app.py

import os
import json
import requests

import datetime
import gradio as gr
import pandas as pd
from huggingface_hub import HfApi, hf_hub_download, snapshot_download
from huggingface_hub.repocard import metadata_load
from apscheduler.schedulers.background import BackgroundScheduler

from tqdm.contrib.concurrent import thread_map

from utils import *

DATASET_REPO_URL = "https://huggingface.co/datasets/pkalkman/drlc-leaderboard-data"
DATASET_REPO_ID = "pkalkman/drlc-leaderboard-data"
HF_TOKEN = os.environ.get("HF_TOKEN")

block = gr.Blocks()
api = HfApi(token=HF_TOKEN)

# Read the environments from the JSON file
with open('envs.json', 'r') as f:
    rl_envs = json.load(f)


def download_leaderboard_dataset():
    # Download the dataset from the Hugging Face Hub
    path = snapshot_download(repo_id=DATASET_REPO_ID, repo_type="dataset")
    return path


def get_data(rl_env, path) -> pd.DataFrame:
    """
    Get data from rl_env CSV file and return as DataFrame
    """
    csv_path = os.path.join(path, rl_env + ".csv")
    data = pd.read_csv(csv_path)
    return data


def get_last_refresh_time(path) -> str:
    """
    Get the latest modification time of any CSV file in the dataset path
    """
    # Get list of all CSV files in the dataset path
    csv_files = [os.path.join(path, f) for f in os.listdir(path) if f.endswith('.csv')]
    
    # Get the latest modification time
    latest_time = max([os.path.getmtime(f) for f in csv_files])
    
    # Convert to human-readable format
    return datetime.datetime.fromtimestamp(latest_time).strftime('%Y-%m-%d %H:%M:%S')


with block:
    path_ = download_leaderboard_dataset()
    # Get the last refresh time
    last_refresh_time = get_last_refresh_time(path_)

    gr.Markdown(f"""
    # 🏆 Deep Reinforcement Learning Course Leaderboard 🏆 
    
    Presenting the latest leaderboard from the Hugging Face Deep RL Course - refresh ({last_refresh_time}).
    """)

    
    for i in range(0, len(rl_envs)):
        rl_env = rl_envs[i]
        with gr.TabItem(rl_env["rl_env_beautiful"]):
            with gr.Row():
                markdown = f"""
                    # {rl_env['rl_env_beautiful']}
                    
                    ### Leaderboard for {rl_env['rl_env_beautiful']}
                    """
                gr.Markdown(markdown)

            with gr.Row():
                # Display the data for this RL environment
                data = get_data(rl_env["rl_env"], path_)
                gr.Dataframe(
                    value=data,
                    headers=["Ranking 🏆", "User 🤗", "Model id 🤖", "Results", "Mean Reward", "Std Reward"],
                    datatype=["number", "markdown", "markdown", "number", "number", "number"],
                    row_count=(100, 'fixed')
                )

block.launch()