mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-27 23:47:46 +00:00
TPTBusiness
74d5a8234e
Connect Protection Manager, Results Database, model_loader, and Technical Indicators to the main fin_quant trading loop. P0 - CRITICAL INTEGRATIONS: 1. PROTECTION MANAGER in factor_runner.py - Automatic protection check after every backtest - Factors with >15% drawdown are rejected - Cooldown, stoploss guard, low performance filters active - Error handling: workflow continues if protection fails 2. RESULTS DATABASE in quant.py - Auto-save experiment results to SQLite after each loop - Stores: IC, Sharpe, Max DD, Annualized Return, Win Rate - Queryable via ResultsDatabase API - Error handling: warning logged, workflow continues P1 - IMPORTANT INTEGRATIONS: 3. MODEL LOADER in model_coder.py - Loads models/local/ as baseline reference for LLM - Transformer, TCN, PatchTST, CNN+LSTM now used as starting point - LLM can improve upon existing models instead of from scratch 4. TECHNICAL INDICATORS in factor_coder.py - RSI, MACD, Bollinger Bands, CCI, ATR available to LLM - Import paths and usage examples in prompts - Better factor generation with professional indicators TESTS (32 new, ALL PASS): - 23 integration tests in test/qlib/test_fin_quant_integration.py - 9 enhanced integration tests in test/integration/test_all_features.py - All 183 tests pass (122 backtesting + 29 qlib + 32 new) Modified files: - rdagent/app/qlib_rd_loop/quant.py: Results Database integration - rdagent/scenarios/qlib/developer/factor_runner.py: Protection Manager - rdagent/scenarios/qlib/developer/model_coder.py: model_loader baseline - rdagent/scenarios/qlib/developer/factor_coder.py: Technical indicators - test/qlib/test_fin_quant_integration.py: NEW - 23 integration tests - test/integration/test_all_features.py: 9 enhanced tests
83 lines
3.0 KiB
Python
83 lines
3.0 KiB
Python
"""
|
|
Qlib Factor Coder - Generates trading factors using LLM.
|
|
|
|
Integrates with technical indicators module to provide
|
|
available indicator functions for factor implementation.
|
|
"""
|
|
|
|
from rdagent.components.coder.factor_coder import FactorCoSTEER
|
|
from rdagent.core.scenario import Scenario
|
|
|
|
|
|
# Technical indicators documentation string for LLM prompts
|
|
TECHNICAL_INDICATORS_DOCSTRING = """
|
|
## Available Technical Indicator Functions
|
|
|
|
You can use these pre-implemented technical indicators in your factor implementations:
|
|
|
|
```python
|
|
from rdagent.components.coder.rl.indicators import (
|
|
calculate_rsi, # Relative Strength Index (0-100, overbought/oversold)
|
|
calculate_macd, # MACD (Moving Average Convergence Divergence)
|
|
calculate_bollinger_bands, # Bollinger Bands (upper, middle, lower)
|
|
calculate_cci, # Commodity Channel Index
|
|
calculate_atr, # Average True Range (volatility)
|
|
prepare_features # Combine all indicators
|
|
)
|
|
|
|
# Example usage:
|
|
rsi = calculate_rsi(df['close'], period=14)
|
|
macd_df = calculate_macd(df['close'])
|
|
bb_df = calculate_bollinger_bands(df['close'], period=20, std_dev=2.0)
|
|
cci = calculate_cci(df['close'], df['high'], df['low'], period=20)
|
|
atr = calculate_atr(df['high'], df['low'], df['close'], period=14)
|
|
```
|
|
|
|
All functions return pandas Series or DataFrames ready to be used as factor values.
|
|
|
|
### Indicator Descriptions
|
|
|
|
- **RSI (Relative Strength Index)**: Momentum oscillator, range 0-100.
|
|
- Above 70 = overbought (potential reversal down)
|
|
- Below 30 = oversold (potential reversal up)
|
|
|
|
- **MACD (Moving Average Convergence Divergence)**: Trend-following momentum.
|
|
- Returns DataFrame with 'macd', 'signal', 'histogram' columns
|
|
- Crossovers indicate potential trend changes
|
|
|
|
- **Bollinger Bands**: Volatility bands around moving average.
|
|
- Returns DataFrame with 'upper', 'middle', 'lower' columns
|
|
- Price near upper band = potentially overbought
|
|
- Price near lower band = potentially oversold
|
|
|
|
- **CCI (Commodity Channel Index)**: Momentum oscillator.
|
|
- Above +100 = overbought
|
|
- Below -100 = oversold
|
|
|
|
- **ATR (Average True Range)**: Volatility measure.
|
|
- Higher values = more volatile market
|
|
- Useful for dynamic stop-loss placement
|
|
"""
|
|
|
|
|
|
class QlibFactorCoSTEER(FactorCoSTEER):
|
|
"""
|
|
Qlib-specific Factor Coder that includes technical indicators documentation.
|
|
|
|
Enhances the scenario with available technical indicator functions
|
|
so the LLM knows what tools it can use for factor generation.
|
|
"""
|
|
|
|
def __init__(self, scen: Scenario, *args, **kwargs) -> None:
|
|
# Add technical indicators documentation to scenario
|
|
if hasattr(scen, "factor_knowledge"):
|
|
scen.factor_knowledge += TECHNICAL_INDICATORS_DOCSTRING
|
|
elif hasattr(scen, "__dict__"):
|
|
scen.technical_indicators_doc = TECHNICAL_INDICATORS_DOCSTRING
|
|
|
|
super().__init__(scen, *args, **kwargs)
|
|
|
|
|
|
# Keep the alias for backward compatibility
|
|
QlibFactorCoSTEER = QlibFactorCoSTEER
|