Scikit-learn
human-activity-recognition
wearable
wrist
time-series
cpu
scikit-learn
File size: 2,182 Bytes
4731b11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
40
41
42
43
44
45
46
47
48
49
50
"""Read frozen WristHARBench fold exports (train/valid/test NPZ) for the package benchmarks.

Only numeric arrays are read (``allow_pickle=False``); the global label vocabulary is
taken from the fold's ``export_manifest.json``. ``X`` is converted to float64 exactly
as the paper runners did, and train+validation are concatenated in that order.
"""
from __future__ import annotations

import json
from pathlib import Path

import numpy as np

STREAMS = (
    "adl_wrist_accel_v1", "capture24_wearable_activity_v1", "domino_watch_accel_v1",
    "gotov_wrist_accel_v1", "handy_wrist_accel_v1", "harmes_left_wrist_accel_v1",
    "harmes_right_wrist_accel_v1", "iuwds_wrist_accel_v1", "mhealth_right_lower_arm_v1",
    "paal_adl_wrist_accel_v1", "pamap2_hand_imu_v1", "wisdm_watch_accel_v1",
)


def load_part(root, dataset, fold, part):
    folder = Path(root) / dataset / f"fold{int(fold)}"
    manifest = json.loads((folder / "export_manifest.json").read_text())
    with np.load(folder / f"{part}.npz", allow_pickle=False) as z:
        out = {"X": np.asarray(z["X"], dtype=np.float64), "y": np.asarray(z["y"], dtype=np.int64),
               "subject": np.asarray(z["subject"]), "time_index": np.asarray(z["time_index"])}
    out["label_names"] = list(manifest["label_names"])
    out["n_classes"] = int(manifest["n_classes"])
    return out


def concat(a, b):
    out = {k: np.concatenate([a[k], b[k]], axis=0) for k in ("X", "y", "subject", "time_index")}
    out["label_names"], out["n_classes"] = a["label_names"], a["n_classes"]
    return out


def load_fold(root, dataset, fold):
    """Return (train, valid, train+valid, test) dictionaries."""
    train, valid, test = (load_part(root, dataset, fold, p) for p in ("train", "valid", "test"))
    return train, valid, concat(train, valid), test


def paper_scores(y_true, y_pred, n_classes):
    """The frozen four-metric definitions used by the release (``wisp_release.scoring``)."""
    from wisp_release.scoring import score
    s = score(np.asarray(y_true, dtype=np.int64), np.asarray(y_pred, dtype=np.int64), int(n_classes))
    return {k: s[k] for k in ("macro_f1", "accuracy", "balanced_accuracy", "worst_class_f1")}