Download code/ampd/split_seed_experiment.py from fryabcfry/cs4486-amp-pd-checkpoints: direct link, hf CLI and curl.
- Browser
- Download file 2.73 kB
-
https://huggingface.co/fryabcfry/cs4486-amp-pd-checkpoints/resolve/main/code/ampd/split_seed_experiment.py
- Command line
-
hf download hf://fryabcfry/cs4486-amp-pd-checkpoints/code/ampd/split_seed_experiment.py
-
curl -L -o split_seed_experiment.py https://huggingface.co/fryabcfry/cs4486-amp-pd-checkpoints/resolve/main/code/ampd/split_seed_experiment.py
2.73 kB
| """Current-visit predictors and rank-only AE screening for repeated patient splits.""" | |
| import json | |
| from pathlib import Path | |
| import numpy as np | |
| import pandas as pd | |
| from ampd.ae_latent_selection import centered_ranks,encode | |
| from ampd.ae_residual import FrozenMonthMLP,correct | |
| from ampd.protein_residual import branch_features | |
| from ampd.omics_boost import transform_pls | |
| METHODS=('reference','selected_ae','pca','pls') | |
| def arrays(path): | |
| with np.load(path,allow_pickle=False) as a: return dict(a) | |
| def rank_latents(z,samples,y): | |
| """Same earliest-patient Spearman ranking as screen_latents, without unused p-values.""" | |
| rows=[] | |
| for target in range(4): | |
| meta=samples.copy().reset_index(drop=True) | |
| meta['row']=np.arange(len(meta));meta['outcome']=y[:,4*target] | |
| first=meta[meta.outcome.notna()].sort_values(['uid','visit_month']).drop_duplicates('uid') | |
| ix=first.row.to_numpy(int);values=first.outcome.to_numpy(float) | |
| rho=centered_ranks(z[ix]).T@centered_ranks(values) | |
| for j in range(z.shape[1]): | |
| active=np.std(z[ix,j])>1e-10 and np.unique(values).size>=3 and len(ix)>=30 | |
| rows.append({'target':f'updrs_{target+1}','latent':j,'n_patients':len(ix),'rho':float(rho[j]) if active else np.nan}) | |
| return pd.DataFrame(rows) | |
| class SplitSeedPredictor: | |
| def __init__(self,bundle): | |
| bundle=Path(bundle) | |
| self.spec=json.loads((bundle/'model.json').read_text()) | |
| self.baseline=FrozenMonthMLP(bundle/'baseline') | |
| self.pca=arrays(bundle/'pca_extractor.npz');self.pca_head=arrays(bundle/'pca.npz') | |
| self.pls=arrays(bundle/'pls.npz') | |
| self.ae_pre=arrays(bundle/'ae_preprocessor.npz');self.ae_net=arrays(bundle/'ae_numeric.npz') | |
| self.ae_head=arrays(bundle/'selected_ae.npz') | |
| def predict(self,events): | |
| for e in events: | |
| if set(e)!={'visit_id','visit_month','proteins'}: raise ValueError('Only current visit_id, visit_month, proteins allowed') | |
| if len(e['proteins'])!=len(self.spec['proteins']): raise ValueError('Protein vocabulary mismatch') | |
| p=np.asarray([e['proteins'] for e in events],float);m=np.asarray([e['visit_month'] for e in events],float) | |
| if np.any(p<0):raise ValueError('Negative protein abundance') | |
| b=self.baseline.predict(m) | |
| z=encode(p,self.ae_pre,self.ae_net);z=(z-self.ae_head['mean'])/self.ae_head['scale'] | |
| return {'reference':b, | |
| 'selected_ae':correct(b,z@self.ae_head['coef'].T,self.ae_head['weights']), | |
| 'pca':correct(b,branch_features(m,p,'pca',self.pca)@self.pca_head['coef'].T,self.pca_head['weights']), | |
| 'pls':correct(b,transform_pls(p,self.pls)@self.pls['coef'].T,self.pls['weights'])} | |