# 33. サ変名詞
# サ変接続の名詞をすべて抽出せよ．
from knock_30 import parse
from itertools import chain, islice
sa_irregular_nouns = {
word['base']
for word in chain.from_iterable(parse()) if word['pos1'] == "サ変接続"
}
for i in islice(sa_irregular_nouns, 10):
print(i)
# 32. 動詞の原形
# 動詞の原形をすべて抽出せよ．
from knock_30 import parse
from itertools import chain, islice
verb_bases = {
word['base']
for word in chain.from_iterable(parse()) if word['pos'] == "動詞"
}
for i in islice(verb_bases, 10):
print(i)
# 34. 「AのB」
# 2つの名詞が「の」で連結されている名詞句を抽出せよ．
from knock_30 import parse
from itertools import chain, islice
noun_phrases = set()
for sent in parse():
for idx in range(len(sent) - 2):
if sent[idx]['pos'] == '名詞' and sent[idx + 2]['pos'] == '名詞' and sent[
idx + 1]['surface'] == 'の':
noun_phrases.add(
f"{sent[idx]['surface']}{'の'}{sent[idx+2]['surface']}")
for i in islice(noun_phrases, 10):
print(i)
def count():
word_count = Counter(word['base'] for word in chain.from_iterable(parse())
if not re.match(r'[!-〿]|\s', word['base']))
return word_count
# 31. 動詞
# 動詞の表層形をすべて抽出せよ．
from knock_30 import parse
from itertools import chain, islice
verb_surfaces = {word['surface'] for word in chain.from_iterable(parse())
if word['pos'] == "動詞"}
for i in islice(verb_surfaces, 10): print(i)