#install.packages("caret", dependencies=c("Depends", "Suggests"))
library(caret)

# attach the iris dataset to the environment
data(iris)
# rename the dataset
dataset <- iris

# define the filename
filename <- "iris.csv"
# load the CSV file from the local directory
dataset <- read.csv(filename, header=FALSE)
# set the column names in the dataset
colnames(dataset) <- c("Sepal.Length","Sepal.Width","Petal.Length","Petal.Width","Species")

# create a list of 80% of the rows in the original dataset we can use for training
validation_index <- createDataPartition(dataset$Species, p=0.80, list=FALSE)
# select 20% of the data for validation
validation <- dataset[-validation_index,]
# use the remaining 80% of data to training and testing the models
dataset <- dataset[validation_index,]

# dimensions of dataset
dim(dataset)

# list types for each attribute
sapply(dataset, class)

# list the levels for the class
levels(dataset$Species)

# summarize the class distribution
percentage <- prop.table(table(dataset$Species)) * 100
cbind(freq=table(dataset$Species), percentage=percentage)

# summarize the class distribution
percentage <- prop.table(table(dataset$Species)) * 100
cbind(freq=table(dataset$Species), percentage=percentage)

summary(dataset)


# split input and output
x <- dataset[,1:4]
y <- dataset[,5]

# boxplot for each attribute on one image
par(mfrow=c(1,4))
  for(i in 1:4) {
  boxplot(x[,i], main=names(iris)[i])
}

# barplot for class breakdown
plot(y)

# scatterplot matrix
featurePlot(x=x, y=y, plot="ellipse")

# box and whisker plots for each attribute
featurePlot(x=x, y=y, plot="box")

# density plots for each attribute by class value
scales <- list(x=list(relation="free"), y=list(relation="free"))
featurePlot(x=x, y=y, plot="density", scales=scales)

# Run algorithms using 10-fold cross validation
control <- trainControl(method="cv", number=10)
metric <- "Accuracy"

# Let’s evaluate 5 different algorithms:
#   1) Linear Discriminant Analysis (LDA)
#   2) Classification and Regression Trees (CART)
#   3) k-Nearest Neighbors (kNN)
#   4) Support Vector Machines (SVM) with a linear kernel
#   5) Random Forest (RF)


###  Linear algorithms  ###
set.seed(7)
fit.lda <- train(Species~., data=dataset, method="lda", metric=metric, trControl=control)


###  Nonlinear algorithms  ###

# CART
set.seed(7)
fit.cart <- train(Species~., data=dataset, method="rpart", metric=metric, trControl=control)

# kNN
set.seed(7)
fit.knn <- train(Species~., data=dataset, method="knn", metric=metric, trControl=control)


###  Advanced algorithms  ###

# SVM
set.seed(7)
fit.svm <- train(Species~., data=dataset, method="svmRadial", metric=metric, trControl=control)

# Random Forest
set.seed(7)
fit.rf <- train(Species~., data=dataset, method="rf", metric=metric, trControl=control)



# summarize accuracy of models
results <- resamples(list(lda=fit.lda, cart=fit.cart, knn=fit.knn, svm=fit.svm, rf=fit.rf))
summary(results)

# compare accuracy of models
dotplot(results)

# summarize Best Model
print(fit.lda)


#%%%%%%%%%%%%%%  Prediction  %%%%%%%%%%%%%%%

# estimate skill of LDA on the validation dataset
predictions <- predict(fit.lda, validation)
confusionMatrix(predictions, validation$Species)