{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Model Comparison\n",
        "\n",
        "This notebook connects to the MLflow tracking server and compares the results of our models.\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": [
        "import mlflow\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import json\n",
        "\n",
        "mlflow.set_tracking_uri('sqlite:///mlflow/mlflow.db')\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": [
        "# Load all runs\n",
        "experiment = mlflow.get_experiment_by_name('multilingual-absa')\n",
        "df = mlflow.search_runs(experiment_ids=[experiment.experiment_id])\n",
        "display(df.head())\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": [
        "# Bar chart: macro-F1 comparison\n",
        "metrics = df[['tags.mlflow.runName', 'metrics.eval_macro_f1', 'metrics.test_f1', 'metrics.test_macro_f1', 'metrics.hindi_zero_shot_macro_f1']].fillna(0)\n",
        "metrics['Best F1'] = metrics[['metrics.eval_macro_f1', 'metrics.test_f1', 'metrics.test_macro_f1']].max(axis=1)\n",
        "\n",
        "plt.figure(figsize=(10, 6))\n",
        "sns.barplot(data=metrics, x='tags.mlflow.runName', y='Best F1')\n",
        "plt.title('Model Comparison by Macro-F1 / Span-F1')\n",
        "plt.xticks(rotation=45)\n",
        "plt.show()\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": [
        "# Load confusion matrix for best sentiment classifier\n",
        "# Note: Assuming the confusion_matrix.json artifact was downloaded or parsed.\n",
        "print('Confusion Matrix (Placeholder for artifact loading)')\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": [
        "# 5 Example Predictions\n",
        "print('Example 1: The food was great but service was slow.')\n",
        "print('Example 2: El sistema operativo es muy estable.')\n",
        "print('... (Load pipeline and infer here)')\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.11.0"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 4
}