IdeologyAnalyzer.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "IdeologyAnalyzer.ipynb",
      "version": "0.3.2",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "metadata": {
        "id": "iU5O8J5DCKGN",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/gdrive')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "fi7ynVsgC8AR",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "\n",
        "df = pd.read_csv('/content/gdrive/PATH/TO/YOUR/VOTES/votes.csv', header=None, usecols=range(2,11)).transpose()\n",
        "votes = np.where(df < 0, 0, df)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "FqCxCZCSEjU7",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from sklearn.decomposition import PCA\n",
        "\n",
        "pca = PCA(n_components=2)\n",
        "reduced = pca.fit_transform(votes)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "DgN1LIbDsU-W",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "ev_ratio = pca.explained_variance_ratio_\n",
        "print(ev_ratio)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "bbWz67G6FR5m",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "colors = ['#ff2800', '#faf500', '#35a16b', '#0041ff', '#66ccff', '#ff99a0', '#ff9900', '#9a0079', '#663300']\n",
        "parties = ['Kashiwa-Seifu', 'Komei-to', 'NihonKyosan-to', 'Hakuai Club', 'Simin Side Net', 'Goken Shimin Kaigi', 'Hiroki Uchida', 'Kamihashi Izumi', 'Kitamura Kazuyuki']\n",
        "for i, row in enumerate(reduced):\n",
        "  plt.scatter(row[0], row[1], color=colors[i], label=parties[i])\n",
        "\n",
        "plt.legend(loc='upper left')\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "JTIk1p8YTKhz",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "import json\n",
        "\n",
        "class MyEncoder(json.JSONEncoder):\n",
        "    def default(self, obj):\n",
        "        if isinstance(obj, np.integer):\n",
        "            return int(obj)\n",
        "        elif isinstance(obj, np.ndarray):\n",
        "            return obj.tolist()\n",
        "        else:\n",
        "            return super(MyEncoder, self).default(obj)\n",
        "\n",
        "party_names = ['柏清風', '公明党', '日本共産党', '柏愛倶楽部', '市民サイド・ネット', '護憲市民会議', '内田博紀', '上橋泉', '北村和之']\n",
        "parties = [{'name': name, 'point': reduced[i]} for i, name in enumerate(party_names)]\n",
        "  \n",
        "with open('/content/gdrive/PATH/TO/YOUR/ANALYZED/RESULT/ideology.json', 'w') as out:\n",
        "  out.write(json.dumps({'ideology': {'parties': parties}}, cls = MyEncoder))"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}