CW041525
Kamal Khalil
2025-04-15
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:
library(mlbench)## Warning: package 'mlbench' was built under R version 4.4.3library(caret)## Warning: package 'caret' was built under R version 4.4.3## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.4.3## Loading required package: lattice## Warning: package 'lattice' was built under R version 4.4.3library(ggplot2)
library(lattice)
library(randomForest)## Warning: package 'randomForest' was built under R version 4.4.3## randomForest 4.7-1.2## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:ggplot2':
##
## margindata(PimaIndiansDiabetes)
trainControl <- trainControl(method = "repeatedcv", number = 10, repeats = 3)
set.seed(7)
fit.cart <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "rpart", trControl = trainControl)
set.seed(7)
fit.lda <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "lda", trControl = trainControl)
set.seed(7)
fit.svm <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "svmRadial", trControl = trainControl)
set.seed(7)
fit.knn <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "knn", trControl = trainControl)
set.seed(7)
fit.rf <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "rf", trControl = trainControl)
results_pima <- resamples(list(CART = fit.cart, LDA = fit.lda, SVM = fit.svm, KNN = fit.knn, RF = fit.rf))
summary(results_pima)##
## Call:
## summary.resamples(object = results_pima)
##
## Models: CART, LDA, SVM, KNN, RF
## Number of resamples: 30
##
## Accuracy
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## CART 0.6753247 0.7272727 0.7532468 0.7469697 0.7662338 0.7922078 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 0.2762566 0.3620724 0.4241878 0.4151867 0.4861107 0.5250000 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 0bwplot(results_pima)
densityplot(results_pima, pch = "|")
dotplot(results_pima)
splom(results_pima)
trainControl <- trainControl(method = "cv", number = 10)
metric <- "Accuracy"
set.seed(7)
fit.lda <- train(Species ~ ., data = iris, method = "lda", metric = metric, trControl = trainControl)
set.seed(7)
fit.cart <- train(Species ~ ., data = iris, method = "rpart", metric = metric, trControl = trainControl)
set.seed(7)
fit.knn <- train(Species ~ ., data = iris, method = "knn", metric = metric, trControl = trainControl)
set.seed(7)
fit.svm <- train(Species ~ ., data = iris, method = "svmRadial", metric = metric, trControl = trainControl)
set.seed(7)
fit.rf <- train(Species ~ ., data = iris, method = "rf", metric = metric, trControl = trainControl)
results_iris <- resamples(list(lda = fit.lda, cart = fit.cart, knn = fit.knn, svm = fit.svm, rf = fit.rf))
summary(results_iris)##
## Call:
## summary.resamples(object = results_iris)
##
## Models: lda, cart, knn, svm, rf
## Number of resamples: 10
##
## Accuracy
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## lda 0.9333333 0.9500000 1.0000000 0.9800000 1.0000000 1 0
## cart 0.8666667 0.9333333 0.9333333 0.9400000 0.9833333 1 0
## knn 0.8666667 0.9333333 1.0000000 0.9666667 1.0000000 1 0
## svm 0.8000000 0.9333333 0.9666667 0.9466667 1.0000000 1 0
## rf 0.8666667 0.9333333 0.9666667 0.9600000 1.0000000 1 0
##
## Kappa
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## lda 0.9 0.925 1.00 0.97 1.000 1 0
## cart 0.8 0.900 0.90 0.91 0.975 1 0
## knn 0.8 0.900 1.00 0.95 1.000 1 0
## svm 0.7 0.900 0.95 0.92 1.000 1 0
## rf 0.8 0.900 0.95 0.94 1.000 1 0dotplot(results_iris)
bwplot(results_iris)
densityplot(results_iris, pch = "|")
splom(results_iris)
set.seed(123)
sample_index <- sample(1:nrow(iris), 0.8 * nrow(iris))
train_iris <- iris[sample_index, ]
test_iris <- iris[-sample_index, ]
model_iris <- train(Species ~ ., data = train_iris, method = "lda")
preds_iris <- predict(model_iris, test_iris)
confusionMatrix(preds_iris, test_iris$Species)## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 14 0
## virginica 0 1 5
##
## Overall Statistics
##
## Accuracy : 0.9667
## 95% CI : (0.8278, 0.9992)
## No Information Rate : 0.5
## P-Value [Acc > NIR] : 2.887e-08
##
## Kappa : 0.9464
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 0.9333 1.0000
## Specificity 1.0000 1.0000 0.9600
## Pos Pred Value 1.0000 1.0000 0.8333
## Neg Pred Value 1.0000 0.9375 1.0000
## Prevalence 0.3333 0.5000 0.1667
## Detection Rate 0.3333 0.4667 0.1667
## Detection Prevalence 0.3333 0.4667 0.2000
## Balanced Accuracy 1.0000 0.9667 0.9800Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.