Add comprehensive project documentation and fix data pipeline

- Add detailed README with architecture diagram and usage instructions
- Add API, configuration, and development documentation
- Fix price data column handling for yfinance auto_adjust=True
- Fix model feature dimension indexing and temporal attention batching
- Add missing imports and position tracking in paper broker
- Add python-dotenv support for environment variables
- Update .gitignore with Python artifacts and environment files

main.py

@@ -58,8 +58,8 @@ def main():
 
     # Initialize model
     logger.info("Initializing GNN model")
-    # Get number of features from first data point
-    num_features = train_dataset[0].x.shape[1]
+    # x has shape (num_stocks, seq_len, num_features); features are in the last dim
+    num_features = train_dataset[0].x.shape[2]
     model = CorporateActionAwareGNN(num_features)
 
     # Optimize model for AMD GPU
@@ -95,9 +95,9 @@ def main():
     backtester = GNNBacktester(model, pipeline)
     portfolio_values, trade_log = backtester.run_backtest(val_dataset)
 
-    # Get benchmark data
+    # Get benchmark data (auto_adjust=True means 'Close' already contains adjusted prices)
     benchmark_data = pipeline.price_data[config.INDEX_TICKER]
-    benchmark_values = benchmark_data.loc[portfolio_values.index]["Adj Close"]
+    benchmark_values = benchmark_data.loc[portfolio_values.index]["Close"]
 
     # Calculate performance metrics
     logger.info("Calculating performance metrics")