trending feature

app.py

@@ -77,7 +77,10 @@ def make_leaderboard(orgs, which_one):
     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"Scraping Organizations ({which_one})", position=0, leave=True):
+        rank = get_ranking_trend(trend, org)
         df = get_models(org, which_one)
         if len(df) == 0:
           continue
@@ -87,6 +90,7 @@ def make_leaderboard(orgs, which_one):
 
         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"],
@@ -99,9 +103,12 @@ def make_leaderboard(orgs, which_one):
               "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"]
+              "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"],
@@ -112,17 +119,22 @@ def make_leaderboard(orgs, which_one):
               "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"]
+              "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"]
+              "Most Like Count": most_info["Most Likes"]["likes"],
+              "Trending Space": rank['id'],
+              "Best Rank at Trending Spaces": rank['rank']
           })
 
     leaderboard = pd.DataFrame(data_rows)
@@ -132,6 +144,9 @@ def make_leaderboard(orgs, which_one):
     leaderboard.insert(0, "Serial Number", range(1, len(leaderboard) + 1))
     return leaderboard
 
+"""# Gradio başlasın
+
+"""
 
 with open("org_names.txt", "r") as f:
   org_names_in_list = [i.rstrip("\n") for i in f.readlines()]
@@ -139,7 +154,6 @@ with open("org_names.txt", "r") as f:
 
 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
@@ -155,6 +169,8 @@ INTRODUCTION_TEXT = f"""
 🛠️ 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.
 """
 
 def clickable(x, which_one):
@@ -164,8 +180,10 @@ def clickable(x, which_one):
       else:
           return "Not Found"
     else:
-        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>'
-
+        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":
@@ -174,6 +192,34 @@ def models_df_to_clickable(df, columns, which_one):
           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"}
+
 demo = gr.Blocks()
 
 with gr.Blocks() as demo:
@@ -182,28 +228,29 @@ with gr.Blocks() as demo:
 
       with gr.TabItem("🏛️ Models", id=1):
 
-          columns_to_convert = ["Organization Name", "Best Model On Open LLM Leaderboard", "Most Downloaded Model", "Most Liked Model"]
+          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")
           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"]
-          gr.Dataframe(models_df.head(400), headers=headers, interactive=True, datatype=["str", "markdown", "str", "str", "str", "markdown", "str", "str", "str", "markdown", "str", "markdown", "str"])
+          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"]
+          columns_to_convert = ["Organization Name", "Most Downloaded Dataset", "Most Liked Dataset", "Trending Dataset"]
           dataset_df = make_leaderboard(org_names_in_list, "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"]
-          gr.Dataframe(dataset_df.head(250), headers=headers, interactive=False, datatype=["str", "markdown", "str", "str", "str", "str", "str", "markdown", "str", "markdown", "str"])
+          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"]
+          columns_to_convert = ["Organization Name", "Most Liked Space", "Trending Space"]
 
           spaces_df = make_leaderboard(org_names_in_list, "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"]
-          gr.Dataframe(spaces_df.head(150), headers=headers, interactive=False,  datatype=["str", "markdown", "str", "str", "str", "markdown", "str"])
+          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(150), headers=headers, interactive=False,  datatype=["str", "markdown", "str", "str", "str", "markdown", "str", "markdown", "str"])
 
 demo.launch()
+