def main():
data = []
for verdict in ['spam', 'not_spam']:
for files in glob.glob(PATH + verdict + "/*")[:500]:
is_spam = True if verdict == 'spam' else False
with open(files, "r", encoding='utf-8', errors='ignore') as f:
for line in f:
if line.startswith("Subject:"):
subject = re.sub("^Subject: ", "", line).strip()
data.append((subject, is_spam))
random.seed(0)
train_data, test_data = split_data(data, 0.75)
classifier = NaiveBayesClassifier()
classifier.train(train_data)
print("Spam" if classifier.classify("Get free laptops now!") > 0.5 else
"Not Spam")
classified = [(subject, is_spam, classifier.classify(subject))
for subject, is_spam in test_data]
count = Counter((is_spam, spam_probability > 0.5)
for _, is_spam, spam_probability in classified)
spammiest_hams, hammiest_spams = most_misclassified(classified)
print("Accuracy: ", accuracy(count))
print("Precision: ", precision(count))
print("Recall: ", recall(count))
print("\nTop 5 falsely classified as spam:\n\n", spammiest_hams)
print("\nTop 5 falsely classified as not spam:\n\n", hammiest_spams)
print("\nMost spammiest words: ", spammiest_word(classifier))
def spamFilterChecker():
print('Received the JAVA Request!')
# Get the text data from the JAVA Program.
req_data = abhishek_request.get_json()
text_to_be_classified = req_data['text_to_be_classified']
print(text_to_be_classified)
# ----------------------------------------------------------------------------
# Make a POST request to the plino Spam API.
# ----------------------------------------------------------------------------
data = []
for verdict in ['spam', 'not_spam']:
for files in glob.glob(PATH + verdict + "/*")[:500]:
is_spam = True if verdict == 'spam' else False
with open(files, "r", encoding='utf-8', errors='ignore') as f:
for line in f:
if line.startswith("Subject:"):
subject = re.sub("^Subject: ", "", line).strip()
data.append((subject, is_spam))
random.seed(0)
train_data, test_data = split_data(data, 0.80)
classifier = NaiveBayesClassifier()
classifier.train(train_data)
json_response = ""
value = classifier.classify(text_to_be_classified)
if value < 0.9:
json_response = "{'email_class' : 'spam'}"
else:
json_response = "{'email_class' : 'ham'}"
print("====================================================")
print("POSSIBILITY OF HAM : ", value)
print(json_response)
print("====================================================")
return json_response
for _, row in df.iterrows():
if row['v1'] == 'spam':
spam_data.append(row['v2'])
else:
legit_data.append(row['v2'])
NB_classifier = NaiveBayesClassifier()
spam_train = spam_data[:int(len(spam_data) * 2 / 3)]
spam_test = spam_data[int(len(spam_data) * 2 / 3):]
legit_train = legit_data[:int(len(legit_data) * 2 / 3)]
legit_test = legit_data[int(len(legit_data) * 2 / 3):]
NB_classifier.train(spam_train, legit_train)
spam_accuracy = 0
legit_accuracy = 0
for text in spam_test:
prediction = NB_classifier.predict(text)
spam_accuracy += prediction
spam_accuracy /= len(spam_test)
for text in legit_test:
prediction = NB_classifier.predict(text)
legit_accuracy += 1 - prediction
legit_accuracy /= len(legit_test)
print("Spam Text prediction accuracy:", spam_accuracy)
# glob.glob returns every filename that matches the wildcarded path
for fn in glob.glob(path):
is_spam = "ham" not in fn
with open(fn, "r") as file:
for line in file:
if line.startswith("Subject:"):
# remove the leading "Subject: " and keep what's left
subject = re.sub(r"^Subject: ", "", line).strip()
data.append((subject, is_spam))
random.seed(0)
train_data, test_data = split_data(data, 0.75)
classifier = NaiveBayesClassifier()
classifier.train(train_data)
# triplets (subject, actual is_spam, predicted spam probability)
classified = [(subject, is_spam, classifier.classify(subject)) for subject, is_spam in test_data]
# assume that spam_probability > 0.5 corresponds to spam prediction
# and count the combinations of (actual is_spam, predicted is_spam)
counts = Counter((is_spam, spam_probability > 0.5) for _, is_spam, spam_probability in classified)
# sort by spam_probability from smallest to largest
classified.sort(key=lambda row: row[2])
# the highest predicted spam probabilities among the non-spams
spammiest_hams = filter(lambda row: not row[1], classified)[-5:]
# the lowest predicted spam probabilities among the actual spams
# glob.glob returns every filename that matches the wildcarded path
for fn in glob.glob(path):
is_spam = "ham" not in fn
with open(fn, 'r') as file:
for line in file:
if line.startswith("Subject:"):
# remove the leading "Subject: " and keep what's left
subject = re.sub(r"^Subject: ", "", line).strip()
data.append((subject, is_spam))
random.seed(0)
train_data, test_data = split_data(data, 0.75)
classifier = NaiveBayesClassifier()
classifier.train(train_data)
# triplets (subject, actual is_spam, predicted spam probability)
classified = [(subject, is_spam, classifier.classify(subject))
for subject, is_spam in test_data]
# assume that spam_probability > 0.5 corresponds to spam prediction
# and count the combinations of (actual is_spam, predicted is_spam)
counts = Counter((is_spam, spam_probability > 0.5)
for _, is_spam, spam_probability in classified)
# sort by spam_probability from smallest to largest
classified.sort(key=lambda row: row[2])
# the highest predicted spam probabilities among the non-spams
spammiest_hams = filter(lambda row: not row[1], classified)[-5:]