Teoria

El paquete CARET (Classification And Regression Training) es un paquete integral con una amplia variedad de algoritmos para el aprendizaje automatico.

Instalar paquetes y cargar librerias 

#install.packages("ggplot2") # Gráficas
library(ggplot2)
#install.packages("lattice") # Crear gráficos
library(lattice)
#install.packages ("caret") # Algoritmos de aprendizaje automático
library (caret)
#install.packages ("datasets") # Usar bases de datos, en este caso Iris
library(datasets)
#install.packages ("DataExplorer") # Análisis Exploratorio
library (DataExplorer)
#install.packages("kernlab")
library(kernlab)
## 
## Attaching package: 'kernlab'
## The following object is masked from 'package:ggplot2':
## 
##     alpha
#install.packages("randomForest")
library(ranger)
library(randomForest)
## randomForest 4.7-1.2
## Type rfNews() to see new features/changes/bug fixes.
## 
## Attaching package: 'randomForest'
## The following object is masked from 'package:ranger':
## 
##     importance
## The following object is masked from 'package:ggplot2':
## 
##     margin

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 ...
plot_missing(df)

plot_histogram(df)

plot_correlation(df)

Partir la base de datos 

# Normalmente 80-20
set.seed(123)
renglones_entrenamiento <- createDataPartition(df$Species, p=0.8, list = FALSE)
entrenamiento <- iris[renglones_entrenamiento, ]
prueba <- iris[-renglones_entrenamiento, ]

Distintos tipos de métodos para Modelar

Los métodos más utilizados para modelar aprendizaje automático:

  • SVM: Support Vector Machine o Máquina de Vectores de Soporte. Hay varios subtipos: Lineal (svmLinear), Radial (svmRadial), Polinómico (svmPoly), etc.

  • Árbol de Decisión: 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)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre1 <- confusionMatrix(resultado_entrenamiento1, entrenamiento$Species)
mcre1
## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         40          0         0
##   versicolor      0         39         0
##   virginica       0          1        40
## 
## Overall Statistics
##                                           
##                Accuracy : 0.9917          
##                  95% CI : (0.9544, 0.9998)
##     No Information Rate : 0.3333          
##     P-Value [Acc > NIR] : < 2.2e-16       
##                                           
##                   Kappa : 0.9875          
##                                           
##  Mcnemar's Test P-Value : NA              
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            0.9750           1.0000
## Specificity                 1.0000            1.0000           0.9875
## Pos Pred Value              1.0000            1.0000           0.9756
## Neg Pred Value              1.0000            0.9877           1.0000
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3250           0.3333
## Detection Prevalence        0.3333            0.3250           0.3417
## Balanced Accuracy           1.0000            0.9875           0.9938
# Matriz de confusion del resultado de la prueba
mcrp1 <- confusionMatrix(resultado_prueba1, prueba$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           0.9500

Modelo 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)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre2 <- confusionMatrix(resultado_entrenamiento2, entrenamiento$Species)
mcre2
## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         40          0         0
##   versicolor      0         39         0
##   virginica       0          1        40
## 
## Overall Statistics
##                                           
##                Accuracy : 0.9917          
##                  95% CI : (0.9544, 0.9998)
##     No Information Rate : 0.3333          
##     P-Value [Acc > NIR] : < 2.2e-16       
##                                           
##                   Kappa : 0.9875          
##                                           
##  Mcnemar's Test P-Value : NA              
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            0.9750           1.0000
## Specificity                 1.0000            1.0000           0.9875
## Pos Pred Value              1.0000            1.0000           0.9756
## Neg Pred Value              1.0000            0.9877           1.0000
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3250           0.3333
## Detection Prevalence        0.3333            0.3250           0.3417
## Balanced Accuracy           1.0000            0.9875           0.9938
# Matriz de confusion del resultado de la prueba
mcrp2 <- confusionMatrix(resultado_prueba2, prueba$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           0.9000

Modelo 3. SVM Poly 

modelo3 <- train(Species ~ ., data=entrenamiento,
                 method = "svmRadial", #Cambiar
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneGride = data.frame(degree=1, C=1, scale=1) #Cambiar
                 )

resultado_entrenamiento3 <- predict(modelo3, entrenamiento)
resultado_prueba3 <- predict(modelo3, prueba)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre3 <- confusionMatrix(resultado_entrenamiento3, entrenamiento$Species)
mcre3
## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         40          0         0
##   versicolor      0         38         0
##   virginica       0          2        40
## 
## Overall Statistics
##                                          
##                Accuracy : 0.9833         
##                  95% CI : (0.9411, 0.998)
##     No Information Rate : 0.3333         
##     P-Value [Acc > NIR] : < 2.2e-16      
##                                          
##                   Kappa : 0.975          
##                                          
##  Mcnemar's Test P-Value : NA             
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            0.9500           1.0000
## Specificity                 1.0000            1.0000           0.9750
## Pos Pred Value              1.0000            1.0000           0.9524
## Neg Pred Value              1.0000            0.9756           1.0000
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3167           0.3333
## Detection Prevalence        0.3333            0.3167           0.3500
## Balanced Accuracy           1.0000            0.9750           0.9875
# Matriz de confusion del resultado de la prueba
mcrp3 <- confusionMatrix(resultado_prueba3, prueba$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           0.9000

Modelo 4. Arboles de decision 

modelo4 <- train(Species ~ ., data=entrenamiento,
                 method = "rpart", #Cambiar
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneLength = 10
                 )

resultado_entrenamiento4 <- predict(modelo4, entrenamiento)
resultado_prueba4 <- predict(modelo3, prueba)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre4 <- confusionMatrix(resultado_entrenamiento4, entrenamiento$Species)
mcre4
## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         40          0         0
##   versicolor      0         39         3
##   virginica       0          1        37
## 
## Overall Statistics
##                                           
##                Accuracy : 0.9667          
##                  95% CI : (0.9169, 0.9908)
##     No Information Rate : 0.3333          
##     P-Value [Acc > NIR] : < 2.2e-16       
##                                           
##                   Kappa : 0.95            
##                                           
##  Mcnemar's Test P-Value : NA              
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            0.9750           0.9250
## Specificity                 1.0000            0.9625           0.9875
## Pos Pred Value              1.0000            0.9286           0.9737
## Neg Pred Value              1.0000            0.9872           0.9634
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3250           0.3083
## Detection Prevalence        0.3333            0.3500           0.3167
## Balanced Accuracy           1.0000            0.9688           0.9563
# Matriz de confusion del resultado de la prueba
mcrp4 <- confusionMatrix(resultado_prueba4, prueba$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           0.9000

Modelo 5. Redes Neuronales 

modelo5 <- train(Species ~ ., data=entrenamiento,
                 method = "nnet", #Cambiar
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10)
                 
                 )
## # weights:  11
## initial  value 119.364237 
## iter  10 value 50.064888
## iter  20 value 48.670264
## iter  30 value 47.831568
## iter  40 value 47.729855
## iter  50 value 47.630183
## iter  60 value 46.018647
## iter  70 value 44.920599
## iter  80 value 42.797890
## iter  90 value 8.375848
## iter 100 value 2.381837
## final  value 2.381837 
## stopped after 100 iterations
## # weights:  27
## initial  value 123.793414 
## iter  10 value 5.868269
## iter  20 value 0.081242
## iter  30 value 0.000303
## final  value 0.000076 
## converged
## # weights:  43
## initial  value 122.731863 
## iter  10 value 3.624311
## iter  20 value 0.010911
## final  value 0.000055 
## converged
## # weights:  11
## initial  value 118.612128 
## iter  10 value 59.262402
## iter  20 value 44.973063
## iter  30 value 43.405883
## final  value 43.399628 
## converged
## # weights:  27
## initial  value 135.631812 
## iter  10 value 26.153324
## iter  20 value 19.519935
## iter  30 value 19.159834
## iter  40 value 19.141040
## final  value 19.140707 
## converged
## # weights:  43
## initial  value 121.810346 
## iter  10 value 25.282006
## iter  20 value 18.168535
## iter  30 value 18.106805
## iter  40 value 18.042974
## iter  50 value 17.658982
## iter  60 value 17.547503
## iter  70 value 17.312348
## iter  80 value 17.282247
## iter  90 value 17.277857
## iter 100 value 17.277302
## final  value 17.277302 
## stopped after 100 iterations
## # weights:  11
## initial  value 133.417421 
## iter  10 value 50.157026
## iter  20 value 49.977347
## iter  30 value 49.964410
## iter  40 value 48.859866
## iter  50 value 31.567030
## iter  60 value 7.857236
## iter  70 value 2.148236
## iter  80 value 2.065323
## iter  90 value 2.039104
## iter 100 value 1.999937
## final  value 1.999937 
## stopped after 100 iterations
## # weights:  27
## initial  value 110.745240 
## iter  10 value 3.752499
## iter  20 value 0.193975
## iter  30 value 0.185500
## iter  40 value 0.176438
## iter  50 value 0.167373
## iter  60 value 0.164644
## iter  70 value 0.162408
## iter  80 value 0.159110
## iter  90 value 0.155530
## iter 100 value 0.152384
## final  value 0.152384 
## stopped after 100 iterations
## # weights:  43
## initial  value 116.918727 
## iter  10 value 3.580954
## iter  20 value 0.259672
## iter  30 value 0.237494
## iter  40 value 0.221850
## iter  50 value 0.183126
## iter  60 value 0.174202
## iter  70 value 0.158959
## iter  80 value 0.145791
## iter  90 value 0.141314
## iter 100 value 0.131996
## final  value 0.131996 
## stopped after 100 iterations
## # weights:  11
## initial  value 131.916635 
## iter  10 value 52.434019
## iter  20 value 49.536656
## iter  30 value 48.762687
## iter  40 value 48.424392
## iter  50 value 47.459406
## iter  60 value 36.638325
## iter  70 value 7.255328
## iter  80 value 3.432719
## iter  90 value 3.028823
## iter 100 value 2.715820
## final  value 2.715820 
## stopped after 100 iterations
## # weights:  27
## initial  value 116.560224 
## iter  10 value 22.377209
## iter  20 value 1.434404
## iter  30 value 0.015301
## final  value 0.000063 
## converged
## # weights:  43
## initial  value 118.392692 
## iter  10 value 3.944569
## iter  20 value 0.306409
## iter  30 value 0.004517
## iter  40 value 0.000251
## final  value 0.000083 
## converged
## # weights:  11
## initial  value 118.460051 
## iter  10 value 64.880183
## iter  20 value 50.068934
## iter  30 value 43.488436
## final  value 43.487537 
## converged
## # weights:  27
## initial  value 126.586947 
## iter  10 value 43.279225
## iter  20 value 21.224741
## iter  30 value 20.749248
## iter  40 value 20.749048
## final  value 20.749047 
## converged
## # weights:  43
## initial  value 151.937613 
## iter  10 value 23.734242
## iter  20 value 18.753404
## iter  30 value 18.118863
## iter  40 value 17.940374
## iter  50 value 17.930575
## iter  60 value 17.929988
## iter  70 value 17.929922
## final  value 17.929921 
## converged
## # weights:  11
## initial  value 132.070198 
## iter  10 value 52.355646
## iter  20 value 48.275663
## iter  30 value 18.372238
## iter  40 value 3.649689
## iter  50 value 3.406804
## iter  60 value 3.276053
## iter  70 value 3.273048
## iter  80 value 3.268892
## iter  90 value 3.259668
## iter 100 value 3.258851
## final  value 3.258851 
## stopped after 100 iterations
## # weights:  27
## initial  value 113.529901 
## iter  10 value 6.241670
## iter  20 value 1.208916
## iter  30 value 0.397811
## iter  40 value 0.386273
## iter  50 value 0.368184
## iter  60 value 0.361141
## iter  70 value 0.359369
## iter  80 value 0.350759
## iter  90 value 0.347615
## iter 100 value 0.342804
## final  value 0.342804 
## stopped after 100 iterations
## # weights:  43
## initial  value 111.717272 
## iter  10 value 3.416090
## iter  20 value 0.377952
## iter  30 value 0.317075
## iter  40 value 0.312838
## iter  50 value 0.309274
## iter  60 value 0.303265
## iter  70 value 0.297596
## iter  80 value 0.295684
## iter  90 value 0.294852
## iter 100 value 0.289916
## final  value 0.289916 
## stopped after 100 iterations
## # weights:  11
## initial  value 128.608870 
## iter  10 value 27.776794
## iter  20 value 5.087471
## iter  30 value 3.563326
## iter  40 value 3.394366
## iter  50 value 3.217410
## iter  60 value 2.980093
## iter  70 value 2.883858
## iter  80 value 2.838704
## iter  90 value 2.675153
## iter 100 value 2.610229
## final  value 2.610229 
## stopped after 100 iterations
## # weights:  27
## initial  value 118.190633 
## iter  10 value 13.123265
## iter  20 value 1.221350
## iter  30 value 0.000379
## final  value 0.000081 
## converged
## # weights:  43
## initial  value 137.653895 
## iter  10 value 5.426639
## iter  20 value 0.178492
## iter  30 value 0.000237
## final  value 0.000096 
## converged
## # weights:  11
## initial  value 119.446713 
## iter  10 value 64.603563
## iter  20 value 43.882482
## iter  30 value 43.662641
## final  value 43.660320 
## converged
## # weights:  27
## initial  value 121.223486 
## iter  10 value 42.509333
## iter  20 value 21.539342
## iter  30 value 20.363180
## iter  40 value 20.229352
## iter  50 value 20.224014
## final  value 20.223979 
## converged
## # weights:  43
## initial  value 148.735730 
## iter  10 value 24.147018
## iter  20 value 19.161635
## iter  30 value 19.000060
## iter  40 value 18.956075
## iter  50 value 18.954353
## final  value 18.954194 
## converged
## # weights:  11
## initial  value 122.206168 
## iter  10 value 28.418454
## iter  20 value 5.277740
## iter  30 value 4.113257
## iter  40 value 4.004701
## iter  50 value 3.877920
## iter  60 value 3.872033
## iter  70 value 3.871948
## iter  80 value 3.871938
## final  value 3.871933 
## converged
## # weights:  27
## initial  value 119.896820 
## iter  10 value 9.755985
## iter  20 value 2.721336
## iter  30 value 0.781265
## iter  40 value 0.654267
## iter  50 value 0.538525
## iter  60 value 0.490774
## iter  70 value 0.486090
## iter  80 value 0.484447
## iter  90 value 0.482461
## iter 100 value 0.479810
## final  value 0.479810 
## stopped after 100 iterations
## # weights:  43
## initial  value 132.364707 
## iter  10 value 18.212595
## iter  20 value 2.692662
## iter  30 value 0.488049
## iter  40 value 0.427922
## iter  50 value 0.379209
## iter  60 value 0.335707
## iter  70 value 0.324587
## iter  80 value 0.312451
## iter  90 value 0.296794
## iter 100 value 0.283337
## final  value 0.283337 
## stopped after 100 iterations
## # weights:  11
## initial  value 114.770789 
## iter  10 value 50.895915
## iter  20 value 21.594661
## iter  30 value 8.579404
## iter  40 value 4.491888
## iter  50 value 1.888615
## iter  60 value 1.774330
## iter  70 value 1.435249
## iter  80 value 1.417704
## iter  90 value 1.279171
## iter 100 value 1.232213
## final  value 1.232213 
## stopped after 100 iterations
## # weights:  27
## initial  value 121.671018 
## iter  10 value 7.637314
## iter  20 value 1.023347
## iter  30 value 0.000176
## iter  30 value 0.000084
## iter  30 value 0.000084
## final  value 0.000084 
## converged
## # weights:  43
## initial  value 125.122579 
## iter  10 value 4.878708
## iter  20 value 0.082765
## iter  30 value 0.000501
## final  value 0.000065 
## converged
## # weights:  11
## initial  value 118.540638 
## iter  10 value 55.901291
## iter  20 value 44.190846
## iter  30 value 44.122993
## final  value 44.122341 
## converged
## # weights:  27
## initial  value 128.560755 
## iter  10 value 31.362040
## iter  20 value 21.703871
## iter  30 value 21.365892
## iter  40 value 21.277271
## final  value 21.274727 
## converged
## # weights:  43
## initial  value 135.332676 
## iter  10 value 36.608914
## iter  20 value 20.428722
## iter  30 value 18.841831
## iter  40 value 18.538820
## iter  50 value 18.465358
## iter  60 value 18.457341
## iter  70 value 18.457287
## iter  70 value 18.457287
## iter  70 value 18.457287
## final  value 18.457287 
## converged
## # weights:  11
## initial  value 122.464598 
## iter  10 value 48.486860
## iter  20 value 27.244665
## iter  30 value 7.563582
## iter  40 value 4.541484
## iter  50 value 4.194044
## iter  60 value 4.061244
## iter  70 value 3.913031
## iter  80 value 3.888366
## iter  90 value 3.865349
## iter 100 value 3.862664
## final  value 3.862664 
## stopped after 100 iterations
## # weights:  27
## initial  value 109.388538 
## iter  10 value 4.747327
## iter  20 value 0.751945
## iter  30 value 0.726463
## iter  40 value 0.654058
## iter  50 value 0.591235
## iter  60 value 0.564247
## iter  70 value 0.544641
## iter  80 value 0.507726
## iter  90 value 0.474908
## iter 100 value 0.453801
## final  value 0.453801 
## stopped after 100 iterations
## # weights:  43
## initial  value 123.169841 
## iter  10 value 4.382165
## iter  20 value 1.563711
## iter  30 value 0.479811
## iter  40 value 0.448049
## iter  50 value 0.432482
## iter  60 value 0.398597
## iter  70 value 0.388515
## iter  80 value 0.377880
## iter  90 value 0.370443
## iter 100 value 0.361109
## final  value 0.361109 
## stopped after 100 iterations
## # weights:  11
## initial  value 119.256445 
## iter  10 value 56.285210
## iter  20 value 7.469969
## iter  30 value 4.099817
## iter  40 value 3.635803
## iter  50 value 3.208790
## iter  60 value 2.977949
## iter  70 value 2.893926
## iter  80 value 2.838948
## iter  90 value 2.732318
## iter 100 value 2.619618
## final  value 2.619618 
## stopped after 100 iterations
## # weights:  27
## initial  value 114.122617 
## iter  10 value 5.558564
## iter  20 value 0.243031
## iter  30 value 0.000334
## final  value 0.000072 
## converged
## # weights:  43
## initial  value 143.357526 
## iter  10 value 5.815688
## iter  20 value 1.869046
## iter  30 value 0.005197
## final  value 0.000051 
## converged
## # weights:  11
## initial  value 121.113960 
## iter  10 value 74.640372
## iter  20 value 46.951522
## iter  30 value 43.380961
## final  value 43.380924 
## converged
## # weights:  27
## initial  value 121.861199 
## iter  10 value 35.206448
## iter  20 value 20.961318
## iter  30 value 19.985500
## iter  40 value 19.932686
## iter  50 value 19.922197
## iter  60 value 19.921722
## final  value 19.921712 
## converged
## # weights:  43
## initial  value 131.939376 
## iter  10 value 25.702828
## iter  20 value 18.608282
## iter  30 value 18.122011
## iter  40 value 18.053090
## iter  50 value 18.039842
## iter  60 value 18.038080
## final  value 18.038075 
## converged
## # weights:  11
## initial  value 117.982337 
## iter  10 value 51.103593
## iter  20 value 48.035321
## iter  30 value 33.273056
## iter  40 value 8.919168
## iter  50 value 4.838973
## iter  60 value 4.530733
## iter  70 value 4.028449
## iter  80 value 3.905338
## iter  90 value 3.870748
## iter 100 value 3.864652
## final  value 3.864652 
## stopped after 100 iterations
## # weights:  27
## initial  value 144.068507 
## iter  10 value 4.404914
## iter  20 value 1.124010
## iter  30 value 0.871467
## iter  40 value 0.719849
## iter  50 value 0.601527
## iter  60 value 0.575084
## iter  70 value 0.560945
## iter  80 value 0.510113
## iter  90 value 0.486598
## iter 100 value 0.474407
## final  value 0.474407 
## stopped after 100 iterations
## # weights:  43
## initial  value 140.508226 
## iter  10 value 9.593176
## iter  20 value 0.781330
## iter  30 value 0.461086
## iter  40 value 0.445335
## iter  50 value 0.411271
## iter  60 value 0.390060
## iter  70 value 0.372303
## iter  80 value 0.363494
## iter  90 value 0.357105
## iter 100 value 0.344014
## final  value 0.344014 
## stopped after 100 iterations
## # weights:  11
## initial  value 129.031039 
## iter  10 value 61.978707
## iter  20 value 58.008696
## iter  30 value 57.768938
## iter  40 value 55.583867
## iter  50 value 52.889449
## iter  60 value 43.602398
## iter  70 value 39.782882
## iter  80 value 34.850087
## iter  90 value 23.311939
## iter 100 value 3.119741
## final  value 3.119741 
## stopped after 100 iterations
## # weights:  27
## initial  value 126.475926 
## iter  10 value 7.096031
## iter  20 value 0.639765
## iter  30 value 0.000106
## iter  30 value 0.000052
## iter  30 value 0.000052
## final  value 0.000052 
## converged
## # weights:  43
## initial  value 134.270158 
## iter  10 value 5.930885
## iter  20 value 1.228181
## iter  30 value 0.010612
## final  value 0.000084 
## converged
## # weights:  11
## initial  value 123.227860 
## iter  10 value 53.165906
## iter  20 value 43.229062
## final  value 43.228624 
## converged
## # weights:  27
## initial  value 127.334763 
## iter  10 value 24.083708
## iter  20 value 19.538749
## iter  30 value 19.295874
## iter  40 value 19.174203
## iter  50 value 19.034503
## final  value 19.034362 
## converged
## # weights:  43
## initial  value 131.621100 
## iter  10 value 35.666079
## iter  20 value 19.486685
## iter  30 value 18.420880
## iter  40 value 17.192733
## iter  50 value 17.154065
## iter  60 value 17.148652
## iter  70 value 17.148346
## final  value 17.148327 
## converged
## # weights:  11
## initial  value 128.213413 
## iter  10 value 49.978543
## iter  20 value 48.871330
## iter  30 value 48.360713
## iter  40 value 44.556033
## iter  50 value 17.787883
## iter  60 value 4.908744
## iter  70 value 4.013138
## iter  80 value 3.170127
## iter  90 value 3.123838
## iter 100 value 2.985978
## final  value 2.985978 
## stopped after 100 iterations
## # weights:  27
## initial  value 127.197897 
## iter  10 value 4.354141
## iter  20 value 1.009145
## iter  30 value 0.462364
## iter  40 value 0.402815
## iter  50 value 0.365000
## iter  60 value 0.341482
## iter  70 value 0.333382
## iter  80 value 0.324477
## iter  90 value 0.314822
## iter 100 value 0.295699
## final  value 0.295699 
## stopped after 100 iterations
## # weights:  43
## initial  value 120.457941 
## iter  10 value 4.476405
## iter  20 value 1.443496
## iter  30 value 0.600594
## iter  40 value 0.498873
## iter  50 value 0.401362
## iter  60 value 0.376749
## iter  70 value 0.357924
## iter  80 value 0.348783
## iter  90 value 0.331318
## iter 100 value 0.326491
## final  value 0.326491 
## stopped after 100 iterations
## # weights:  11
## initial  value 135.093527 
## iter  10 value 21.860640
## iter  20 value 3.813716
## iter  30 value 2.509928
## iter  40 value 2.384751
## iter  50 value 2.276547
## iter  60 value 2.250532
## iter  70 value 2.153859
## iter  80 value 1.699918
## iter  90 value 0.834569
## iter 100 value 0.573835
## final  value 0.573835 
## stopped after 100 iterations
## # weights:  27
## initial  value 126.256021 
## iter  10 value 5.294353
## iter  20 value 0.037650
## final  value 0.000071 
## converged
## # weights:  43
## initial  value 130.459188 
## iter  10 value 5.484744
## iter  20 value 0.810428
## iter  30 value 0.002412
## final  value 0.000073 
## converged
## # weights:  11
## initial  value 127.596687 
## iter  10 value 53.593172
## iter  20 value 44.128618
## iter  30 value 43.966078
## final  value 43.966037 
## converged
## # weights:  27
## initial  value 155.037982 
## iter  10 value 27.774198
## iter  20 value 20.783237
## iter  30 value 19.876683
## iter  40 value 19.868884
## final  value 19.868385 
## converged
## # weights:  43
## initial  value 171.725834 
## iter  10 value 23.134324
## iter  20 value 18.599155
## iter  30 value 18.436512
## iter  40 value 18.422714
## iter  50 value 18.422201
## final  value 18.422189 
## converged
## # weights:  11
## initial  value 130.488537 
## iter  10 value 85.816017
## iter  20 value 50.748640
## iter  30 value 48.927856
## iter  40 value 47.709677
## iter  50 value 47.582838
## iter  60 value 47.519960
## iter  70 value 47.507163
## iter  80 value 47.501926
## iter  90 value 47.497119
## final  value 47.494823 
## converged
## # weights:  27
## initial  value 122.543665 
## iter  10 value 19.518466
## iter  20 value 2.052800
## iter  30 value 0.886034
## iter  40 value 0.804745
## iter  50 value 0.648603
## iter  60 value 0.585834
## iter  70 value 0.553642
## iter  80 value 0.497885
## iter  90 value 0.458749
## iter 100 value 0.449044
## final  value 0.449044 
## stopped after 100 iterations
## # weights:  43
## initial  value 153.095425 
## iter  10 value 7.901518
## iter  20 value 0.690893
## iter  30 value 0.636107
## iter  40 value 0.584777
## iter  50 value 0.567513
## iter  60 value 0.534749
## iter  70 value 0.522132
## iter  80 value 0.506614
## iter  90 value 0.501144
## iter 100 value 0.474534
## final  value 0.474534 
## stopped after 100 iterations
## # weights:  11
## initial  value 135.364864 
## iter  10 value 59.004600
## iter  20 value 49.914439
## iter  30 value 49.908413
## final  value 49.906914 
## converged
## # weights:  27
## initial  value 128.151297 
## iter  10 value 6.337487
## iter  20 value 0.146259
## iter  30 value 0.000104
## iter  30 value 0.000057
## iter  30 value 0.000056
## final  value 0.000056 
## converged
## # weights:  43
## initial  value 139.035430 
## iter  10 value 5.342379
## iter  20 value 0.250943
## iter  30 value 0.000708
## final  value 0.000094 
## converged
## # weights:  11
## initial  value 118.420609 
## iter  10 value 64.974347
## iter  20 value 56.804050
## iter  30 value 44.067872
## final  value 42.994871 
## converged
## # weights:  27
## initial  value 136.089534 
## iter  10 value 27.295517
## iter  20 value 19.795109
## iter  30 value 18.797967
## iter  40 value 18.724373
## iter  50 value 18.718133
## final  value 18.718133 
## converged
## # weights:  43
## initial  value 117.387025 
## iter  10 value 26.556247
## iter  20 value 17.899514
## iter  30 value 17.809471
## iter  40 value 17.764813
## iter  50 value 17.756615
## final  value 17.756610 
## converged
## # weights:  11
## initial  value 136.528004 
## iter  10 value 23.039236
## iter  20 value 3.818892
## iter  30 value 3.195511
## iter  40 value 3.122077
## iter  50 value 3.106837
## iter  60 value 3.094371
## iter  70 value 3.093128
## iter  80 value 3.092464
## iter  90 value 3.092407
## iter 100 value 3.092292
## final  value 3.092292 
## stopped after 100 iterations
## # weights:  27
## initial  value 123.626570 
## iter  10 value 5.162502
## iter  20 value 0.512650
## iter  30 value 0.387310
## iter  40 value 0.363980
## iter  50 value 0.342939
## iter  60 value 0.322494
## iter  70 value 0.309017
## iter  80 value 0.303599
## iter  90 value 0.292640
## iter 100 value 0.274828
## final  value 0.274828 
## stopped after 100 iterations
## # weights:  43
## initial  value 129.709743 
## iter  10 value 6.399049
## iter  20 value 1.484154
## iter  30 value 0.424066
## iter  40 value 0.333323
## iter  50 value 0.290299
## iter  60 value 0.271136
## iter  70 value 0.254488
## iter  80 value 0.244931
## iter  90 value 0.241006
## iter 100 value 0.235645
## final  value 0.235645 
## stopped after 100 iterations
## # weights:  11
## initial  value 120.630519 
## iter  10 value 59.934734
## iter  20 value 50.061401
## iter  30 value 48.902842
## iter  40 value 40.689201
## iter  50 value 9.246081
## iter  60 value 4.798559
## iter  70 value 4.402083
## iter  80 value 3.747997
## iter  90 value 2.052315
## iter 100 value 1.813680
## final  value 1.813680 
## stopped after 100 iterations
## # weights:  27
## initial  value 115.288383 
## iter  10 value 17.230857
## iter  20 value 0.332887
## iter  30 value 0.000452
## final  value 0.000047 
## converged
## # weights:  43
## initial  value 115.350758 
## iter  10 value 15.083811
## iter  20 value 1.751399
## iter  30 value 0.182284
## iter  40 value 0.001019
## iter  50 value 0.000302
## final  value 0.000086 
## converged
## # weights:  11
## initial  value 127.529840 
## iter  10 value 55.578483
## iter  20 value 44.112002
## final  value 44.104970 
## converged
## # weights:  27
## initial  value 147.959026 
## iter  10 value 29.305877
## iter  20 value 20.335408
## iter  30 value 20.112010
## iter  40 value 20.104860
## final  value 20.104627 
## converged
## # weights:  43
## initial  value 131.392852 
## iter  10 value 32.272199
## iter  20 value 19.766570
## iter  30 value 18.836523
## iter  40 value 18.443541
## iter  50 value 18.340096
## iter  60 value 18.328809
## iter  70 value 18.327322
## final  value 18.327123 
## converged
## # weights:  11
## initial  value 125.205767 
## iter  10 value 48.380736
## iter  20 value 35.618174
## iter  30 value 11.397083
## iter  40 value 4.475791
## iter  50 value 4.074765
## iter  60 value 4.016958
## iter  70 value 3.974500
## iter  80 value 3.912831
## iter  90 value 3.848654
## iter 100 value 3.844326
## final  value 3.844326 
## stopped after 100 iterations
## # weights:  27
## initial  value 128.588080 
## iter  10 value 5.384040
## iter  20 value 1.619297
## iter  30 value 0.882242
## iter  40 value 0.851849
## iter  50 value 0.641502
## iter  60 value 0.619737
## iter  70 value 0.595281
## iter  80 value 0.535622
## iter  90 value 0.493317
## iter 100 value 0.486438
## final  value 0.486438 
## stopped after 100 iterations
## # weights:  43
## initial  value 126.933423 
## iter  10 value 11.502520
## iter  20 value 2.523881
## iter  30 value 0.724044
## iter  40 value 0.650789
## iter  50 value 0.604091
## iter  60 value 0.567950
## iter  70 value 0.545173
## iter  80 value 0.515780
## iter  90 value 0.502725
## iter 100 value 0.469805
## final  value 0.469805 
## stopped after 100 iterations
## # weights:  11
## initial  value 128.841813 
## iter  10 value 49.888557
## iter  20 value 48.854861
## iter  30 value 46.284065
## iter  40 value 45.933053
## iter  50 value 44.949410
## iter  60 value 42.929580
## iter  70 value 8.036085
## iter  80 value 4.112129
## iter  90 value 3.437158
## iter 100 value 1.625705
## final  value 1.625705 
## stopped after 100 iterations
## # weights:  27
## initial  value 155.763709 
## iter  10 value 22.044760
## iter  20 value 3.180958
## iter  30 value 0.258484
## iter  40 value 0.001788
## final  value 0.000094 
## converged
## # weights:  43
## initial  value 122.457708 
## iter  10 value 3.485470
## iter  20 value 0.019486
## final  value 0.000064 
## converged
## # weights:  11
## initial  value 115.895686 
## iter  10 value 59.149623
## iter  20 value 51.309942
## iter  30 value 43.719794
## final  value 43.715117 
## converged
## # weights:  27
## initial  value 114.668249 
## iter  10 value 28.092323
## iter  20 value 20.979628
## iter  30 value 20.625230
## iter  40 value 20.624005
## iter  40 value 20.624005
## iter  40 value 20.624005
## final  value 20.624005 
## converged
## # weights:  43
## initial  value 129.863362 
## iter  10 value 27.825492
## iter  20 value 19.487986
## iter  30 value 18.594719
## iter  40 value 18.496859
## iter  50 value 18.474010
## iter  60 value 18.420539
## iter  70 value 18.058704
## iter  80 value 17.803440
## iter  90 value 17.708693
## iter 100 value 17.696027
## final  value 17.696027 
## stopped after 100 iterations
## # weights:  11
## initial  value 129.196853 
## iter  10 value 49.961302
## iter  20 value 49.655075
## iter  30 value 48.919385
## iter  40 value 16.000700
## iter  50 value 5.571821
## iter  60 value 3.368120
## iter  70 value 3.145819
## iter  80 value 2.971756
## iter  90 value 2.931838
## iter 100 value 2.922727
## final  value 2.922727 
## stopped after 100 iterations
## # weights:  27
## initial  value 136.352067 
## iter  10 value 19.746721
## iter  20 value 1.762322
## iter  30 value 0.773155
## iter  40 value 0.739820
## iter  50 value 0.683111
## iter  60 value 0.531832
## iter  70 value 0.499564
## iter  80 value 0.416175
## iter  90 value 0.395498
## iter 100 value 0.327184
## final  value 0.327184 
## stopped after 100 iterations
## # weights:  43
## initial  value 130.762361 
## iter  10 value 7.155063
## iter  20 value 0.314087
## iter  30 value 0.295210
## iter  40 value 0.287887
## iter  50 value 0.264294
## iter  60 value 0.251011
## iter  70 value 0.228303
## iter  80 value 0.207026
## iter  90 value 0.200442
## iter 100 value 0.194906
## final  value 0.194906 
## stopped after 100 iterations
## # weights:  11
## initial  value 145.900216 
## iter  10 value 64.757220
## iter  20 value 48.348164
## iter  30 value 46.796576
## final  value 46.796573 
## converged
resultado_entrenamiento5 <- predict(modelo5, entrenamiento)
resultado_prueba5 <- predict(modelo5, prueba)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre5 <- confusionMatrix(resultado_entrenamiento5, entrenamiento$Species)
mcre5
## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         40          0         0
##   versicolor      0         36         0
##   virginica       0          4        40
## 
## Overall Statistics
##                                           
##                Accuracy : 0.9667          
##                  95% CI : (0.9169, 0.9908)
##     No Information Rate : 0.3333          
##     P-Value [Acc > NIR] : < 2.2e-16       
##                                           
##                   Kappa : 0.95            
##                                           
##  Mcnemar's Test P-Value : NA              
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            0.9000           1.0000
## Specificity                 1.0000            1.0000           0.9500
## Pos Pred Value              1.0000            1.0000           0.9091
## Neg Pred Value              1.0000            0.9524           1.0000
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3000           0.3333
## Detection Prevalence        0.3333            0.3000           0.3667
## Balanced Accuracy           1.0000            0.9500           0.9750
# Matriz de confusion del resultado de la prueba
mcrp5 <- confusionMatrix(resultado_prueba5, prueba$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           0.9750

Modelo 6. Random Forest 

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))
                 )
## 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 range
resultado_entrenamiento6 <- predict(modelo6, entrenamiento)
resultado_prueba6 <- predict(modelo6, prueba)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre6 <- confusionMatrix(resultado_entrenamiento6, entrenamiento$Species)
mcre6
## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         40          0         0
##   versicolor      0         40         0
##   virginica       0          0        40
## 
## Overall Statistics
##                                      
##                Accuracy : 1          
##                  95% CI : (0.9697, 1)
##     No Information Rate : 0.3333     
##     P-Value [Acc > NIR] : < 2.2e-16  
##                                      
##                   Kappa : 1          
##                                      
##  Mcnemar's Test P-Value : NA         
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            1.0000           1.0000
## Specificity                 1.0000            1.0000           1.0000
## Pos Pred Value              1.0000            1.0000           1.0000
## Neg Pred Value              1.0000            1.0000           1.0000
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3333           0.3333
## Detection Prevalence        0.3333            0.3333           0.3333
## Balanced Accuracy           1.0000            1.0000           1.0000
# Matriz de confusion del resultado de la prueba
mcrp6 <- confusionMatrix(resultado_prueba6, prueba$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           0.9000

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("Precisón de entrenamiento", "Precisión de Prueba")
resultados
##                           svmLinear svmRadial   svmPoly     rpart      nnet
## Precisón de entrenamiento 0.9916667 0.9916667 0.9833333 0.9666667 0.9666667
## Precisión de Prueba       0.9666667 0.9333333 0.9333333 0.9333333 0.9666667
##                                  rf
## Precisón de entrenamiento 1.0000000
## Precisión de Prueba       0.9333333

Conclusiones

De acuerdo con la tabla de resultados, se observa que ninguno de los métodos evaluados presenta indicios de sobreajuste, lo cual confirma la consistencia de los modelos. Entre las alternativas probadas, el enfoque basado en redes neuronales destaca por su mejor desempeño global, por lo que se recomienda seleccionarlo como el modelo final para este análisis.

---
title: "CARET"
author: "Miguel Angel Lopez"
date: "2025-08-22"
output: 
  html_document:
    toc: True
    toc_float: True
    code_download: true
    theme: cerulean
---

<center>
![](/Users/miguel/Desktop/Flor.jpg)

</center>

# <span style="color:blue;"> Teoria </span>
El paquete CARET (Classification And Regression Training) es un paquete integral con una amplia variedad de algoritmos para el aprendizaje automatico.

# <span style="color:blue;"> Instalar paquetes y cargar librerias </span>
```{r}
#install.packages("ggplot2") # Gráficas
library(ggplot2)
#install.packages("lattice") # Crear gráficos
library(lattice)
#install.packages ("caret") # Algoritmos de aprendizaje automático
library (caret)
#install.packages ("datasets") # Usar bases de datos, en este caso Iris
library(datasets)
#install.packages ("DataExplorer") # Análisis Exploratorio
library (DataExplorer)
#install.packages("kernlab")
library(kernlab)
#install.packages("randomForest")
library(ranger)
library(randomForest)
```


# <span style="color:blue;"> Crear la base de datos </span>

```{r}
df <- data.frame(iris)
```

# <span style="color:blue;"> Entender la base de datos </span>
```{r}
summary(df)
str(df)
plot_missing(df)
plot_histogram(df)
plot_correlation(df)
```

# <span style="color:blue;"> Partir la base de datos </span>

```{r}
# Normalmente 80-20
set.seed(123)
renglones_entrenamiento <- createDataPartition(df$Species, p=0.8, list = FALSE)
entrenamiento <- iris[renglones_entrenamiento, ]
prueba <- iris[-renglones_entrenamiento, ]
```

# <span style="color:blue;"> Distintos tipos de métodos para Modelar </span>

Los métodos más utilizados para modelar aprendizaje automático:

* *SVM: *Support Vector Machine o Máquina de Vectores de Soporte. Hay varios subtipos: Lineal (svmLinear), Radial (svmRadial), Polinómico (svmPoly), etc.

* *Árbol de Decisión*: rpart
* *Redes Neuronales*: nnet
* *Random Forest* o Bosques Aleatorios: rf

# <span style="color:blue;"> Modelo 1. SVM Lineal </span>
```{r}
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)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre1 <- confusionMatrix(resultado_entrenamiento1, entrenamiento$Species)
mcre1
# Matriz de confusion del resultado de la prueba
mcrp1 <- confusionMatrix(resultado_prueba1, prueba$Species)
mcrp1
```

# <span style="color:blue;"> Modelo 2. SVM Radial </span>
```{r}
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)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre2 <- confusionMatrix(resultado_entrenamiento2, entrenamiento$Species)
mcre2
# Matriz de confusion del resultado de la prueba
mcrp2 <- confusionMatrix(resultado_prueba2, prueba$Species)
mcrp2
```

# <span style="color:blue;"> Modelo 3. SVM Poly </span>
```{r}
modelo3 <- train(Species ~ ., data=entrenamiento,
                 method = "svmRadial", #Cambiar
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneGride = data.frame(degree=1, C=1, scale=1) #Cambiar
                 )

resultado_entrenamiento3 <- predict(modelo3, entrenamiento)
resultado_prueba3 <- predict(modelo3, prueba)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre3 <- confusionMatrix(resultado_entrenamiento3, entrenamiento$Species)
mcre3
# Matriz de confusion del resultado de la prueba
mcrp3 <- confusionMatrix(resultado_prueba3, prueba$Species)
mcrp3
```

# <span style="color:blue;"> Modelo 4. Arboles de decision </span>
```{r message=FALSE, warning=FALSE}
modelo4 <- train(Species ~ ., data=entrenamiento,
                 method = "rpart", #Cambiar
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneLength = 10
                 )

resultado_entrenamiento4 <- predict(modelo4, entrenamiento)
resultado_prueba4 <- predict(modelo3, prueba)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre4 <- confusionMatrix(resultado_entrenamiento4, entrenamiento$Species)
mcre4
# Matriz de confusion del resultado de la prueba
mcrp4 <- confusionMatrix(resultado_prueba4, prueba$Species)
mcrp4
```

# <span style="color:blue;"> Modelo 5. Redes Neuronales </span>
```{r}
modelo5 <- train(Species ~ ., data=entrenamiento,
                 method = "nnet", #Cambiar
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10)
                 
                 )

resultado_entrenamiento5 <- predict(modelo5, entrenamiento)
resultado_prueba5 <- predict(modelo5, prueba)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre5 <- confusionMatrix(resultado_entrenamiento5, entrenamiento$Species)
mcre5
# Matriz de confusion del resultado de la prueba
mcrp5 <- confusionMatrix(resultado_prueba5, prueba$Species)
mcrp5
```

# <span style="color:blue;"> Modelo 6. Random Forest </span>
```{r}
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))
                 )

resultado_entrenamiento6 <- predict(modelo6, entrenamiento)
resultado_prueba6 <- predict(modelo6, prueba)

#Matrices de confusión
# Es una tabla de evaluación que desglosa el rendimiento del modelo de clasficiación.

#Matriz de confusion del resultado del entrenamiento
mcre6 <- confusionMatrix(resultado_entrenamiento6, entrenamiento$Species)
mcre6
# Matriz de confusion del resultado de la prueba
mcrp6 <- confusionMatrix(resultado_prueba6, prueba$Species)
mcrp6
```

# <span style="color:blue;"> Resultados</span>
```{r}
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("Precisón de entrenamiento", "Precisión de Prueba")
resultados
```

# <span style="color: blue"> Conclusiones </span>
De acuerdo con la tabla de resultados, se observa que ninguno de los métodos evaluados presenta indicios de sobreajuste, lo cual confirma la consistencia de los modelos. Entre las alternativas probadas, el enfoque basado en redes neuronales destaca por su mejor desempeño global, por lo que se recomienda seleccionarlo como el modelo final para este análisis. 








