joblib.dump(DTBody, 'Saved_Model/Body/Decision_Tree_Model_Body')
if __name__ == '__main__':
numpy.set_printoptions(threshold=sys.maxsize)
# The first part is to create the dataset
data = Extract_features.Create_the_dataSet()
y = data['label']
# We get the important word from the headers
WordsToVector.getTheWordHeader(data)
# We create a list with email object
# each email contains the header, body and the label
list_emails = Email.List_of_emails(data)
# Split the dataset for 80% train and 20% test
X_train, X_test, y_train, y_test = train_test_split(list_emails, y, train_size=0.8)
# make a list of all the header of the emails
email_headers_train = [x.header for x in X_train if not pd.isnull(x.header)]
email_headers_test = [x.header for x in X_test if not pd.isnull(x.header)]
# Two way to work on text: 1) CountVector 2)TfIdf
CountTrain, CountTest, vector = WordsToVector.CountVector(email_headers_train, email_headers_test)
CountTrainTf, CountTestTf, vectorTf = WordsToVector.TfIdf(email_headers_train, email_headers_test)
y_train = y_train.fillna("0")
y_test = y_test.fillna("0")
