twe_alignment_path(x: ndarray, y: ndarray, window: float | None = None, nu: float = 0.001, lmbda: float = 1.0, itakura_max_slope: float | None = None) Tuple[List[Tuple[int, int]], float][source]

Compute the TWE alignment path between two time series.

xnp.ndarray, of shape (n_channels, n_timepoints) or (n_timepoints,)

First time series.

ynp.ndarray, of shape (m_channels, m_timepoints) or (m_timepoints,)

Second time series.

windowfloat, default=None

The window to use for the bounding matrix. If None, no bounding matrix is used.

nufloat, default=0.001

A non-negative constant which characterizes the stiffness of the elastic twe measure. Must be > 0.

lmbdafloat, default=1.0

A constant penalty that punishes the editing efforts. Must be >= 1.0.

itakura_max_slopefloat, default=None

Maximum slope as a proportion of the number of time points used to create Itakura parallelogram on the bounding matrix. Must be between 0. and 1.

List[Tuple[int, int]]

The alignment path between the two time series where each element is a tuple of the index in x and the index in y that have the best alignment according to the cost matrix.


The twe distance betweeen the two time series.


If x and y are not 1D or 2D arrays.


>>> import numpy as np
>>> from aeon.distances import twe_alignment_path
>>> x = np.array([[1, 2, 3, 6]])
>>> y = np.array([[1, 2, 3, 4]])
>>> twe_alignment_path(x, y)
([(0, 0), (1, 1), (2, 2), (3, 3)], 2.0)