韻を扱いたいpart4 - Qiita

from pykakasi import kakasi import re from collections import defaultdict from janome.tokenizer import Tokenizer with open("./gennama.txt","r") as f: data = f.read() tokenizer = Tokenizer() tokens = tokenizer.tokenize(data) surface_list = [] part_of_speech_list = [] for token in tokens: surface_list.append(token.surface) part_of_speech_list.append(token.part_of_speech.split(",")[0]) segment_text =