Add transmission datasets and update mining data

Add two new static datasets for cross-region arbitrage calculations:
- transmission_capacity: region-to-region capacity limits (20 rows)
- transmission_cost: transmission costs per path (20 rows)

Update mining dataset with EUR pricing and power metrics:
- Change btc_price_usd to btc_price_eur
- Add power_efficiency_th_per_mw, power_demand_mw
- Add revenue_eur_per_mwh, profit_eur_per_mwh
- Remove mining_profitability column

Changes include:
- scripts/02_fetch_historical.py: rewrite fetch_bitcoin_mining_data()
- scripts/01_generate_synthetic.py: add transmission data generators
- config/data_config.yaml: add transmission config, update bitcoin config
- config/schema.yaml: add 2 new schemas, update bitcoin_mining schema
- scripts/03_process_merge.py: add 2 new datasets
- scripts/04_validate.py: add 2 new datasets
- test/test_data.py: update for new datasets and bitcoin price reference

Total datasets: 9 (734,491 rows, 17.89 MB)

test/test_data.py

@@ -22,7 +22,9 @@ def main():
         'conventional_generation',
         'load_profiles',
         'data_centers',
-        'bitcoin_mining'
+        'bitcoin_mining',
+        'transmission_capacity',
+        'transmission_cost'
     ]
     
     print("\n1. LOADING DATASETS")
@@ -37,7 +39,7 @@ def main():
         else:
             print(f"  ✗ {name:25} NOT FOUND")
     
-    print(f"\nTotal datasets loaded: {len(loaded)}/7")
+    print(f"\nTotal datasets loaded: {len(loaded)}/9")
     
     print("\n2. SAMPLE DATA PREVIEWS")
     print("-" * 60)
@@ -80,9 +82,25 @@ def main():
     if 'bitcoin_mining' in loaded:
         df = loaded['bitcoin_mining']
         print(f"\nBitcoin Mining:")
-        print(f"  BTC Price: ${df['btc_price_usd'].mean():.2f} avg, ${df['btc_price_usd'].max():.2f} max")
+        print(f"  BTC Price: €{df['btc_price_eur'].mean():.2f} avg, €{df['btc_price_eur'].max():.2f} max")
         print(f"  Hashrate: {df['hashrate_ths'].mean():.2f} EH/s avg")
-        print(f"  Profitability: ${df['mining_profitability'].mean():.4f} /TH/day avg")
+        print(f"  Power Demand: {df['power_demand_mw'].mean():.1f} MW avg")
+        print(f"  Revenue: €{df['revenue_eur_per_mwh'].mean():.2f} /MWh avg")
+        print(f"  Profit: €{df['profit_eur_per_mwh'].mean():.2f} /MWh avg")
+
+    if 'transmission_capacity' in loaded:
+        df = loaded['transmission_capacity']
+        print(f"\nTransmission Capacity:")
+        print(f"  Total interconnectors: {len(df)}")
+        print(f"  Avg capacity: {df['capacity_mw'].mean():.0f} MW")
+        print(f"  Avg efficiency: {df['efficiency'].mean():.2%}")
+
+    if 'transmission_cost' in loaded:
+        df = loaded['transmission_cost']
+        print(f"\nTransmission Cost:")
+        print(f"  Total paths: {len(df)}")
+        print(f"  Avg cost: €{df['cost_eur_mwh'].mean():.2f} /MWh")
+        print(f"  Avg loss: {df['loss_percent'].mean():.2f}%")
     
     if 'data_centers' in loaded:
         df = loaded['data_centers']