter 60 value 4.130372
## iter 70 value 4.047645
## iter 80 value 3.974757
## iter 90 value 3.892953
## iter 100 value 3.880627
## final value 3.880627
## stopped after 100 iterations
## # weights: 27
## initial value 156.724237
## iter 10 value 31.687326
## iter 20 value 13.871604
## iter 30 value 11.415025
## iter 40 value 4.734947
## iter 50 value 1.658477
## iter 60 value 1.395765
## iter 70 value 0.901869
## iter 80 value 0.612757
## iter 90 value 0.549314
## iter 100 value 0.538747
## final value 0.538747
## stopped after 100 iterations
## # weights: 43
## initial value 132.598227
## iter 10 value 13.217554
## iter 20 value 3.162245
## iter 30 value 0.557260
## iter 40 value 0.448381
## iter 50 value 0.415241
## iter 60 value 0.381674
## iter 70 value 0.363224
## iter 80 value 0.355472
## iter 90 value 0.350360
## iter 100 value 0.345746
## final value 0.345746
## stopped after 100 iterations
## # weights: 11
## initial value 132.139541
## iter 10 value 53.874624
## iter 20 value 49.262219
## iter 30 value 49.200325
## iter 40 value 48.489657
## iter 50 value 47.952170
## iter 60 value 47.819369
## iter 70 value 47.659295
## iter 80 value 47.630938
## iter 90 value 47.585539
## iter 100 value 47.552074
## final value 47.552074
## stopped after 100 iterations
## # weights: 27
## initial value 122.797825
## iter 10 value 11.536029
## iter 20 value 1.166215
## iter 30 value 0.002579
## final value 0.000066
## converged
## # weights: 43
## initial value 111.656108
## iter 10 value 4.672364
## iter 20 value 0.141012
## iter 30 value 0.001779
## iter 40 value 0.000649
## final value 0.000068
## converged
## # weights: 11
## initial value 123.343747
## iter 10 value 54.681912
## iter 20 value 43.801812
## iter 30 value 43.746268
## final value 43.745415
## converged
## # weights: 27
## initial value 123.511781
## iter 10 value 25.492386
## iter 20 value 20.202171
## iter 30 value 19.920891
## final value 19.919737
## converged
## # weights: 43
## initial value 109.464495
## iter 10 value 21.689217
## iter 20 value 18.433883
## iter 30 value 18.149227
## iter 40 value 18.115337
## iter 50 value 18.114134
## final value 18.114127
## converged
## # weights: 11
## initial value 128.961908
## iter 10 value 49.469897
## iter 20 value 44.367486
## iter 30 value 21.778378
## iter 40 value 6.844399
## iter 50 value 4.596111
## iter 60 value 4.420636
## iter 70 value 3.971717
## iter 80 value 3.937134
## iter 90 value 3.837716
## iter 100 value 3.831022
## final value 3.831022
## stopped after 100 iterations
## # weights: 27
## initial value 117.146045
## iter 10 value 7.488152
## iter 20 value 0.471752
## iter 30 value 0.421101
## iter 40 value 0.368511
## iter 50 value 0.342218
## iter 60 value 0.331822
## iter 70 value 0.317132
## iter 80 value 0.306914
## iter 90 value 0.296449
## iter 100 value 0.281767
## final value 0.281767
## stopped after 100 iterations
## # weights: 43
## initial value 140.529472
## iter 10 value 19.875220
## iter 20 value 2.954415
## iter 30 value 1.161097
## iter 40 value 1.019260
## iter 50 value 0.890732
## iter 60 value 0.728691
## iter 70 value 0.663176
## iter 80 value 0.613073
## iter 90 value 0.578710
## iter 100 value 0.540378
## final value 0.540378
## stopped after 100 iterations
## # weights: 11
## initial value 127.631173
## iter 10 value 21.873628
## iter 20 value 4.440109
## iter 30 value 0.177788
## iter 40 value 0.094798
## iter 50 value 0.024690
## iter 60 value 0.024059
## iter 70 value 0.023937
## iter 80 value 0.020992
## iter 90 value 0.020810
## iter 100 value 0.020705
## final value 0.020705
## stopped after 100 iterations
## # weights: 27
## initial value 127.012445
## iter 10 value 33.312366
## iter 20 value 1.204810
## iter 30 value 0.003554
## final value 0.000078
## converged
## # weights: 43
## initial value 121.024455
## iter 10 value 1.700603
## iter 20 value 0.003619
## final value 0.000088
## converged
## # weights: 11
## initial value 121.802701
## iter 10 value 67.660888
## iter 20 value 55.525621
## iter 30 value 42.687102
## final value 42.579623
## converged
## # weights: 27
## initial value 116.162681
## iter 10 value 27.378517
## iter 20 value 19.998507
## iter 30 value 19.985737
## iter 40 value 19.985715
## iter 40 value 19.985715
## iter 40 value 19.985715
## final value 19.985715
## converged
## # weights: 43
## initial value 118.143759
## iter 10 value 22.054136
## iter 20 value 17.989103
## iter 30 value 17.619595
## iter 40 value 17.317946
## iter 50 value 17.225372
## iter 60 value 17.222953
## iter 70 value 17.222487
## iter 80 value 17.222437
## iter 80 value 17.222437
## iter 80 value 17.222437
## final value 17.222437
## converged
## # weights: 11
## initial value 118.355062
## iter 10 value 49.818324
## iter 20 value 38.647325
## iter 30 value 15.844677
## iter 40 value 2.582960
## iter 50 value 2.136811
## iter 60 value 2.035498
## iter 70 value 2.033350
## iter 80 value 2.021573
## iter 90 value 1.995371
## iter 100 value 1.994256
## final value 1.994256
## stopped after 100 iterations
## # weights: 27
## initial value 130.821997
## iter 10 value 19.933529
## iter 20 value 0.975068
## iter 30 value 0.473534
## iter 40 value 0.432481
## iter 50 value 0.372884
## iter 60 value 0.295422
## iter 70 value 0.276597
## iter 80 value 0.263857
## iter 90 value 0.216302
## iter 100 value 0.209542
## final value 0.209542
## stopped after 100 iterations
## # weights: 43
## initial value 144.732840
## iter 10 value 10.040236
## iter 20 value 0.345443
## iter 30 value 0.298449
## iter 40 value 0.270041
## iter 50 value 0.225858
## iter 60 value 0.195855
## iter 70 value 0.176125
## iter 80 value 0.164022
## iter 90 value 0.152679
## iter 100 value 0.150088
## final value 0.150088
## stopped after 100 iterations
## # weights: 11
## initial value 129.869113
## iter 10 value 50.042465
## iter 20 value 49.908565
## iter 30 value 49.906746
## final value 49.906672
## converged
## # weights: 27
## initial value 136.216049
## iter 10 value 10.058478
## iter 20 value 0.927014
## iter 30 value 0.000386
## final value 0.000089
## converged
## # weights: 43
## initial value 116.240399
## iter 10 value 2.687573
## iter 20 value 0.910154
## iter 30 value 0.001158
## final value 0.000058
## converged
## # weights: 11
## initial value 122.548705
## iter 10 value 48.475518
## iter 20 value 43.263734
## final value 43.262103
## converged
## # weights: 27
## initial value 151.969882
## iter 10 value 29.866683
## iter 20 value 20.041938
## iter 30 value 19.181326
## iter 40 value 18.658426
## iter 50 value 18.646346
## iter 60 value 18.646228
## final value 18.646221
## converged
## # weights: 43
## initial value 123.857709
## iter 10 value 21.867276
## iter 20 value 18.327082
## iter 30 value 18.061485
## iter 40 value 18.034598
## iter 50 value 18.032834
## final value 18.032819
## converged
## # weights: 11
## initial value 133.691360
## iter 10 value 27.686299
## iter 20 value 3.688826
## iter 30 value 2.998116
## iter 40 value 2.982774
## iter 50 value 2.975593
## iter 60 value 2.973846
## iter 70 value 2.972998
## iter 80 value 2.972919
## final value 2.972915
## converged
## # weights: 27
## initial value 121.910769
## iter 10 value 4.186175
## iter 20 value 1.397080
## iter 30 value 0.429392
## iter 40 value 0.403901
## iter 50 value 0.371671
## iter 60 value 0.353374
## iter 70 value 0.346994
## iter 80 value 0.340640
## iter 90 value 0.326373
## iter 100 value 0.320888
## final value 0.320888
## stopped after 100 iterations
## # weights: 43
## initial value 150.467908
## iter 10 value 2.516940
## iter 20 value 0.515624
## iter 30 value 0.419086
## iter 40 value 0.400951
## iter 50 value 0.356741
## iter 60 value 0.321748
## iter 70 value 0.269242
## iter 80 value 0.257949
## iter 90 value 0.244026
## iter 100 value 0.230916
## final value 0.230916
## stopped after 100 iterations
## # weights: 11
## initial value 130.397834
## iter 10 value 50.573102
## iter 20 value 49.909353
## final value 49.906794
## converged
## # weights: 27
## initial value 142.795978
## iter 10 value 8.325156
## iter 20 value 1.733508
## iter 30 value 0.008474
## final value 0.000056
## converged
## # weights: 43
## initial value 147.890271
## iter 10 value 14.812090
## iter 20 value 0.484823
## iter 30 value 0.000580
## final value 0.000074
## converged
## # weights: 11
## initial value 122.928070
## iter 10 value 67.652212
## iter 20 value 46.324443
## iter 30 value 44.176746
## final value 44.154954
## converged
## # weights: 27
## initial value 118.635144
## iter 10 value 27.365477
## iter 20 value 20.236166
## iter 30 value 19.919856
## final value 19.919323
## converged
## # weights: 43
## initial value 123.713602
## iter 10 value 23.115917
## iter 20 value 19.181439
## iter 30 value 19.146092
## iter 40 value 19.135538
## iter 50 value 19.135363
## iter 60 value 19.135305
## final value 19.135297
## converged
## # weights: 11
## initial value 124.268451
## iter 10 value 50.415686
## iter 20 value 50.122205
## iter 30 value 50.099925
## iter 40 value 50.039219
## iter 50 value 48.795443
## iter 60 value 45.810850
## iter 70 value 44.976509
## iter 80 value 44.652199
## iter 90 value 43.655722
## iter 100 value 21.549290
## final value 21.549290
## stopped after 100 iterations
## # weights: 27
## initial value 121.168989
## iter 10 value 12.887627
## iter 20 value 1.421530
## iter 30 value 0.596446
## iter 40 value 0.525751
## iter 50 value 0.482633
## iter 60 value 0.455870
## iter 70 value 0.441781
## iter 80 value 0.405097
## iter 90 value 0.379758
## iter 100 value 0.359516
## final value 0.359516
## stopped after 100 iterations
## # weights: 43
## initial value 154.331260
## iter 10 value 9.135896
## iter 20 value 1.287634
## iter 30 value 0.536307
## iter 40 value 0.516772
## iter 50 value 0.444990
## iter 60 value 0.422222
## iter 70 value 0.414269
## iter 80 value 0.388936
## iter 90 value 0.382924
## iter 100 value 0.374877
## final value 0.374877
## stopped after 100 iterations
## # weights: 11
## initial value 119.161548
## iter 10 value 49.944558
## iter 20 value 48.322924
## iter 30 value 46.428533
## iter 40 value 46.268965
## iter 50 value 46.227049
## iter 60 value 46.155518
## iter 70 value 45.699558
## iter 80 value 37.848275
## iter 90 value 7.852629
## iter 100 value 4.666912
## final value 4.666912
## stopped after 100 iterations
## # weights: 27
## initial value 121.994742
## iter 10 value 4.269484
## iter 20 value 0.323645
## iter 30 value 0.000228
## final value 0.000073
## converged
## # weights: 43
## initial value 120.712721
## iter 10 value 11.633228
## iter 20 value 1.928801
## iter 30 value 0.089821
## iter 40 value 0.000470
## final value 0.000048
## converged
## # weights: 11
## initial value 125.023647
## iter 10 value 52.033224
## iter 20 value 43.475534
## iter 30 value 43.428235
## final value 43.428214
## converged
## # weights: 27
## initial value 150.243876
## iter 10 value 32.636911
## iter 20 value 21.467254
## iter 30 value 19.692563
## iter 40 value 19.331538
## iter 50 value 19.321372
## iter 60 value 19.321093
## final value 19.321088
## converged
## # weights: 43
## initial value 137.965234
## iter 10 value 22.585768
## iter 20 value 18.845985
## iter 30 value 18.359487
## iter 40 value 18.060579
## iter 50 value 17.805017
## iter 60 value 17.768557
## iter 70 value 17.768156
## iter 80 value 17.768097
## final value 17.768090
## converged
## # weights: 11
## initial value 127.936624
## iter 10 value 64.892982
## iter 20 value 52.457973
## iter 30 value 51.893780
## iter 40 value 46.822596
## iter 50 value 20.931506
## iter 60 value 5.855746
## iter 70 value 4.449348
## iter 80 value 3.934110
## iter 90 value 3.778873
## iter 100 value 3.726881
## final value 3.726881
## stopped after 100 iterations
## # weights: 27
## initial value 124.538161
## iter 10 value 19.935878
## iter 20 value 1.179326
## iter 30 value 0.515886
## iter 40 value 0.495212
## iter 50 value 0.459550
## iter 60 value 0.425014
## iter 70 value 0.408161
## iter 80 value 0.387730
## iter 90 value 0.360044
## iter 100 value 0.337881
## final value 0.337881
## stopped after 100 iterations
## # weights: 43
## initial value 133.979878
## iter 10 value 12.011468
## iter 20 value 0.941094
## iter 30 value 0.495870
## iter 40 value 0.477345
## iter 50 value 0.464609
## iter 60 value 0.425356
## iter 70 value 0.381548
## iter 80 value 0.333472
## iter 90 value 0.319381
## iter 100 value 0.304457
## final value 0.304457
## stopped after 100 iterations
## # weights: 11
## initial value 129.556405
## iter 10 value 49.342383
## iter 20 value 35.419965
## iter 30 value 5.074745
## iter 40 value 2.940088
## iter 50 value 2.543858
## iter 60 value 2.312929
## iter 70 value 2.281995
## iter 80 value 2.059116
## iter 90 value 2.012601
## iter 100 value 1.857343
## final value 1.857343
## stopped after 100 iterations
## # weights: 27
## initial value 155.931952
## iter 10 value 9.651371
## iter 20 value 1.510703
## iter 30 value 0.025766
## iter 40 value 0.003870
## iter 50 value 0.000229
## final value 0.000085
## converged
## # weights: 43
## initial value 139.919182
## iter 10 value 7.001515
## iter 20 value 2.265308
## iter 30 value 0.480211
## iter 40 value 0.046809
## iter 50 value 0.001016
## iter 60 value 0.000148
## final value 0.000085
## converged
## # weights: 11
## initial value 137.379619
## iter 10 value 58.587747
## iter 20 value 45.493964
## final value 43.369230
## converged
## # weights: 27
## initial value 122.183968
## iter 10 value 34.103176
## iter 20 value 19.778653
## iter 30 value 19.482816
## iter 40 value 19.412523
## iter 50 value 19.406639
## final value 19.406612
## converged
## # weights: 43
## initial value 127.464513
## iter 10 value 20.014903
## iter 20 value 18.283826
## iter 30 value 17.864550
## iter 40 value 17.854806
## iter 50 value 17.852930
## final value 17.852879
## converged
## # weights: 11
## initial value 126.686154
## iter 10 value 47.126881
## iter 20 value 13.760512
## iter 30 value 5.663815
## iter 40 value 4.107040
## iter 50 value 3.970174
## iter 60 value 3.913599
## iter 70 value 3.760966
## iter 80 value 3.757224
## iter 90 value 3.753338
## iter 100 value 3.748772
## final value 3.748772
## stopped after 100 iterations
## # weights: 27
## initial value 144.486253
## iter 10 value 4.284520
## iter 20 value 0.488472
## iter 30 value 0.440576
## iter 40 value 0.431107
## iter 50 value 0.424352
## iter 60 value 0.415746
## iter 70 value 0.413581
## iter 80 value 0.410783
## iter 90 value 0.409591
## iter 100 value 0.408124
## final value 0.408124
## stopped after 100 iterations
## # weights: 43
## initial value 127.608663
## iter 10 value 4.647335
## iter 20 value 1.221540
## iter 30 value 0.611939
## iter 40 value 0.560234
## iter 50 value 0.535709
## iter 60 value 0.477525
## iter 70 value 0.419169
## iter 80 value 0.399554
## iter 90 value 0.391996
## iter 100 value 0.375996
## final value 0.375996
## stopped after 100 iterations
## # weights: 11
## initial value 138.169000
## iter 10 value 58.741341
## iter 20 value 46.635586
## final value 46.598157
## convergedresultado_entrenamiento5 <- predict(modelo5, entrenamiento)
resultado_prueba5 <- predict(modelo5, prueba)
# Matriz de ConfusiC3n
# Es una tabla de evaluaciC3n que desglosa el rendimiento del modelo de clasificaciC3n.
# Matriz de ConfusiC3n del Resultado del Entrenamiento
mcre5 <- confusionMatrix(resultado_entrenamiento5, entrenamiento$Species)
mcre5## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 40 0 0
## versicolor 0 36 0
## virginica 0 4 40
##
## Overall Statistics
##
## Accuracy : 0.9667
## 95% CI : (0.9169, 0.9908)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.95
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.9000 1.0000
## Specificity 1.0000 1.0000 0.9500
## Pos Pred Value 1.0000 1.0000 0.9091
## Neg Pred Value 1.0000 0.9524 1.0000
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3000 0.3333
## Detection Prevalence 0.3333 0.3000 0.3667
## Balanced Accuracy 1.0000 0.9500 0.9750# Matriz de ConfusiC3n del Resultado de la Prueba
mcrp5 <- confusionMatrix(resultado_prueba5, prueba$Species)
mcrp5## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 9 0
## virginica 0 1 10
##
## Overall Statistics
##
## Accuracy : 0.9667
## 95% CI : (0.8278, 0.9992)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : 2.963e-13
##
## Kappa : 0.95
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.9000 1.0000
## Specificity 1.0000 1.0000 0.9500
## Pos Pred Value 1.0000 1.0000 0.9091
## Neg Pred Value 1.0000 0.9524 1.0000
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3000 0.3333
## Detection Prevalence 0.3333 0.3000 0.3667
## Balanced Accuracy 1.0000 0.9500 0.9750Modelo 6. Bosques Aleatorios
modelo6 <- train(Species ~ ., data=entrenamiento,
method = "rf", #Cambiar
preProcess = c("scale", "center"),
trControl = trainControl(method="cv", number=10),
tuneGrid = expand.grid(mtry = c(2,4,6)) #Cambiar
)## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid range
## Warning in randomForest.default(x, y, mtry = param$mtry, ...): invalid mtry:
## reset to within valid rangeresultado_entrenamiento6 <- predict(modelo6, entrenamiento)
resultado_prueba6 <- predict(modelo6, prueba)
# Matriz de ConfusiC3n
# Es una tabla de evaluaciC3n que desglosa el rendimiento del modelo de clasificaciC3n.
# Matriz de ConfusiC3n del Resultado del Entrenamiento
mcre6 <- confusionMatrix(resultado_entrenamiento6, entrenamiento$Species)
mcre6## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 40 0 0
## versicolor 0 40 0
## virginica 0 0 40
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.9697, 1)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 1.0000
## Specificity 1.0000 1.0000 1.0000
## Pos Pred Value 1.0000 1.0000 1.0000
## Neg Pred Value 1.0000 1.0000 1.0000
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.3333
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 1.0000 1.0000# Matriz de ConfusiC3n del Resultado de la Prueba
mcrp6 <- confusionMatrix(resultado_prueba6, prueba$Species)
mcrp6## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 10 2
## virginica 0 0 8
##
## Overall Statistics
##
## Accuracy : 0.9333
## 95% CI : (0.7793, 0.9918)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : 8.747e-12
##
## Kappa : 0.9
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 0.8000
## Specificity 1.0000 0.9000 1.0000
## Pos Pred Value 1.0000 0.8333 1.0000
## Neg Pred Value 1.0000 1.0000 0.9091
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.2667
## Detection Prevalence 0.3333 0.4000 0.2667
## Balanced Accuracy 1.0000 0.9500 0.9000Tabla de Resultados
resultados <- data.frame(
"svmLinear" = c(mcre1$overall["Accuracy"], mcrp1$overall["Accuracy"]),
"svmRadial" = c(mcre2$overall["Accuracy"], mcrp2$overall["Accuracy"]),
"svmPoly" = c(mcre3$overall["Accuracy"], mcrp3$overall["Accuracy"]),
"rpart" = c(mcre4$overall["Accuracy"], mcrp4$overall["Accuracy"]),
"nnet" = c(mcre5$overall["Accuracy"], mcrp5$overall["Accuracy"]),
"rf" = c(mcre6$overall["Accuracy"], mcrp6$overall["Accuracy"])
)
rownames(resultados) <- c("PrecisiC3n de entrenamiento", "PrecisiC3n de prueba")
resultados## svmLinear svmRadial svmPoly rpart nnet
## PrecisiC3n de entrenamiento 0.9916667 0.9916667 0.9666667 0.9666667 0.9666667
## PrecisiC3n de prueba 0.9666667 0.9333333 0.9333333 0.9333333 0.9666667
## rf
## PrecisiC3n de entrenamiento 1.0000000
## PrecisiC3n de prueba 0.9333333Conclusiones
Se evaluaron seis modelos de clasificación utilizando el paquete caret: SVM Lineal, SVM Radial, SVM Polinómico, Árbol de Decisión (rpart), Red Neuronal (nnet) y Random Forest, con el objetivo de predecir la especie de la flor a partir de sus características físicas.
Los resultados muestran que todos los modelos obtuvieron un alto nivel de precisión, con valores de accuracy en los datos de prueba entre 93.33% y 96.67%, lo que indica que las variables utilizadas tienen una fuerte capacidad predictiva. El modelo SVM Lineal y la Red Neuronal presentaron el mejor desempeño general, alcanzando un 99% y 96.67% de accuracy en los datos de prueba, lo que demuestra una excelente capacidad de generalización.
Por otro lado, el modelo Random Forest obtuvo 100% de accuracy en entrenamiento, pero menor precisión en los datos de prueba de 93%, lo que puede indicar un ligero sobreajuste, es decir, que el modelo trabaja bien con los datos actuales de entrenamiento pero al momento de agregar nuevos, no es el mejor prediciendo a comparacion de los otros modelos.
En general, todos los modelos son adecuados para este problema; sin embargo, el SVM Lineal se considera el mejor modelo, ya que tiebe una alta precisión tanto en entrenamiento como en prueba, mostrando un buen equilibrio entre aprendizaje y capacidad de predicción en nuevos datos. Si nos adentramos a otros parametros del SVM Lineal, podemos ver que en la matriz de confusion el modelo clasificó correctamente 29 de 30 observaciones, cometiendo solo un error. Ademas, el valor de Kappa de 95% indica una concordancia alta entre las predicciones y los valores reales, confirmando que el modelo es altamente confiable. Por otro lado, la sensibilidad y especificidad cercanas a 1 demuestran que el modelo identifica correctamente cada especie y rara vez las confunde entre sí. En general, el modelo tiene una alta capacidad predictiva y es preciso para la clasificación.