def build_training_set_from_text(text, category, sender=None, subject=None):
text = fix_bad_unicode(text)
text = strip_signature(text, sender)
features = extract_bigrams(text)
training_set = []
training_set = training_set + [(get_feature(word), category) for word in features]
training_set = training_set + [({sender: True}, category), ({subject: True}, category)]
return training_set
def build_training_set_from_text(text, category, sender=None, subject=None):
text = fix_bad_unicode(text)
text = strip_signature(text, sender)
features = extract_bigrams(text)
training_set = []
training_set = training_set + [(get_feature(word), category) for word in features]
training_set = training_set + [({sender: True}, category), ({subject: True}, category)]
return training_set
def classify(text, sender=None, subject=None):
training_set = load_training_set()
classifier = NaiveBayesClassifier.train(training_set)
test_data = bag_of_words(extract_bigrams(text))
if sender is not None:
test_data[sender] = True
if subject is not None:
test_data[subject] = True
classified = classifier.prob_classify(test_data)
pprint({categories[sample]: classified.prob(sample) for sample in classified.samples()})
return categories[classified.max()]
def classify(text, sender=None, subject=None):
training_set = load_training_set()
classifier = NaiveBayesClassifier.train(training_set)
test_data = bag_of_words(extract_bigrams(text))
if sender is not None:
test_data[sender] = True
if subject is not None:
test_data[subject] = True
classified = classifier.prob_classify(test_data)
pprint({
categories[sample]: classified.prob(sample)
for sample in classified.samples()
})
return categories[classified.max()]
def build_training_set(path='../email_dataset'):
training_set = []
files = listdir(path)
for email_file in files:
with io.open('{}/{}'.format(path, email_file), 'r', encoding='utf8') as email:
print u'Parsing file: {}'.format(email_file)
category, sender, receiver, subject = int(
email.readline().strip()), email.readline().strip(), email.readline().strip(), email.readline().strip()
print u'Training set updated with: [{}]'.format(subject)
text = fix_bad_unicode(email.read())
text = strip_signature(text, sender)
features = extract_bigrams(text)
training_set = training_set + [(get_feature(word), category) for word in features]
training_set = training_set + [({sender: True}, category), ({subject: True}, category)]
return training_set
def build_training_set(path="../email_dataset"):
training_set = []
files = listdir(path)
for email_file in files:
with io.open("{}/{}".format(path, email_file), "r", encoding="utf8") as email:
print u"Parsing file: {}".format(email_file)
category, sender, receiver, subject = (
int(email.readline().strip()),
email.readline().strip(),
email.readline().strip(),
email.readline().strip(),
)
print u"Training set updated with: [{}]".format(subject)
text = fix_bad_unicode(email.read())
text = strip_signature(text, sender)
features = extract_bigrams(text)
training_set = training_set + [(get_feature(word), category) for word in features]
training_set = training_set + [({sender: True}, category), ({subject: True}, category)]
return training_set
def create_training_dict(text, category):
tokens = extract_bigrams(text)
return [(bag_of_words(tokens), category)]
def create_training_dict(text, category):
tokens = extract_bigrams(text)
return [(bag_of_words(tokens), category)]
