# Vectorize ticket descriptions using Word2Vec
textList = [TaggedDocument(doc, [i]) for i, doc in enumerate(unformattedList)]
numCores = multiprocessing.cpu_count() # Compute the number of logical processors (how many workers we will use to train the Doc2Vec model)
x = np.array(Doc2Vec(textList, workers=numCores, vector_size=150))

# Vectorize ticket labels/tags using MultiLabelBinarizer
tagList = relevantDF.Tags
vectorizer2 = MultiLabelBinarizer()
vectorizer2.fit(tagList)
y = vectorizer2.transform(tagList)

# Split test data and convert test data to arrays
xTrain, xTest, yTrain, yTest = train_test_split(x, y, test_size=0.20)