def tf_idf_trans_feature_vector():
token_array = text_processed()
training_token_array, test_token_array = split_string_2_data_array(
token_array, 0.8)
print(token_array)
vectorizer = TfidfTransformer(stop_words='english', analyzer="word")
# tokenize and build vocab
X = vectorizer.fit_transform(token_array)
analyze = vectorizer.build_analyzer()
print(analyze("subject is not the case"))
# summarize
print(vectorizer.get_feature_names())
# summarize encoded vector
print(X.toarray())
return X
