classifier.py 文件源码

def createData():
    spwords = [unidecode(a.lower()) for a in set(nltk.corpus.cess_esp.words()) if len(a)>3]
    enwords = [a.lower() for a in set(nltk.corpus.brown.words()) if len(a)>3]
    jpwords = [unidecode(a) for a in jeita.words() if (len(unidecode(a)) and unidecode(a)[0].islower())]
    jpwords = [a for a in set(jpwords) if len(a)>3]
    # minLen = min(len(enwords), len(spwords), len(jpwords))

    featuresets = \
        [(createTupleDict(w,numChars),'English') for w in enwords] + \
        [(createTupleDict(w,numChars),'Spanish') for w in spwords] + \
        [(createTupleDict(w,numChars),'Japanese') for w in jpwords]

    random.shuffle(featuresets)

    l=int(len(featuresets)*0.8)

    training_set = featuresets[:l]
    testing_set = featuresets[l:]
    return (training_set, testing_set)