src/json_leaderboard.py

import json
import pandas as pd
from pathlib import Path


def load_leaderboard_from_json(json_path="leaderboard_data.json"):
    """Load leaderboard data from JSON file"""
    try:
        with open(json_path, 'r', encoding='utf-8') as f:
            data = json.load(f)
        return data['leaderboard']
    except FileNotFoundError:
        print(f"JSON file {json_path} not found")
        return []
    except json.JSONDecodeError:
        print(f"Error decoding JSON file {json_path}")
        return []


def create_leaderboard_df(json_path="leaderboard_data.json"):
    """Create a pandas DataFrame from JSON leaderboard data"""
    leaderboard_data = load_leaderboard_from_json(json_path)
    
    if not leaderboard_data:
        return pd.DataFrame()
    
    # Convert to DataFrame
    df = pd.DataFrame(leaderboard_data)
    
    # Sort by ACC score (descending)
    df = df.sort_values('acc', ascending=False).reset_index(drop=True)
    
    # Add ranking icons and make model names clickable links to papers
    def add_ranking_icon_and_link(index, model_name, paper_link):
        if index == 0:
            return f'🥇 <a href="{paper_link}" target="_blank">{model_name}</a>'
        elif index == 1:
            return f'🥈 <a href="{paper_link}" target="_blank">{model_name}</a>'
        elif index == 2:
            return f'🥉 <a href="{paper_link}" target="_blank">{model_name}</a>'
        else:
            return f'<a href="{paper_link}" target="_blank">{model_name}</a>'
    
    # Format the DataFrame for display
    display_df = pd.DataFrame({
        'Model': [add_ranking_icon_and_link(i, model, link) for i, (model, link) in enumerate(zip(df['model'], df['link']))],
        'Release Date': df['release_date'],
        'HF Model': df['hf'].apply(lambda x: f'<a href="{x}" target="_blank">🤗</a>' if x != "-" else "-"),
        'MoE': df['moe'].apply(lambda x: '-' if x == '-' else ('✓' if x else '✗')),
        'Parameters': df['params'],
        'Open Source': df['open_source'].apply(lambda x: '✓' if x else '✗'),
        'ACC Score': df['acc'].apply(lambda x: f"{x:.1f}")
    })
    
    return display_df


def get_leaderboard_stats(json_path="leaderboard_data.json"):
    """Get statistics about the leaderboard"""
    leaderboard_data = load_leaderboard_from_json(json_path)
    
    if not leaderboard_data:
        return {}
    
    df = pd.DataFrame(leaderboard_data)
    
    stats = {
        'total_models': len(df),
        'open_source_models': df['open_source'].sum(),
        'moe_models': df['moe'].apply(lambda x: 1 if x is True else 0).sum(),
        'avg_acc': df['acc'].mean(),
        'max_acc': df['acc'].max(),
        'min_acc': df['acc'].min()
    }
    
    return stats