#Download and extract data !wget https://spamassassin.apache.org/old/publiccorpus/20021010_easy_ham.tar.bz2 !wget https://spamassassin.apache.org/old/publiccorpus/20021010_hard_ham.tar.bz2 !wget https://spamassassin.apache.org/old/publiccorpus/20021010_spam.tar.bz2 !tar -xjf 20021010_easy_ham.tar.bz2 !tar -xjf 20021010_hard_ham.tar.bz2 !tar -xjf 20021010_spam.tar.bz2

!ls -lah

# Write your pre-processing code here import os import codecs from sklearn.model_selection import train_test_split # Folder names easy_ham_folder = "easy_ham" spam_folder = "spam" # Function that opens and loads the emails and adds them to lists def load_emails(folder,label,encoding='ISO-8859-1' ): emails = [] email_labels = [] for filename in os.listdir(folder): email = "" with open(os.path.join(folder, filename), 'r', encoding=encoding) as f: for chunk in iter(lambda: f.read(4096), ""): email += chunk emails.append(email) email_labels.append(label) return emails, email_labels # Building datasets ham, ham_label = load_emails(easy_ham_folder, 'Ham') spam, spam_label = load_emails(spam_folder, 'Spam') # Splitting the datasets into train sets and test sets hamtrain, hamtest, ham_label_train, ham_label_test = train_test_split(ham,ham_label, test_size=0.3, random_state=None) spamtrain, spamtest, spam_label_train, spam_label_test = train_test_split(spam,spam_label, test_size=0.3, random_state=None)

#Write your code here from sklearn.feature_extraction.text import CountVectorizer from sklearn.naive_bayes import BernoulliNB, MultinomialNB from sklearn.metrics import confusion_matrix, classification_report,ConfusionMatrixDisplay import matplotlib.pyplot as plt # Combining the training sets into one trainingset = hamtrain + spamtrain traininglabels = ham_label_train + spam_label_train # Combining the testing sets into one testset = hamtest + spamtest testlabels = ham_label_test + spam_label_test vectorize = CountVectorizer() # Vectoricing the train and test sets vectorize_train_set = vectorize.fit_transform(trainingset) vectorize_test_set = vectorize.transform(testset) # Initilising the Multinomial and Bernoulli Naive Bayes and fittning the data mnb = MultinomialNB() bnb = BernoulliNB() mnb.fit(vectorize_train_set,traininglabels) bnb.fit(vectorize_train_set,traininglabels) # Predicting on the test data pred_mnb = mnb.predict(vectorize_test_set) pred_bnb = bnb.predict(vectorize_test_set) # Create a classification report to evaluate the models class_report_mnb = classification_report(testlabels,pred_mnb) class_report_bnb = classification_report(testlabels, pred_bnb) print(class_report_mnb) print(class_report_bnb) # Create confusion matrices for both methods cm_mnb = confusion_matrix(testlabels,pred_mnb) cm_bnb = confusion_matrix(testlabels,pred_bnb) # Rates of TP and TN tp_mnb = cm_mnb[0][0]/(cm_mnb[0][0] + cm_mnb[1][0]) fn_mnb = cm_mnb[1][0]/(cm_mnb[0][0] + cm_mnb[1][0]) tp_bnb = cm_bnb[0][0]/(cm_bnb[0][0] + cm_bnb[1][0]) fn_bnb = cm_bnb[1][0]/(cm_bnb[0][0] + cm_bnb[1][0]) # Displaying the mnb matrix mnb_display = ConfusionMatrixDisplay(confusion_matrix=cm_mnb, display_labels=['Ham','Spam']) mnb_display.plot() plt.title(f'MnBTrue positives: {tp_mnb}, false negatives: {fn_mnb}') # Displaying the bnb matrix bnb_display = ConfusionMatrixDisplay(confusion_matrix=cm_bnb,display_labels=['Ham','Spam']) bnb_display.plot() plt.title(f'BnB True positives: {tp_bnb}, false negatives: {fn_bnb}')

#Code to report results here hard_ham_email = 'hard_ham' hard_ham, hard_ham_label = load_emails(hard_ham_email,'Hard ham') hardhamtrain, hardhamtest, hardham_label_train, hardham_label_test = train_test_split(hard_ham,hard_ham_label, test_size=0.3, random_state=None) trainingset_hard_ham = hardhamtrain + spamtrain traininglabels_hard_ham = hardham_label_train + spam_label_train testset_hard_ham = hardhamtest + spamtest testlabels_hard_ham = hardham_label_test + spam_label_test # Vectorising the hard ham data vectorize_hh = CountVectorizer() vectorize_hhtrain_set = vectorize_hh.fit_transform(trainingset_hard_ham) vectorize_hhtest_set = vectorize_hh.transform(testset_hard_ham) # Initilising the Multinomial and Bernoulli Naive Bayes and fittning the data mnb_hh = MultinomialNB() bnb_hh = BernoulliNB() mnb_hh.fit(vectorize_hhtrain_set,traininglabels_hard_ham) bnb_hh.fit(vectorize_hhtrain_set,traininglabels_hard_ham) # Predicting on the test data pred_mnb_hh = mnb_hh.predict(vectorize_hhtest_set) pred_bnb_hh = bnb_hh.predict(vectorize_hhtest_set) # Create a classification report to evaluate the models class_report_mnb_hh = classification_report(testlabels_hard_ham,pred_mnb_hh) class_report_bnb_hh = classification_report(testlabels_hard_ham, pred_bnb_hh) print(class_report_mnb_hh) print(class_report_bnb_hh) # Create confusion matrices for both methods cm_mnb_hh = confusion_matrix(testlabels_hard_ham,pred_mnb_hh) cm_bnb_hh = confusion_matrix(testlabels_hard_ham,pred_bnb_hh) # Rates of TP and TN tp_mnb_hh = cm_mnb_hh[0][0]/(cm_mnb_hh[0][0] + cm_mnb_hh[1][0]) fn_mnb_hh = cm_mnb_hh[1][0]/(cm_mnb_hh[0][0] + cm_mnb_hh[1][0]) tp_bnb_hh = cm_bnb_hh[0][0]/(cm_bnb_hh[0][0] + cm_bnb_hh[1][0]) fn_bnb_hh = cm_bnb_hh[1][0]/(cm_bnb_hh[0][0] + cm_bnb_hh[1][0]) # Displaying the mnb matrix mnb_hh_display = ConfusionMatrixDisplay(confusion_matrix=cm_mnb_hh, display_labels=['Hard Ham','Spam']) mnb_hh_display.plot() plt.title(f'Mnb True positives: {tp_mnb_hh}, false negatives: {fn_mnb_hh}') # Displaying the bnb matrix bnb_display_hh = ConfusionMatrixDisplay(confusion_matrix=cm_bnb_hh,display_labels=['Hard Ham','Spam']) bnb_display_hh.plot() plt.title(f'BnBTrue positives: {tp_bnb_hh}, false negatives: {fn_bnb_hh}')