File size: 1,710 Bytes
04ae9bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
"""Load the three retained current-visit models without discarded branches."""
from pathlib import Path
import numpy as np
from ampd.ae_residual import AEResidualPredictor, FrozenMonthMLP, correct
from ampd.omics_boost import transform_pls
from ampd.simple_mlp_baseline import SimpleMLPPredictor


class PLSPredictor:
    def __init__(self, bundle):
        bundle = Path(bundle)
        self.baseline = FrozenMonthMLP(bundle / "baseline")
        self.spec = self.baseline.spec
        with np.load(bundle / "pls.npz", allow_pickle=False) as data:
            self.params = dict(data)

    def predict(self, events):
        for event in events:
            if set(event) != {"visit_id", "visit_month", "proteins"}:
                raise ValueError("Only current visit_id, visit_month and proteins are accepted")
            if len(event["proteins"]) != len(self.spec["proteins"]):
                raise ValueError("Protein vocabulary mismatch")
        proteins = np.asarray([e["proteins"] for e in events], dtype=float)
        if np.any(proteins < 0):
            raise ValueError("Protein abundances must be nonnegative")
        baseline = self.baseline.predict([e["visit_month"] for e in events])
        residual = transform_pls(proteins, self.params) @ self.params["coef"].T
        return {"baseline": baseline, "pls": correct(baseline, residual, self.params["weights"])}


def load_retained(kind, bundle):
    if kind == "baseline_mlp":
        return SimpleMLPPredictor(bundle, feature_sets=("month_protein",))
    if kind == "selected_ae":
        return AEResidualPredictor(bundle, arms=("selected_latent_r",))
    if kind == "pls":
        return PLSPredictor(bundle)
    raise ValueError(kind)