{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\yuxua\\AppData\\Local\\Temp\\ipykernel_14096\\1296094769.py:21: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown\n",
      "  plt.show()\n"
     ]
    }
   ],
   "source": [
    "from data_visualization import create_horizontal_bar_chart\n",
    "from leaderboard_utils import get_mario_leaderboard\n",
    "import matplotlib.pyplot as plt\n",
    "import json\n",
    "\n",
    "# Load the rank data\n",
    "with open('rank_data_03_25_2025.json', 'r') as f:\n",
    "    rank_data = json.load(f)\n",
    "\n",
    "# Get the leaderboard data\n",
    "df = get_mario_leaderboard(rank_data)\n",
    "\n",
    "# Create the bar chart\n",
    "game_name = \"Super Mario Bros\"\n",
    "fig = create_horizontal_bar_chart(df, game_name)\n",
    "\n",
    "# Save the figure in current directory\n",
    "fig.savefig('mario_performance.png', bbox_inches='tight', dpi=300)\n",
    "\n",
    "# Display the chart\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\yuxua\\AppData\\Local\\Temp\\ipykernel_14096\\1659021522.py:153: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown\n",
      "  plt.show()\n"
     ]
    }
   ],
   "source": [
    "from leaderboard_utils import get_combined_leaderboard, GAME_ORDER\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "import json\n",
    "\n",
    "# Load the rank data\n",
    "with open('rank_data_03_25_2025.json', 'r') as f:\n",
    "    rank_data = json.load(f)\n",
    "\n",
    "# Get combined leaderboard with all games\n",
    "selected_games = {game: True for game in GAME_ORDER}\n",
    "df = get_combined_leaderboard(rank_data, selected_games)\n",
    "\n",
    "# Create figure and axis with better styling\n",
    "sns.set_style(\"whitegrid\")\n",
    "plt.figure(figsize=(16, 9))\n",
    "ax = plt.gca()\n",
    "\n",
    "# Get unique models\n",
    "models = df['Player'].unique()\n",
    "n_games = len(GAME_ORDER)\n",
    "\n",
    "# Define a professional color palette\n",
    "colors = ['#2E86C1', '#E74C3C', '#27AE60', '#F39C12', '#8E44AD',\n",
    "          '#16A085', '#D35400', '#2980B9', '#C0392B', '#2ECC71']\n",
    "\n",
    "def normalize_values(values, mean, std):\n",
    "    \"\"\"\n",
    "    Normalize values using z-score and scale to 0-100 range\n",
    "    \"\"\"\n",
    "    if std == 0:\n",
    "        return [50 if v > 0 else 0 for v in values]\n",
    "    \n",
    "    z_scores = [(v - mean) / std for v in values]\n",
    "    scaled_values = [max(0, min(100, (z * 30) + 50)) for z in z_scores]\n",
    "    return scaled_values\n",
    "\n",
    "# Calculate normalized scores for each game\n",
    "for game_idx, game in enumerate(GAME_ORDER):\n",
    "    # Get all scores for this game\n",
    "    game_scores = []\n",
    "    for model in models:\n",
    "        score = df[df['Player'] == model][f'{game} Score'].values[0]\n",
    "        if score != '_' and float(score) > 0:  # Only include non-zero scores\n",
    "            game_scores.append((model, float(score)))\n",
    "    \n",
    "    # Sort scores from highest to lowest\n",
    "    game_scores.sort(key=lambda x: x[1], reverse=True)\n",
    "    \n",
    "    # Extract sorted models and scores\n",
    "    sorted_models = [x[0] for x in game_scores]\n",
    "    scores = [x[1] for x in game_scores]\n",
    "    \n",
    "    # Calculate mean and std for normalization\n",
    "    mean = np.mean(scores)\n",
    "    std = np.std(scores)\n",
    "    \n",
    "    # Normalize scores\n",
    "    normalized_scores = normalize_values(scores, mean, std)\n",
    "    \n",
    "    # Calculate bar width based on number of models in this game\n",
    "    n_models_in_game = len(sorted_models)\n",
    "    bar_width = 0.8 / n_models_in_game\n",
    "    \n",
    "    # Plot bars for each model\n",
    "    for i, (model, score) in enumerate(zip(sorted_models, normalized_scores)):\n",
    "        ax.bar(game_idx + i*bar_width, score, \n",
    "              width=bar_width, \n",
    "              label=model if game_idx == 0 else \"\",  # Only add label for first game\n",
    "              color=colors[i % len(colors)],\n",
    "              alpha=0.8)\n",
    "\n",
    "# Customize the plot\n",
    "ax.set_xticks(np.arange(n_games))\n",
    "ax.set_xticklabels(GAME_ORDER, rotation=45, ha='right', fontsize=10)\n",
    "ax.set_ylabel('Normalized Performance Score', fontsize=12)\n",
    "ax.set_title('AI Model Performance Comparison Across Gaming Tasks\\n(Showing only participating models for each game)', \n",
    "             fontsize=14, pad=20)\n",
    "\n",
    "# Add grid lines\n",
    "ax.grid(True, axis='y', linestyle='--', alpha=0.3)\n",
    "\n",
    "# Create legend with unique entries\n",
    "handles, labels = ax.get_legend_handles_labels()\n",
    "by_label = dict(zip(labels, handles))\n",
    "ax.legend(by_label.values(), by_label.keys(), \n",
    "          bbox_to_anchor=(1.05, 1), \n",
    "          loc='upper left',\n",
    "          fontsize=9,\n",
    "          title='AI Models',\n",
    "          title_fontsize=10)\n",
    "\n",
    "# Add a note about the visualization\n",
    "plt.figtext(0.5, 0.01, \n",
    "           'Note: Scores are normalized within each game. Only models that participated in each game are shown.',\n",
    "           ha='center', fontsize=9, style='italic')\n",
    "\n",
    "# Adjust layout to prevent label cutoff\n",
    "plt.tight_layout()\n",
    "\n",
    "# Save the figure\n",
    "plt.savefig('ai_model_gaming_performance_clean.png', bbox_inches='tight', dpi=300)\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "local_cua",
   "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": "3.10.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}