{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# La Liga Score Predictor Demo\n",
        "\n",
        "This notebook shows the simplest way to load the public model bundle and run a prediction from team names plus match date.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from la_liga_score_predictor import LaLigaScorePredictor\n",
        "\n",
        "predictor = LaLigaScorePredictor.from_defaults(dataset_csv_path='sample_history.csv')\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "result = predictor.predict_match(\n",
        "    home_team='Athletic',\n",
        "    away_team='Osasuna',\n",
        "    match_date='2026-04-21',\n",
        ")\n",
        "result\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Batch Example\n",
        "\n",
        "You can also loop through `sample_fixtures.csv` or your own fixture list and write the outputs to a CSV.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "import csv\n",
        "from pathlib import Path\n",
        "\n",
        "rows = []\n",
        "with Path('sample_fixtures.csv').open(newline='', encoding='utf-8') as src:\n",
        "    reader = csv.DictReader(src)\n",
        "    for row in reader:\n",
        "        prediction = predictor.predict_match(\n",
        "            home_team=row['home_team'],\n",
        "            away_team=row['away_team'],\n",
        "            match_date=row['match_date'],\n",
        "        )\n",
        "        rows.append({\n",
        "            'home_team': row['home_team'],\n",
        "            'away_team': row['away_team'],\n",
        "            'match_date': row['match_date'],\n",
        "            'predicted_score': prediction['predicted_score'],\n",
        "            'home_win': prediction['result_probabilities']['home_win'],\n",
        "            'draw': prediction['result_probabilities']['draw'],\n",
        "            'away_win': prediction['result_probabilities']['away_win'],\n",
        "            'confidence_level': prediction['confidence_level'],\n",
        "        })\n",
        "rows\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.10"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}