AI slop - Build stock pair backtester for Alpaca markets#21
AI slop - Build stock pair backtester for Alpaca markets#21
Conversation
lee101
commented
Nov 18, 2025
lee101
commented
- Created batch_run_market_simulator.py for running simulations across multiple stock pairs
- Downloads historical data from Alpaca API to trainingdata/ directory
- Runs market simulator for each symbol and tracks PnL over time
- Saves results to strategytraining/ directory with rankings
- Supports default symbols from trade_stock_e2e.py or all Alpaca tradable symbols
- Calculates performance metrics: Sharpe ratio, win rate, profit factor, drawdown
- Saves PnL timeseries, summary CSV, and full results JSON
- Added comprehensive documentation in docs/BATCH_SIMULATOR.md
- Added example usage script example_batch_run.sh
- Created batch_run_market_simulator.py for running simulations across multiple stock pairs - Downloads historical data from Alpaca API to trainingdata/ directory - Runs market simulator for each symbol and tracks PnL over time - Saves results to strategytraining/ directory with rankings - Supports default symbols from trade_stock_e2e.py or all Alpaca tradable symbols - Calculates performance metrics: Sharpe ratio, win rate, profit factor, drawdown - Saves PnL timeseries, summary CSV, and full results JSON - Added comprehensive documentation in docs/BATCH_SIMULATOR.md - Added example usage script example_batch_run.sh
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| result = run_simulation_for_symbol( | ||
| symbol=symbol, | ||
| simulation_days=args.simulation_days, | ||
| initial_cash=args.initial_cash, | ||
| output_dir=args.output_dir, | ||
| force_kronos=args.force_kronos |
There was a problem hiding this comment.
Lines 544‑549 call simulate_strategy without ever telling it where the just-downloaded data lives. Earlier in this script all historical bars are written under args.data_dir (default trainingdata/), but simulate_strategy (via activate_simulation) always loads from its own default tototraining/trainingdata. Because no override or copy is provided, every run falls back to the simulator’s synthetic price series and completely ignores the Alpaca CSVs you downloaded. The advertised workflow (“download, then simulate those symbols”) therefore never evaluates on real data. Please plumb the chosen --data-dir through to the simulator (or download into its default root) so the downloaded files are actually used.
Useful? React with 👍 / 👎.
lee101
force-pushed
the
main
branch
2 times, most recently
from
198c06f to
4b5c43f
Compare
…s802 NEW #40 (+981%) Additional champions beyond s404/s507/s609/s704 already committed: - s410: +2945%@5bps, Sortino=5.76, 5bps>8bps very robust (second spike in s401-500) - s802: +981%@5bps, Sortino=N/A (first s801-900 range find, very early) - s506: +723%@5bps (solid but not exceptional) - s801-900 sweep launched, monitor updated with champion save logic - s701-800 monitor updated with champion save logic Pattern confirmed: each 100-seed range produces 1-2 exceptional isolated spikes. s401-500 is unusual with TWO champions (s404 #4 and s410 #21). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…+3063%), s513/s804 ROBUST New 5bps production champions discovered: - s416 (s401-500): +4091% ann, Sortino=6.18, 5bps>8bps ROBUST — NEW #11! - s321 (s301-400): +3063% ann, Sortino=5.07 - s513 (s501-600): +2525% ann, Sortino=5.50, 5bps>8bps ROBUST - s804 (s801-900): +1943% ann, Sortino=5.19, 5bps>8bps ROBUST - s192 (s121-200): +1886% ann, Sortino=4.67, 5bps>8bps ROBUST - s415 (s401-500): +1757% ann, Sortino=4.79, 5bps>8bps ROBUST - s807 (s801-900): +934% ann, Sortino=6.37, 5bps>8bps ROBUST (high Sortino!) - s191 (s121-200): +1457% ann, Sortino=3.90, ROBUST s401-500 is the HOTTEST range: s404(#4)+s416(#11)+s410(#21)+s415(#31) = 4 champions Added crypto70_5bps_leaderboard.csv — automated 5bps production leaderboard Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2 participants
