Dockerで日本語形態素解析エンジンMeCabのPython開発環境を構築～後半

root@457cbb65a38c:/# pip3 install --upgrade pip
root@457cbb65a38c:/# pip3 install upyterlab
root@457cbb65a38c:/# pip3 install pandas
root@457cbb65a38c:/# pip3 install mecab-python3
root@457cbb65a38c:/# pip3 list
Package              Version    
-------------------- -----------
...(略)
jupyterlab           3.4.3
...(略)
mecab-python3        1.0.5
...(略)
pandas               1.4.2
...(略)
pip                  20.0.2
...(略)
root@457cbb65a38c:/# 

root@457cbb65a38c:/# python3
Python 3.8.10 (default, Mar 15 2022, 12:22:08) 
[GCC 9.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import MeCab
>>> wakati = MeCab.Tagger("-Owakati")
Traceback (most recent call last):
  File "/usr/local/lib/python3.8/dist-packages/MeCab/__init__.py", line 133, in __init__
    super(Tagger, self).__init__(args)
RuntimeError

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib/python3.8/dist-packages/MeCab/__init__.py", line 135, in __init__
    raise RuntimeError(error_info(rawargs)) from ee
RuntimeError:
----------------------------------------------------------

Failed initializing MeCab. Please see the README for possible solutions:

    https://github.com/SamuraiT/mecab-python3#common-issues

If you are still having trouble, please file an issue here, and include the
ERROR DETAILS below:

    https://github.com/SamuraiT/mecab-python3/issues

issueを英語で書く必要はありません。

------------------- ERROR DETAILS ------------------------
arguments: -Owakati
[ifs] no such file or directory: /usr/local/etc/mecabrc
----------------------------------------------------------

root@457cbb65a38c:/# find / -name mecabrc -print
/etc/mecabrc

root@457cbb65a38c:/# ln -s /etc/mecabrc /usr/local/etc/mecabrc
root@457cbb65a38c:/# find / -name mecabrc -print
/etc/mecabrc
/usr/local/etc/mecabrc
root@457cbb65a38c:/# ls -l /usr/local/etc/
total 4
drwxr-xr-x 4 root root 4096 Jun 19 01:52 jupyter
lrwxrwxrwx 1 root root   12 Jun 19 02:14 mecabrc -> /etc/mecabrc

root@457cbb65a38c:/# python3
Python 3.8.10 (default, Mar 15 2022, 12:22:08)
[GCC 9.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import MeCab
>>> wakati = MeCab.Tagger("-Owakati")
>>> print(wakati.parse("私はpythonが大好きです。"))
私 は python が 大好き です 。

>>> mecab = MeCab.Tagger()
>>> text = "今日はよい天気です。"
>>> print(mecab.parse(text))
今日    名詞,副詞可能,*,*,*,*,今日,キョウ,キョー
は      助詞,係助詞,*,*,*,*,は,ハ,ワ
よい    形容詞,自立,*,*,形容詞・アウオ段,基本形,よい,ヨイ,ヨイ
天気    名詞,一般,*,*,*,*,天気,テンキ,テンキ
です    助動詞,*,*,*,特殊・デス,基本形,です,デス,デス
。      記号,句点,*,*,*,*,。,。,。
EOS

>>>

# ベースイメージ
FROM ubuntu:20.04

# 必要そうなものをinstall
RUN apt-get update && apt-get -y upgrade

# 任意バージョンのpython install
RUN apt -y install python3-pip

# mecabをインストール
RUN apt -y install mecab
RUN apt -y install libmecab-dev
RUN apt -y install mecab-ipadic-utf8

#必要なpythonパッケージをpipでインストール
RUN pip3 install --upgrade pip && pip3 install jupyterlab
RUN pip3 install pandas
RUN pip3 install mecab-python3

#サイズ削減のため不要なものは削除
RUN apt-get autoremove -y

# ポートを開けておきます
EXPOSE 8888

# ホストとのデータやり取りにボリュームを確保
VOLUME [ "/myvol" ]

# mecab-python3を動かすためにmecabrcのシンボリックリンク追加
RUN ln -s /etc/mecabrc /usr/local/etc/mecabrc

# イメージ作成
docker build -t py_env .

# コンテナ作成
docker create -it -v $pwd/myvol:/myvol --name mycontainer -p 8888:8888 py_env

# コンテナ起動
docker start mycontainer

# dockerに接続
docker exec -it mycontainer bash

root@34ab452dba78:/# jupyter lab --port=8888 --ip=0.0.0.0 --allow-root
[I 2022-06-19 03:40:39.157 ServerApp] jupyterlab | extension was successfully linked.
[I 2022-06-19 03:40:39.168 ServerApp] nbclassic | extension was successfully linked.
...(略)
[W 2022-06-19 03:40:39.375 ServerApp] No web browser found: could not locate runnable browser.
[C 2022-06-19 03:40:39.376 ServerApp]

    To access the server, open this file in a browser:
        file:///root/.local/share/jupyter/runtime/jpserver-17-open.html
    Or copy and paste one of these URLs:
        http://34ab452dba78:8888/lab?token=733434bab61760811f2d2ae310f5bb154a17954d8e1fe81b
     or http://127.0.0.1:8888/lab?token=733434bab61760811f2d2ae310f5bb154a17954d8e1fe81b

import MeCab
mecab = MeCab.Tagger()
text = "東京駅から地下鉄に乗って、NHKまで行ってみた。"
print(mecab.parse(text))