"""Strict loaders for the public PULSE files. ``load_stream`` -> the raw table of one file (column names + numeric values) ``load_modality`` -> the model input of one modality, ``float32 (T, F)`` ``load_recording`` -> several modalities of one recording, cut to a common length None of these returns ``None`` or skips anything: a missing file raises :class:`MissingFileError`, a stream that does not provide the modality raises :class:`ModalityUnavailableError`, and a stream that fails a quality rule raises :class:`DataQualityError`. Which recordings a task *expects* is decided before loading, from the frozen availability table (see ``pulse.data.manifest``). """ from __future__ import annotations import json from dataclasses import dataclass, field from typing import Dict, List, Optional, Sequence, Tuple import numpy as np from ..errors import DataQualityError, MissingFileError, ModalityUnavailableError from ..paths import DataRoot from . import modalities as M MAX_ABS_VALUE = 1e6 MAX_ZERO_FRACTION = 0.9 @dataclass class Stream: """One file: feature column names, values (float64, NaN kept) and time.""" rid: str stream: str path: str columns: List[str] values: np.ndarray # (T, C) float64; non-numeric -> NaN time: Optional[np.ndarray] # (T,) seconds, if the file has a time column raw_columns: List[str] # all columns as in the file @property def n_rows(self) -> int: return int(self.values.shape[0]) def _read_table(path: str): import pandas as pd # imported lazily: pandas must load before torch on some clusters sep = "\t" if path.endswith(".tsv") else "," df = pd.read_csv(path, sep=sep, low_memory=False) df.columns = [str(c).strip() for c in df.columns] return df def stream_path(dr: DataRoot, rid: str, stream: str) -> str: if stream not in M.STREAM_FILES: raise KeyError(f"unknown stream {stream!r}; known: {sorted(M.STREAM_FILES)}") if stream == "mocap_skeleton": return str(dr.mocap_tsv_path(rid, must_exist=True)) return str(dr.stream_path(rid, M.STREAM_FILES[stream], must_exist=True)) def load_stream(dr: DataRoot, rid: str, stream: str) -> Stream: """Read one raw file. Feature columns exclude Frame/Time/time/UTC/'* Type'.""" import pandas as pd path = stream_path(dr, rid, stream) df = _read_table(path) raw_cols = list(df.columns) tcol = "time" if "time" in df.columns else None time = df[tcol].to_numpy(dtype=np.float64) if tcol else None feat = [c for c in raw_cols if c not in M.SKIP_COLS and not any(c.endswith(s) for s in M.SKIP_COL_SUFFIXES)] if stream == "myo_pose": # categorical event stream: keep the labels as strings vals = df[feat].astype(str).to_numpy() return Stream(rid, stream, path, feat, vals, time, raw_cols) sub = df[feat] obj = sub.select_dtypes(include=["object"]).columns if len(obj): sub = sub.copy() sub[obj] = sub[obj].apply(pd.to_numeric, errors="coerce") vals = sub.to_numpy(dtype=np.float64) return Stream(rid, stream, path, feat, vals, time, raw_cols) # --------------------------------------------------------------------------- # feature selection per modality # --------------------------------------------------------------------------- def _require_columns(st: Stream, wanted: Sequence[str], modality: str, reason: str) -> List[int]: idx = {c: i for i, c in enumerate(st.columns)} missing = [c for c in wanted if c not in idx] if missing: raise ModalityUnavailableError( f"{st.rid}: {modality} needs {len(wanted)} columns, {len(missing)} missing " f"(e.g. {missing[0]!r}) in {st.path}", reason) return [idx[c] for c in wanted] def select_feature_columns(st: Stream, modality: str) -> Tuple[List[str], List[int]]: """Return (column names, column indices) that form ``modality``.""" spec = M.get_spec(modality) if spec.stream != st.stream: raise ValueError(f"{modality} is computed from {spec.stream}, not {st.stream}") if modality == "emg": cols = list(M.EMG_COLS) if len(st.columns) != len(cols): raise ModalityUnavailableError( f"{st.rid}: EMG file has {len(st.columns)} channels, expected 8", "emg_columns") return cols, _require_columns(st, cols, modality, "emg_columns") if modality == "pressure": cols = list(M.PRESSURE_COLS) if len(st.columns) != len(cols): raise ModalityUnavailableError( f"{st.rid}: pressure file has {len(st.columns)} cells, expected 50", "pressure_columns") return cols, _require_columns(st, cols, modality, "pressure_columns") if modality == "myo_quat": cols = list(M.MYO_QUAT_COLS) return cols, _require_columns(st, cols, modality, "myo_quat_columns") if modality in ("imu", "imu_wrist", "imu_finger"): n = len(st.columns) if n != M.IMU_N_COLS: raise ModalityUnavailableError( f"{st.rid}: IMU file has {n} columns, expected {M.IMU_N_COLS} " f"(10 sensors x 18); treated as a missing modality", f"imu_columns_{n}") if modality == "imu": return list(st.columns), list(range(n)) pre = M.IMU_SENSOR_SUBSETS[modality] sel = [(c, i) for i, c in enumerate(st.columns) if c.startswith(pre)] if len(sel) != M.get_spec(modality).expected_dim: raise ModalityUnavailableError( f"{st.rid}: {modality} selects {len(sel)} columns", f"{modality}_columns") return [c for c, _ in sel], [i for _, i in sel] if modality in ("eyetrack", "eyetrack_gaze", "eyetrack_ocular"): core = list(M.EYETRACK_CORE_COLS) idx = _require_columns(st, core, modality, "eyetrack_core_columns") if modality == "eyetrack": return core, idx pats = M.EYETRACK_SUBSETS[modality] sel = [(c, i) for c, i in zip(core, idx) if any(p in c for p in pats)] return [c for c, _ in sel], [i for _, i in sel] if modality in ("mocap", "mocap_markers"): if not st.columns: raise ModalityUnavailableError(f"{st.rid}: no MoCap columns", "mocap_columns") if modality == "mocap" and "Hips_X" not in st.columns: raise ModalityUnavailableError(f"{st.rid}: skeleton TSV has no Hips_X", "mocap_no_hips") return list(st.columns), list(range(len(st.columns))) raise KeyError(modality) def skeleton_hip_relative_velocity(arr: np.ndarray, cols: Sequence[str]) -> np.ndarray: """Original benchmark MoCap features: hip-relative positions + velocity. Input ``(T, F)`` with absolute ``*_X/_Y/_Z`` positions and quaternions. Output ``(T, F + N_pos)``: all features with positions minus the hip position, followed by the frame-to-frame difference of the position columns (first frame 0). """ ci = {c: i for i, c in enumerate(cols)} hx, hy, hz = ci["Hips_X"], ci["Hips_Y"], ci["Hips_Z"] xs = [i for i, c in enumerate(cols) if c.endswith("_X")] ys = [i for i, c in enumerate(cols) if c.endswith("_Y")] zs = [i for i, c in enumerate(cols) if c.endswith("_Z")] pos = sorted(xs + ys + zs) rel = arr.copy() hip = arr[:, [hx, hy, hz]].copy() rel[:, xs] -= hip[:, [0]] rel[:, ys] -= hip[:, [1]] rel[:, zs] -= hip[:, [2]] p = rel[:, pos] vel = np.zeros_like(p) vel[1:] = p[1:] - p[:-1] return np.concatenate([rel, vel], axis=1) def quality_check(arr: np.ndarray, rid: str, modality: str) -> None: spec = M.get_spec(modality) if arr.size == 0: raise DataQualityError(f"{rid}: {modality} is empty", "empty") max_abs = float(np.max(np.abs(arr))) if max_abs > MAX_ABS_VALUE: raise DataQualityError( f"{rid}: {modality} has |x| up to {max_abs:.3g} > {MAX_ABS_VALUE:g} (corrupted)", "extreme_values") if spec.zero_check: zf = float(np.mean(arr == 0.0)) if zf > MAX_ZERO_FRACTION: raise DataQualityError( f"{rid}: {modality} is {100 * zf:.1f}% zeros (> {100 * MAX_ZERO_FRACTION:.0f}%, " "sensor dropout)", "mostly_zero") @dataclass class ModalityArray: rid: str modality: str data: np.ndarray # (T, F) float32, NaN/inf mapped to 0 columns: List[str] # names of the F input columns (before any velocity) path: str def modality_from_stream(st: Stream, modality: str) -> ModalityArray: cols, idx = select_feature_columns(st, modality) arr = np.nan_to_num(st.values[:, idx].astype(np.float64), nan=0.0, posinf=0.0, neginf=0.0) quality_check(arr, st.rid, modality) if modality == "mocap": arr = skeleton_hip_relative_velocity(arr, cols) spec = M.get_spec(modality) if spec.expected_dim is not None and arr.shape[1] != spec.expected_dim: raise ModalityUnavailableError( f"{st.rid}: {modality} has {arr.shape[1]} features, expected {spec.expected_dim}", f"{modality}_dim") return ModalityArray(st.rid, modality, arr.astype(np.float32), cols, st.path) def load_modality(dr: DataRoot, rid: str, modality: str) -> ModalityArray: st = load_stream(dr, rid, M.base_stream(modality)) return modality_from_stream(st, modality) @dataclass class RecordingArrays: rid: str arrays: Dict[str, np.ndarray] # modality -> (T, F) float32, common T columns: Dict[str, List[str]] raw_lengths: Dict[str, int] # rows before cutting to the common length #: frames dropped at the start of a modality by ``align_trimmed`` (see #: :func:`release_trim_window`); empty when no stream was shifted start_offsets: Dict[str, int] = field(default_factory=dict) @property def n_frames(self) -> int: return next(iter(self.arrays.values())).shape[0] if self.arrays else 0 def concat(self, order: Optional[Sequence[str]] = None) -> np.ndarray: order = list(order or self.arrays.keys()) return np.concatenate([self.arrays[m] for m in order], axis=1) def release_trim_window(meta: dict) -> Optional[Tuple[int, int]]: """``(front, n)`` if some streams of a recording cover only frames ``[front, front + n)`` of its alignment timeline, else ``None``. In v1.1 the EMG, eye-tracking and pressure files of v2s6, v13s2 and v13s3 were re-trimmed for the release to the MoCap capture window, while IMU, MoCap (TSV and marker CSV) and the Myo orientation streams still cover the whole timeline (``n_samples`` rows). The window is the MoCap padding recorded in ``alignment_metadata.json`` (``mocap_padding.mocap_sq``: ``front_samples``, ``n_frames``); for v2s6 and v13s3 the re-trimmed files equal the earlier full-length streams sliced at exactly this window. """ n_total = meta.get("n_samples") pads = meta.get("mocap_padding") or {} pad = pads.get("mocap_sq") or pads.get("mocap") or {} front, n = pad.get("front_samples"), pad.get("n_frames") if not n_total or front is None or n is None: return None front, n, n_total = int(front), int(n), int(n_total) if n <= 0 or n >= n_total or front + n > n_total: return None return front, n def load_recording(dr: DataRoot, rid: str, modalities: Sequence[str], gate_modalities: Sequence[str] = (), align_trimmed: bool = False) -> RecordingArrays: """Load ``modalities`` of one recording, cut to the shortest stream. ``gate_modalities`` are loaded and validated (so a recording is used only if those streams are present and pass the same rules) but not returned. This is how a 4-modality run is restricted to the recordings of a 5-modality run. ``align_trimmed`` (opt-in; default off keeps the original behaviour): when the requested modalities mix streams re-trimmed by the release (exactly ``n`` rows of :func:`release_trim_window`) with full-timeline streams, the full-timeline streams are first sliced to ``[front, front + n)`` so that frame ``i`` of every returned array is the same instant. Without it, the three affected recordings are cut from the start and the IMU / MoCap streams lead the EMG / eye / pressure streams by 3.4-10.5 s. A requested stream whose length is neither ``n`` nor at least ``front + n`` raises :class:`DataQualityError` (it cannot be placed on either timeline). """ streams: Dict[str, Stream] = {} out: Dict[str, np.ndarray] = {} cols: Dict[str, List[str]] = {} lengths: Dict[str, int] = {} for mod in list(gate_modalities) + list(modalities): sname = M.base_stream(mod) if sname not in streams: streams[sname] = load_stream(dr, rid, sname) ma = modality_from_stream(streams[sname], mod) if mod in modalities: out[mod] = ma.data cols[mod] = ma.columns lengths[mod] = ma.data.shape[0] offsets: Dict[str, int] = {} if align_trimmed and out and len({a.shape[0] for a in out.values()}) > 1: win = release_trim_window(load_alignment_metadata(dr, rid)) if win is not None: front, n = win short = [m for m, a in out.items() if a.shape[0] == n] full = [m for m, a in out.items() if a.shape[0] >= front + n and a.shape[0] != n] odd = {m: int(a.shape[0]) for m, a in out.items() if m not in short and m not in full} if short and odd: # neither the re-trimmed window nor the full timeline: shifting the # others but not these (or cutting all from the start) would misalign raise DataQualityError( f"{rid}: streams {odd} are neither the re-trimmed window ({n} rows) nor " f"cover the full timeline (>= {front + n} rows); cannot align", "trim_window") if short and full: for m in full: out[m] = out[m][front:front + n] offsets[m] = front if out: t = min(a.shape[0] for a in out.values()) out = {m: a[:t] for m, a in out.items()} return RecordingArrays(rid, out, cols, lengths, offsets) def load_alignment_metadata(dr: DataRoot, rid: str) -> dict: p = dr.alignment_metadata_path(rid) with open(p, encoding="utf-8") as f: return json.load(f) __all__ = [ "Stream", "ModalityArray", "RecordingArrays", "load_stream", "load_modality", "load_recording", "release_trim_window", "modality_from_stream", "select_feature_columns", "quality_check", "skeleton_hip_relative_velocity", "load_alignment_metadata", "MissingFileError", ]