R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

summary(cars)
##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Including Plots

You can also embed plots, for example:

#load Packages
library(caret)
## Warning: package 'caret' was built under R version 4.3.3
## Loading required package: ggplot2
## Loading required package: lattice
library(klaR)
## Warning: package 'klaR' was built under R version 4.3.3
## Loading required package: MASS
#load data
data(iris)

#define an 80%/20% train/test split of dataset
trainIndex <- createDataPartition(iris$Species, p = 0.80, list = FALSE)
dataTrain <- iris[trainIndex,]
dataTest <- iris[-trainIndex,]

#train a naive bayes model
fit<- NaiveBayes(Species~., data= dataTrain)

#make predictions 
predictions <- predict(fit, dataTest[,1:4])

#summarize results
confusionMatrix(predictions$class, dataTest$Species)
## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         10          0         0
##   versicolor      0         10         3
##   virginica       0          0         7
## 
## Overall Statistics
##                                           
##                Accuracy : 0.9             
##                  95% CI : (0.7347, 0.9789)
##     No Information Rate : 0.3333          
##     P-Value [Acc > NIR] : 1.665e-10       
##                                           
##                   Kappa : 0.85            
##                                           
##  Mcnemar's Test P-Value : NA              
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            1.0000           0.7000
## Specificity                 1.0000            0.8500           1.0000
## Pos Pred Value              1.0000            0.7692           1.0000
## Neg Pred Value              1.0000            1.0000           0.8696
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3333           0.2333
## Detection Prevalence        0.3333            0.4333           0.2333
## Balanced Accuracy           1.0000            0.9250           0.8500
library(caret)
data(iris)

trainControl <- trainControl(method = "boot", number = 1000)

fit<- train(Species~., data = iris, trControl= trainControl, method = "nb")
## Warning in FUN(X[[i]], ...): Numerical 0 probability for all classes with
## observation 40
## Warning in FUN(X[[i]], ...): Numerical 0 probability for all classes with
## observation 45
## Warning in FUN(X[[i]], ...): Numerical 0 probability for all classes with
## observation 19
print(fit)
## Naive Bayes 
## 
## 150 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Bootstrapped (1000 reps) 
## Summary of sample sizes: 150, 150, 150, 150, 150, 150, ... 
## Resampling results across tuning parameters:
## 
##   usekernel  Accuracy   Kappa    
##   FALSE      0.9519983  0.9272566
##    TRUE      0.9540298  0.9303334
## 
## Tuning parameter 'fL' was held constant at a value of 0
## Tuning
##  parameter 'adjust' was held constant at a value of 1
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were fL = 0, usekernel = TRUE and adjust
##  = 1.
trainControl <- trainControl(method= "repeatedcv", number =10, repeats = 3)

fit <- train(Species~., data = iris, trControl= trainControl, method = "nb")
print(fit)
## Naive Bayes 
## 
## 150 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 135, 135, 135, 135, 135, 135, ... 
## Resampling results across tuning parameters:
## 
##   usekernel  Accuracy   Kappa    
##   FALSE      0.9533333  0.9300000
##    TRUE      0.9577778  0.9366667
## 
## Tuning parameter 'fL' was held constant at a value of 0
## Tuning
##  parameter 'adjust' was held constant at a value of 1
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were fL = 0, usekernel = TRUE and adjust
##  = 1.
# define training control
trainControl <-trainControl(method="LOOCV")
# evaluate the model
fit <- train(Species~., data=iris, trControl=trainControl, method="nb")
# display the results
print(fit)
## Naive Bayes 
## 
## 150 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Leave-One-Out Cross-Validation 
## Summary of sample sizes: 149, 149, 149, 149, 149, 149, ... 
## Resampling results across tuning parameters:
## 
##   usekernel  Accuracy   Kappa
##   FALSE      0.9533333  0.93 
##    TRUE      0.9600000  0.94 
## 
## Tuning parameter 'fL' was held constant at a value of 0
## Tuning
##  parameter 'adjust' was held constant at a value of 1
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were fL = 0, usekernel = TRUE and adjust
##  = 1.
library(mlbench)
library(caret)
data("PimaIndiansDiabetes")


# Prepare training scheme
trainControl <-trainControl(method="repeatedcv", number=10, repeats=3)
#CART
fit.cart <- train(diabetes~., data=PimaIndiansDiabetes, method="rpart", trControl=trainControl)
print(fit.cart )
## CART 
## 
## 768 samples
##   8 predictor
##   2 classes: 'neg', 'pos' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 691, 692, 691, 691, 691, 691, ... 
## Resampling results across tuning parameters:
## 
##   cp          Accuracy   Kappa    
##   0.01741294  0.7438767  0.4163808
##   0.10447761  0.7230463  0.3628402
##   0.24253731  0.7027056  0.2915315
## 
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was cp = 0.01741294.
set.seed(7)
#LDA
set.seed(7)
fit.lda <- train(diabetes~., data=PimaIndiansDiabetes, method="lda", trControl=trainControl)
print(fit.lda)
## Linear Discriminant Analysis 
## 
## 768 samples
##   8 predictor
##   2 classes: 'neg', 'pos' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 691, 691, 691, 691, 691, 691, ... 
## Resampling results:
## 
##   Accuracy   Kappa    
##   0.7791069  0.4862025
#SVM
set.seed(7)
fit.svm<- train(diabetes~., data=PimaIndiansDiabetes, method="svmRadial", trControl=trainControl)
print(fit.svm)
## Support Vector Machines with Radial Basis Function Kernel 
## 
## 768 samples
##   8 predictor
##   2 classes: 'neg', 'pos' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 691, 691, 691, 691, 691, 691, ... 
## Resampling results across tuning parameters:
## 
##   C     Accuracy   Kappa    
##   0.25  0.7712919  0.4621585
##   0.50  0.7625769  0.4485309
##   1.00  0.7560549  0.4339951
## 
## Tuning parameter 'sigma' was held constant at a value of 0.124824
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were sigma = 0.124824 and C = 0.25.
#KNN
set.seed(7)
fit.knn<- train(diabetes~., data=PimaIndiansDiabetes, method="knn", trControl=trainControl)
print(fit.knn)
## k-Nearest Neighbors 
## 
## 768 samples
##   8 predictor
##   2 classes: 'neg', 'pos' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 691, 691, 691, 691, 691, 691, ... 
## Resampling results across tuning parameters:
## 
##   k  Accuracy   Kappa    
##   5  0.7191900  0.3580128
##   7  0.7261734  0.3779733
##   9  0.7369503  0.3984995
## 
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was k = 9.
#Random Forest
library(randomForest)
## Warning: package 'randomForest' was built under R version 4.3.3
## randomForest 4.7-1.1
## Type rfNews() to see new features/changes/bug fixes.
## 
## Attaching package: 'randomForest'
## The following object is masked from 'package:ggplot2':
## 
##     margin
set.seed(7)
fit.rf<- train(diabetes~., data=PimaIndiansDiabetes, method="rf", trControl=trainControl)
print(fit.rf)
## Random Forest 
## 
## 768 samples
##   8 predictor
##   2 classes: 'neg', 'pos' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 691, 691, 691, 691, 691, 691, ... 
## Resampling results across tuning parameters:
## 
##   mtry  Accuracy   Kappa    
##   2     0.7638528  0.4630809
##   5     0.7634256  0.4664261
##   8     0.7599738  0.4596437
## 
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 2.
# Collect
results <- resamples(list(CART = fit.cart, LDA = fit.lda, SVM = fit.svm, KNN = fit.knn, RF = fit.rf))
print(results)
## 
## Call:
## resamples.default(x = list(CART = fit.cart, LDA = fit.lda, SVM = fit.svm, KNN
##  = fit.knn, RF = fit.rf))
## 
## Models: CART, LDA, SVM, KNN, RF 
## Number of resamples: 30 
## Performance metrics: Accuracy, Kappa 
## Time estimates for: everything, final model fit
summary(results)
## 
## Call:
## summary.resamples(object = results)
## 
## Models: CART, LDA, SVM, KNN, RF 
## Number of resamples: 30 
## 
## Accuracy 
##           Min.   1st Qu.    Median      Mean   3rd Qu.      Max. NA's
## CART 0.6493506 0.7272727 0.7451299 0.7438767 0.7759740 0.8311688    0
## LDA  0.7142857 0.7508117 0.7662338 0.7791069 0.8000256 0.9078947    0
## SVM  0.7236842 0.7508117 0.7631579 0.7712919 0.7915243 0.8947368    0
## KNN  0.6753247 0.7036056 0.7272727 0.7369503 0.7662338 0.8311688    0
## RF   0.6842105 0.7305195 0.7597403 0.7638528 0.8019481 0.8421053    0
## 
## Kappa 
##           Min.   1st Qu.    Median      Mean   3rd Qu.      Max. NA's
## CART 0.2187500 0.3620724 0.4237889 0.4163808 0.4844424 0.6127660    0
## LDA  0.3011551 0.4192537 0.4662541 0.4862025 0.5308596 0.7812500    0
## SVM  0.3391908 0.3997116 0.4460612 0.4621585 0.5234605 0.7475083    0
## KNN  0.2553191 0.3406000 0.3841761 0.3984995 0.4539789 0.6195363    0
## RF   0.2951613 0.3778304 0.4640696 0.4630809 0.5447483 0.6426332    0
table(PimaIndiansDiabetes$diabetes)
## 
## neg pos 
## 500 268
prop.table(table(PimaIndiansDiabetes$diabetes))
## 
##       neg       pos 
## 0.6510417 0.3489583
scales <- list( x = list(relation = "free"), y = list(relation = "free"))
bwplot(results, scale = scales)

splom(results)

diffs <- diff(results)
summary(diffs)
## 
## Call:
## summary.diff.resamples(object = diffs)
## 
## p-value adjustment: bonferroni 
## Upper diagonal: estimates of the difference
## Lower diagonal: p-value for H0: difference = 0
## 
## Accuracy 
##      CART      LDA       SVM       KNN       RF       
## CART           -0.035230 -0.027415  0.006926 -0.019976
## LDA  0.0442284            0.007815  0.042157  0.015254
## SVM  0.0603866 0.9156892            0.034342  0.007439
## KNN  1.0000000 6.68e-05  0.0002941           -0.026902
## RF   0.4540067 0.4490617 1.0000000 0.0183793          
## 
## Kappa 
##      CART      LDA        SVM        KNN        RF        
## CART           -0.0698216 -0.0457776  0.0178813 -0.0467001
## LDA  0.1715518             0.0240440  0.0877029  0.0231215
## SVM  0.5504705 0.3562734              0.0636589 -0.0009225
## KNN  1.0000000 0.0003858  0.0040823             -0.0645814
## RF   0.5679555 1.0000000  1.0000000  0.0158974

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.