DP demo.ipynb

dp-demo.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "DP demo.ipynb",
      "provenance": [],
      "private_outputs": true,
      "collapsed_sections": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/NTT123/ccb5ecbb7f737c2630624dda463201dd/dp-demo.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bpePf2AZtYkw",
        "colab_type": "text"
      },
      "source": [
        "## Install Tools/Libraries"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JG7nn9cyGote",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## compilation\n",
        "apt install g++ unzip zip build-essential bison flex \n",
        "\n",
        "## download from google drive\n",
        "pip install gdown\n",
        "\n",
        "## bazel build system\n",
        "wget https://github.com/bazelbuild/bazel/releases/download/1.2.1/bazel-1.2.1-installer-linux-x86_64.sh\n",
        "chmod +x bazel-1.2.1-installer-linux-x86_64.sh\n",
        "## install bazel\n",
        "./bazel-1.2.1-installer-linux-x86_64.sh --user"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_vk6EJiRtfuP",
        "colab_type": "text"
      },
      "source": [
        "## Compile Postgres + differential-privacy library"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Wk1P8KZRj4uo",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## activate bazel\n",
        "source /home/scriptsuser/.bazel/bin/bazel-complete.bash"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FCcGIPsXGiGL",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## clone modified google differrential privacy library\n",
        "git clone https://github.com/NTT123/differential-privacy.git"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4bZsfWgGHKc9",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "cd differential-privacy/"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JVlisUJlNGgj",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## download, compile postgresql\n",
        "wget https://ftp.postgresql.org/pub/source/v11.6/postgresql-11.6.tar.bz2\n",
        "tar xjf postgresql-11.6.tar.bz2\n",
        "cd postgresql-11.6; ./configure; make -j2\n",
        "\n",
        "# install postgres + add postgres user\n",
        "sudo -s\n",
        "make install; echo -e \"abc123\\nabc123\\n\\n\\n\\n\\n\\n\\n\\n\" | adduser postgres; mkdir /usr/local/pgsql/data; chown postgres /usr/local/pgsql/data\n",
        "exit # back to ScriptUsers"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1n21Z7TFkxYA",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## go back to differential privacy directory\n",
        "cd .."
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MMfrYnasOiH7",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## fix build config (from macOS -> Linux)\n",
        "sed -i 's/darwin-fastbuild/k8-fastbuild/g' differential_privacy/postgres/BUILD"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JnNt2gxQk-PB",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## build dp library\n",
        "bazel build differential_privacy/..."
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "A7XxnUUqRawT",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## build and install dp extention for postgres\n",
        "export PG_DIR=/usr/local/pgsql; export PATH=\"$PATH:$HOME/bin\"; cd /content/differential-privacy; ./differential_privacy/postgres/install_extension.sh"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NVP8AbIIp0qo",
        "colab_type": "text"
      },
      "source": [
        "## Run postgres server + Initialize database"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Tr8GZGSBMZtn",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## start postgres server under posgres user\n",
        "su - postgres\n",
        "/usr/local/pgsql/bin/initdb -D /usr/local/pgsql/data\n",
        "/usr/local/pgsql/bin/pg_ctl -D /usr/local/pgsql/data -l logfile start\n",
        "exit"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6L9RyURwQgPc",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## create a database `test`\n",
        "sudo -u postgres /usr/local/pgsql/bin/createdb test"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "C-xKi6jgTVsQ",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## download csv dataset\n",
        "PATH=/home/scriptsuser/.local/bin gdown https://drive.google.com/uc?id=1_Iq_UWUngLX6nSGycqb8N5_9wBJ_cJ8E"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "N9kQdaGHT6g6",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## create an SQL script \n",
        "\n",
        "cat > init.sql <<EOL\n",
        "select current_database();\n",
        "create table transactions (InvoiceNo int,StockCode text,Description text,Quantity int,InvoiceDate text,UnitPrice numeric,CustomerID int,Country text);\n",
        "\n",
        "\\COPY transactions (InvoiceNo,StockCode,Description,Quantity,InvoiceDate,UnitPrice,CustomerID,Country) FROM './onlineretail.csv' CSV HEADER DELIMITER ',' encoding 'windows-1251';\n",
        "\n",
        "CREATE EXTENSION anon_func;\n",
        "EOL"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FuPNEjv-RRiC",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "## run initial SQL script\n",
        "sudo -u postgres /usr/local/pgsql/bin/psql -d test -f init.sql"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}