Spaces:
Sleeping
Sleeping
| """Run M1, M2, M3, and RF under leave-one-trial-out yield prediction. | |
| Adds the M3 structural features, runs LOTO for each of the four models, | |
| and writes the per-fold metrics, per-plot predictions, and the cross-fold | |
| summary. | |
| Usage: | |
| uv run python scripts/run_loto_models.py \\ | |
| --input outputs/df_model_yield_by_plot.csv \\ | |
| --out-dir outputs/loto/ | |
| """ | |
| from __future__ import annotations | |
| import argparse | |
| from pathlib import Path | |
| import pandas as pd | |
| from potatopheno.evaluate import ( | |
| run_loto_linear, | |
| run_loto_rf, | |
| summarize_across_trials, | |
| ) | |
| from potatopheno.models import ( | |
| PREDICTORS_M1, | |
| PREDICTORS_M2, | |
| PREDICTORS_M3, | |
| PREDICTORS_RF, | |
| RESPONSE, | |
| RF_KWARGS, | |
| add_model_features, | |
| ) | |
| def _parse_args() -> argparse.Namespace: | |
| p = argparse.ArgumentParser(description=__doc__.splitlines()[0]) | |
| p.add_argument( | |
| "--input", | |
| type=Path, | |
| required=True, | |
| help="Plot-level model dataset (output of build_plot_model_dataset.py).", | |
| ) | |
| p.add_argument( | |
| "--out-dir", | |
| type=Path, | |
| required=True, | |
| help="Directory to write the metrics, predictions, and summary CSVs.", | |
| ) | |
| return p.parse_args() | |
| def main() -> None: | |
| args = _parse_args() | |
| args.out_dir.mkdir(parents=True, exist_ok=True) | |
| df = pd.read_csv(args.input) | |
| df = add_model_features(df) | |
| runs = [ | |
| ("M1", run_loto_linear, PREDICTORS_M1, {}), | |
| ("M2", run_loto_linear, PREDICTORS_M2, {}), | |
| ("M3", run_loto_linear, PREDICTORS_M3, {}), | |
| ("RF", run_loto_rf, PREDICTORS_RF, RF_KWARGS), | |
| ] | |
| pred_parts: list[pd.DataFrame] = [] | |
| metric_parts: list[pd.DataFrame] = [] | |
| for name, runner, predictors, extra in runs: | |
| df_pred, df_metrics = runner(df, predictors, RESPONSE, name, **extra) | |
| pred_parts.append(df_pred) | |
| metric_parts.append(df_metrics) | |
| df_pred_all = pd.concat(pred_parts, ignore_index=True) | |
| df_metrics_all = ( | |
| pd.concat(metric_parts, ignore_index=True) | |
| .sort_values(["model", "test_trial"]) | |
| .reset_index(drop=True) | |
| ) | |
| df_summary = summarize_across_trials(df_metrics_all).sort_values("mean_MAPE") | |
| df_metrics_all.to_csv(args.out_dir / "loto_metrics_by_fold.csv", index=False) | |
| df_pred_all.to_csv(args.out_dir / "loto_predictions_by_plot.csv", index=False) | |
| df_summary.to_csv(args.out_dir / "loto_summary_by_model.csv", index=False) | |
| print("\nLOTO metrics by fold:\n") | |
| print(df_metrics_all.round(3).to_string(index=False)) | |
| print("\nLOTO summary across folds (mean of trial-level metrics):\n") | |
| print(df_summary.round(3).to_string(index=False)) | |
| print(f"\n[DONE] wrote 3 CSVs → {args.out_dir}") | |
| if __name__ == "__main__": | |
| main() | |