u++の備忘録

言語処理100本ノック 2020「32. 動詞の原形」

問題文

nlp100.github.io

問題の概要

30. 形態素解析結果の読み込み」で作成したデータ構造から「x['pos'] == '動詞'」の「base」部分を取り出します。

def parse_mecab(block):
    res = []
    for line in block.split('\n'):
        if line == '':
            return res
        (surface, attr) = line.split('\t')
        attr = attr.split(',')
        lineDict = {
            'surface': surface,
            'base': attr[6],
            'pos': attr[0],
            'pos1': attr[1]
        }
        res.append(lineDict)


def extract_base(block):
    res = list(filter(lambda x: x['pos'] == '動詞', block))
    res = [r['base'] for r in res]
    return res


filename = 'ch04/neko.txt.mecab'
with open(filename, mode='rt', encoding='utf-8') as f:
    blocks = f.read().split('EOS\n')
blocks = list(filter(lambda x: x != '', blocks))
blocks = [parse_mecab(block) for block in blocks]
ans = [extract_base(block) for block in blocks]
print(ans[5])