def text_vector(self, text, laplace): text = nlp.tokens(text) vector = [] for word in self.word_list: score = 1 if word in text else 0 vector.append(score) return vector
def build_word_list(self): text, _ = load_data.load_questions(self.file_path) text = text[0::2] text = [nlp.tokens(t) for t in text] text = [word for sentence in text for word in sentence] text = list(set(text)) text.sort() return text