"""Protein corrections selected from training-patient cross-validation.""" from __future__ import annotations import json from pathlib import Path import numpy as np from ampd.current_protein import errors from ampd.omics_boost import fit_pls, transform_pls from ampd.protein_representation import RepresentationPredictor, encode, fit_representation from ampd.protein_residual import correct FAMILIES = {"pca": [2, 4, 8, 16], "pls": [1, 2, 4, 8, 16], "missing": [2, 4, 8, 16]} ALPHAS = (1., 10., 100., 1000.) BLENDS = sorted([(a, b) for a in [0., .25, .5, .75, 1.] for b in [0., .25, .5, .75, 1.] if a+b <= 1.], key=lambda p: (sum(p), p)) def fit_features(family, dim, month, proteins, residual): if family == "pls": return fit_pls(proteins, residual, dim) params, _ = fit_representation(month, proteins, "missing" if family == "missing" else "pca") return params def features(family, dim, proteins, params): if family == "pls": return transform_pls(proteins, params) raw = encode("missing" if family == "missing" else "pca", proteins, params) return ((raw-params["feature_mean"])/params["feature_scale"])[:, :dim].astype(np.float64) def blend_predictions(base, pca, pls, weights): result = base.copy().astype(float) for target, (a, b) in enumerate(weights): cols = slice(target*4, (target+1)*4) result[:, cols] = np.clip(base[:, cols] + a*(pca[:, cols]-base[:, cols]) + b*(pls[:, cols]-base[:, cols]), 0, 86) return result def choose_blend(y, base, pca, pls): result, candidates = [], [] for target in range(4): cols = slice(target*4, (target+1)*4) scores = [] for a, b in BLENDS: prediction = np.clip(base[:, cols]+a*(pca[:, cols]-base[:, cols])+b*(pls[:, cols]-base[:, cols]), 0, 86) scores.append(float(np.nanmean(errors(y[:, cols], prediction)))) index = next(i for i, score in enumerate(scores) if score <= min(scores)+1e-10) result.append(BLENDS[index]) candidates.append({"target": target+1, "candidates": [{"pca": a, "pls": b, "smape": s} for (a, b), s in zip(BLENDS, scores)]}) return result, candidates class CVProteinPredictor: def __init__(self, bundle): bundle = Path(bundle) self.spec = json.loads((bundle / "model.json").read_text()) self.baseline = RepresentationPredictor(bundle / "baseline") self.models = {} for family in FAMILIES: with np.load(bundle / f"{family}.npz", allow_pickle=False) as archive: self.models[family] = dict(archive) with np.load(bundle / "shared_pls.npz", allow_pickle=False) as archive: self.shared = dict(archive) def predict(self, events): base = self.baseline.predict(events) proteins = np.asarray([e["proteins"] for e in events], dtype=float) result = {"none": base, "shared_pls": correct(base, transform_pls(proteins, self.shared) @ self.shared["coef"].T, self.shared["weights"])} for family, model in self.models.items(): dim = self.spec["selections"][family]["dim"] x = features(family, dim, proteins, model) result[f"cv_{family}"] = correct(base, x @ model["coef"].T, model["weights"]) result["equal_blend"] = .5*result["cv_pca"]+.5*result["cv_pls"] result["cv_blend"] = blend_predictions(base, result["cv_pca"], result["cv_pls"], self.spec["blend_weights"]) return result