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')
# Classifies every file under "folder" as either a Python or Java file,
# considering you have subdirectories with examples of each language.
#print classify_folder("folder")
print('')
print(' == Low Level Functions == ')
print(' -- Classic Cancer Test Problem --')
# 1% chance of having cancer.
b = Bayes([('not cancer', 0.99), ('cancer', 0.01)])
# Test positive, 9.6% false positives and 80% true positives
b.update((9.6, 80))
print(b)
print('Most likely:', b.most_likely())
print('')
print(' -- Spam Filter With Existing Model --')
# Database with number of sightings of each words in (genuine, spam)
# 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:
def test_most_likely(self):
b = Bayes({'a': 9, 'b': 1})
self.assertEqual(b.most_likely(), 'a')
self.assertEqual(b.most_likely(0), 'a')
self.assertEqual(b.most_likely(0.89), 'a')
self.assertIsNone(b.most_likely(0.91))
def test_most_likely(self):
b = Bayes({'a': 9, 'b': 1})
self.assertEqual(b.most_likely(), 'a')
self.assertEqual(b.most_likely(0), 'a')
self.assertEqual(b.most_likely(0.89), 'a')
self.assertIsNone(b.most_likely(0.91))
# Classifies every file under "folder" as either a Python or Java file,
# considering you have subdirectories with examples of each language.
#print classify_folder("folder")
print('')
print(' == Low Level Functions == ')
print(' -- Classic Cancer Test Problem --')
# 1% chance of having cancer.
b = Bayes([('not cancer', 0.99), ('cancer', 0.01)])
# Test positive, 9.6% false positives and 80% true positives
b.update((9.6, 80))
print(b)
print('Most likely:', b.most_likely())
print('')
print(' -- Spam Filter With Existing Model --')
# Database with number of sightings of each words in (genuine, spam)
# 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:
