Spaces:
Sleeping
Sleeping
| """Run the morphometrics stage end-to-end across all trials. | |
| Reads YOLO-seg .txt predictions and the matching source images, computes | |
| per-tuber polygon morphometrics, converts to real-scale (inches and | |
| square inches), assigns USDA size class, and concatenates the three | |
| trials into a single combined CSV. | |
| Usage: | |
| uv run python scripts/extract_morphometrics.py \\ | |
| --out outputs/df_class_real_scale_ALL.csv | |
| """ | |
| from __future__ import annotations | |
| import argparse | |
| from pathlib import Path | |
| import pandas as pd | |
| from potatopheno.calibration import BELT_WIDTH_IN_DEFAULT, apply_real_scale | |
| from potatopheno.classification import assign_usda_class | |
| from potatopheno.io import build_morphometrics_dataframe, plot_id_from_image_id | |
| TRIALS = ("NCPT", "ADC", "NCR") | |
| def _parse_args() -> argparse.Namespace: | |
| p = argparse.ArgumentParser(description=__doc__.splitlines()[0]) | |
| p.add_argument( | |
| "--preds-root", | |
| type=Path, | |
| required=True, | |
| help="Root of YOLO preds. Expects <trial>/preds/*.txt under it.", | |
| ) | |
| p.add_argument( | |
| "--images-root", | |
| type=Path, | |
| required=True, | |
| help="Root of raw images. Expects 2025<TRIAL>/*.JPG under it.", | |
| ) | |
| p.add_argument( | |
| "--out", | |
| type=Path, | |
| required=True, | |
| help="Path of the combined per-tuber CSV to write.", | |
| ) | |
| p.add_argument( | |
| "--trials", | |
| type=lambda s: tuple(t.strip() for t in s.split(",") if t.strip()), | |
| default=TRIALS, | |
| help=f"Comma-separated trial names. Default: {','.join(TRIALS)}.", | |
| ) | |
| p.add_argument( | |
| "--belt-width-in", | |
| type=float, | |
| default=BELT_WIDTH_IN_DEFAULT, | |
| help="Conveyor belt width in inches used for pixel-to-inch calibration.", | |
| ) | |
| return p.parse_args() | |
| def main() -> None: | |
| args = _parse_args() | |
| args.out.parent.mkdir(parents=True, exist_ok=True) | |
| per_trial: list[pd.DataFrame] = [] | |
| for trial in args.trials: | |
| preds_dir = args.preds_root / trial / "preds" | |
| images_dir = args.images_root / f"2025{trial}" | |
| df = build_morphometrics_dataframe(trial, images_dir, preds_dir) | |
| df["Plot"] = plot_id_from_image_id(df["image_id"]) | |
| df = apply_real_scale(df, belt_width_in=args.belt_width_in) | |
| df = assign_usda_class(df) | |
| print( | |
| f"[{trial}] images={df['image_id'].nunique()} " | |
| f"instances={len(df)} " | |
| f"class_counts={df['class'].value_counts().to_dict()}" | |
| ) | |
| per_trial.append(df) | |
| combined = pd.concat(per_trial, ignore_index=True) | |
| combined.to_csv(args.out, index=False) | |
| print( | |
| f"\n[DONE] wrote {len(combined)} rows across " | |
| f"{combined['trial'].nunique()} trials → {args.out}" | |
| ) | |
| if __name__ == "__main__": | |
| main() | |