ML_COMPARISON
mugo
10 November 2023
library(caret)## Loading required package: ggplot2## Loading required package: latticelibrary(randomForest)## 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':
##
## margindata("iris")
dataset <- iris
summary(dataset)## 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
##
##
## names(dataset)## [1] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width" "Species"PARTITIONING
validation_index <- createDataPartition(dataset$Species, p=0.80, list=FALSE)
validation <- dataset[-validation_index,]
dataset <- dataset[validation_index,]
dim(dataset)## [1] 120 5sapply(dataset, class)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## "numeric" "numeric" "numeric" "numeric" "factor"head(dataset)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5.0 3.4 1.5 0.2 setosalevels(dataset$Species)## [1] "setosa" "versicolor" "virginica"percentage <- prop.table(table(dataset$Species)) * 100
cbind(freq=table(dataset$Species), percentage=percentage)## freq percentage
## setosa 40 33.33333
## versicolor 40 33.33333
## virginica 40 33.33333summary(dataset)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## Min. :4.300 Min. :2.00 Min. :1.000 Min. :0.100 setosa :40
## 1st Qu.:5.100 1st Qu.:2.80 1st Qu.:1.575 1st Qu.:0.300 versicolor:40
## Median :5.800 Median :3.00 Median :4.400 Median :1.300 virginica :40
## Mean :5.857 Mean :3.05 Mean :3.767 Mean :1.197
## 3rd Qu.:6.400 3rd Qu.:3.30 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.40 Max. :6.900 Max. :2.500x <- dataset[,1:4]
y <- dataset[,5]
par(mfrow=c(1,4))
for(i in 1:4) {
boxplot(x[,i], main=names(iris)[i])
}
plot(y)
featurePlot(x=x, y=y, plot="ellipse")
featurePlot(x=x, y=y, plot="box")
scales <- list(x=list(relation="free"), y=list(relation="free"))
featurePlot(x=x, y=y, plot="density", scales=scales)
control <- trainControl(method="cv", number=10)
metric <- "Accuracy"
set.seed(7)
fit.lda <- train(Species~., data=dataset, method="lda", metric=metric, trControl=control)
set.seed(7)
fit.cart <- train(Species~., data=dataset, method="rpart", metric=metric, trControl=control)
set.seed(7)
fit.knn <- train(Species~., data=dataset, method="knn", metric=metric, trControl=control)
set.seed(7)
fit.svm <- train(Species~., data=dataset, method="svmRadial", metric=metric, trControl=control)
set.seed(7)
fit.rf <- train(Species~., data=dataset, method="rf", metric=metric, trControl=control)
results <- resamples(list(lda=fit.lda, cart=fit.cart, knn=fit.knn, svm=fit.svm, rf=fit.rf))
summary(results)##
## Call:
## summary.resamples(object = results)
##
## Models: lda, cart, knn, svm, rf
## Number of resamples: 10
##
## Accuracy
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## lda 0.9166667 1.0000000 1 0.9833333 1 1 0
## cart 0.8333333 0.9166667 1 0.9583333 1 1 0
## knn 0.8333333 1.0000000 1 0.9750000 1 1 0
## svm 0.8333333 0.9166667 1 0.9500000 1 1 0
## rf 0.8333333 0.9166667 1 0.9583333 1 1 0
##
## Kappa
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## lda 0.875 1.000 1 0.9750 1 1 0
## cart 0.750 0.875 1 0.9375 1 1 0
## knn 0.750 1.000 1 0.9625 1 1 0
## svm 0.750 0.875 1 0.9250 1 1 0
## rf 0.750 0.875 1 0.9375 1 1 0dotplot(results)
print(fit.lda)## Linear Discriminant Analysis
##
## 120 samples
## 4 predictor
## 3 classes: 'setosa', 'versicolor', 'virginica'
##
## No pre-processing
## Resampling: Cross-Validated (10 fold)
## Summary of sample sizes: 108, 108, 108, 108, 108, 108, ...
## Resampling results:
##
## Accuracy Kappa
## 0.9833333 0.975predictions <- predict(fit.lda, validation)
confusionMatrix(predictions, validation$Species)## 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