+1
This commit is contained in:
Dobromir Popov
@ -2193,135 +2193,24 @@ class DataProvider:
|
||||
logger.error(f"Error getting BOM matrix for {symbol}: {e}")
|
||||
return None
|
||||
|
||||
def generate_synthetic_bom_features(self, symbol: str) -> List[float]:
|
||||
def get_real_bom_features(self, symbol: str) -> Optional[List[float]]:
|
||||
"""
|
||||
Generate synthetic BOM features when real COB data is not available
|
||||
Get REAL BOM features from actual market data ONLY
|
||||
|
||||
This creates realistic-looking order book features based on current market data
|
||||
NO SYNTHETIC DATA - Returns None if real data is not available
|
||||
"""
|
||||
try:
|
||||
features = []
|
||||
# Try to get real COB data from integration
|
||||
if hasattr(self, 'cob_integration') and self.cob_integration:
|
||||
return self._extract_real_bom_features(symbol, self.cob_integration)
|
||||
|
||||
# Get current price for context
|
||||
current_price = self.get_current_price(symbol)
|
||||
if current_price is None:
|
||||
current_price = 3000.0 # Fallback price
|
||||
|
||||
# === 1. CONSOLIDATED ORDER BOOK DATA (40 features) ===
|
||||
# Top 10 bid levels (price offset + volume)
|
||||
for i in range(10):
|
||||
price_offset = -0.001 * (i + 1) * (1 + np.random.normal(0, 0.1)) # Negative for bids
|
||||
volume_normalized = np.random.exponential(0.5) * (1.0 - i * 0.1) # Decreasing with depth
|
||||
features.extend([price_offset, volume_normalized])
|
||||
|
||||
# Top 10 ask levels (price offset + volume)
|
||||
for i in range(10):
|
||||
price_offset = 0.001 * (i + 1) * (1 + np.random.normal(0, 0.1)) # Positive for asks
|
||||
volume_normalized = np.random.exponential(0.5) * (1.0 - i * 0.1) # Decreasing with depth
|
||||
features.extend([price_offset, volume_normalized])
|
||||
|
||||
# === 2. VOLUME PROFILE FEATURES (30 features) ===
|
||||
# Top 10 volume levels (buy%, sell%, total volume)
|
||||
for i in range(10):
|
||||
buy_percent = 0.3 + np.random.normal(0, 0.2) # Around 30-70% buy
|
||||
buy_percent = max(0.0, min(1.0, buy_percent))
|
||||
sell_percent = 1.0 - buy_percent
|
||||
total_volume = np.random.exponential(1.0) * (1.0 - i * 0.05)
|
||||
features.extend([buy_percent, sell_percent, total_volume])
|
||||
|
||||
# === 3. ORDER FLOW INTENSITY (25 features) ===
|
||||
# Aggressive order flow
|
||||
features.extend([
|
||||
0.5 + np.random.normal(0, 0.1), # Aggressive buy ratio
|
||||
0.5 + np.random.normal(0, 0.1), # Aggressive sell ratio
|
||||
0.4 + np.random.normal(0, 0.1), # Buy volume ratio
|
||||
0.4 + np.random.normal(0, 0.1), # Sell volume ratio
|
||||
np.random.exponential(100), # Avg aggressive buy size
|
||||
np.random.exponential(100), # Avg aggressive sell size
|
||||
])
|
||||
|
||||
# Block trade detection
|
||||
features.extend([
|
||||
0.1 + np.random.exponential(0.05), # Large trade ratio
|
||||
0.2 + np.random.exponential(0.1), # Large trade volume ratio
|
||||
np.random.exponential(1000), # Avg large trade size
|
||||
])
|
||||
|
||||
# Flow velocity metrics
|
||||
features.extend([
|
||||
1.0 + np.random.normal(0, 0.2), # Avg time delta
|
||||
0.1 + np.random.exponential(0.05), # Time velocity variance
|
||||
0.5 + np.random.normal(0, 0.1), # Trade clustering
|
||||
])
|
||||
|
||||
# Institutional activity indicators
|
||||
features.extend([
|
||||
0.05 + np.random.exponential(0.02), # Iceberg detection
|
||||
0.3 + np.random.normal(0, 0.1), # Hidden order ratio
|
||||
0.2 + np.random.normal(0, 0.05), # Smart money flow
|
||||
0.1 + np.random.exponential(0.03), # Algorithmic activity
|
||||
])
|
||||
|
||||
# Market maker behavior
|
||||
features.extend([
|
||||
0.6 + np.random.normal(0, 0.1), # MM provision ratio
|
||||
0.4 + np.random.normal(0, 0.1), # MM take ratio
|
||||
0.02 + np.random.normal(0, 0.005), # Spread tightening
|
||||
1.0 + np.random.normal(0, 0.2), # Quote update frequency
|
||||
0.8 + np.random.normal(0, 0.1), # Quote stability
|
||||
])
|
||||
|
||||
# === 4. MARKET MICROSTRUCTURE SIGNALS (25 features) ===
|
||||
# Order book pressure
|
||||
features.extend([
|
||||
0.5 + np.random.normal(0, 0.1), # Bid pressure
|
||||
0.5 + np.random.normal(0, 0.1), # Ask pressure
|
||||
0.0 + np.random.normal(0, 0.05), # Pressure imbalance
|
||||
1.0 + np.random.normal(0, 0.2), # Pressure intensity
|
||||
0.5 + np.random.normal(0, 0.1), # Depth stability
|
||||
])
|
||||
|
||||
# Price level concentration
|
||||
features.extend([
|
||||
0.3 + np.random.normal(0, 0.1), # Bid concentration
|
||||
0.3 + np.random.normal(0, 0.1), # Ask concentration
|
||||
0.8 + np.random.normal(0, 0.1), # Top level dominance
|
||||
0.2 + np.random.normal(0, 0.05), # Fragmentation index
|
||||
0.6 + np.random.normal(0, 0.1), # Liquidity clustering
|
||||
])
|
||||
|
||||
# Temporal dynamics
|
||||
features.extend([
|
||||
0.1 + np.random.normal(0, 0.02), # Volatility factor
|
||||
1.0 + np.random.normal(0, 0.1), # Momentum factor
|
||||
0.0 + np.random.normal(0, 0.05), # Mean reversion
|
||||
0.5 + np.random.normal(0, 0.1), # Trend alignment
|
||||
0.8 + np.random.normal(0, 0.1), # Pattern consistency
|
||||
])
|
||||
|
||||
# Exchange-specific patterns
|
||||
features.extend([
|
||||
0.4 + np.random.normal(0, 0.1), # Cross-exchange correlation
|
||||
0.3 + np.random.normal(0, 0.1), # Exchange arbitrage
|
||||
0.2 + np.random.normal(0, 0.05), # Latency patterns
|
||||
0.8 + np.random.normal(0, 0.1), # Sync quality
|
||||
0.6 + np.random.normal(0, 0.1), # Data freshness
|
||||
])
|
||||
|
||||
# Ensure exactly 120 features
|
||||
if len(features) > 120:
|
||||
features = features[:120]
|
||||
elif len(features) < 120:
|
||||
features.extend([0.0] * (120 - len(features)))
|
||||
|
||||
# Clamp all values to reasonable ranges
|
||||
features = [max(-5.0, min(5.0, f)) for f in features]
|
||||
|
||||
return features
|
||||
# No real data available - return None instead of synthetic
|
||||
logger.warning(f"No real BOM data available for {symbol} - waiting for real market data")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating synthetic BOM features for {symbol}: {e}")
|
||||
return [0.0] * 120
|
||||
logger.error(f"Error getting real BOM features for {symbol}: {e}")
|
||||
return None
|
||||
|
||||
def start_bom_cache_updates(self, cob_integration=None):
|
||||
"""
|
||||
@ -2342,17 +2231,14 @@ class DataProvider:
|
||||
if bom_features:
|
||||
self.update_bom_cache(symbol, bom_features, cob_integration)
|
||||
else:
|
||||
# Fallback to synthetic
|
||||
synthetic_features = self.generate_synthetic_bom_features(symbol)
|
||||
self.update_bom_cache(symbol, synthetic_features)
|
||||
# NO SYNTHETIC FALLBACK - Wait for real data
|
||||
logger.warning(f"No real BOM features available for {symbol} - waiting for real data")
|
||||
except Exception as e:
|
||||
logger.warning(f"Error getting real BOM features for {symbol}: {e}")
|
||||
synthetic_features = self.generate_synthetic_bom_features(symbol)
|
||||
self.update_bom_cache(symbol, synthetic_features)
|
||||
logger.warning(f"Waiting for real data instead of using synthetic")
|
||||
else:
|
||||
# Generate synthetic BOM features
|
||||
synthetic_features = self.generate_synthetic_bom_features(symbol)
|
||||
self.update_bom_cache(symbol, synthetic_features)
|
||||
# NO SYNTHETIC FEATURES - Wait for real COB integration
|
||||
logger.warning(f"No COB integration available for {symbol} - waiting for real data")
|
||||
|
||||
time.sleep(1.0) # Update every second
|
||||
|
||||
@ -2470,7 +2356,9 @@ class DataProvider:
|
||||
"""Extract flow and microstructure features"""
|
||||
try:
|
||||
# For now, return synthetic features since full implementation would be complex
|
||||
return self.generate_synthetic_bom_features(symbol)[70:] # Last 50 features
|
||||
# NO SYNTHETIC DATA - Return None if no real microstructure data
|
||||
logger.warning(f"No real microstructure data available for {symbol}")
|
||||
return None
|
||||
except:
|
||||
return [0.0] * 50
|
||||
|
||||
|
||||
Reference in New Issue
Block a user