한글 자연어 처리를 위한 준비, colab, 기타등등

기본 모듈 확인

import tensorflow as tf
import gensim
import sklearn
import keras
import nltk
import konlpy

"""from bs4 import BeautifulSoup
import requests
import openpyxl
import math
import pandas
import re"""

print("tensorflow: "+tf.__version__)
print("keras: "+ keras.__version__)
print("gensim: "+ gensim.__version__)
print("sklearn: "+ sklearn.__version__)
print("nltk: "+ nltk.__version__)

konlpy 설치

%%bash
apt-get update
apt-get install g++ openjdk-8-jdk python-dev python3-dev
pip3 install JPype1
pip3 install konlpy

Java 환경변수 설정

%env JAVA_HOME "/usr/lib/jvm/java-8-openjdk-amd64"

mecab 설치

%%bash
bash <(curl -s https://raw.githubusercontent.com/konlpy/konlpy/master/scripts/mecab.sh)
pip3 install /tmp/mecab-python-0.996