Compute the multi-dimensional z-normalized matrix profile with a `dask` cluster This is a highly distributed implementation around the Numba JIT-compiled parallelized `_mstump` function which computes the multi-dimensional matrix profile according to STOMP. Note that only self-join
(
dask_client,
T_A,
T_B,
m,
excl_zone,
M_T,
Σ_T,
μ_Q,
σ_Q,
T_subseq_isconstant,
Q_subseq_isconstant,
include,
discords,
)
| 13 | |
| 14 | |
| 15 | def _dask_mstumped( |
| 16 | dask_client, |
| 17 | T_A, |
| 18 | T_B, |
| 19 | m, |
| 20 | excl_zone, |
| 21 | M_T, |
| 22 | Σ_T, |
| 23 | μ_Q, |
| 24 | σ_Q, |
| 25 | T_subseq_isconstant, |
| 26 | Q_subseq_isconstant, |
| 27 | include, |
| 28 | discords, |
| 29 | ): |
| 30 | """ |
| 31 | Compute the multi-dimensional z-normalized matrix profile with a `dask` cluster |
| 32 | |
| 33 | This is a highly distributed implementation around the Numba JIT-compiled |
| 34 | parallelized `_mstump` function which computes the multi-dimensional matrix |
| 35 | profile according to STOMP. Note that only self-joins are supported. |
| 36 | |
| 37 | Parameters |
| 38 | ---------- |
| 39 | dask_client : client |
| 40 | A ``dask`` client. Setting up a ``dask`` cluster is beyond |
| 41 | the scope of this library. Please refer to the ``dask`` |
| 42 | documentation. |
| 43 | |
| 44 | T_A : numpy.ndarray |
| 45 | The time series or sequence for which to compute the multi-dimensional |
| 46 | matrix profile. Each row in `T_A` represents data from the same |
| 47 | dimension while each column in `T_A` represents data from a different |
| 48 | dimension. |
| 49 | |
| 50 | T_B : numpy.ndarray |
| 51 | The time series or sequence that will be used to annotate T_A. For every |
| 52 | subsequence in T_A, its nearest neighbor in T_B will be recorded. |
| 53 | |
| 54 | m : int |
| 55 | Window size |
| 56 | |
| 57 | excl_zone : int |
| 58 | The half width for the exclusion zone relative to the current |
| 59 | sliding window |
| 60 | |
| 61 | M_T : numpy.ndarray |
| 62 | Sliding mean of time series, `T` |
| 63 | |
| 64 | Σ_T : numpy.ndarray |
| 65 | Sliding standard deviation of time series, `T` |
| 66 | |
| 67 | μ_Q : numpy.ndarray |
| 68 | Mean of the query sequence, `Q`, relative to the current sliding window |
| 69 | |
| 70 | σ_Q : numpy.ndarray |
| 71 | Standard deviation of the query sequence, `Q`, relative to the current |
| 72 | sliding window |
nothing calls this directly
no test coverage detected