"""Split checks and the fit call shared by the accelerated search.""" import numpy as np def check_splits(*parts): """Require sequence metadata, one global vocabulary and disjoint group IDs.""" first = parts[0] if not first.label_names: raise ValueError("Supply the ordered global label_names") seen = set() for data in parts: if data.label_names != first.label_names or data.X.shape[1:] != first.X.shape[1:]: raise ValueError("Split vocabularies and time/channel shapes must match") if data.subject is None or data.time_index is None or not len(data.y): raise ValueError("Every split needs nonempty windows, subject and time_index") if np.min(data.y) < 0 or np.max(data.y) >= len(first.label_names): raise ValueError("Class ID outside supplied global vocabulary") groups = set(np.asarray(data.subject).astype(str)) if groups & seen: raise ValueError("Participant/sequence groups overlap between splits") seen |= groups def fit_on(model, data): return model.fit(data.X, data.y, groups=data.subject, time_index=data.time_index, n_classes=data.n_classes)