go back to old temp

app.py

@@ -1,4 +1,6 @@
 import os
+os.system("wget https://raw.githubusercontent.com/Weyaxi/scrape-open-llm-leaderboard/main/openllm.py")
+from openllm import *
 import requests
 import pandas as pd
 from bs4 import BeautifulSoup
@@ -15,6 +17,7 @@ HF_TOKEN = os.getenv('HF_TOKEN')
 
 
 headers_models = ["🔢 Serial Number", "👤 Author 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", "🏷️ Type"]
@@ -70,7 +73,15 @@ def get_sum(df_for_sum_function):
     return {"Downloads": sum_downloads, "Likes": sum_likes}
 
 
-
+def get_openllm_leaderboard():
+    try:
+        data = get_json_format_data()
+        finished_models = get_datas(data)
+        df = pd.DataFrame(finished_models)
+        return df['Model'].tolist()
+    except Exception as e:  # something is wrong about the leaderboard so return empty list
+        print(e)
+        return []
 
 
 def get_ranking(model_list, target_org):
@@ -121,6 +132,7 @@ def group_models_by_author(all_things):
 
 def make_leaderboard(orgs, users, which_one, data):
     data_rows = []
+    open_llm_leaderboard = get_openllm_leaderboard() if which_one == "models" else None
 
     trend = get_trending_list(1, which_one)
     hepsi = [orgs, users]
@@ -139,12 +151,15 @@ def make_leaderboard(orgs, users, which_one, data):
             most_info = get_most(df)
 
             if which_one == "models":
-                
+                open_llm_leaderboard_get_org = get_ranking(open_llm_leaderboard, org)
+
                 data_rows.append({
                     "Author 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 in ["Not Found", "Error on Leaderboard"] else open_llm_leaderboard_get_org,
+                    "Best Rank On Open LLM Leaderboard": open_llm_leaderboard_get_org[1] if open_llm_leaderboard_get_org not in ["Not Found", "Error on Leaderboard"] 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"],
@@ -188,7 +203,6 @@ def make_leaderboard(orgs, users, which_one, data):
                 })
 
     leaderboard = pd.DataFrame(data_rows)
-    print(leaderboard.head())
     temp = ["Total Downloads"] if which_one != "spaces" else ["Total Likes"]
 
     leaderboard = leaderboard.sort_values(by=temp, ascending=False)
@@ -278,6 +292,8 @@ INTRODUCTION_TEXT = f"""
 
 🛠️ 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).
 
+📒 **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/datasets/spaces, first 300 models/datasets/spaces is being retrieved from huggingface.
 
 ## 🔍 Searching Organizations and Users
@@ -523,13 +539,13 @@ with gr.Blocks() as demo:
         search_bar_in_df = gr.Textbox(placeholder="🔍 Search for a author", show_label=False)
     
     with gr.TabItem("🏛️ Models", id=1):
-        columns_to_convert = ["Author Name", "Most Downloaded Model",
+        columns_to_convert = ["Author Name", "Best Model On Open LLM Leaderboard", "Most Downloaded Model",
                               "Most Liked Model", "Trending Model"]
         models_df = make_leaderboard(org_names_in_list, user_names_in_list, "models", group_models_by_author(all_models))
         models_df = models_df_to_clickable(models_df, columns_to_convert, "models")
 
         gr_models = gr.Dataframe(apply_headers(models_df, headers_models).head(400), headers=headers_models, interactive=True,
-                                 datatype=["str", "markdown", "str", "str", "str", "str", "str",
+                                 datatype=["str", "markdown", "str", "str", "str", "markdown", "str", "str", "str",
                                            "markdown", "str", "markdown", "str", "markdown", "str", "str"])
 
     with gr.TabItem("📊 Datasets", id=2):
@@ -591,4 +607,3 @@ filtered_spaces_users = update_table_spaces(orgs=False, users=True, return_all=T
 filtered_spaces_orgs = update_table_spaces(orgs=True, users=False, return_all=True)['👤 Author Name'].tolist()
 
 demo.launch(debug=True)
-