def get_word_dict()

in models.py [0:0]

• 10 lines of code
• 6 McCabe index (conditional complexity)

    def get_word_dict(self, sentences, tokenize=True):
        # create vocab of words
        word_dict = {}
        sentences = [s.split() if not tokenize else self.tokenize(s) for s in sentences]
        for sent in sentences:
            for word in sent:
                if word not in word_dict:
                    word_dict[word] = ''
        word_dict[self.bos] = ''
        word_dict[self.eos] = ''
        return word_dict