def mpdist(ts, ts_b, w, threshold=0.05, n_jobs=1): """ Computes the MPDist between the two series ts and ts_b. For more details refer to the paper: Matrix Profile XII: MPdist: A Novel Time Series Distance Measure to Allow Data Mining in More Challenging Scenarios. Shaghayegh Gharghabi, Shima Imani, Anthony Bagnall, Amirali Darvishzadeh, Eamonn Keogh. ICDM 2018 Parameters ---------- ts : array_like The time series to compute the matrix profile for. ts_b : array_like The time series to compare against. w : int The window size. threshold : float, Default 0.05 The percentile in which the distance is taken from. By default it is set to 0.05 based on empircal research results from the paper. Generally, you should not change this unless you know what you are doing! This value must be a float greater than 0 and less than 1. n_jobs : int, Default = 1 Number of cpu cores to use. Returns ------- float : mpdist The MPDist. """ ts = core.to_np_array(ts).astype('d') ts_b = core.to_np_array(ts_b).astype('d') n_jobs = core.valid_n_jobs(n_jobs) if not core.is_one_dimensional(ts): raise ValueError('ts must be one dimensional!') if not core.is_one_dimensional(ts_b): raise ValueError('ts_b must be one dimensional!') if not isinstance(threshold, float) or threshold <= 0 or threshold >= 1: raise ValueError('threshold must be a float greater than 0 and less'\ ' than 1') mp, mpi, mpb, mpib = cympx_ab_parallel(ts, ts_b, w, 0, n_jobs) mp_abba = np.append(mp, mpb) data_len = len(ts) + len(ts_b) abba_sorted = np.sort(mp_abba[~core.nan_inf_indices(mp_abba)]) distance = np.inf if len(abba_sorted) > 0: upper_idx = int(np.ceil(threshold * data_len)) - 1 idx = np.min([len(abba_sorted) - 1, upper_idx]) distance = abba_sorted[idx] return distance
def mpdist(ts, ts_b, w, n_jobs=1): """ Computes the MPDist between the two series ts and ts_b. For more details refer to the paper: Matrix Profile XII: MPdist: A Novel Time Series Distance Measure to Allow Data Mining in More Challenging Scenarios. Shaghayegh Gharghabi, Shima Imani, Anthony Bagnall, Amirali Darvishzadeh, Eamonn Keogh. ICDM 2018 Parameters ---------- ts : array_like The time series to compute the matrix profile for. ts_b : array_like The time series to compare against. w : int The window size. n_jobs : int, Default = 1 Number of cpu cores to use. Returns ------- float : The MPDist. """ ts = core.to_np_array(ts).astype('d') ts_b = core.to_np_array(ts_b).astype('d') n_jobs = core.valid_n_jobs(n_jobs) if not core.is_one_dimensional(ts): raise ValueError('ts must be one dimensional!') if not core.is_one_dimensional(ts_b): raise ValueError('ts_b must be one dimensional!') mp, mpi, mpb, mpib = cympx_ab_parallel(ts, ts_b, w, 0, n_jobs) mp_abba = np.append(mp, mpb) data_len = len(ts) + len(ts_b) abba_sorted = np.sort(mp_abba[~core.nan_inf_indices(mp_abba)]) distance = np.inf if len(abba_sorted) > 0: idx = np.min([len(abba_sorted) - 1, int(np.ceil(0.05 * data_len)) - 1]) distance = abba_sorted[idx] return distance
def mpx(ts, w, query=None, cross_correlation=False, n_jobs=1): """ The MPX algorithm computes the matrix profile without using the FFT. Parameters ---------- ts : array_like The time series to compute the matrix profile for. w : int The window size. query : array_like Optionally a query series. cross_correlation : bool, Default=False Setermine if cross_correlation distance should be returned. It defaults to Euclidean Distance. n_jobs : int, Default = 1 Number of cpu cores to use. Returns ------- A dict of key data points computed. { 'mp': The matrix profile, 'pi': The matrix profile 1NN indices, 'rmp': The right matrix profile, 'rpi': The right matrix profile 1NN indices, 'lmp': The left matrix profile, 'lpi': The left matrix profile 1NN indices, 'metric': The distance metric computed for the mp, 'w': The window size used to compute the matrix profile, 'ez': The exclusion zone used, 'join': Flag indicating if a similarity join was computed, 'sample_pct': Percentage of samples used in computing the MP, 'data': { 'ts': Time series data, 'query': Query data if supplied } 'class': "MatrixProfile" 'algorithm': "mpx" } """ ts = core.to_np_array(ts).astype('d') n_jobs = core.valid_n_jobs(n_jobs) is_join = False if core.is_array_like(query): query = core.to_np_array(query).astype('d') is_join = True mp, mpi, mpb, mpib = cympx_ab_parallel(ts, query, w, int(cross_correlation), n_jobs) else: mp, mpi = cympx_parallel(ts, w, int(cross_correlation), n_jobs) mp = np.asarray(mp) mpi = np.asarray(mpi) distance_metric = 'euclidean' if cross_correlation: distance_metric = 'cross_correlation' return { 'mp': mp, 'pi': mpi, 'rmp': None, 'rpi': None, 'lmp': None, 'lpi': None, 'metric': distance_metric, 'w': w, 'ez': int(np.floor(w / 4)), 'join': is_join, 'sample_pct': 1, 'data': { 'ts': ts, 'query': query }, 'class': 'MatrixProfile', 'algorithm': 'mpx' }
def mpx(ts, w, query=None, cross_correlation=False, n_jobs=1): """ The MPX algorithm computes the matrix profile without using the FFT. Parameters ---------- ts : array_like The time series to compute the matrix profile for. w : int The window size. query : array_like Optionally a query series. cross_correlation : bool, Default=False Determine if cross_correlation distance should be returned. It defaults to Euclidean Distance. n_jobs : int, Default = 1 Number of cpu cores to use. Returns ------- dict : profile A MatrixProfile data structure. >>> { >>> 'mp': The matrix profile, >>> 'pi': The matrix profile 1NN indices, >>> 'rmp': The right matrix profile, >>> 'rpi': The right matrix profile 1NN indices, >>> 'lmp': The left matrix profile, >>> 'lpi': The left matrix profile 1NN indices, >>> 'metric': The distance metric computed for the mp, >>> 'w': The window size used to compute the matrix profile, >>> 'ez': The exclusion zone used, >>> 'join': Flag indicating if a similarity join was computed, >>> 'sample_pct': Percentage of samples used in computing the MP, >>> 'data': { >>> 'ts': Time series data, >>> 'query': Query data if supplied >>> } >>> 'class': "MatrixProfile" >>> 'algorithm': "mpx" >>> } """ # --- Drew's addition --- dtype = core.get_dtype(ts) ts = core.to_np_array(ts).astype(dtype) #ts = core.to_np_array(ts).astype('d') n_jobs = core.valid_n_jobs(n_jobs) is_join = False if core.is_array_like(query): query = core.to_np_array(query).astype(dtype) #query = core.to_np_array(query).astype('d') is_join = True mp, mpi, mpb, mpib = cympx_ab_parallel(ts, query, w, int(cross_correlation), n_jobs) else: # --- More changes... --- if np.issubdtype(dtype, 'U'): #ts = np.array([ord(x) for x in ts], dtype = 'd') mp, mpi = mpx_single_char(ts, w) else: mp, mpi = cympx_parallel(ts, w, int(cross_correlation), n_jobs) # --- That's it for now... --- #mp, mpi = cympx_parallel(ts, w, int(cross_correlation), n_jobs) mp = np.asarray(mp) mpi = np.asarray(mpi) if np.issubdtype(dtype, 'U'): distance_metric = 'hamming' else: distance_metric = 'euclidean' if cross_correlation: distance_metric = 'cross_correlation' return { 'mp': mp, 'pi': mpi, 'rmp': None, 'rpi': None, 'lmp': None, 'lpi': None, 'metric': distance_metric, 'w': w, 'ez': int(np.ceil(w / 4.0)) if is_join else 0, 'join': is_join, 'sample_pct': 1, 'data': { 'ts': ts, 'query': query }, 'class': 'MatrixProfile', 'algorithm': 'mpx' }