Merge pull request #12 from EAName/main

.gitignore

@@ -1,8 +1,12 @@
-# Python
+# Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
 *$py.class
+
+# C extensions
 *.so
+
+# Distribution / packaging
 .Python
 build/
 develop-eggs/
@@ -15,13 +19,14 @@ lib64/
 parts/
 sdist/
 var/
-wheels/
 *.egg-info/
 .installed.cfg
 *.egg
 MANIFEST
 
 # PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
 *.manifest
 *.spec
 
@@ -32,6 +37,7 @@ pip-delete-this-directory.txt
 # Unit test / coverage reports
 htmlcov/
 .tox/
+.nox/
 .coverage
 .coverage.*
 .cache
@@ -41,61 +47,99 @@ coverage.xml
 .hypothesis/
 .pytest_cache/
 
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+/docs/_build/
+
+# PyBuilder
+.target/
+
 # Jupyter Notebook
 .ipynb_checkpoints
+notebooks/*.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
 
 # pyenv
 .python-version
 
-# celery beat schedule file
-celerybeat-schedule
+# pipenv
+Pipfile.lock
+
+# poetry
+poetry.lock
+
+# mypy
+.mypy_cache/
+.dmypy.json
+
+# Pyre type checker
+.pyre/
 
-# SageMath parsed files
-*.sage.py
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# VS Code
+.vscode/
 
 # Environments
 .env
-.venv
-env/
+.env.*
+.venv/
 venv/
 ENV/
 env.bak/
 venv.bak/
 
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
+# Docker
+*.pid
+*.pid.lock
 
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Project specific
+# Logs
 logs/
-data/
 *.log
+
+# Data, models, and plots (keep .gitkeep)
+data/*
+!data/.gitkeep
+models/*
+!models/.gitkeep
+plots/*
+!plots/.gitkeep
+
+# Ignore large files
+*.h5
+*.hdf5
+*.pkl
+*.joblib
 *.csv
-*.json
+*.zip
+*.tar.gz
+*.ckpt
 
-# IDE
-.vscode/
-.idea/
-*.swp
-*.swo
-*~
+# Allow config and example env
+!config.yaml
+!.env.example
 
-# OS
+# Misc
 .DS_Store
-.DS_Store?
-._*
-.Spotlight-V100
-.Trashes
-ehthumbs.db
 Thumbs.db 

agentic_ai_system/finrl_agent.py

@@ -18,6 +18,7 @@ import logging
 from typing import Dict, List, Tuple, Optional, Any
 from dataclasses import dataclass
 import yaml
+import inspect
 
 logger = logging.getLogger(__name__)
 
@@ -254,7 +255,18 @@ class FinRLAgent:
         self.eval_env = None
         self.callback = None
         
-        logger.info(f"Initializing FinRL agent with algorithm: {config.algorithm}")
+        logger.info(f"Initializing FinRL agent with algorithm: {self.config.algorithm}")
+
+    def _get_valid_kwargs(self, algo_class):
+        """Return a dict of config fields valid for the given algorithm class, excluding tensorboard_log."""
+        sig = inspect.signature(algo_class.__init__)
+        valid_keys = set(sig.parameters.keys())
+        # Exclude 'self', 'policy', and 'tensorboard_log' which are always passed explicitly
+        valid_keys.discard('self')
+        valid_keys.discard('policy')
+        valid_keys.discard('tensorboard_log')
+        # Build kwargs from config dataclass
+        return {k: getattr(self.config, k) for k in self.config.__dataclass_fields__ if k in valid_keys}
     
     def create_environment(self, data: pd.DataFrame, config: Dict[str, Any], 
                           initial_balance: float = 100000, use_real_broker: bool = False) -> TradingEnvironment:
@@ -335,54 +347,35 @@ class FinRLAgent:
             
             # Initialize model based on algorithm
             if self.config.algorithm == "PPO":
+                algo_kwargs = self._get_valid_kwargs(PPO)
                 self.model = PPO(
                     "MlpPolicy",
                     self.env,
-                    learning_rate=self.config.learning_rate,
-                    batch_size=self.config.batch_size,
-                    buffer_size=self.config.buffer_size,
-                    learning_starts=self.config.learning_starts,
-                    gamma=self.config.gamma,
-                    train_freq=self.config.train_freq,
-                    gradient_steps=self.config.gradient_steps,
-                    verbose=self.config.verbose,
+                    **algo_kwargs,
                     tensorboard_log=self.config.tensorboard_log
                 )
             elif self.config.algorithm == "A2C":
+                algo_kwargs = self._get_valid_kwargs(A2C)
                 self.model = A2C(
                     "MlpPolicy",
                     self.env,
-                    learning_rate=self.config.learning_rate,
-                    gamma=self.config.gamma,
-                    verbose=self.config.verbose,
+                    **algo_kwargs,
                     tensorboard_log=self.config.tensorboard_log
                 )
             elif self.config.algorithm == "DDPG":
+                algo_kwargs = self._get_valid_kwargs(DDPG)
                 self.model = DDPG(
                     "MlpPolicy",
                     self.env,
-                    learning_rate=self.config.learning_rate,
-                    buffer_size=self.config.buffer_size,
-                    learning_starts=self.config.learning_starts,
-                    gamma=self.config.gamma,
-                    tau=self.config.tau,
-                    train_freq=self.config.train_freq,
-                    gradient_steps=self.config.gradient_steps,
-                    verbose=self.config.verbose,
+                    **algo_kwargs,
                     tensorboard_log=self.config.tensorboard_log
                 )
             elif self.config.algorithm == "TD3":
+                algo_kwargs = self._get_valid_kwargs(TD3)
                 self.model = TD3(
                     "MlpPolicy",
                     self.env,
-                    learning_rate=self.config.learning_rate,
-                    buffer_size=self.config.buffer_size,
-                    learning_starts=self.config.learning_starts,
-                    gamma=self.config.gamma,
-                    tau=self.config.tau,
-                    train_freq=self.config.train_freq,
-                    gradient_steps=self.config.gradient_steps,
-                    verbose=self.config.verbose,
+                    **algo_kwargs,
                     tensorboard_log=self.config.tensorboard_log
                 )
             else:
@@ -660,4 +653,9 @@ class FinRLAgent:
         ema_fast = prices.ewm(span=fast).mean()
         ema_slow = prices.ewm(span=slow).mean()
         macd = ema_fast - ema_slow
-        return macd 
+        return macd
+
+
+def create_finrl_agent_from_config(config: FinRLConfig) -> FinRLAgent:
+    """Create a FinRL agent from configuration"""
+    return FinRLAgent(config) 

finrl_demo.py

@@ -127,15 +127,14 @@ def train_finrl_agent(config: dict, train_data: pd.DataFrame, test_data: pd.Data
     logger.info("Starting FinRL agent training")
     
     # Create FinRL agent
-    finrl_config = FinRLConfig(**config['finrl'])
+    finrl_config = FinRLConfig(**{k: v for k, v in config['finrl'].items() if k in FinRLConfig.__dataclass_fields__})
     agent = FinRLAgent(finrl_config)
     
     # Train the agent
     training_result = agent.train(
         data=train_data,
-        total_timesteps=config['finrl']['training']['total_timesteps'],
-        eval_freq=config['finrl']['training']['eval_freq'],
-        eval_data=test_data
+        config=config,
+        total_timesteps=config['finrl']['training']['total_timesteps']
     )
     
     logger.info(f"Training completed: {training_result}")
@@ -149,27 +148,31 @@ def train_finrl_agent(config: dict, train_data: pd.DataFrame, test_data: pd.Data
     return agent
 
 
-def evaluate_agent(agent: FinRLAgent, test_data: pd.DataFrame) -> dict:
+def evaluate_agent(agent: FinRLAgent, test_data: pd.DataFrame, config: dict) -> dict:
     """Evaluate the trained agent"""
     logger.info("Evaluating FinRL agent")
     
     # Evaluate on test data
-    evaluation_results = agent.evaluate(test_data)
+    evaluation_results = agent.evaluate(test_data, config)
     
     logger.info(f"Evaluation results: {evaluation_results}")
     
     return evaluation_results
 
 
-def generate_predictions(agent: FinRLAgent, test_data: pd.DataFrame) -> list:
+def generate_predictions(agent: FinRLAgent, test_data: pd.DataFrame, config: dict) -> list:
     """Generate trading predictions"""
     logger.info("Generating trading predictions")
     
-    predictions = agent.predict(test_data)
+    prediction_results = agent.predict(test_data, config)
     
-    logger.info(f"Generated {len(predictions)} predictions")
-    
-    return predictions
+    if prediction_results['success']:
+        predictions = prediction_results['actions']
+        logger.info(f"Generated {len(predictions)} predictions")
+        return predictions
+    else:
+        logger.error(f"Prediction failed: {prediction_results['error']}")
+        return []
 
 
 def plot_results(test_data: pd.DataFrame, predictions: list, evaluation_results: dict):
@@ -182,16 +185,17 @@ def plot_results(test_data: pd.DataFrame, predictions: list, evaluation_results:
     # Plot 1: Price and predictions
     axes[0].plot(test_data.index, test_data['close'], label='Close Price', alpha=0.7)
     
-    # Mark buy/sell signals
-    buy_signals = [i for i, pred in enumerate(predictions) if pred == 2]
-    sell_signals = [i for i, pred in enumerate(predictions) if pred == 0]
-    
-    if buy_signals:
-        axes[0].scatter(test_data.index[buy_signals], test_data['close'].iloc[buy_signals], 
-                       color='green', marker='^', s=100, label='Buy Signal', alpha=0.8)
-    if sell_signals:
-        axes[0].scatter(test_data.index[sell_signals], test_data['close'].iloc[sell_signals], 
-                       color='red', marker='v', s=100, label='Sell Signal', alpha=0.8)
+    # Mark buy/sell signals only if predictions are available
+    if predictions:
+        buy_signals = [i for i, pred in enumerate(predictions) if pred == 2]
+        sell_signals = [i for i, pred in enumerate(predictions) if pred == 0]
+        
+        if buy_signals:
+            axes[0].scatter(test_data.index[buy_signals], test_data['close'].iloc[buy_signals], 
+                           color='green', marker='^', s=100, label='Buy Signal', alpha=0.8)
+        if sell_signals:
+            axes[0].scatter(test_data.index[sell_signals], test_data['close'].iloc[sell_signals], 
+                           color='red', marker='v', s=100, label='Sell Signal', alpha=0.8)
     
     axes[0].set_title('Price Action and Trading Signals')
     axes[0].set_ylabel('Price')
@@ -236,23 +240,30 @@ def print_summary(evaluation_results: dict, predictions: list):
     print("FINRL TRADING SYSTEM SUMMARY")
     print("="*60)
     
-    print(f"Algorithm: {evaluation_results.get('algorithm', 'Unknown')}")
-    print(f"Total Return: {evaluation_results['total_return']:.2%}")
-    print(f"Final Portfolio Value: ${evaluation_results['final_portfolio_value']:,.2f}")
-    print(f"Total Reward: {evaluation_results['total_reward']:.4f}")
-    print(f"Sharpe Ratio: {evaluation_results['sharpe_ratio']:.4f}")
-    print(f"Number of Trading Steps: {evaluation_results['steps']}")
+    if evaluation_results.get('success', False):
+        print(f"Algorithm: {evaluation_results.get('algorithm', 'Unknown')}")
+        print(f"Total Return: {evaluation_results.get('total_return', 0):.2%}")
+        print(f"Final Portfolio Value: ${evaluation_results.get('final_portfolio_value', 0):,.2f}")
+        print(f"Total Reward: {evaluation_results.get('total_reward', 0):.4f}")
+        print(f"Sharpe Ratio: {evaluation_results.get('sharpe_ratio', 0):.4f}")
+        print(f"Number of Trading Steps: {evaluation_results.get('steps', 0)}")
+        print(f"Max Drawdown: {evaluation_results.get('max_drawdown', 0):.2%}")
+    else:
+        print(f"Evaluation failed: {evaluation_results.get('error', 'Unknown error')}")
     
     # Trading statistics
-    buy_signals = sum(1 for pred in predictions if pred == 2)
-    sell_signals = sum(1 for pred in predictions if pred == 0)
-    hold_signals = sum(1 for pred in predictions if pred == 1)
-    
-    print(f"\nTrading Signals:")
-    print(f"  Buy signals: {buy_signals}")
-    print(f"  Sell signals: {sell_signals}")
-    print(f"  Hold signals: {hold_signals}")
-    print(f"  Total signals: {len(predictions)}")
+    if predictions:
+        buy_signals = sum(1 for pred in predictions if pred == 2)
+        sell_signals = sum(1 for pred in predictions if pred == 0)
+        hold_signals = sum(1 for pred in predictions if pred == 1)
+        
+        print(f"\nTrading Signals:")
+        print(f"  Buy signals: {buy_signals}")
+        print(f"  Sell signals: {sell_signals}")
+        print(f"  Hold signals: {hold_signals}")
+        print(f"  Total signals: {len(predictions)}")
+    else:
+        print(f"\nNo trading predictions available")
     
     print("\n" + "="*60)
 
@@ -273,10 +284,10 @@ def main():
         agent = train_finrl_agent(config, train_data, test_data)
         
         # Evaluate agent
-        evaluation_results = evaluate_agent(agent, test_data)
+        evaluation_results = evaluate_agent(agent, test_data, config)
         
         # Generate predictions
-        predictions = generate_predictions(agent, test_data)
+        predictions = generate_predictions(agent, test_data, config)
         
         # Create visualizations
         plot_results(test_data, predictions, evaluation_results)