app-backup.py

import gradio as gr
import pandas as pd
import plotly.express as px
from datetime import datetime, timedelta
import requests
from io import BytesIO

def create_trend_chart(space_id, daily_ranks_df):
    if space_id is None or daily_ranks_df.empty:
        return None
    
    try:
        space_data = daily_ranks_df[daily_ranks_df['id'] == space_id].copy()
        if space_data.empty:
            return None
        
        space_data = space_data.sort_values('date')
        
        fig = px.line(
            space_data,
            x='date',
            y='rank',
            title=f'Daily Rank Trend for {space_id}',
            labels={'date': 'Date', 'rank': 'Rank'},
            markers=True,
            height=500  # 수정된 부분
        )
        
        fig.update_layout(
            xaxis_title="Date",
            yaxis_title="Rank",
            yaxis=dict(
                range=[100, 1],
                tickmode='linear',
                tick0=1,
                dtick=10
            ),
            hovermode='x unified',
            plot_bgcolor='white',
            paper_bgcolor='white',
            showlegend=False,
            margin=dict(t=50, r=20, b=40, l=40)
        )
        
        fig.update_xaxes(showgrid=True, gridwidth=1, gridcolor='lightgray')
        fig.update_yaxes(showgrid=True, gridwidth=1, gridcolor='lightgray')
        
        fig.update_traces(
            line_color='#2563eb',
            line_width=2,
            marker=dict(size=8, color='#2563eb')
        )
        
        return fig
    except Exception as e:
        print(f"Error creating chart: {e}")
        return None

def get_duplicate_spaces(top_100_spaces):
    # ID에서 username/spacename 형식에서 username만 추출
    top_100_spaces['clean_id'] = top_100_spaces['id'].apply(lambda x: x.split('/')[0])
    
    # username별 trending score 합산
    score_sums = top_100_spaces.groupby('clean_id')['trendingScore'].sum()
    
    # 디버깅용 출력
    print("\n=== ID별 스코어 합산 결과 ===")
    for id, score in score_sums.sort_values(ascending=False).head(20).items():
        print(f"ID: {id}, Total Score: {score}")
    
    # 합산된 스코어로 정렬하여 상위 20개 선택
    top_20_scores = score_sums.sort_values(ascending=False).head(20)
    return top_20_scores

def create_duplicates_chart(score_sums):
    if score_sums.empty:
        return None
    
    # 데이터프레임 생성
    df = pd.DataFrame({
        'id': score_sums.index,
        'total_score': score_sums.values,
        'rank': range(1, len(score_sums) + 1)
    })
    
    # 디버깅용 출력
    print("\n=== 차트 데이터 ===")
    print(df)
    
    fig = px.bar(
        df,
        x='id',
        y='rank',
        title="Top 20 Spaces by Combined Trending Score",
        height=500,  # 수정된 부분
        text='total_score'
    )
    
    fig.update_layout(
        showlegend=False,
        margin=dict(t=50, r=20, b=40, l=40),
        plot_bgcolor='white',
        paper_bgcolor='white',
        xaxis_tickangle=-45,
        yaxis=dict(
            range=[20.5, 0.5],
            tickmode='linear',
            tick0=1,
            dtick=1
        )
    )
    
    fig.update_traces(
        marker_color='#4CAF50',
        texttemplate='%{text:.1f}',
        textposition='outside',
        hovertemplate='ID: %{x}<br>Rank: %{y}<br>Total Score: %{text:.1f}<extra></extra>'
    )
    
    fig.update_xaxes(
        title_text="User ID",
        showgrid=True,
        gridwidth=1,
        gridcolor='lightgray'
    )
    
    fig.update_yaxes(
        title_text="Rank",
        showgrid=True,
        gridwidth=1,
        gridcolor='lightgray'
    )
    
    return fig

def update_display(selection):
    global daily_ranks_df
    
    if not selection:
        return None, gr.HTML(value="<div style='text-align: center; padding: 20px; color: #666;'>Select a space to view details</div>")
    
    try:
        space_id = selection
        
        latest_data = daily_ranks_df[
            daily_ranks_df['id'] == space_id
        ].sort_values('date').iloc[-1]
        
        info_text = f"""
        <div style="padding: 16px; background-color: white; border-radius: 8px; box-shadow: 0 1px 3px rgba(0,0,0,0.1);">
            <h3 style="margin: 0 0 12px 0;">Space Details</h3>
            <p style="margin: 4px 0;"><strong>ID:</strong> {space_id}</p>
            <p style="margin: 4px 0;"><strong>Current Rank:</strong> {int(latest_data['rank'])}</p>
            <p style="margin: 4px 0;"><strong>Trending Score:</strong> {latest_data['trendingScore']:.2f}</p>
            <p style="margin: 4px 0;"><strong>Created At:</strong> {latest_data['createdAt'].strftime('%Y-%m-%d')}</p>
            <p style="margin: 12px 0 0 0;">
                <a href="https://huggingface.co/spaces/{space_id}" 
                   target="_blank" 
                   style="color: #2563eb; text-decoration: none;">
                    View Space ↗
                </a>
            </p>
        </div>
        """
        
        chart = create_trend_chart(space_id, daily_ranks_df)
        
        return chart, gr.HTML(value=info_text)
        
    except Exception as e:
        print(f"Error in update_display: {e}")
        return None, gr.HTML(value=f"<div style='color: red;'>Error processing data: {str(e)}</div>")

def load_and_process_data():
    try:
        url = "https://huggingface.co/datasets/cfahlgren1/hub-stats/resolve/main/spaces.parquet"
        response = requests.get(url)
        df = pd.read_parquet(BytesIO(response.content))
        
        thirty_days_ago = datetime.now() - timedelta(days=30)
        df['createdAt'] = pd.to_datetime(df['createdAt'])
        df = df[df['createdAt'] >= thirty_days_ago].copy()
        
        dates = pd.date_range(start=thirty_days_ago, end=datetime.now(), freq='D')
        daily_ranks = []
        
        for date in dates:
            date_data = df[df['createdAt'].dt.date <= date.date()].copy()
            date_data = date_data.sort_values(['trendingScore', 'id'], ascending=[False, True])
            date_data['rank'] = range(1, len(date_data) + 1)
            date_data['date'] = date.date()
            daily_ranks.append(
                date_data[['id', 'date', 'rank', 'trendingScore', 'createdAt']]
            )
        
        daily_ranks_df = pd.concat(daily_ranks, ignore_index=True)
        
        latest_date = daily_ranks_df['date'].max()
        top_100_spaces = daily_ranks_df[
            (daily_ranks_df['date'] == latest_date) &
            (daily_ranks_df['rank'] <= 100)
        ].sort_values('rank').copy()
        
        return daily_ranks_df, top_100_spaces
    except Exception as e:
        print(f"Error loading data: {e}")
        return pd.DataFrame(), pd.DataFrame()

# 데이터 로드
print("Loading initial data...")
daily_ranks_df, top_100_spaces = load_and_process_data()
print("Data loaded successfully!")

# 중복 스페이스 데이터 계산
duplicates = get_duplicate_spaces(top_100_spaces)
duplicates_chart = create_duplicates_chart(duplicates)

# Gradio 인터페이스 생성
with gr.Blocks(theme=gr.themes.Soft()) as demo:
    gr.Markdown("""
    # HF Space Ranking Tracker(~30 Dailys)
    
    Track, analyze, and discover trending AI applications in the Hugging Face ecosystem. Our service continuously monitors and ranks all Spaces over a 30-day period, providing detailed analytics and daily ranking changes for the top 100 performers.
    """)
    
    with gr.Tabs():
        with gr.Tab("Dashboard"):
            with gr.Row(variant="panel"):
                with gr.Column(scale=5):  # 수정된 부분
                    trend_plot = gr.Plot(
                        label="Daily Rank Trend",
                        container=True
                    )
                with gr.Column(scale=5):  # 수정된 부분
                    duplicates_plot = gr.Plot(
                        label="Multiple Entries Analysis",
                        value=duplicates_chart,
                        container=True
                    )
            
            with gr.Row():
                info_box = gr.HTML(
                    value="<div style='text-align: center; padding: 20px; color: #666;'>Select a space to view details</div>"
                )
            
            space_selection = gr.Radio(
                choices=[row['id'] for _, row in top_100_spaces.iterrows()],
                value=None,
                visible=False
            )
            
            html_content = """
            <div style='display: flex; flex-wrap: wrap; gap: 16px; justify-content: center;'>
            """ + "".join([
                f"""
                <div class="space-card" 
                     data-space-id="{row['id']}"
                     style="
                    border: 1px solid #e5e7eb;
                    border-radius: 8px;
                    padding: 16px;
                    margin: 8px;
                    background-color: hsl(210, {max(30, 90 - (row['rank'] / 100 * 60))}%, {min(97, 85 + (row['rank'] / 100 * 10))}%);
                    box-shadow: 0 1px 3px rgba(0,0,0,0.1);
                    display: inline-block;
                    width: 250px;
                    vertical-align: top;
                    cursor: pointer;
                    transition: all 0.2s;
                "
                onmouseover="this.style.transform='translateY(-2px)';this.style.boxShadow='0 4px 6px rgba(0,0,0,0.1)';"
                onmouseout="this.style.transform='none';this.style.boxShadow='0 1px 3px rgba(0,0,0,0.1)';"
                >
                    <div style="font-size: 1.2em; font-weight: bold; margin-bottom: 8px;">
                        #{int(row['rank'])}
                    </div>
                    <div style="margin-bottom: 8px;">
                        {row['id']}
                    </div>
                    <div style="color: #666; margin-bottom: 12px;">
                        Score: {row['trendingScore']:.2f}
                    </div>
                    <div style="display: flex; gap: 8px;">
                        <a href="https://huggingface.co/spaces/{row['id']}" 
                           target="_blank" 
                           style="padding: 6px 12px; background-color: white; color: #2563eb; text-decoration: none; border-radius: 4px; font-size: 0.9em; border: 1px solid #2563eb;"
                           onclick="event.stopPropagation();">
                            View Space ↗
                        </a>
                        <button onclick="event.preventDefault(); gradioEvent('{row['id']}');"
                                style="padding: 6px 12px; background-color: #2563eb; color: white; border: none; border-radius: 4px; cursor: pointer; font-size: 0.9em;">
                            View Trend
                        </button>
                    </div>
                </div>
                """
                for _, row in top_100_spaces.iterrows()
            ]) + """
            </div>
            <script>
            function gradioEvent(spaceId) {
                const radio = document.querySelector(`input[type="radio"][value="${spaceId}"]`);
                if (radio) {
                    radio.checked = true;
                    const event = new Event('change');
                    radio.dispatchEvent(event);
                }
            }
            </script>
            """
            
            with gr.Row():
                space_grid = gr.HTML(value=html_content)
        
        with gr.Tab("About"):
            gr.Markdown("""
            ### Our Tracking System
            
            #### What We Track
            - Daily ranking changes for all Hugging Face Spaces
            - Comprehensive trending scores based on 30-day activity
            - Detailed performance metrics for top 100 Spaces
            - Historical ranking data with daily granularity
            
            #### Key Features
            - **Real-time Rankings**: Stay updated with daily rank changes
            - **Interactive Visualizations**: Track ranking trajectories over time
            - **Trend Analysis**: Identify emerging popular AI applications
            - **Direct Access**: Quick links to explore trending Spaces
            - **Performance Metrics**: Detailed trending scores and statistics
            
            ### Why Use HF Space Ranking Tracker?
            - Discover trending AI demos and applications
            - Monitor your Space's performance and popularity
            - Identify emerging trends in the AI community
            - Make data-driven decisions about your AI projects
            - Stay ahead of the curve in AI application development
            
            Our dashboard provides a comprehensive view of the Hugging Face Spaces ecosystem, helping developers, researchers, and enthusiasts track and understand the dynamics of popular AI applications. Whether you're monitoring your own Space's performance or discovering new trending applications, HF Space Ranking Tracker offers the insights you need.
            
            Experience the pulse of the AI community through our daily updated rankings and discover what's making waves in the world of practical AI applications.
            """)
    
    space_selection.change(
        fn=update_display,
        inputs=[space_selection],
        outputs=[trend_plot, info_box],
        api_name="update_display"
    )

if __name__ == "__main__":
    demo.launch(share=True)