upload app.py

app.py

@@ -0,0 +1,305 @@
+"""MineROI-Net Gradio App - Updated to use complete historical blockchain data"""
+
+import gradio as gr
+import pandas as pd
+import plotly.graph_objects as go
+from datetime import datetime, timedelta
+import os
+from miner_specs import MINER_SPECS, get_miner_list, ELECTRICITY_RATES
+from fetch_blockchain_data import get_blockchain_data_for_date, load_complete_blockchain_data
+from preprocessing import get_latest_sequence
+from electricity_prices import get_electricity_rate
+from predictor import MineROIPredictor
+from fetch_asic_prices import fetch_asic_price_for_date, FALLBACK_PRICES
+
+MODEL_PATH = "best_model_weights.pth"
+
+# Predictor (global)
+predictor = None
+
+
+def init_predictor():
+    """Initialize predictor once"""
+    global predictor
+    if predictor is None:
+        predictor = MineROIPredictor(MODEL_PATH)
+
+
+def init_app():
+    """Initialize app - load complete blockchain data into memory"""
+    print("\n" + "="*80)
+    print("🚀 INITIALIZING MINEROI-NET APP")
+    print("="*80)
+    
+    # Load complete blockchain data into memory (one-time)
+    complete_df = load_complete_blockchain_data()
+    
+    if complete_df is not None:
+        print(f"\n✅ Complete blockchain data loaded successfully!")
+        print(f"   {len(complete_df):,} days available")
+        print(f"   Date range: {complete_df['date'].min().date()} to {complete_df['date'].max().date()}")
+        print(f"\n✅ You can now predict for ANY date in this range!")
+    else:
+        print(f"\n⚠️  WARNING: blockchain_data_complete.csv not found!")
+        print(f"   App will work with limited recent data only")
+        print(f"\n📥 To enable full historical predictions:")
+        print(f"   1. Run: python download_complete_blockchain_data.py")
+        print(f"   2. Upload blockchain_data_complete.csv to your Gradio space")
+    
+    print("="*80 + "\n")
+    
+    # Initialize predictor
+    init_predictor()
+
+
+def predict_roi(miner_name, region, prediction_date):
+    """Make prediction for a specific date"""
+    try:
+        window_size = 30
+        
+        # Convert prediction_date to datetime
+        if isinstance(prediction_date, str):
+            prediction_date = datetime.strptime(prediction_date, '%Y-%m-%d')
+        
+        print(f"\n{'='*80}")
+        print(f"PREDICTION REQUEST")
+        print(f"{'='*80}")
+        print(f"Miner: {miner_name}")
+        print(f"Region: {region}")
+        print(f"Date: {prediction_date.date()}")
+        print(f"{'='*80}\n")
+        
+        # Get blockchain data for this specific date (30 days before + target date)
+        print(f"📡 Fetching blockchain data for {prediction_date.date()}...")
+        blockchain_df = get_blockchain_data_for_date(prediction_date, window_size=window_size)
+        
+        if blockchain_df is None or len(blockchain_df) < window_size:
+            error_msg = f"""
+            <div style='background: #e74c3c; color: white; padding: 20px; border-radius: 10px;'>
+                <h3 style='margin: 0;'>❌ Error: Insufficient Data</h3>
+                <p style='margin: 10px 0 0 0;'>
+                    Not enough blockchain data available for {prediction_date.date()}.
+                    Need at least {window_size} days of historical data.
+                </p>
+            </div>
+            """
+            return error_msg, error_msg, None, None
+        
+        print(f"✅ Got {len(blockchain_df)} days of data")
+        print(f"   Date range: {blockchain_df['date'].min().date()} to {blockchain_df['date'].max().date()}")
+        
+        # Fetch ASIC price for the selected date
+        print(f"\n💰 Fetching ASIC price for {prediction_date.date()}...")
+        miner_prices, data_available = fetch_asic_price_for_date(prediction_date)
+        
+        if not data_available:
+            warning_html = f"""
+            <div style='background: #f39c12; color: white; padding: 15px; border-radius: 10px; margin-bottom: 20px;'>
+                <h3 style='margin: 0;'>⚠️ Warning: Price Data Unavailable</h3>
+                <p style='margin: 10px 0 0 0;'>
+                    No ASIC price data available for {prediction_date.date()}.
+                    Using fallback prices (approximate market values).
+                </p>
+            </div>
+            """
+        else:
+            warning_html = ""
+        
+        miner_price = miner_prices.get(miner_name, FALLBACK_PRICES.get(miner_name, 2500))
+        price_source = "API" if data_available else "Fallback"
+        
+        print(f"   Price for {miner_name}: ${miner_price:,.2f} ({price_source})")
+        
+        # Get sequence (now uses blockchain_df which is date-specific)
+        print(f"\n🔧 Preparing features...")
+        sequence, _, pred_date = get_latest_sequence(blockchain_df, miner_name, miner_price, region, window_size)
+        print(f"✅ Sequence prepared: {sequence.shape}")
+        
+        # Predict
+        print(f"\n🤖 Running prediction...")
+        result = predictor.predict(sequence, region)
+        print(f"✅ Prediction: {result['predicted_label']} ({result['confidence']:.1%})")
+        
+        # Create displays
+        miner_info = create_miner_info(miner_name, miner_price, region, price_source, prediction_date)
+        prediction_html = warning_html + create_prediction_html(result, pred_date, window_size)
+        confidence_chart = create_confidence_chart(result['probabilities'])
+        price_chart = create_price_chart(blockchain_df, window_size)
+        
+        print(f"{'='*80}\n")
+        
+        return miner_info, prediction_html, confidence_chart, price_chart
+        
+    except Exception as e:
+        import traceback
+        error_details = traceback.format_exc()
+        print(f"\n❌ ERROR:")
+        print(error_details)
+        
+        error = f"""
+        <div style='background: #e74c3c; color: white; padding: 20px; border-radius: 10px;'>
+            <h3 style='margin: 0;'>❌ Prediction Error</h3>
+            <p style='margin: 10px 0 0 0;'>{str(e)}</p>
+        </div>
+        """
+        return error, error, None, None
+
+
+def create_miner_info(miner_name, price, region, source, prediction_date):
+    specs = MINER_SPECS[miner_name]
+    # Daily electricity rate for the prediction date (with fallback beyond CSV range)
+    elec_rate = get_electricity_rate(region, prediction_date.date())
+    daily_cost = (specs['power'] * 24 / 1000) * elec_rate
+    
+    # Color coding for source
+    if source == "API":
+        badge_color = "#27ae60"  # Green
+    else:
+        badge_color = "#e74c3c"  # Red for fallback
+    
+    return f"""
+    <div style="background: #1e1e1e; padding: 20px; border-radius: 10px; border: 1px solid #333; color: #ffffff;">
+        <h3 style="color: #F7931A; margin-top: 0;">{specs['full_name']}</h3>
+        <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 15px;">
+            <div>
+                <p style="color: #ffffff;"><strong style="color: #ffffff;">Hashrate:</strong> {specs['hashrate']} TH/s</p>
+                <p style="color: #ffffff;"><strong style="color: #ffffff;">Power:</strong> {specs['power']} W</p>
+                <p style="color: #ffffff;"><strong style="color: #ffffff;">Efficiency:</strong> {specs['efficiency']} W/TH</p>
+            </div>
+            <div>
+                <p style="color: #ffffff;"><strong style="color: #ffffff;">Price ({prediction_date.date()}):</strong> ${price:,.2f} 
+                   <span style="background: {badge_color}; color: white; padding: 2px 8px; border-radius: 4px; font-size: 0.8em;">{source}</span>
+                </p>
+                <p style="color: #ffffff;"><strong style="color: #ffffff;">Region:</strong> {region.title()}</p>
+                <p style="color: #ffffff;"><strong style="color: #ffffff;">Electricity:</strong> ${elec_rate:.4f}/kWh</p>
+            </div>
+        </div>
+        <div style="margin-top: 15px; padding-top: 15px; border-top: 1px solid #333;">
+            <p style="color: #ffffff;"><strong style="color: #ffffff;">Daily Electricity Cost:</strong> ${daily_cost:.2f}</p>
+        </div>
+    </div>
+    """
+
+
+def create_prediction_html(result, date, window):
+    label = result['predicted_label']
+    conf = result['confidence']
+    
+    if 'Unprofitable' in label:
+        color, emoji, rec = '#e74c3c', '🔴', 'NOT RECOMMENDED'
+    elif 'Marginal' in label:
+        color, emoji, rec = '#f39c12', '🟡', 'PROCEED WITH CAUTION'
+    else:
+        color, emoji, rec = '#27ae60', '🟢', 'GOOD OPPORTUNITY'
+    
+    return f"""
+    <div style="background: #1e1e1e; padding: 30px; border-radius: 10px; border: 2px solid {color}; text-align: center; color: #ffffff;">
+        <h2 style="color: {color}; margin: 0 0 10px 0;">{emoji} {label}</h2>
+        <p style="font-size: 1.2em; margin: 10px 0; color: #ffffff;"><strong style="color: #ffffff;">Confidence: {conf:.1%}</strong></p>
+        <p style="font-size: 1.5em; color: {color}; margin: 20px 0;"><strong style="color: {color};">{rec}</strong></p>
+        <p style="color: #cccccc; margin: 10px 0 0 0; font-size: 0.9em;">
+            Prediction based on data up to: {date.strftime('%Y-%m-%d')}<br>Window: {window} days
+        </p>
+    </div>
+    """
+
+
+def create_confidence_chart(probs):
+    categories = ['Unprofitable', 'Marginal', 'Profitable']
+    values = [probs['unprofitable'], probs['marginal'], probs['profitable']]
+    colors = ['#e74c3c', '#f39c12', '#27ae60']
+    
+    fig = go.Figure()
+    fig.add_trace(go.Bar(x=categories, y=values, marker_color=colors, text=[f'{v:.1%}' for v in values], textposition='auto'))
+    fig.update_layout(title='Prediction Confidence', yaxis_title='Probability', yaxis=dict(range=[0, 1], tickformat='.0%'),
+                       template='plotly_dark', height=300, margin=dict(l=0, r=0, t=40, b=0))
+    return fig
+
+
+def create_price_chart(df, window):
+    # Show more context if available
+    display_days = min(len(df), window * 2)
+    df_display = df.tail(display_days)
+    
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(x=df_display['date'], y=df_display['bitcoin_price'], mode='lines', name='Bitcoin Price', line=dict(color='#F7931A', width=2)))
+    fig.update_layout(title=f'Bitcoin Price ({len(df_display)} Days)', xaxis_title='Date', yaxis_title='Price (USD)',
+                       template='plotly_dark', height=300, margin=dict(l=0, r=0, t=40, b=0))
+    return fig
+
+
+def create_interface():
+    # Default date: today
+    today = datetime.now().date()
+    
+    # Check if complete data is available to set min_date
+    complete_df = load_complete_blockchain_data()
+    if complete_df is not None:
+        min_date = complete_df['date'].min().date()
+        max_date = complete_df['date'].max().date()
+        date_info = f"{min_date} to {max_date}"
+    else:
+        min_date = datetime(2018, 1, 22).date()
+        max_date = today
+        date_info = "⚠️ Limited (complete data not loaded)"
+    
+    with gr.Blocks(title="MineROI-Net") as app:
+        gr.Markdown("# 🪙 MineROI-Net: Bitcoin Mining Hardware ROI Predictor")
+        # gr.Markdown("### Powered by Complete Historical Blockchain Data")
+        
+        with gr.Row():
+            with gr.Column(scale=1):
+                gr.Markdown("### Configuration")
+                miner = gr.Dropdown(choices=sorted(get_miner_list()), value='s19pro', label="ASIC Miner")
+                region = gr.Dropdown(choices=['texas', 'china', 'ethiopia'], value='texas', label="Region")
+                
+                # Date picker for prediction date
+                prediction_date = gr.Textbox(
+                    label="📅 Prediction Date",
+                    value=str(today),
+                    info=f"Format: YYYY-MM-DD (e.g., 2024-12-08)",
+                    placeholder="2024-12-08",
+                    elem_classes="date-input"
+                )
+                
+                btn = gr.Button("🔮 Predict ROI", variant="primary", size="lg")
+                
+                gr.Markdown(f"""
+                ### About
+                - 🔴 **Unprofitable** (ROI ≤ 0)
+                - 🟡 **Marginal** (0 < ROI < 1)
+                - 🟢 **Profitable** (ROI ≥ 1)
+                
+                **Model:** 83.7% accuracy (30-day window)
+                
+                **Date Range:** {date_info}
+                
+                **Price Source:**
+                - 🟢 Green badge = Real API data
+                - 🔴 Red badge = Fallback estimate
+                
+                **Data Source:**
+                - Uses complete historical blockchain data
+                - Loaded at app startup for fast predictions
+                """)
+            
+            with gr.Column(scale=2):
+                gr.Markdown("### Results")
+                miner_info = gr.HTML()
+                prediction = gr.HTML()
+                with gr.Row():
+                    conf_plot = gr.Plot()
+                    price_plot = gr.Plot()
+        
+        btn.click(fn=predict_roi, inputs=[miner, region, prediction_date], outputs=[miner_info, prediction, conf_plot, price_plot])
+    
+    return app
+
+
+if __name__ == "__main__":
+    # Initialize app (loads complete data into memory)
+    init_app()
+    
+    # Launch
+    app = create_interface()
+    app.launch(server_name="0.0.0.0", server_port=7860, share=True)