Observed, emission, trend, and every per-component path as columns.
The layout behind to_dict and to_pandas: the scalar paths
first, then for each component \(j\) (one-based in the column
names) its amplitude, frequency, phase, phase offset, gate and
contribution.
- Return type:
dict[str, NDArray[double]]
- Returns:
Arrays of \(r\) rows keyed observed, emission, trend,
oscillation and amplitude_j, frequency_j, phase_j,
phase_offset_j, gate_j, component_j for j = 1 .. k.
