import os
import csv

from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
from konlpy.tag import Okt

okt = Okt()
def DocToNouns(docs):
    return [{
        'id': i,
        'nouns': ' '.join(okt.nouns(doc)),
    } for i, doc in enumerate(docs)]

BASE_DIR = os.path.dirname(os.path.abspath(__file__))

posts = []
with open(os.path.join(BASE_DIR + '/', 'data.csv'), 'r', encoding='utf-8-sig') as db:
    reader = csv.reader(db)
    for data in reader:
        posts.append(data)

nouns = DocToNouns(posts)
print(nouns)