CW4825
Augusta Singleton
2025-04-08
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: latticelibrary(lattice)
data(PimaIndiansDiabetes)
set.seed(7)
train_control <- trainControl(method = "repeatedcv", number = 10, repeats = 3)
fit.cart <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "rpart", trControl = train_control)
fit.lda <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "lda", trControl = train_control)
fit.svm <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "svmRadial", trControl = train_control)
fit.knn <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "knn", trControl = train_control)
fit.rf <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = "rf", trControl = train_control)
results <- resamples(list(CART=fit.cart, LDA=fit.lda, SVM=fit.svm, KNN=fit.knn, RF=fit.rf))
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 0.6753247 0.7272727 0.7532468 0.7469697 0.7662338 0.7922078 0
## LDA 0.7105263 0.7532468 0.7662338 0.7755867 0.8051948 0.8441558 0
## SVM 0.6623377 0.7245813 0.7582023 0.7604295 0.8000256 0.8571429 0
## KNN 0.6710526 0.7166353 0.7272727 0.7382319 0.7500000 0.8311688 0
## RF 0.6883117 0.7402597 0.7662338 0.7691274 0.8051948 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 0.2996968 0.4131568 0.4614831 0.4791233 0.5429981 0.6357827 0
## SVM 0.1740924 0.3557056 0.4112320 0.4338005 0.5261585 0.6602487 0
## KNN 0.2484177 0.3406000 0.3866611 0.4017113 0.4353306 0.6260740 0
## RF 0.3036925 0.4070045 0.4562480 0.4770543 0.5531915 0.6286645 0bwplot(results, scales = list(x = list(relation = "free"), y = list(relation = "free")))
densityplot(results, pch = "|")
dotplot(results)
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 -0.028617 -0.013460 0.008738 -0.022158
## LDA 0.028794 0.015157 0.037355 0.006459
## SVM 1.000000 1.000000 0.022198 -0.008698
## KNN 1.000000 0.001726 0.624760 -0.030895
## RF 0.362334 1.000000 1.000000 0.052505
##
## Kappa
## CART LDA SVM KNN RF
## CART -0.063937 -0.018614 0.013475 -0.061868
## LDA 0.03352 0.045323 0.077412 0.002069
## SVM 1.00000 1.00000 0.032089 -0.043254
## KNN 1.00000 0.01666 1.00000 -0.075343
## RF 0.14265 1.00000 1.00000 0.02578set.seed(101)
index <- createDataPartition(PimaIndiansDiabetes$diabetes, p = 0.8, list = FALSE)
train_set <- PimaIndiansDiabetes[index, ]
test_set <- PimaIndiansDiabetes[-index, ]
final_model <- train(diabetes ~ ., data = train_set, method = "lda")
predictions <- predict(final_model, test_set)
confusionMatrix(predictions, test_set$diabetes)## Confusion Matrix and Statistics
##
## Reference
## Prediction neg pos
## neg 83 24
## pos 17 29
##
## Accuracy : 0.732
## 95% CI : (0.6545, 0.8003)
## No Information Rate : 0.6536
## P-Value [Acc > NIR] : 0.02367
##
## Kappa : 0.3893
##
## Mcnemar's Test P-Value : 0.34874
##
## Sensitivity : 0.8300
## Specificity : 0.5472
## Pos Pred Value : 0.7757
## Neg Pred Value : 0.6304
## Prevalence : 0.6536
## Detection Rate : 0.5425
## Detection Prevalence : 0.6993
## Balanced Accuracy : 0.6886
##
## 'Positive' Class : neg
## data(iris)
head(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosaset.seed(42)
control_iris <- trainControl(method = "cv", number = 10)
metric <- "Accuracy"
fit.lda.iris <- train(Species ~ ., data = iris, method = "lda", metric = metric, trControl = control_iris)
fit.cart.iris <- train(Species ~ ., data = iris, method = "rpart", metric = metric, trControl = control_iris)
fit.knn.iris <- train(Species ~ ., data = iris, method = "knn", metric = metric, trControl = control_iris)
fit.svm.iris <- train(Species ~ ., data = iris, method = "svmRadial", metric = metric, trControl = control_iris)
fit.rf.iris <- train(Species ~ ., data = iris, method = "rf", metric = metric, trControl = control_iris)
results_iris <- resamples(list(LDA=fit.lda.iris, CART=fit.cart.iris, KNN=fit.knn.iris, SVM=fit.svm.iris, RF=fit.rf.iris))
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 1 0
## CART 0.8000000 0.9333333 0.9333333 0.9400000 1 1 0
## KNN 0.8666667 0.9500000 1.0000000 0.9733333 1 1 0
## SVM 0.8666667 0.9333333 1.0000000 0.9666667 1 1 0
## RF 0.8666667 0.9333333 0.9666667 0.9600000 1 1 0
##
## Kappa
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## LDA 0.9 0.925 1.00 0.97 1 1 0
## CART 0.7 0.900 0.90 0.91 1 1 0
## KNN 0.8 0.925 1.00 0.96 1 1 0
## SVM 0.8 0.900 1.00 0.95 1 1 0
## RF 0.8 0.900 0.95 0.94 1 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 0.9800Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.