extract_feature.py 文件源码

def extract_dictionary_feature(file_name, col_tag=0, col_content=1):
    # ????
    adv = codecs.open('./data/vocabulary/adv.txt', 'rb', encoding='utf-8').read().split('\n')
    inverse = codecs.open('./data/vocabulary/inverse.txt', 'rb', encoding='utf-8').read().split('\n')
    negdict = codecs.open('./data/vocabulary/negdict.txt', 'rb', encoding='utf-8').read().split('\n')
    posdict = codecs.open('./data/vocabulary/posdict.txt', 'rb', encoding='utf-8').read().split('\n')

    contents = pd.read_excel(file_name, header=None)

    print 'cut words...'
    cw = lambda x: [pair for pair in psg.lcut(x) if pair.word not in stopwords]
    contents['pairs'] = contents[col_content].apply(cw)
    matrix = reviews2matrix(list(contents['pairs']), posdict, negdict, inverse, adv)
    x = matrix2vec(matrix)
    y = list(contents[col_tag])
    return x, y