mne_denoise.ssa.ssa_decompose#
- mne_denoise.ssa.ssa_decompose(x: ndarray, window_length: int | None = None, *, window_seconds: float | None = None, sfreq: float | None = None, max_window: int = 100) tuple[ndarray, dict[str, Any]][source]#
Decompose a one-dimensional series into Basic SSA components.
- Parameters:
- xarray-like, shape (n_times,)
Finite scalar time series.
- window_lengthint | None, default=None
Embedding dimension in samples. If None, choose it automatically.
- window_secondsfloat | None, default=None
Embedding duration in seconds; mutually exclusive with window_length and requiring sfreq.
- sfreqfloat | None, default=None
Sampling frequency in Hz, used with window_seconds and automatic selection.
- max_windowint, default=100
Maximum automatic embedding dimension.
- Returns:
- componentsndarray, shape (n_components, n_times)
Reconstructed elementary components in decreasing singular-value order.
- infodict
Resolved window, trajectory shape, singular values, and numerical rank.
- Raises:
- TypeError
If a scalar parameter has an invalid type.
- ValueError
If x or the requested embedding is invalid.
Notes
The trajectory matrix is decomposed by SVD and reconstructed by anti-diagonal averaging. [1].
References