def test_is_spam_function_one_returns_true_acc_test_seven(self):
return_val = EmailAnalyzer.is_spam_function_one(False, 20, 70, 50)
self.assertTrue(return_val)
def test_is_spam_function_one_returns_false_acc_test_eight(self):
return_val = EmailAnalyzer.is_spam_function_one(False, 20, 70, 80)
self.assertFalse(return_val)
def test_is_spam_function_one_returns_false_acc_test_four(self):
return_val = EmailAnalyzer.is_spam_function_one(False, 35, 50, 50)
self.assertFalse(return_val)
def test_is_spam_function_one_returns_true_acc_test_five(self):
return_val = EmailAnalyzer.is_spam_function_one(True, 20, 50, 80)
self.assertTrue(return_val)
def test_is_spam_function_one_returns_false_icc_test_twenty(self):
return_val = EmailAnalyzer.is_spam_function_one(True, 35, 80, 60)
self.assertTrue(return_val)
def test_is_spam_function_one_returns_false_acc_test_two(self):
return_val = EmailAnalyzer.is_spam_function_one(True, 35, 65, 80)
self.assertFalse(return_val)
def test_is_spam_function_one_returns_false_icc_test_seventeen(self):
return_val = EmailAnalyzer.is_spam_function_one(False, 35, 65, 80)
self.assertFalse(return_val)
def test_is_spam_function_one_returns_true_icc_test_nineteen(self):
return_val = EmailAnalyzer.is_spam_function_one(True, 35, 65, 60)
self.assertTrue(return_val)
def test_is_spam_function_one_returns_false_icc_test_sixteen(self):
return_val = EmailAnalyzer.is_spam_function_one(True, 20, 50, 50)
self.assertTrue(return_val)
def test_is_spam_function_one_returns_false_icc_test_twelve(self):
return_val = EmailAnalyzer.is_spam_function_one(False, 20, 65, 60)
self.assertTrue(return_val)
def test_is_spam_function_one_returns_false_icc_test_four(self):
return_val = EmailAnalyzer.is_spam_function_one(True, 15, 65, 50)
self.assertTrue(return_val)
def test_is_spam_function_one_returns_true_icc_test_three(self):
return_val = EmailAnalyzer.is_spam_function_one(False, 15, 65, 50)
self.assertTrue(return_val)
class RENEGE:
"""Class pour realiser le filtrage du spam en utilisant vocabular.json file et
CRUD et EmalAnalyze classes"""
def __init__(self):
self.email_file = "800-mails.json"
self.crud = CRUD()
self.e_mail = EmailAnalyzer()
def calculate_user_trust(self, user_id):
#extracting json data
date_of_first_seen_message = self.crud.get_user_data(user_id, "Date_of_first_seen_message")
date_of_last_seen_message = self.crud.get_user_data(user_id, "Date_of_last_seen_message")
n_ham = self.crud.get_user_data(user_id, "HamN")
n_spam = self.crud.get_user_data(user_id, "SpamN")
groups = self.crud.get_user_data(user_id, "Groups")
#calculate the sum of trust values of all groups
sum_trust = 0
for group in groups :
group_id = self.crud.get_group_id(group)
sum_trust += self.crud.get_group_data(group_id, 'Trust')
#now that we have all the needed vars, calculate trust1, trust2 and trust
trust1 = (date_of_last_seen_message * n_ham) / (date_of_first_seen_message * (n_ham + n_spam))
trust2 = sum_trust / len(groups)
trust = (trust1 + trust2) / 2
if trust2 < 50:
trust = trust2
if trust1 > 100:
trust = 100
#before returning a value, check if trust is between 0 and 100
if trust < 0:
trust = 0
elif trust > 100:
trust = 100
return trust
def classify_emails(self, calculation_mode, is_log_est, is_log_combo):
'''
fonction deja implemente
Description: fonction pour commencer l'analyse des e-mails.
Sortie: bool, 'True' pour succes, 'False' dans le cas de failure.
'''
try:
self.process_email(self.get_email(), calculation_mode, is_log_est, is_log_combo)
return True
except Exception:
raise Exception
def process_email(self, new_emails, calculation_mode, is_log_est, is_log_combo):
'''
Description: fonction pour analyser chaque nouvel e-mail dans le
dictionare. Elle gere l'ajout des nouveux utilisateurs et/ou modification
de l'information existante sur les utilisateurs et groupes.
Sortie: bool, 'True' pour succes, 'False' dans le cas de failure.
'''
print(type(new_emails))
emails = new_emails["dataset"]
for email in emails:
email_adr = email['mail']['From']
date = email['mail']['Date']
spam = email['mail']['Spam'] == 'true'
subject = email['mail']['Subject']
body = email['mail']['Body']
user_id = self.crud.get_user_id(email_adr)
if user_id:
self.update_user_info(email_adr, date, spam)
else:
self.add_user_info(email_adr, date)
# trust de l'utilisateur
trust = self.crud.get_user_data(user_id, "Trust")
# moyenne du trust de tous les groupes
user_group = self.crud.get_user_data(user_id, "Groups")
sum_trust = 0
groups = self.crud.read_groups_file()
for group in groups :
if group['List_of_members'] == user_group:
sum_trust += group['Trust']
avg_group_trust = sum_trust / len(groups)
# difference de jours entre last_seen_msg et first_seen_msg
user_activity = self.substract_dates(self.crud.get_user_data(email_adr, "Date_of_last_seen_message"),
self.crud.get_user_data(email_adr, "Date_of_first_seen_message"))
if(calculation_mode == 1):
spam = self.e_mail.is_spam_function_one(spam, user_activity, trust, avg_group_trust)
elif(calculation_mode == 2):
spam = self.e_mail.is_spam_function_two(spam, trust, avg_group_trust)
elif(calculation_mode == 0):
spam = self.e_mail.is_spam(subject, body, is_log_est, is_log_combo, 0)
# mettre a jour l'utilisateur avec la nouvelle valeur de spam
self.update_user_info(email_adr, date, spam)
return True
def substract_dates(self, last_seen_msg, first_seen_msg):
# calcul de difference de jours entre le dernier et le premier message
last_seen_msg = str(last_seen_msg).split("-")
first_seen_msg = str(first_seen_msg).split("-")
user_activity = date(int(last_seen_msg[0]), int(last_seen_msg[1]), int(last_seen_msg[2]))
- date(int(first_seen_msg[0]), int(first_seen_msg[1]), int(first_seen_msg[2]))
# convertir la soustraction en int
user_activity = int((str(user_activity).split(" "))[0])
return user_activity