markov2.py 文件源码

def train(self, chain_len = None):
        """ Trains the markov data structure by creating chains of desired length """
        if not chain_len:
            chain_len = self.CHAIN_LENGTH

        self.CHAIN_LEN = chain_len

        self.everything['corpus'] = {}
        self.corpus = self.everything['corpus']

        for f in self.everything['input']:
            for line in sent_tokenize( self.everything['input'][f] ):
                words = word_tokenize(line)

                for chain in self._make_chains(words):
                    k = " ".join( chain[:-1] ) # key is everything but last word
                    v = chain[-1] # value is last word

                    try:
                        self.corpus[k].append(v)
                    except:
                        self.corpus[k] = [v]