"""Small, fixed-parameter ablations of the three presentation improvements.""" import json from pathlib import Path import numpy as np from ampd.retained_models import load_retained from ampd.protein_residual import branch_features, correct from ampd.protein_representation import protein_matrix from ampd.omics_boost import transform_pls METHODS = ('reference', 'ae_full', 'ae_all_latents', 'ae_no_shrinkage', 'pca_full', 'pca_no_compression', 'pca_no_shrinkage', 'pls_full', 'pls_unsupervised', 'pls_no_shrinkage') def load_npz(path): with np.load(path, allow_pickle=False) as data: return dict(data) def raw_features(proteins, pre): return ((protein_matrix(proteins, pre)-pre['raw_mean'])/pre['raw_scale']).astype(np.float32).astype(float) class AblationPredictor: def __init__(self, bundle): bundle = Path(bundle) self.spec = json.loads((bundle/'model.json').read_text()) for key in ('ae_bundle', 'pls_bundle'): reference = Path(self.spec[key]) if not reference.is_absolute(): self.spec[key] = str((bundle.parents[2] / reference).resolve()) self.ae = load_retained('selected_ae', self.spec['ae_bundle']) self.pls = load_retained('pls', self.spec['pls_bundle']) self.pre = load_npz(bundle/'pca_extractor.npz') self.heads = {name: load_npz(bundle/f'{name}.npz') for name in ['ae_all_latents','pca_full','pca_no_compression','pls_unsupervised']} def predict(self, events): # Retained predictors validate exact fields and vocabulary lengths. ae = self.ae.components(events) pls = self.pls.predict(events) proteins = np.asarray([e['proteins'] for e in events], dtype=float) months = np.asarray([e['visit_month'] for e in events], dtype=float) baseline = pls['baseline'] np.testing.assert_array_equal(baseline, ae['baseline']) z = (ae['latent']-self.ae.feature_pre['latent_mean'])/self.ae.feature_pre['latent_scale'] pca = branch_features(months, proteins, 'pca', self.pre) raw = raw_features(proteins, self.pre) unsup = transform_pls(proteins, self.heads['pls_unsupervised']) pca_r = pca @ self.heads['pca_full']['coef'].T pls_r = transform_pls(proteins, self.pls.params) @ self.pls.params['coef'].T result = {'reference': baseline, 'ae_full': ae['predictions']['selected_latent_r'], 'pls_full': pls['pls'], 'ae_no_shrinkage': correct(baseline, ae['raw_residuals']['selected_latent_r'], np.ones(4)), 'pca_full': correct(baseline, pca_r, self.heads['pca_full']['weights']), 'pca_no_shrinkage': correct(baseline, pca_r, np.ones(4)), 'pls_no_shrinkage': correct(baseline, pls_r, np.ones(4))} for name, x in [('ae_all_latents',z),('pca_no_compression',raw),('pls_unsupervised',unsup)]: head = self.heads[name] result[name] = correct(baseline, x @ head['coef'].T, head['weights']) return result