Q4.1

plot(alldata$X1, alldata$X2, col = c("blue", "red")[alldata$Y], pch = c("o","+")[alldata$Y])

Q4.2

<aside> 💡 (a) Στην κλάση "1"

</aside>

# required libraries
library(class)

# split data for training set
xtrain = alldata[,-3]
ytain = alldata[,3]

# create model and predict
knn(xtrain, c(1.5, -0.5), ytrain, k = 3)

Q4.3

<aside> 💡 0,6

</aside>

# required libraries
library(class)

# create model and predict
knn(xtrain, c(-1, 1), ytrain, k = 5, prob = TRUE)

Q4.4

<aside> 💡 (c) Μικρότερο από 0.01

</aside>

# required libraries
library(neuralnet)

# create model
model <- neuralnet(Y ~ X1 + X2, alldata, hidden = 2, threshold = 0.01)

# calculate Training Error and Mean of result
yEstimateTrain = compute(model, alldata[, c(1:2)])$net.result
TrainingError = alldata$Y - yEstimateTrain
MAE = mean(abs(TrainingError))

# print MAE
print(MAE)