def test_extract_events_odds(self):
instances = {'spam': ["buy viagra", "buy cialis"] * 100 + ["meeting love"],
'genuine': ["meeting tomorrow", "buy milk"] * 100}
odds = Bayes.extract_events_odds(instances)
b = Bayes({'spam': 0.9, 'genuine': 0.1})
b.update_from_events('buy coffee for meeting'.split(), odds)
self.assertEqual(b.most_likely(0.8), 'genuine')
def test_extract_events_odds(self):
instances = {
'spam': ["buy viagra", "buy cialis"] * 100 + ["meeting love"],
'genuine': ["meeting tomorrow", "buy milk"] * 100
}
odds = Bayes.extract_events_odds(instances)
b = Bayes({'spam': 0.9, 'genuine': 0.1})
b.update_from_events('buy coffee for meeting'.split(), odds)
self.assertEqual(b.most_likely(0.8), 'genuine')
# emails.
words_odds = {'buy': (5, 100), 'viagra': (1, 1000), 'meeting': (15, 2)}
# Emails to be analyzed.
emails = [
"let's schedule a meeting for tomorrow", # 100% genuine (meeting)
"buy some viagra", # 100% spam (buy, viagra)
"buy coffee for the meeting", # buy x meeting, should be genuine
]
for email in emails:
# Start with priors of 90% chance being genuine, 10% spam.
# Probabilities are normalized automatically.
b = Bayes([('genuine', 90), ('spam', 10)])
# Update probabilities, using the words in the emails as events and the
# database of chances to figure out the change.
b.update_from_events(email.split(), words_odds)
# Print the email and if it's likely spam or not.
print(email[:15] + '...', b.most_likely())
print('')
print(' -- Spam Filter With Email Corpus -- ')
# Email corpus. A hundred spam emails to buy products and with the word
# "meeting" thrown around. Genuine emails are about meetings and buying
# milk.
instances = {
'spam': ["buy viagra", "buy cialis"] * 100 + ["meeting love"],
'genuine': ["meeting tomorrow", "buy milk"] * 100
}
def test_update_from_events(self):
b = Bayes([1, 1])
b.update_from_events(['a', 'a', 'a'], {'a': (0.5, 2)})
self.assertEqual(b, [0.5 ** 3, 2 ** 3])
def test_update_from_events(self):
b = Bayes([1, 1])
b.update_from_events(['a', 'a', 'a'], {'a': (0.5, 2)})
self.assertEqual(b, [0.5**3, 2**3])
# emails.
words_odds = {'buy': (5, 100), 'viagra': (1, 1000), 'meeting': (15, 2)}
# Emails to be analyzed.
emails = [
"let's schedule a meeting for tomorrow", # 100% genuine (meeting)
"buy some viagra", # 100% spam (buy, viagra)
"buy coffee for the meeting", # buy x meeting, should be genuine
]
for email in emails:
# Start with priors of 90% chance being genuine, 10% spam.
# Probabilities are normalized automatically.
b = Bayes([('genuine', 90), ('spam', 10)])
# Update probabilities, using the words in the emails as events and the
# database of chances to figure out the change.
b.update_from_events(email.split(), words_odds)
# Print the email and if it's likely spam or not.
print(email[:15] + '...', b.most_likely())
print('')
print(' -- Spam Filter With Email Corpus -- ')
# Email corpus. A hundred spam emails to buy products and with the word
# "meeting" thrown around. Genuine emails are about meetings and buying
# milk.
instances = {'spam': ["buy viagra", "buy cialis"] * 100 + ["meeting love"],
'genuine': ["meeting tomorrow", "buy milk"] * 100}
# Use str.split to extract features/events/words from the corpus and build
# the model.
