Randomly split the messages into a training set D1 (80% of messages) and a testing set D2 (20% of messages). Calculate the testing accuracy, confusion matrix, precision, recall, and F-score of the Na¨ıve Bayes classifier in determining whether a message is spam or ham. Submit your source code. Note: Let's assume that spam is the positive class

In the step-by-step

Step-by-step explanation:

This is the code i created using the R software and the packages "caret" and "e0171".

The script was supposed to work in all general cases.

library (caret)

library (e1071)

# Categorical vector

spam < - c ("spam","not_spam")

spam_vec < - sample (spam, 60, replace = T)

# Supposing two independent variables so that the kappa will be close to 0.

x1 < - rnorm (60)

x2 < - rnorm (60)

# Creating the dataset

data1 < - cbind (spam_vec, x1, x2)

data1 < - as. data. frame (data1)

names (data1) < - make. names (c ("spamvec","x","y"))

# Creating the partition

index < - createDataPartition (data1$spamvec,

p=0.8, list=FALSE)

training_data < - data1[index,]

testing_data < - data1[-index,]

fitControl < - trainControl (method = "cv",

number = 5,

savePred = TRUE,

classProb = TRUE)

tune. grid < - expand. grid (C = seq (0, 10,.1))

# Scaling the predictors

preProcess_cs < - preProcess (training_data[, - 1],

method = c ("center", "scale"))

spam_training_cs < - predict (preProcess_cs, training_data)

spam_testing_cs < - predict (preProcess_cs, testing_data)

# Training a Naive Bayes to predict binary outcome

Naive_Bayes_Model=naiveBayes (spamvec ~.,

data=spam_training_cs,

tuneGrid = tune. grid,

trControl = fitControl)

# Confusion matrix

prediction < - predict (Naive_Bayes_Model, spam_testing_cs)

confusionMatrix (prediction, spam_testing_cs$spamvec, positive = "spam")

confM < - confusionMatrix (prediction, spam_testing_cs$spamvec, positive = "spam")

accuracy < - confM$overall[1]

accuracy