Spaces:
Sleeping
Sleeping
| """Fit M1, M2, M3 on the full plot-level dataset and save coefficients. | |
| These in-sample fits are used by the demo app for single-image yield | |
| prediction. The demo only has features from one uploaded image, so there | |
| is no test fold; we want the best-known M3 mapping from (class areas, | |
| mean_area) to predicted obs_sum_B_A1_A2_OV. | |
| Usage: | |
| uv run python scripts/fit_final_models.py \\ | |
| --input outputs/df_model_yield_by_plot.csv \\ | |
| --out app/m3_coefficients.json | |
| """ | |
| from __future__ import annotations | |
| import argparse | |
| import json | |
| from pathlib import Path | |
| import pandas as pd | |
| from sklearn.linear_model import LinearRegression | |
| from sklearn.metrics import r2_score | |
| from potatopheno.models import ( | |
| PREDICTORS_M1, | |
| PREDICTORS_M2, | |
| PREDICTORS_M3, | |
| RESPONSE, | |
| 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.") | |
| p.add_argument( | |
| "--out", | |
| type=Path, | |
| required=True, | |
| help="Path to write the JSON coefficients file (used by the Gradio app).", | |
| ) | |
| return p.parse_args() | |
| def _fit(df: pd.DataFrame, predictors: tuple[str, ...], name: str) -> dict: | |
| subset = df.dropna(subset=list(predictors) + [RESPONSE]) | |
| X = subset[list(predictors)] | |
| y = subset[RESPONSE] | |
| model = LinearRegression() | |
| model.fit(X, y) | |
| pred = model.predict(X) | |
| return { | |
| "name": name, | |
| "predictors": list(predictors), | |
| "response": RESPONSE, | |
| "intercept": float(model.intercept_), | |
| "coefficients": {p: float(c) for p, c in zip(predictors, model.coef_)}, | |
| "n_train_plots": int(len(subset)), | |
| "in_sample_r2": float(r2_score(y, pred)), | |
| } | |
| def main() -> None: | |
| args = _parse_args() | |
| df = pd.read_csv(args.input) | |
| df = add_model_features(df) | |
| fits = { | |
| "M1": _fit(df, PREDICTORS_M1, "M1"), | |
| "M2": _fit(df, PREDICTORS_M2, "M2"), | |
| "M3": _fit(df, PREDICTORS_M3, "M3"), | |
| } | |
| args.out.parent.mkdir(parents=True, exist_ok=True) | |
| with open(args.out, "w") as f: | |
| json.dump(fits, f, indent=2) | |
| for name, fit in fits.items(): | |
| print( | |
| f"{name}: n_train={fit['n_train_plots']:>4} in-sample R²={fit['in_sample_r2']:.3f} " | |
| f"intercept={fit['intercept']:+.3f}" | |
| ) | |
| print(f"\n[DONE] wrote → {args.out}") | |
| if __name__ == "__main__": | |
| main() | |