language_model.py 文件源码

def generate(cfd, start_word, n):
        word = start_word
        words = []
        for i in range(n):
            words.append(word)
            # word = cfd[word].max()
            fd = cfd[word]
            n_next_words = sum(fd.values())
            if n_next_words > 0:
                probabilities = [fd[w]/float(n_next_words) for w in sorted(fd.keys())]
                word = choice(sorted(fd.keys()), p=probabilities)
            else:
                # Pick random word
                old_word = word
                # TODO: use unigram probabilities later
                word = choice(cfd.keys())
        words.append(word)
        sentence = ' '.join(words)
        # TODO: modify above for punctuation
        return sentence