def test_update(self):
b = Bayes([1, 2])
b.update((2, 1))
self.assertEqual(b, [1, 1])
b.update((2, 1))
self.assertEqual(b, [2, 1])
b.update((2, 0))
self.assertEqual(b, [1, 0])
def test_update(self):
b = Bayes([1, 2])
b.update((2, 1))
self.assertEqual(b, [1, 1])
b.update((2, 1))
self.assertEqual(b, [2, 1])
b.update((2, 0))
self.assertEqual(b, [1, 0])
# you have directories with examples of each language.
#print classify_file("unknown_file", ["java_files", "python_files"])
# 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
]
# you have directories with examples of each language.
#print classify_file("unknown_file", ["java_files", "python_files"])
# 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
]
