隊列パース.ipynb

隊列パース.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyOxW3+Niy+cCgx3yuOIjmFh",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/kun432/d897f4ece48156beebf779895330c997/.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "zennの記事を元に以下を追加してみた。\n",
        "\n",
        "- 各コーナーでの内外の位置取り\n",
        "- matplotlibでかんたんな可視化\n",
        "\n",
        "参考）pyparsingで競馬のコーナー通過順位をパース\n",
        "https://zenn.dev/moripon/articles/ed5caa9c1d621e\n"
      ],
      "metadata": {
        "id": "qngtoogbjC2m"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install japanize-matplotlib"
      ],
      "metadata": {
        "id": "46uGuY2ObEWu"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "UCipf59VE4EB"
      },
      "outputs": [],
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import pyparsing as pp\n",
        "import matplotlib.cm as cm\n",
        "import matplotlib.pyplot as plt\n",
        "import japanize_matplotlib"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# DataFrame列名定義\n",
        "columns = ['diff', 'horse_no', 'side']\n",
        "\n",
        "# 差の定数(unit:馬身)\n",
        "DIFF_GROUP = 0.3\n",
        "DIFF_MIN = 1.5\n",
        "DIFF_MID = 3.0\n",
        "DIFF_MUCH = 6.0\n",
        "\n",
        "class ParsePass():\n",
        "    \n",
        "    def __init__(self):\n",
        "        \n",
        "        # 馬番\n",
        "        horse_no = pp.Word(pp.nums).setParseAction(self._horse_no_action)\n",
        "        \n",
        "        # 馬群\n",
        "        group = pp.Suppress(pp.Literal('(')) + \\\n",
        "                    pp.Optional(pp.delimitedList(pp.Word(pp.nums), delim=',')) + \\\n",
        "                    pp.Suppress(pp.Literal(')'))\n",
        "        group.ignore('*')\n",
        "        group.setParseAction(self._group_action)\n",
        "\n",
        "        # 情報要素\n",
        "        element = (group | horse_no)\n",
        "        \n",
        "        # 前走馬との差\n",
        "        diff_min = pp.Suppress(pp.Optional(pp.Literal(','))).setParseAction(self._diff_min_action) + element\n",
        "        diff_mid = pp.Suppress(pp.Literal('-')).setParseAction(self._diff_mid_action) + element\n",
        "        diff_much = pp.Suppress(pp.Literal('=')).setParseAction(self._diff_much_action) + element\n",
        "\n",
        "        # 全体定義\n",
        "        self._passing_order = element + pp.ZeroOrMore( diff_mid | diff_much | diff_min )\n",
        "        \n",
        "    def _horse_no_action(self, token):\n",
        "        \n",
        "        self._data = self._data.append({'diff':self._diff, 'horse_no':token[0], 'side':1 }, ignore_index=True)\n",
        "        return\n",
        "\n",
        "    def _group_action(self, token):\n",
        "        \n",
        "        for i, no in enumerate(token):\n",
        "            self._data = self._data.append({'diff':self._diff, 'horse_no':no, 'side':1+i}, ignore_index=True)\n",
        "            self._diff += DIFF_GROUP\n",
        "        self._diff -= DIFF_GROUP\n",
        "        return\n",
        "        \n",
        "    def _diff_min_action(self, token):\n",
        "        \n",
        "        self._diff += DIFF_MIN\n",
        "        return\n",
        "        \n",
        "    def _diff_mid_action(self, token):\n",
        "        \n",
        "        self._diff += DIFF_MID\n",
        "        return\n",
        "    \n",
        "    def _diff_much_action(self, token):\n",
        "        \n",
        "        self._diff += DIFF_MUCH\n",
        "        return\n",
        "        \n",
        "    def parse(self, pass_str):\n",
        "        \n",
        "        # 初期化\n",
        "        self._data = pd.DataFrame(columns=columns)\n",
        "        self._diff = 0\n",
        "        # parse\n",
        "        self._passing_order.parseString(pass_str)\n",
        "        # index調整\n",
        "        self._data.index = np.arange(1, len(self._data)+1)\n",
        "        self._data.index.name = 'rank'\n",
        "\n",
        "        return(self._data)"
      ],
      "metadata": {
        "id": "mvMLNW17E_0B"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pass_data = '(*12,10,15)5-(1,13)-(2,4)3(6,9)(14,11)(8,7)'#@param {type: \"string\"}"
      ],
      "metadata": {
        "id": "KndSiMxMkMCh"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pass_parsing = ParsePass()\n",
        "df = pass_parsing.parse(pass_str)\n",
        "df"
      ],
      "metadata": {
        "id": "yV6efWYeFLG7"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(df[\"diff\"].max(),df[\"side\"].max()))\n",
        "plt.scatter(df[\"diff\"], df[\"side\"], s=100)\n",
        "plt.xlabel(\"前　←　前後　→　後\", fontsize=15)\n",
        "plt.ylabel(\"内　←　内外　→　外\", fontsize=15)\n",
        "plt.title(\"隊列\", fontsize=20)\n",
        "plt.yticks([0,1,2,3,4], color=\"w\") "
      ],
      "metadata": {
        "id": "yac18U0njctj"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}