app.py

import re
import json
import requests
import pandas as pd
from tqdm import tqdm
from bs4 import BeautifulSoup
from huggingface_hub import HfApi, list_models, list_datasets, list_spaces
import gradio as gr
from apscheduler.schedulers.background import BackgroundScheduler
import datetime


api = HfApi()


def get_most(df_for_most_function):
  download_sorted_df = df_for_most_function.sort_values(by=['downloads'], ascending=False)
  most_downloaded = download_sorted_df.iloc[0]

  like_sorted_df = df_for_most_function.sort_values(by=['likes'], ascending=False)
  most_liked = like_sorted_df.iloc[0]

  return {"Most Download": {"id": most_downloaded['id'], "downloads": most_downloaded['downloads'], "likes": most_downloaded['likes']}, "Most Likes": {"id": most_liked['id'], "downloads": most_liked['downloads'], "likes": most_liked['likes']}}

def get_sum(df_for_sum_function):
  sum_downloads = sum(df_for_sum_function['downloads'].tolist())
  sum_likes = sum(df_for_sum_function['likes'].tolist())

  return {"Downloads": sum_downloads, "Likes": sum_likes}

def get_openllm_leaderboard():
    try:
      url = 'https://huggingfaceh4-open-llm-leaderboard.hf.space/'
      response = requests.get(url)
      soup = BeautifulSoup(response.content, 'html.parser')
      script_elements = soup.find_all('script')
      data = json.loads(str(script_elements[1])[31:-10])

      component_index = 19

      result_list = []
      i = 0
      while True:
          try:
              normal_name = data['components'][component_index]['props']['value']['data'][i][-1]
              result_list.append(normal_name)
              i += 1
          except (IndexError, AttributeError):
              return result_list
    except Exception as e:
      print("Error on open llm leaderboard: ", e)
      return []


def get_ranking(model_list, target_org):
    if model_list == []:
        return "Error on Leaderboard"
    for index, model in enumerate(model_list):
      if model.split("/")[0].lower() == target_org.lower():
          return [index+1, model]
    return "Not Found"


def get_models(which_one):
  if which_one == "models":
    data = api.list_models()
  elif which_one == "datasets":
    data = api.list_datasets()
  elif which_one == "spaces":
    data = api.list_spaces()

  all_list = []
  for i in tqdm(data, desc=f"Scraping {which_one}", position=0, leave=True):
      i = i.__dict__

      id = i["id"].split("/")
      if len(id) != 1:
        json_format_data = {"author": id[0] ,"id": "/".join(id), "downloads": i['downloads'], "likes": i['likes']} if which_one != "spaces" else {"author": id[0] ,"id": "/".join(id), "downloads": 0, "likes": i['likes']}


        all_list.append(json_format_data)
  return all_list


def search(models_dict, author_name):
    return pd.DataFrame(models_dict.get(author_name, []))


def group_models_by_author(all_things):
    models_by_author = {}
    for model in all_things:
        author_name = model['author']
        if author_name not in models_by_author:
            models_by_author[author_name] = []
        models_by_author[author_name].append(model)
    return models_by_author


def make_leaderboard(orgs, which_one, data):
    data_rows = []
    open_llm_leaderboard = get_openllm_leaderboard() if which_one == "models" else None

    trend = get_trending_list(1, which_one)
    
    for org in tqdm(orgs, desc=f"Proccesing Organizations ({which_one})", position=0, leave=True):
        rank = get_ranking_trend(trend, org)

        df = search(data, org)

        if len(df) == 0:
          continue
        num_things = len(df)
        sum_info = get_sum(df)
        most_info = get_most(df)

        if which_one == "models":
          open_llm_leaderboard_get_org = get_ranking(open_llm_leaderboard, org)
            
          data_rows.append({
              "Organization Name": org,
              "Total Downloads": sum_info["Downloads"],
              "Total Likes": sum_info["Likes"],
              "Number of Models": num_things,
              "Best Model On Open LLM Leaderboard": open_llm_leaderboard_get_org[1] if open_llm_leaderboard_get_org != "Not Found" else open_llm_leaderboard_get_org,
              "Best Rank On Open LLM Leaderboard": open_llm_leaderboard_get_org[0] if open_llm_leaderboard_get_org != "Not Found" else open_llm_leaderboard_get_org,
              "Average Downloads per Model": int(sum_info["Downloads"] / num_things) if num_things != 0 else 0,
              "Average Likes per Model": int(sum_info["Likes"] / num_things) if num_things != 0 else 0,
              "Most Downloaded Model": most_info["Most Download"]["id"],
              "Most Download Count": most_info["Most Download"]["downloads"],
              "Most Liked Model": most_info["Most Likes"]["id"],
              "Most Like Count": most_info["Most Likes"]["likes"],
              "Trending Model": rank['id'],
              "Best Rank at Trending Models": rank['rank']
          })
        elif which_one == "datasets":

          data_rows.append({
              "Organization Name": org,
              "Total Downloads": sum_info["Downloads"],
              "Total Likes": sum_info["Likes"],
              "Number of Datasets": num_things,
              "Average Downloads per Dataset": int(sum_info["Downloads"] / num_things) if num_things != 0 else 0,
              "Average Likes per Dataset": int(sum_info["Likes"] / num_things) if num_things != 0 else 0,
              "Most Downloaded Dataset": most_info["Most Download"]["id"],
              "Most Download Count": most_info["Most Download"]["downloads"],
              "Most Liked Dataset": most_info["Most Likes"]["id"],
              "Most Like Count": most_info["Most Likes"]["likes"],
              "Trending Dataset": rank['id'],
              "Best Rank at Trending Datasets": rank['rank']
          })

        elif which_one == "spaces":

          data_rows.append({
              "Organization Name": org,
              "Total Likes": sum_info["Likes"],
              "Number of Spaces": num_things,
              "Average Likes per Space": int(sum_info["Likes"] / num_things) if num_things != 0 else 0,
              "Most Liked Space": most_info["Most Likes"]["id"],
              "Most Like Count": most_info["Most Likes"]["likes"],
              "Trending Space": rank['id'],
              "Best Rank at Trending Spaces": rank['rank']
          })

    leaderboard = pd.DataFrame(data_rows)
    temp = ["Total Downloads"] if which_one != "spaces" else ["Total Likes"]

    leaderboard = leaderboard.sort_values(by=temp, ascending=False)
    leaderboard.insert(0, "Serial Number", range(1, len(leaderboard) + 1))
    return leaderboard


def clickable(x, which_one):
    if which_one == "models":
      if x != "Not Found":
          return f'<a target="_blank" href="https://huggingface.co./{x}" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">{x}</a>'
      else:
          return "Not Found"
    else:
        if x != "Not Found":
            return f'<a target="_blank" href="https://huggingface.co./{which_one}/{x}" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">{x}</a>'
        return "Not Found"
        
def models_df_to_clickable(df, columns, which_one):
    for column in columns:
        if column == "Organization Name":
          df[column] = df[column].apply(lambda x: clickable(x, "models"))
        else:
          df[column] = df[column].apply(lambda x: clickable(x, which_one))
    return df


def get_trending_list(pages, which_one):
  trending_list = []
  for i in range(pages):
    json_data = requests.get(f"https://huggingface.co./{which_one}-json?p={i}").json()

    for thing in json_data[which_one]:
        id = thing["id"]
        likes = thing["likes"]

        if which_one != "spaces":
          downloads = thing["downloads"]

          trending_list.append({"id": id, "downloads": downloads, "likes": likes})
        else:
          trending_list.append({"id": id,  "likes": likes})

  return trending_list

def get_ranking_trend(json_data, org_name):
    names = [item['id'].split("/")[0] for item in json_data]
    models = [item['id'] for item in json_data]
    if org_name in names:
      temp = names.index(org_name)
      return {"id": models[temp], "rank": temp+1}
    else:
      return {"id": "Not Found", "rank": "Not Found"}

def restart_space():
    api.restart_space(repo_id="TFLai/organization-leaderboard", token=HF_TOKEN)


with open("org_names.txt", "r") as f:
  org_names_in_list = [i.rstrip("\n") for i in f.readlines()]

datetime = str(datetime.datetime.now().strftime("%Y-%m-%d %H:%M"))
INTRODUCTION_TEXT = f"""
🎯 The Organization Leaderboard aims to track organization rankings. This space is inspired by the [Open LLM Leaderboard](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard).

## Available Dataframes:

- 🏛️ Models

- 📊 Datasets

- 🚀 Spaces

## Backend

🛠️ The leaderboard's backend mainly runs on the [Hugging Face Hub API](https://huggingface.co./docs/huggingface_hub/v0.5.1/en/package_reference/hf_api).

🛠️ Organization names are retrieved using web scraping from [Huggingface Organizations](https://huggingface.co./organizations).

**🌐 Note:** In the model's dataframe, there are some columns related to the [Open LLM Leaderboard](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard). This data is also retrieved through web scraping.

**🌐 Note:** In trending models, first 300 models/datasets/spaces is being retrieved from huggingface.

## Last Update

⌛ This space is last updated in **{datetime}**.
"""

with gr.Blocks() as demo:
      gr.Markdown("""<h1 align="center" id="space-title">🤗 Organization Leaderboard</h1>""")
      gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")

      all_models = get_models("models")
      all_datasets  = get_models("datasets")
      all_spaces = get_models("spaces")


      with gr.TabItem("🏛️ Models", id=1):
          columns_to_convert = ["Organization Name", "Best Model On Open LLM Leaderboard", "Most Downloaded Model", "Most Liked Model", "Trending Model"]
          models_df = make_leaderboard(org_names_in_list, "models", group_models_by_author(all_models))
          models_df = models_df_to_clickable(models_df, columns_to_convert, "models")

          headers = ["🔢 Serial Number", "🏢 Organization Name", "📥 Total Downloads", "👍 Total Likes", "🤖 Number of Models", "🏆 Best Model On Open LLM Leaderboard", "🥇 Best Rank On Open LLM Leaderboard", "📊 Average Downloads per Model", "📈 Average Likes per Model", "🚀 Most Downloaded Model", "📈 Most Download Count", "❤️ Most Liked Model", "👍 Most Like Count", "🔥 Trending Model", "👑 Best Rank at Trending Models"]
          gr.Dataframe(models_df.head(400), headers=headers, interactive=True, datatype=["str", "markdown", "str", "str", "str", "markdown", "str", "str", "str", "markdown", "str", "markdown", "str", "markdown", "str"])

      with gr.TabItem("📊 Datasets", id=2):
          columns_to_convert = ["Organization Name", "Most Downloaded Dataset", "Most Liked Dataset", "Trending Dataset"]
          dataset_df = make_leaderboard(org_names_in_list, "datasets", group_models_by_author(all_datasets))
          dataset_df = models_df_to_clickable(dataset_df, columns_to_convert, "datasets")

          headers = ["🔢 Serial Number", "🏢 Organization Name", "📥 Total Downloads", "👍 Total Likes", "📊 Number of Datasets", "📊 Average Downloads per Dataset", "📈 Average Likes per Dataset", "🚀 Most Downloaded Dataset", "📈 Most Download Count", "❤️ Most Liked Dataset", "👍 Most Like Count", "🔥 Trending Dataset", "👑 Best Rank at Trending Datasets"]
          gr.Dataframe(dataset_df.head(250), headers=headers, interactive=False, datatype=["str", "markdown", "str", "str", "str", "str", "str", "markdown", "str", "markdown", "str", "markdown", "str"])

      with gr.TabItem("🚀 Spaces", id=3):
          columns_to_convert = ["Organization Name", "Most Liked Space", "Trending Space"]

          spaces_df = make_leaderboard(org_names_in_list, "spaces", group_models_by_author(all_spaces))
          spaces_df = models_df_to_clickable(spaces_df, columns_to_convert, "spaces")

          headers = ["🔢 Serial Number", "🏢 Organization Name", "👍 Total Likes", "🚀 Number of Spaces", "📈 Average Likes per Space", "❤️ Most Liked Space", "👍 Most Like Count", "🔥 Trending Space", "👑 Best Rank at Trending Spaces"]
          gr.Dataframe(spaces_df.head(200), headers=headers, interactive=False,  datatype=["str", "markdown", "str", "str", "str", "markdown", "str", "markdown", "str"])



scheduler = BackgroundScheduler()
scheduler.add_job(restart_space, "interval", seconds=21600)
demo.launch()