def classify_email_with_enron(email):
"""
Classify spam possibility of given email with enron dataset.
Args:
email (str):
Raw e-mail.
Returns:
Spam or not.
"""
vocablary_dict = email_processor.create_enron_dictionary()
feature_vector = email_processor.feature_vector_from_email(
email, vocablary_dict)
double_dimesion_email = np.reshape(feature_vector, (-1, 3000))
if os.path.exists('enron_features_matrix.npy'
) == False & os.path.exists('enron_labels.npy') == False:
features_matrix, labels = email_processor.extract_enron_features()
np.save('enron_features_matrix.npy', features_matrix)
np.save('enron_labels.npy', labels)
else:
features_matrix = np.load('enron_features_matrix.npy')
labels = np.load('enron_labels.npy')
X_train, _, y_train, _ = train_test_split(features_matrix,
labels,
test_size=0.40)
linear_svc.fit(X_train, y_train)
return linear_svc.predict(double_dimesion_email)
def test_feature_vector_from_email(self):
email = "<*****@*****.**> Do You Want To Make $1000 Or More Per Week? https://github.com"
vocablary_dict = email_processor.get_vocablary_dict()
feature_vector = email_processor.feature_vector_from_email(
email, vocablary_dict
)
self.assertEqual(len(feature_vector), 1899)
def classify_email(email):
"""
Classify spam possibility of given email.
Args:
email (str):
Raw e-mail.
Returns:
Spam or not.
"""
train_svm()
vocablary_dict = email_processor.get_vocablary_dict()
feature_vector = email_processor.feature_vector_from_email(
email, vocablary_dict)
double_dimesion_email = np.reshape(feature_vector, (-1, 1899))
spam_prediction = linear_svm.predict(double_dimesion_email)
return spam_prediction