app.py

import gradio as gr
import pandas as pd
from huggingface_hub import HfApi
from collections import defaultdict

# ------------------------------------------------------
# Get spaces with more details
api = HfApi()
spaces = api.list_spaces(limit=40000)  # Limiting to 40000 for now

# Create a DataFrame
data = []
for space in spaces:
    data.append({
        'id': space.id,
        'title': space.id.split('/')[-1],
        'author': space.author if space.author else space.id.split('/')[0],
        'likes': space.likes,
        'tags': space.tags if hasattr(space, 'tags') else [],
    })

df = pd.DataFrame(data)
print("Total spaces collected:", len(df))
print("\nSample of the data:")
print(df.head())

# ------------------------------------------------------

# Define categories and their keywords
categories = {
    'Text-to-Speech': ['tts', 'speech', 'voice', 'audio', 'kokoro'],
    'Transcription': ['transcribe', 'transcription'],
    'Agents': ['agent', 'agents', 'smol', 'multi-step', 'autobot', 'autoGPT' 'agentic'],
    'Image Generation': ['stable-diffusion', 'diffusion', 'flux', 'dalle', 'gan', 'sdxl', 'midjourney', 'diffusion', 'image', 'img2img', 'style', 'art'],
    'Video': ['video', 'animation', 'motion', 'sora'],
    'Face/Portrait': ['face', 'portrait', 'gaze', 'facial'],
    'Chat/LLM': ['chat', 'llm', 'gpt', 'llama', 'text', 'language'],
    '3D': ['3d', 'mesh', 'point-cloud', 'depth'],
    'Audio': ['audio', 'tts', 'music', 'whisper', 'sound', 'voice'],
    'Vision': ['vision', 'detection', 'recognition', 'classifier'],
    'CLIP': ['image-to-text', 'describe-image'],
    'Games': ['game', 'games', 'play', 'playground'],
    'Finance': ['finance', 'stock', 'money', 'currency', 'bank', 'market'],
    'SAM': ['sam', 'segmentation', 'mask'],
    'Science': ['science', 'physics', 'chemistry', 'biology', 'math', 'astronomy', 'geology', 'meteorology', 'engineering', 'medicine', 'health', 'nutrition', 'environment', 'ecology', 'geography', 'geology', 'geophysics'],
    'Education': ['education', 'school', 'university', 'college', 'teaching', 'learning', 'study', 'research'],
    'Graph': ['graph', 'network', 'node', 'edge', 'path', 'tree', 'cycle', 'flow', 'matching', 'coloring', 'swarm'],
    'Research': ['research', 'study', 'experiment', 'paper', 'discovery', 'innovation', 'exploration', 'analysis'],
    'Document Analyis': ['pdf', 'RAG', 'idefecs'],
    'WebGPU': ['localModel', 'webGPU'],
    'Point Tracking': ['CoTracker', 'tapir', 'tapnet', 'point', 'track'],
    'Games': ['game', 'Unity', 'UE5', 'Unreal'],
    'Leaderboard': ['arena', 'leaderboard', 'timeline'],
    'Other': []  # Default category
}

def categorize_space(title, tags):
    title_lower = title.lower()
    # Convert tags to lowercase if tags exist
    tags_lower = [t.lower() for t in tags] if tags else []
    
    for category, keywords in categories.items():
        # Check both title and tags for keywords
        if any(keyword in title_lower for keyword in keywords) or \
           any(keyword in tag for keyword in keywords for tag in tags_lower):
            return category
    return 'Other'

# Add category to DataFrame
df['category'] = df.apply(lambda x: categorize_space(x['title'], x['tags']), axis=1)

# Show category distribution
category_counts = df['category'].value_counts()
print("\nCategory Distribution:")
print(category_counts)

# Show sample spaces from each category
print("\nSample spaces from each category:")
for category in categories.keys():
    print(f"\n{category}:")
    sample = df[df['category'] == category].head(3)
    print(sample[['title', 'likes']].to_string())
    
# ------------------------------------------------------
# Add total likes per category
category_likes = df.groupby('category')['likes'].sum().sort_values(ascending=False)
print("Total likes per category:")
print(category_likes)

print("\nTop 10 spaces in each category (sorted by likes):")
for category in categories.keys():
    print(f"\n=== {category} ===")
    top_10 = df[df['category'] == category].nlargest(10, 'likes')[['title', 'likes']]
    # Format output with padding for better readability
    print(top_10.to_string(index=False))

# ------------------------------------------------------

# Add space URLs
df['url'] = 'https://huggingface.co/spaces/' + df['id']

# Show the top 10 spaces from each category with their links
# print("Top 10 spaces in each category with links:")
# for category in categories.keys():
    # print(f"\n=== {category} ===")
    # top_10 = df[df['category'] == category].nlargest(10, 'likes')[['title', 'likes', 'url']]
    # Format output with padding for better readability
    # print(top_5.to_string(index=False))

# ------------------------------------------------------

def search_spaces(search_text, category):
    if category == "All Categories":
        spaces_df = df
    else:
        spaces_df = df[df['category'] == category]
    
    if search_text:
        spaces_df = spaces_df[spaces_df['title'].str.lower().str.contains(search_text.lower())]
    
    spaces = spaces_df.nlargest(30, 'likes')[['title', 'likes', 'url', 'category']]
    
    # Get category stats
    total_spaces = len(spaces_df)
    total_likes = spaces_df['likes'].sum()
    
    # Format the results as HTML with clickable links and stats
    html_content = f"""
    <div style='margin-bottom: 20px; padding: 10px; background-color: var(--color-background-primary); 
                border: 1px solid var(--color-border-primary); border-radius: 5px;'>
        <h3 style='color: var(--color-text-primary);'>Statistics:</h3>
        <p style='color: var(--color-text-primary);'>Total Spaces: {total_spaces}</p>
        <p style='color: var(--color-text-primary);'>Total Likes: {total_likes:,}</p>
    </div>
    <div style='max-height: 800px; overflow-y: auto;'>
        <div style='display: grid; grid-template-columns: repeat(3, 1fr); gap: 15px; padding: 10px;'>
    """
    
    for _, row in spaces.iterrows():
        # In the search_spaces function, update the card HTML template:
        html_content += f"""
        <div style='padding: 15px; 
                    border: 2px solid var(--color-border-primary); 
                    border-radius: 5px; 
                    background-color: var(--color-background-primary);
                    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
                    display: flex;
                    flex-direction: column;
                    height: 100%;
                    position: relative;'>
            <h3 style='margin-top: 0; margin-bottom: 10px;'>
                <a href='{row['url']}' target='_blank' 
                   style='color: #2196F3; 
                          text-decoration: none; 
                          font-weight: bold;'>{row['title']}</a>
            </h3>
            <div style='height: 2px; 
                        background: var(--color-border-primary);
                        margin: 10px 0;
                        width: 100%;'></div>
            <p style='color: var(--color-text-primary); margin: 8px 0;'>
                <span style='background-color: var(--color-accent-soft); 
                           padding: 2px 8px; 
                           border-radius: 12px;
                           font-size: 0.9em;'>
                    {row['category']}
                </span>
            </p>
            <p style='color: var(--color-text-primary); 
                      margin-top: auto; 
                      padding-top: 10px;
                      border-top: 1px solid var(--color-border-primary);'>
                ❤️ {row['likes']:,} likes
            </p>
        </div>
        """
    
    html_content += "</div></div>"
    return html_content

# Create the Gradio interface
def create_app():
    with gr.Blocks(
        title="Hugging Face Spaces Explorer",
        theme=gr.themes.Soft(
            primary_hue="blue",
            secondary_hue="blue",
        )
    ) as app:
        gr.Markdown("""
        # 🤗 Hugging Face Spaces Explorer
        Explore and discover popular Hugging Face Spaces by category
        """)
        
        with gr.Row():
            with gr.Column(scale=1):
                # Category selection
                category_dropdown = gr.Dropdown(
                    choices=["All Categories"] + sorted(df['category'].unique()),
                    label="Select Category",
                    value="All Categories"
                )
                # Search box
                search_input = gr.Textbox(
                    label="Search Spaces",
                    placeholder="Enter search terms..."
                )
            
        # Display area for spaces
        spaces_display = gr.HTML(value=search_spaces("", "All Categories"))
        
        # Update display when category or search changes
        category_dropdown.change(
            fn=search_spaces,
            inputs=[search_input, category_dropdown],
            outputs=spaces_display
        )
        search_input.change(
            fn=search_spaces,
            inputs=[search_input, category_dropdown],
            outputs=spaces_display
        )
    
    return app

# Launch the app
app = create_app()
app.launch(share=True)