Function maamp_multi_distance_profile

stumpy/maamp.py:397–457

Multi-dimensional wrapper to compute the multi-dimensional non-normalized (i.e., without z-normalization) distance profile for a given query window within the times series or sequence that is denoted by the `query_idx` index. Parameters ---------- query_idx : int Th

(query_idx, T, m, include=None, discords=False, p=2.0)

def maamp_multi_distance_profile(query_idx, T, m, include=None, discords=False, p=2.0):
    """
    Multi-dimensional wrapper to compute the multi-dimensional non-normalized (i.e.,
    without z-normalization) distance profile for a given query window within the
    times series or sequence that is denoted by the `query_idx` index.

    Parameters
    ----------
    query_idx : int
        The window index to calculate the multi-dimensional distance profile

    T : numpy.ndarray
        The time series or sequence for which the multi-dimensional distance profile
        will be returned

    m : int
        Window size

    include : numpy.ndarray, default None
        A list of (zero-based) indices corresponding to the dimensions in `T` that
        must be included in the constrained multidimensional motif search.
        For more information, see Section IV D in:

        `DOI: 10.1109/ICDM.2017.66 \
        <https://www.cs.ucr.edu/~eamonn/Motif_Discovery_ICDM.pdf>`__

    discords : bool, default False
        When set to `True`, this reverses the distance profile to favor discords rather
        than motifs. Note that indices in `include` are still maintained and respected.

    p : float, default 2.0
        The p-norm to apply for computing the Minkowski distance. Minkowski distance is
        typically used with `p` being 1 or 2, which correspond to the Manhattan distance
        and the Euclidean distance, respectively.

    Returns
    -------
    D : numpy.ndarray
        Multi-dimensional distance profile for the window with index equal to
        `query_idx`
    """
    T, T_subseq_isfinite = core.preprocess_non_normalized(T, m)

    if T.ndim <= 1:  # pragma: no cover
        err = f"T is {T.ndim}-dimensional and must be at least 2-dimensional"
        raise ValueError(f"{err}")

    core.check_window_size(m, max_size=T.shape[1], n=T.shape[1])

    if include is not None:  # pragma: no cover
        include = core._preprocess_include(include)

    excl_zone = int(
        np.ceil(m / config.STUMPY_EXCL_ZONE_DENOM)
    )  # See Definition 3 and Figure 3

    D = _maamp_multi_distance_profile(
        query_idx, T, T, m, T_subseq_isfinite, p, include, discords, excl_zone