"""Compute paper-aligned metrics and plot input, target, and prediction."""

import json
from pathlib import Path

import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
import numpy as np
import yaml


ROOT = Path(__file__).resolve().parents[1]


def metrics(candidate_n, candidate_p, target_n, target_p):
    rmse = np.sqrt(np.mean((candidate_n - target_n) ** 2, axis=(0, 2)))
    sample_variable_rmse = np.sqrt(np.mean((candidate_n - target_n) ** 2, axis=2))
    mass_h = np.mean(np.abs(candidate_p[:, 1].sum(1) - target_p[:, 1].sum(1)) / candidate_p.shape[2])
    mass_r = np.mean(np.abs(candidate_p[:, 2].sum(1) - target_p[:, 2].sum(1)) / candidate_p.shape[2])
    h_bias = np.mean(candidate_p[:, 1] - target_p[:, 1])
    return {"J": float(sample_variable_rmse.mean()), "rmse_u": float(rmse[0]),
            "rmse_h": float(rmse[1]), "rmse_r": float(rmse[2]),
            "mass_error_h_per_point": float(mass_h), "mass_error_r_per_point": float(mass_r),
            "h_bias": float(h_bias)}


def main():
    config = yaml.safe_load((ROOT / "conf/config.yaml").read_text())
    data = np.load(ROOT / config["paths"]["inference"])
    if str(data["format_version"]) != config["data"]["format_version"]:
        raise ValueError("prediction format mismatch")
    input_n, target_n, prediction_n = data["inputs"][:, :3], data["targets"], data["predictions"]
    input_p, target_p, prediction_p = data["xa"], data["targets_physical"], data["predictions_physical"]
    expected = (len(target_n), 3, 250)
    if any(array.shape != expected for array in (input_n, target_n, prediction_n, input_p, target_p, prediction_p)):
        raise ValueError("evaluation arrays must have shape [B,3,250]")
    baseline = metrics(input_n, input_p, target_n, target_p)
    prediction = metrics(prediction_n, prediction_p, target_n, target_p)
    improvement = {key: float(100 * (baseline[key] - prediction[key]) / baseline[key])
                   for key in ("J", "rmse_u", "rmse_h", "rmse_r", "mass_error_h_per_point", "mass_error_r_per_point")
                   if baseline[key] != 0}
    if baseline["h_bias"] != 0:
        improvement["absolute_h_bias"] = float(
            100 * (abs(baseline["h_bias"]) - abs(prediction["h_bias"])) / abs(baseline["h_bias"])
        )
    report = {"samples": len(target_n), "baseline_input": baseline, "prediction": prediction,
              "relative_improvement_percent": improvement,
              "note": "Structured synthetic engineering validation; not paper performance."}
    values = list(baseline.values()) + list(prediction.values()) + list(improvement.values())
    if not np.isfinite(values).all():
        raise FloatingPointError("non-finite evaluation metric")
    output = ROOT / config["paths"]["evaluation_dir"]
    output.mkdir(parents=True, exist_ok=True)
    (output / "metrics.json").write_text(json.dumps(report, indent=2) + "\n")
    x = np.arange(250) * float(config["data"]["domain_km"]) / 250
    figure, axes = plt.subplots(3, 1, figsize=(11, 8), sharex=True)
    for index, (axis, variable) in enumerate(zip(axes, ("u", "h", "r"))):
        axis.plot(x, input_p[0, index], color="steelblue", label="input X^a", linewidth=1.4)
        axis.plot(x, target_p[0, index], color="black", label="QPEns target", linewidth=1.5)
        axis.plot(x, prediction_p[0, index], color="firebrick", label="CNN prediction", linewidth=1.3)
        if variable == "r":
            axis.fill_between(x, 0, data["radar"][0, 0] * max(target_p[0, 2].max(), 1e-6), color="gold", alpha=0.2, label="radar mask")
        axis.set_ylabel(variable); axis.grid(alpha=0.2)
    axes[0].legend(ncol=3); axes[-1].set_xlabel("distance (km)")
    figure.suptitle("MassConservingCNN structured synthetic validation")
    figure.tight_layout(); figure.savefig(output / "input_target_prediction.png", dpi=150); plt.close(figure)
    print(f"evaluation={output.relative_to(ROOT)} J={prediction['J']:.6f} h_mass={prediction['mass_error_h_per_point']:.6f}")


if __name__ == "__main__":
    main()