Commit History
-
feat: default ingest to Yahoo and restore a full README
Edwin Salguero +1: CursorUse Yahoo Finance as the default tape for config, CLI, Gradio, and UIs; fail closed instead of silently simulating. Merge the algotrader 2.0 lab docs with the v1 FinRL/agentic README and drop the Northwestern line. Co-authored-by: Cursor <cursoragent@cursor.com>3d257f3 -
Fix three correctness bugs in the Yahoo ingest
ClaudeUnverified signatureAll three are silent: nothing raises, the numbers are just wrong. Unadjusted prices. yahoo.auto_adjust defaulted to false and _normalize_ohlcv selects only the required columns, discarding 'adj close'. So splits were not adjusted for: NVDA's June 2024 10:1 reads as a -90% single-day return and AAPL's 2020 4:1 as -75%. Any strategy or risk control spanning a split saw a phantom crash. Default is now true, opting out logs a warning, and _warn_if_unadjusted names the dates of daily-or-slower bars moving more than 35% as a backstop when adjustment is off. Partial bars reported as final. _poll_once pulls period='5d' and _ingest_new_bars took every row past the watermark, including the period Yahoo is still building. It emitted that in-progress bar, advanced _last_bar_ts past it, and so never re-emitted the finished version — the strategy acted on a close that had not happened yet, then never saw the real one. _drop_incomplete now withholds a bar until its interval has elapsed; yahoo.emit_…9d67baa -
feat: add Yahoo ingest on the FinRL tree and stop extra branch creation
Edwin Salguero +1: CursorKeep csv/alpaca/synthetic/FinRL paths unchanged. Add yfinance>=1.0 as an optional data_source, rewrite the README, and remove Dependabot plus the weekly dependency-updates workflow so only main and dev remain. Co-authored-by: Cursor <cursoragent@cursor.com>8a5d4f8
-
feat: Add comprehensive Alpaca integration with FinRL
Edwin Salguero- Add Alpaca broker module for real trading capabilities - Integrate Alpaca with FinRL reinforcement learning agent - Update execution agent to support real broker integration - Enhance data ingestion with Alpaca market data support - Add environment configuration for API credentials - Update demo script to showcase Alpaca integration - Comprehensive documentation updates - Support for paper and live trading modes46590b0 -
Add FinRL integration with comprehensive RL trading agent
Edwin Salguero- Add FinRL agent with support for PPO, A2C, DDPG, and TD3 algorithms - Create custom trading environment compatible with Gymnasium - Implement technical indicators integration (RSI, Bollinger Bands, MACD) - Add comprehensive configuration system for FinRL parameters - Create demo script with training, evaluation, and visualization - Add comprehensive test suite for FinRL functionality - Update requirements.txt with FinRL dependencies - Update README with detailed FinRL documentation - Create necessary directories for models, logs, and plots2c67d05
-
Initial commit: Enhanced Algorithmic Trading System with Synthetic Data Generation, Comprehensive Logging, and Extensive Testing
Edwin Salguero- Added synthetic data generator with realistic market data simulation - Implemented comprehensive logging system with rotating log files - Created extensive test suite with unit and integration tests - Enhanced strategy agent with technical indicators (SMA, RSI, Bollinger Bands, MACD) - Improved execution agent with realistic order simulation - Added backtesting and live trading capabilities - Updated configuration system with synthetic data and logging settings - Created comprehensive documentation and demo script859af74