VagrantでJupyter LabとMongoDBをインストールした仮想マシン(CentOS7.4)を構築する

Jupyter Labでインタラクティブなコンピューティング環境を提供する事ができます。

〇Jupyter Labの画面

仮想マシンの構築方法

以下のVagrantfileで、Jupyter LabとMongoDBをインストールした仮想マシン(CentOS7.4)を構築できます。

Vagrantfile

VAGRANTFILE_API_VERSION = "2"

Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
  config.vm.box = "bento/centos-7.4"
  config.vm.hostname = "co74jupyterlabmongodb"
  config.vm.provider :virtualbox do |vbox|
     vbox.name = "co74jupyterlabmongodb"
     vbox.cpus = 2
     vbox.memory = 2048
     vbox.customize ["modifyvm", :id, "--nicpromisc2","allow-all"]
  end
config.vm.network "private_network", ip: "192.168.55.105", :netmask => "255.255.255.0"
config.vm.network "public_network", ip:"192.168.1.105", :netmask => "255.255.255.0"
  config.vm.provision "shell", inline: <<-SHELL
localectl set-locale LANG=ja_JP.UTF-8

yum -y install curl

cat << EOF > /etc/init.d/disable-transparent-hugepages
#!/bin/bash
### BEGIN INIT INFO
# Provides:          disable-transparent-hugepages
# Required-Start:    $local_fs
# Required-Stop:
# X-Start-Before:    mongod mongodb-mms-automation-agent
# Default-Start:     2 3 4 5
# Default-Stop:      0 1 6
# Short-Description: Disable Linux transparent huge pages
# Description:       Disable Linux transparent huge pages, to improve
#                    database performance.
### END INIT INFO

case \\$1 in
  start)
    if [ -d /sys/kernel/mm/transparent_hugepage ]; then
      thp_path=/sys/kernel/mm/transparent_hugepage
    elif [ -d /sys/kernel/mm/redhat_transparent_hugepage ]; then
      thp_path=/sys/kernel/mm/redhat_transparent_hugepage
    else
      return 0
    fi

    echo 'never' > \\${thp_path}/enabled
    echo 'never' > \\${thp_path}/defrag

    re='^[0-1]+$'
    if [[ \\$(cat \\${thp_path}/khugepaged/defrag) =~ \\$re ]]
    then
      # RHEL 7
      echo 0  > \\${thp_path}/khugepaged/defrag
    else
      # RHEL 6
      echo 'no' > \\${thp_path}/khugepaged/defrag
    fi

    unset re
    unset thp_path
    ;;
esac
EOF
chmod 755 /etc/init.d/disable-transparent-hugepages
chkconfig --add disable-transparent-hugepages
/etc/init.d/disable-transparent-hugepages start

cat << EOF > /etc/yum.repos.d/mongodb-org-3.6.repo
[mongodb-org-3.6]
name=MongoDB Repository
baseurl=https://repo.mongodb.org/yum/redhat/7/mongodb-org/3.6/x86_64/
gpgcheck=1
enabled=1
gpgkey=https://www.mongodb.org/static/pgp/server-3.6.asc
EOF
yum install -y mongodb-org

mkdir -p /srv/mongodb/
openssl rand -base64 741 > /srv/mongodb/mongodb-keyfile
chmod 600 /srv/mongodb/mongodb-keyfile
chown mongod:mongod /srv/mongodb/mongodb-keyfile

systemctl enable mongod
systemctl start mongod

# wait until mongod starts listening.
while netstat -lnt | awk '$4 ~ /:27017$/ {exit 1}'; do sleep 10; done

cat << EOF | mongo
var db = db.getSiblingDB('admin');
db.createUser({user:"admin",pwd:"admin",roles:[{role:"userAdminAnyDatabase",db:"admin"}]});
EOF


echo 'security:' >> /etc/mongod.conf
echo '  authorization: enabled' >> /etc/mongod.conf
echo '  keyFile: /srv/mongodb/mongodb-keyfile' >> /etc/mongod.conf
sed -i -e 's/bindIp: 127.0.0.1/bindIp: 192.168.55.105/' /etc/mongod.conf

systemctl restart mongod
while netstat -lnt | awk '$4 ~ /:27017$/ {exit 1}'; do sleep 10; done

# create a test user.
cat << EOF | mongo --host 192.168.55.105 -u "admin" -p "admin" --authenticationDatabase "admin"
var db = db.getSiblingDB('test');
db.createUser({user:"test",pwd:"test",roles:[{role:"readWrite",db:"test"}]});
EOF

# create sample data
cat << EOF | mongo --host 192.168.55.105 -u "test" -p "test" --authenticationDatabase "test"
var db = db.getSiblingDB('test');
db.products.insert( { item: "chair", qty: 15 } );
db.products.insert( { item: "table", qty: 3 } );
db.products.find();
EOF



# install anaconda
wget https://repo.continuum.io/archive/Anaconda3-5.1.0-Linux-x86_64.sh
chmod +x Anaconda3-5.1.0-Linux-x86_64.sh
./Anaconda3-5.1.0-Linux-x86_64.sh -b -p /opt/anaconda
source /opt/anaconda/bin/activate
pip install --upgrade pip
pip install jupyterlab

# install pymongo
pip install pymongo

useradd py
mkdir -p /home/py
chown -R py:py /home/py
sudo -u py bash -c "mkdir /home/py/.jupyter"
sudo -u py bash -c "cat << EOF > /home/py/.jupyter/jupyter_notebook_config.py
conf = get_config()
conf.NotebookApp.ip = '*'
conf.NotebookApp.open_browser = False
conf.NotebookApp.port = 8080
conf.NotebookApp.token = 'jupyter'
EOF"

cat << EOF > /etc/systemd/system/jupyter.service
[Unit]
Description=Jupyter notebook
[Service]
Type=simple
ExecStartPre=source /opt/anaconda/bin/activate
ExecStart=/opt/anaconda/bin/jupyter lab
User=py
Group=py
WorkingDirectory=/home/py
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
EOF
sudo systemctl enable jupyter
sudo systemctl start jupyter

echo 'access -> http://192.168.55.105:8080/?token=jupyter'
SHELL
end

〇動作確認用コード

import pymongo

# connect to mongodb
client = pymongo.MongoClient('mongodb://test:test@192.168.55.105/test')

db = client.test
products = db.products

for data in products.find():
  print(data)

関連情報

・Jupyterに関する他の情報はこちらを参照してください。