Update app.py

app.py

@@ -1,22 +1,11 @@
-
-## Comprehensive Model Performance Analysis
-
-### Importing Required Libraries
 import pandas as pd
 import matplotlib.pyplot as plt
 import seaborn as sns
 import gradio as gr
 import requests
 from bs4 import BeautifulSoup
-import io
-import os
-import base64
-import zipfile
-from PIL import Image
-from io import BytesIO
 
-### Input Data
-# Data with links to Hugging Face repositories
+# Local dataset (optional, for pre-loaded data)
 data_full = [
     ['CultriX/Qwen2.5-14B-SLERPv7', 'https://huggingface.co/CultriX/Qwen2.5-14B-SLERPv7', 0.7205, 0.8272, 0.7541, 0.6581, 0.5, 0.729],
     ['djuna/Q2.5-Veltha-14B-0.5', 'https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5', 0.7492, 0.8386, 0.7305, 0.598, 0.43, 0.7817],
@@ -44,79 +33,57 @@ data_full = [
     ['CultriX/Qwen2.5-14B-Wernickev7', 'https://huggingface.co/CultriX/Qwen2.5-14B-Wernickev7', 0.7147, 0.7599, 0.6097, 0.7056, 0.57, 0.7164],
     ['CultriX/Qwen2.5-14B-FinalMerge-tmp2', 'https://huggingface.co/CultriX/Qwen2.5-14B-FinalMerge-tmp2', 0.7255, 0.8192, 0.7535, 0.6671, 0.5, 0.7612],
 ]
+
 columns = ["Model Configuration", "Model Link", "tinyArc", "tinyHellaswag", "tinyMMLU", "tinyTruthfulQA", "tinyTruthfulQA_mc1", "tinyWinogrande"]
 df_full = pd.DataFrame(data_full, columns=columns)
 
-### Visualization and Analytics Functions
+def scrape_model_page(model_url):
+    """
+    Scrapes the Hugging Face model page for YAML configuration and other details.
+    """
+    try:
+        # Fetch the model page
+        response = requests.get(model_url)
+        if response.status_code != 200:
+            return f"Error: Unable to fetch the page (Status Code: {response.status_code})"
+        
+        soup = BeautifulSoup(response.text, "html.parser")
 
-# 1. Plot Average Scores
-def plot_average_scores():
-    df_full["Average Score"] = df_full.iloc[:, 2:].mean(axis=1)
-    df_avg_sorted = df_full.sort_values(by="Average Score", ascending=False)
-    plt.figure(figsize=(12, 8))
-    plt.barh(df_avg_sorted["Model Configuration"], df_avg_sorted["Average Score"])
-    plt.title("Average Performance of Models Across Tasks", fontsize=16)
-    plt.xlabel("Average Score", fontsize=14)
-    plt.ylabel("Model Configuration", fontsize=14)
-    plt.gca().invert_yaxis()
-    plt.grid(axis='x', linestyle='--', alpha=0.7)
-    plt.tight_layout()
-    plt.show()
+        # Extract YAML configuration (usually inside <pre> tags)
+        yaml_config = soup.find("pre")
+        yaml_text = yaml_config.text.strip() if yaml_config else "No YAML configuration found."
 
-# 2. Plot Task Performance
-def plot_task_performance():
-    df_full_melted = df_full.melt(id_vars=["Model Configuration", "Model Link"], var_name="Task", value_name="Score")
-    plt.figure(figsize=(14, 10))
-    for model in df_full["Model Configuration"]:
-        model_data = df_full_melted[df_full_melted["Model Configuration"] == model]
-        plt.plot(model_data["Task"], model_data["Score"], marker="o", label=model)
-    plt.title("Performance of All Models Across Tasks", fontsize=16)
-    plt.xlabel("Task", fontsize=14)
-    plt.ylabel("Score", fontsize=14)
-    plt.xticks(rotation=45)
-    plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left', fontsize=9)
-    plt.grid(axis='y', linestyle='--', alpha=0.7)
-    plt.tight_layout()
-    plt.show()
+        # Extract additional metadata or performance (if available)
+        metadata_section = soup.find("div", class_="metadata")
+        metadata_text = metadata_section.text.strip() if metadata_section else "No metadata found."
 
-# 3. Plot Task-Specific Top Models
-def plot_task_specific_top_models():
-    top_models = df_full.iloc[:, 2:].idxmax()
-    top_scores = df_full.iloc[:, 2:].max()
-    results = pd.DataFrame({"Top Model": top_models, "Score": top_scores}).reset_index().rename(columns={"index": "Task"})
-    plt.figure(figsize=(12, 6))
-    plt.bar(results["Task"], results["Score"])
-    plt.title("Task-Specific Top Models", fontsize=16)
-    plt.xlabel("Task", fontsize=14)
-    plt.ylabel("Score", fontsize=14)
-    plt.grid(axis="y", linestyle="--", alpha=0.7)
-    plt.tight_layout()
-    plt.show()
+        # Return the scraped details
+        return f"**YAML Configuration:**\n{yaml_text}\n\n**Metadata:**\n{metadata_text}"
 
-### YAML Configuration and Scraping Utilities
-# 1. Scrape MergeKit Configuration
-def scrape_mergekit_config(model_name):
-    model_link = df_full.loc[df_full["Model Configuration"] == model_name, "Model Link"].values[0]
-    response = requests.get(model_link)
-    if response.status_code != 200:
-        return f"Failed to fetch model page for {model_name}. Please check the link."
-    soup = BeautifulSoup(response.text, "html.parser")
-    yaml_config = soup.find("pre")
-    return yaml_config.text.strip() if yaml_config else f"No YAML configuration found for {model_name}."
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-### Performance Heatmap
-def plot_heatmap():
-    plt.figure(figsize=(12, 8))
-    sns.heatmap(df_full.iloc[:, 2:], annot=True, cmap="YlGnBu", xticklabels=columns[2:], yticklabels=df_full["Model Configuration"])
-    plt.title("Performance Heatmap", fontsize=16)
-    plt.tight_layout()
-    plt.show()
+def display_scraped_model_data(model_url):
+    """
+    Displays YAML configuration and metadata for a given model URL.
+    """
+    return scrape_model_page(model_url)
 
-### Gradio App
-# Building the Interface
 with gr.Blocks() as demo:
-    gr.Markdown("# Comprehensive Model Performance Analysis")
-    gr.Image(type="pil", label="Average Performance Plot")
-    gr.Image(type="pil", label="Task Performance Plot")
-    gr.Image(type="pil", label="Task-Specific Top Models")
-    demo.launch()
+    gr.Markdown("# Model Performance Analysis with Live Scraping")
+
+    # Pre-loaded dataset features
+    with gr.Row():
+        btn1 = gr.Button("Show Summary Statistics")
+        stats_output = gr.Dataframe()
+        btn1.click(lambda: df_full.describe().T, outputs=stats_output)
+
+    # Live scraping feature
+    gr.Markdown("## Live Scraping Features")
+    with gr.Row():
+        url_input = gr.Textbox(label="Enter Hugging Face Model URL", placeholder="https://huggingface.co/<model>")
+        scrape_btn = gr.Button("Scrape Model Page")
+        scrape_output = gr.Textbox(label="Scraped Data", lines=15)
+        scrape_btn.click(display_scraped_model_data, inputs=url_input, outputs=scrape_output)
+
+demo.launch()