File size: 1,525 Bytes
590a501 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | #!/usr/bin/env python3
"""Train LightGBM on GP-mined features."""
import sys
from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
if str(ROOT) not in sys.path:
sys.path.insert(0, str(ROOT))
import pandas as pd
from models.lightgbm_model import prepare_ml_matrix, train_lightgbm
def main():
feature_path = ROOT / "outputs" / "gp_mining" / "qlib_gp_run_0" / "ML_Features_qlib.csv"
if not feature_path.exists():
feature_path = feature_path.with_suffix(".parquet")
if not feature_path.exists():
raise FileNotFoundError("Run GP mining first: python scripts/run_gp_mining.py")
df = pd.read_parquet(feature_path) if feature_path.suffix == ".parquet" else pd.read_csv(feature_path)
df["date"] = pd.to_datetime(df["date"])
work, feature_cols = prepare_ml_matrix(df)
train_df = work[work["date"] < "2018-01-01"]
valid_df = work[(work["date"] >= "2018-01-01") & (work["date"] < "2019-04-01")]
test_df = work[work["date"] >= "2019-04-01"]
model = train_lightgbm(
train_df,
valid_df,
feature_cols,
model_path=ROOT / "outputs" / "models" / "lightgbm_gp.txt",
)
test_pred = model.predict(test_df[feature_cols])
test_df = test_df.copy()
test_df["pred_score"] = test_pred
test_df[["date", "symbol", "pred_score", "target_return"]].to_csv(
ROOT / "outputs" / "models" / "test_predictions.csv",
index=False,
)
print("Test predictions saved.")
if __name__ == "__main__":
main()
|