rl-pricing 0.5.0__py3-none-any.whl

rl/autotrain/r1.py

@@ -0,0 +1,124 @@
+"""Driver for the R1 runs: the toolkit's ensemble with the FinRL authors' recipe.
+
+Sets what the toolkit lets us match from Yang, Liu, Zhong and Walid (ICAIF
+2020): the four indicators (``macd``, ``rsi_30``, ``cci_30``, ``dx_30``), the
+training steps per algorithm (A2C 30,000, PPO 100,000, DDPG 10,000), PPO with
+``ent_coef`` 0.005 and 128-step rollouts in minibatches of 16 (the authors'
+``nminibatches=8``), and DDPG with Ornstein-Uhlenbeck action noise of sigma
+0.5. A2C and the rest of DDPG keep the toolkit defaults, as does everything
+else (0.1% fees per side, $1,000,000, ``hmax`` 100, reward scaling 1e-4,
+63-session rebalance and validation windows, next-open fills, observation
+normalisation, refit of the winner). Each algorithm also trades its own
+account (``standalone_accounts``).
+
+Prices come from a CSV in the toolkit format (``date,tic,open,high,low,close,
+volume``), e.g. from :mod:`rl.marketdata.sharadar`::
+
+    python -m rl.autotrain.r1 --data-file prices.csv --seed 0 --run-name r1_a_s0
+"""
+
+import argparse
+import copy
+import logging
+
+from rl.autotrain.training import TrainConfig, run_ensemble
+from rl.config import config
+
+AUTHORS_INDICATORS = ("macd", "rsi_30", "cci_30", "dx_30")
+AUTHORS_TIMESTEPS = {"a2c": 30_000, "ppo": 100_000, "ddpg": 10_000}
+AUTHORS_DDPG_NOISE_SIGMA = 0.5
+
+
+def authors_model_kwargs(ddpg_noise_sigma=AUTHORS_DDPG_NOISE_SIGMA):
+    """Per-algorithm model settings (each replaces the config.py default)."""
+    return {
+        "a2c": copy.deepcopy(config.A2C_PARAMS),
+        # 128 steps in 8 minibatches; every other PPO setting is stable-baselines3's default.
+        "ppo": {"n_steps": 128, "batch_size": 16, "ent_coef": 0.005},
+        "ddpg": {
+            **copy.deepcopy(config.DDPG_PARAMS),
+            "action_noise": {"type": "ornstein_uhlenbeck", "sigma": ddpg_noise_sigma},
+        },
+    }
+
+
+def r1_config(
+    data_file,
+    *,
+    seed,
+    use_turbulence=True,
+    ticker_list=None,
+    start_date="2009-01-02",
+    start_trade_date="2016-01-04",
+    end_date="2026-01-01",
+    ddpg_noise_sigma=AUTHORS_DDPG_NOISE_SIGMA,
+    ensemble_timesteps=None,
+    standalone_accounts=True,
+    run_name=None,
+    results_dir=config.RESULTS_DIR,
+    **overrides,
+):
+    """The :class:`TrainConfig` of one R1 ensemble run.
+
+    ``end_date`` is exclusive (the default includes 2025-12-31). ``overrides``
+    set any other :class:`TrainConfig` field.
+    """
+    settings = dict(
+        agent="ensemble",
+        task="trading",
+        data_source="csv",
+        data_file=data_file,
+        ticker_list=ticker_list,
+        start_date=start_date,
+        start_trade_date=start_trade_date,
+        end_date=end_date,
+        tech_indicator_list=list(AUTHORS_INDICATORS),
+        use_turbulence=use_turbulence,
+        ensemble_timesteps=dict(AUTHORS_TIMESTEPS if ensemble_timesteps is None else ensemble_timesteps),
+        ensemble_model_kwargs=authors_model_kwargs(ddpg_noise_sigma),
+        standalone_accounts=standalone_accounts,
+        seed=seed,
+        run_name=run_name,
+        results_dir=results_dir,
+    )
+    settings.update(overrides)
+    return TrainConfig(**settings).validate()
+
+
+def run_r1(data_file, *, seed, **options):
+    """Run the ensemble for ``seed`` (see :func:`r1_config`); returns :func:`run_ensemble`'s dict."""
+    return run_ensemble(r1_config(data_file, seed=seed, **options))
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser(description=__doc__.split("\n\n")[0])
+    parser.add_argument("--data-file", required=True, help="CSV of date,tic,open,high,low,close,volume")
+    parser.add_argument("--seed", type=int, required=True)
+    parser.add_argument("--tickers", nargs="+", help="default: every ticker in the file")
+    parser.add_argument("--no-turbulence", action="store_true", help="arm B: no liquidation rule")
+    parser.add_argument("--start-date", default="2009-01-02")
+    parser.add_argument("--start-trade-date", default="2016-01-04")
+    parser.add_argument("--end-date", default="2026-01-01", help="exclusive")
+    parser.add_argument("--ddpg-noise-sigma", type=float, default=AUTHORS_DDPG_NOISE_SIGMA)
+    parser.add_argument("--run-name")
+    parser.add_argument("--results-dir", default=config.RESULTS_DIR)
+    options = parser.parse_args(argv)
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s: %(message)s"
+    )
+    return run_r1(
+        options.data_file,
+        seed=options.seed,
+        use_turbulence=not options.no_turbulence,
+        ticker_list=options.tickers,
+        start_date=options.start_date,
+        start_trade_date=options.start_trade_date,
+        end_date=options.end_date,
+        ddpg_noise_sigma=options.ddpg_noise_sigma,
+        run_name=options.run_name,
+        results_dir=options.results_dir,
+    )
+
+
+if __name__ == "__main__":
+    main()