def test_string(self): freq = '440' with pytest.raises(SPYTypeError): scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000])
def samplerate(self, sr): if sr is None: self._samplerate = None return try: scalar_parser(sr, varname="samplerate", lims=[1, np.inf]) except Exception as exc: raise exc self._samplerate = sr
def test_integer_like(self): freq = 440.0 scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000]) # not integer-like freq = 440.5 with pytest.raises(SPYValueError): scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000])
def test_within_limits(self): value = 440 scalar_parser(value, varname="value", ntype="int_like", lims=[10, 1000]) freq = 2 # outside bounds with pytest.raises(SPYValueError): scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000])
def validate_padding(pad_to_length, lenTrials): """ Simplified padding """ # supported padding options not_valid = False if not isinstance(pad_to_length, (Number, str, type(None))): not_valid = True elif isinstance(pad_to_length, str) and pad_to_length not in availablePaddingOpt: not_valid = True if isinstance(pad_to_length, bool): # bool is an int subclass, check for it separately... not_valid = True if not_valid: lgl = "`None`, 'nextpow2' or an integer like number" actual = f"{pad_to_length}" raise SPYValueError(legal=lgl, varname="pad_to_length", actual=actual) # here we check for equal lengths trials in case of no user specified absolute padding length # we do a rough 'maxlen' padding, nextpow2 will be overruled in this case if lenTrials.min() != lenTrials.max() and not isinstance( pad_to_length, Number): abs_pad = int(lenTrials.max()) msg = f"Unequal trial lengths present, automatic padding to {abs_pad} samples" SPYWarning(msg) # zero padding of ALL trials the same way if isinstance(pad_to_length, Number): scalar_parser(pad_to_length, varname='pad_to_length', ntype='int_like', lims=[lenTrials.max(), np.inf]) abs_pad = pad_to_length # or pad to optimal FFT lengths # (not possible for unequal lengths trials) elif pad_to_length == 'nextpow2': # after padding abs_pad = _nextpow2(int(lenTrials.min())) # no padding, equal lengths trials elif pad_to_length is None: abs_pad = int(lenTrials.max()) # `abs_pad` is now the (soon to be padded) signal length in samples return abs_pad
def _layout_subplot_panels(npanels, nrow=None, ncol=None, ndefault=5, maxpanels=50): """ Create space-optimal subplot grid given required number of panels Parameters ---------- npanels : int Number of required subplot panels in figure nrow : int or None Required number of panel rows. Note, if both `nrow` and `ncol` are not `None`, then ``nrow * ncol >= npanels`` has to be satisfied, otherwise a :class:`~syncopy.shared.errors.SPYValueError` is raised. ncol : int or None Required number of panel columns. Note, if both `nrow` and `ncol` are not `None`, then ``nrow * ncol >= npanels`` has to be satisfied, otherwise a :class:`~syncopy.shared.errors.SPYValueError` is raised. ndefault: int Default number of panel columns for grid construction (only relevant if both `nrow` and `ncol` are `None`). maxpanels : int Maximally allowed number of subplot panels for which a grid is constructed Returns ------- nrow : int Number of rows of constructed subplot panel grid nrow : int Number of columns of constructed subplot panel grid Notes ----- If both `nrow` and `ncol` are `None`, the constructed grid will have the dimension `N` x `ndefault`, where `N` is chosen "optimally", i.e., the smallest integer that satisfies ``ndefault * N >= npanels``. Note further, that this is an auxiliary method that is intended purely for internal use. Thus, error-checking is only performed on potentially user-provided inputs (`nrow` and `ncol`). See also -------- :func:`._setup_figure` : create and prepare figures for Syncopy visualizations Examples -------- Create grid of default dimensions to hold eight panels >>> _layout_subplot_panels(8, ndefault=5) (2, 5) Create a grid that must have 4 rows >>> _layout_subplot_panels(8, nrow=4) (4, 2) Create a grid that must have 8 columns >>> _layout_subplot_panels(8, ncol=8) (1, 8) """ # Abort if requested panel count is less than one or exceeds provided maximum try: scalar_parser(npanels, varname="npanels", ntype="int_like", lims=[1, np.inf]) except Exception as exc: raise exc if npanels > maxpanels: lgl = "a maximum of {} panels in total".format(maxpanels) raise SPYValueError(legal=lgl, actual=str(npanels), varname="npanels") # Row specifcation was provided, cols may or may not if nrow is not None: try: scalar_parser(nrow, varname="nrow", ntype="int_like", lims=[1, np.inf]) except Exception as exc: raise exc if ncol is None: ncol = np.ceil(npanels / nrow).astype(np.intp) # Column specifcation was provided, rows may or may not if ncol is not None: try: scalar_parser(ncol, varname="ncol", ntype="int_like", lims=[1, np.inf]) except Exception as exc: raise exc if nrow is None: nrow = np.ceil(npanels / ncol).astype(np.intp) # After the preparations above, this condition is *only* satisfied if both # `nrow` = `ncol` = `None` -> then use generic grid-layout if nrow is None: ncol = ndefault nrow = np.ceil(npanels / ncol).astype(np.intp) ncol = min(ncol, npanels) # Complain appropriately if requested no. of panels does not fit inside grid if nrow * ncol < npanels: lgl = "row- and column-specification of grid to fit all panels" act = "grid with {0} rows and {1} columns but {2} panels" raise SPYValueError(legal=lgl, actual=act.format(nrow, ncol, npanels), varname="nrow/ncol") # In case a grid was provided too big for the requested no. of panels (e.g., # 8 panels in an 4 x 3 grid -> would fit in 3 x 3), just warn, don't crash if nrow * ncol - npanels >= ncol: msg = "Grid dimension ({0} rows x {1} columns) larger than necessary " +\ "for {2} panels. " SPYWarning(msg.format(nrow, ncol, npanels)) return nrow, ncol
def definetrial(obj, trialdefinition=None, pre=None, post=None, start=None, trigger=None, stop=None, clip_edges=False): """(Re-)define trials of a Syncopy data object Data can be structured into trials based on timestamps of a start, trigger and end events:: start trigger stop |---- pre ----|--------|---------|--- post----| Parameters ---------- obj : Syncopy data object (:class:`BaseData`-like) trialdefinition : :class:`EventData` object or Mx3 array [start, stop, trigger_offset] sample indices for `M` trials pre : float offset time (s) before start event post : float offset time (s) after end event start : int event code (id) to be used for start of trial stop : int event code (id) to be used for end of trial trigger : event code (id) to be used center (t=0) of trial clip_edges : bool trim trials to actual data-boundaries. Returns ------- Syncopy data object (:class:`BaseData`-like)) Notes ----- :func:`definetrial` supports the following argument combinations: >>> # define M trials based on [start, end, offset] indices >>> definetrial(obj, trialdefinition=[M x 3] array) >>> # define trials based on event codes stored in <:class:`EventData` object> >>> definetrial(obj, trialdefinition=<EventData object>, pre=0, post=0, start=startCode, stop=stopCode, trigger=triggerCode) >>> # apply same trial definition as defined in <:class:`EventData` object> >>> definetrial(<AnalogData object>, trialdefinition=<EventData object w/sampleinfo/t0/trialinfo>) >>> # define whole recording as single trial >>> definetrial(obj, trialdefinition=None) """ # Start by vetting input object try: data_parser(obj, varname="obj") except Exception as exc: raise exc if obj.data is None: lgl = "non-empty Syncopy data object" act = "empty Syncopy data object" raise SPYValueError(legal=lgl, varname="obj", actual=act) # Check array/object holding trial specifications if trialdefinition is not None: if trialdefinition.__class__.__name__ == "EventData": try: data_parser(trialdefinition, varname="trialdefinition", writable=None, empty=False) except Exception as exc: raise exc evt = True else: try: array_parser(trialdefinition, varname="trialdefinition", dims=2) except Exception as exc: raise exc if any([ "ContinuousData" in str(base) for base in obj.__class__.__mro__ ]): scount = obj.data.shape[obj.dimord.index("time")] else: scount = np.inf try: array_parser(trialdefinition[:, :2], varname="sampleinfo", dims=(None, 2), hasnan=False, hasinf=False, ntype="int_like", lims=[0, scount]) except Exception as exc: raise exc trl = np.array(trialdefinition, dtype="float") ref = obj tgt = obj evt = False else: # Construct object-class-specific `trl` arrays treating data-set as single trial if any( ["ContinuousData" in str(base) for base in obj.__class__.__mro__]): trl = np.array([[0, obj.data.shape[obj.dimord.index("time")], 0]]) else: sidx = obj.dimord.index("sample") trl = np.array([[ np.nanmin(obj.data[:, sidx]), np.nanmax(obj.data[:, sidx]), 0 ]]) ref = obj tgt = obj evt = False # AnalogData + EventData w/sampleinfo if obj.__class__.__name__ == "AnalogData" and evt and trialdefinition.sampleinfo is not None: if obj.samplerate is None or trialdefinition.samplerate is None: lgl = "non-`None` value - make sure `samplerate` is set before defining trials" act = "None" raise SPYValueError(legal=lgl, varname="samplerate", actual=act) ref = trialdefinition tgt = obj trl = np.array(ref.trialinfo) t0 = np.array(ref._t0).reshape((ref._t0.size, 1)) trl = np.hstack([ref.sampleinfo, t0, trl]) trl = np.round((trl / ref.samplerate) * tgt.samplerate).astype(int) # AnalogData + EventData w/keywords or just EventData w/keywords if any([kw is not None for kw in [pre, post, start, trigger, stop]]): # Make sure we actually have valid data objects to work with if obj.__class__.__name__ == "EventData" and evt is False: ref = obj tgt = obj elif obj.__class__.__name__ == "AnalogData" and evt is True: ref = trialdefinition tgt = obj else: lgl = "AnalogData with associated EventData object" act = "{} and {}".format(obj.__class__.__name__, trialdefinition.__class__.__name__) raise SPYValueError(legal=lgl, actual=act, varname="input") # The only case we might actually need it: ensure `clip_edges` is valid if not isinstance(clip_edges, bool): raise SPYTypeError(clip_edges, varname="clip_edges", expected="Boolean") # Ensure that objects have their sampling-rates set, otherwise break if ref.samplerate is None or tgt.samplerate is None: lgl = "non-`None` value - make sure `samplerate` is set before defining trials" act = "None" raise SPYValueError(legal=lgl, varname="samplerate", actual=act) # Get input dimensions szin = [] for var in [pre, post, start, trigger, stop]: if isinstance(var, (np.ndarray, list)): szin.append(len(var)) if np.unique(szin).size > 1: lgl = "all trial-related arrays to have the same length" act = "arrays with sizes {}".format( str(np.unique(szin)).replace("[", "").replace("]", "")) raise SPYValueError(legal=lgl, varname="trial-keywords", actual=act) if len(szin): ntrials = szin[0] ninc = 1 else: ntrials = 1 ninc = 0 # If both `pre` and `start` or `post` and `stop` are `None`, abort if (pre is None and start is None) or (post is None and stop is None): lgl = "`pre` or `start` and `post` or `stop` to be not `None`" act = "both `pre` and `start` and/or `post` and `stop` are simultaneously `None`" raise SPYValueError(legal=lgl, actual=act) if (trigger is None) and (pre is not None or post is not None): lgl = "non-None `trigger` with `pre`/`post` timing information" act = "`trigger` = `None`" raise SPYValueError(legal=lgl, actual=act) # If provided, ensure keywords make sense, otherwise allocate defaults kwrds = {} vdict = { "pre": { "var": pre, "hasnan": False, "ntype": None, "fillvalue": 0 }, "post": { "var": post, "hasnan": False, "ntype": None, "fillvalue": 0 }, "start": { "var": start, "hasnan": None, "ntype": "int_like", "fillvalue": np.nan }, "trigger": { "var": trigger, "hasnan": None, "ntype": "int_like", "fillvalue": np.nan }, "stop": { "var": stop, "hasnan": None, "ntype": "int_like", "fillvalue": np.nan } } for vname, opts in vdict.items(): if opts["var"] is not None: if isinstance(opts["var"], numbers.Number): try: scalar_parser(opts["var"], varname=vname, ntype=opts["ntype"], lims=[-np.inf, np.inf]) except Exception as exc: raise exc opts["var"] = np.full((ntrials, ), opts["var"]) else: try: array_parser(opts["var"], varname=vname, hasinf=False, hasnan=opts["hasnan"], ntype=opts["ntype"], dims=(ntrials, )) except Exception as exc: raise exc kwrds[vname] = opts["var"] else: kwrds[vname] = np.full((ntrials, ), opts["fillvalue"]) # Prepare `trl` and convert event-codes + sample-numbers to lists trl = [] evtid = list(ref.data[:, ref.dimord.index("eventid")]) evtsp = list(ref.data[:, ref.dimord.index("sample")]) nevents = len(evtid) searching = True trialno = 0 cnt = 0 act = "" # Do this line-by-line: halt on error (if event-id is not found in `ref`) while searching: # Allocate begin and end of trial begin = None end = None t0 = 0 idxl = [] # First, try to assign `start`, then `t0` if not np.isnan(kwrds["start"][trialno]): try: sidx = evtid.index(kwrds["start"][trialno]) except: act = str(kwrds["start"][trialno]) vname = "start" break begin = evtsp[sidx] / ref.samplerate evtid[sidx] = -np.pi idxl.append(sidx) if not np.isnan(kwrds["trigger"][trialno]): try: idx = evtid.index(kwrds["trigger"][trialno]) except: act = str(kwrds["trigger"][trialno]) vname = "trigger" break t0 = evtsp[idx] / ref.samplerate evtid[idx] = -np.pi idxl.append(idx) # Trial-begin is either `trigger - pre` or `start - pre` if begin is not None: begin -= kwrds["pre"][trialno] else: begin = t0 - kwrds["pre"][trialno] # Try to assign `stop`, if we got nothing, use `t0 + post` if not np.isnan(kwrds["stop"][trialno]): evtid[:sidx] = [np.pi] * sidx try: idx = evtid.index(kwrds["stop"][trialno]) except: act = str(kwrds["stop"][trialno]) vname = "stop" break end = evtsp[idx] / ref.samplerate + kwrds["post"][trialno] evtid[idx] = -np.pi idxl.append(idx) else: end = t0 + kwrds["post"][trialno] # Off-set `t0` t0 -= begin # Make sure current trial setup makes (some) sense if begin >= end: lgl = "non-overlapping trial begin-/end-samples" act = "trial-begin at {}, trial-end at {}".format( str(begin), str(end)) raise SPYValueError(legal=lgl, actual=act) # Finally, write line of `trl` trl.append([begin, end, t0]) # Update counters and end this mess when we're done trialno += ninc cnt += 1 evtsp = evtsp[max(idxl, default=-1) + 1:] evtid = evtid[max(idxl, default=-1) + 1:] if trialno == ntrials or cnt == nevents: searching = False # Abort if the above loop ran into troubles if len(trl) < ntrials: if len(act) > 0: raise SPYValueError(legal="existing event-id", varname=vname, actual=act) # Make `trl` a NumPy array trl = np.round(np.array(trl) * tgt.samplerate).astype(int) # If appropriate, clip `trl` to AnalogData object's bounds (if wanted) if clip_edges and evt: msk = trl[:, 0] < 0 trl[msk, 0] = 0 dmax = tgt.data.shape[tgt.dimord.index("time")] msk = trl[:, 1] > dmax trl[msk, 1] = dmax if np.any(trl[:, 0] >= trl[:, 1]): lgl = "non-overlapping trials" act = "some trials are overlapping after clipping to AnalogData object range" raise SPYValueError(legal=lgl, actual=act) # The triplet `sampleinfo`, `t0` and `trialinfo` works identically for # all data genres if trl.shape[1] < 3: raise SPYValueError( "array of shape (no. of trials, 3+)", varname="trialdefinition", actual="shape = {shp:s}".format(shp=str(trl.shape))) # Finally: assign `sampleinfo`, `t0` and `trialinfo` (and potentially `trialid`) tgt._trialdefinition = trl # In the discrete case, we have some additinal work to do if any(["DiscreteData" in str(base) for base in tgt.__class__.__mro__]): # Compute trial-IDs by matching data samples with provided trial-bounds samples = tgt.data[:, tgt.dimord.index("sample")] starts = tgt.sampleinfo[:, 0] ends = tgt.sampleinfo[:, 1] startids = np.searchsorted(starts, samples, side="right") endids = np.searchsorted(ends, samples, side="left") mask = startids == endids startids -= 1 # Samples not belonging into any trial get a trial-ID of -1 startids[mask] = int(startids.min() <= 0) * (-1) tgt.trialid = startids # Write log entry if ref == tgt: ref.log = "updated trial-definition with [" \ + " x ".join([str(numel) for numel in trl.shape]) \ + "] element array" else: ref_log = ref._log.replace("\n\n", "\n\t") tgt.log = "trial-definition extracted from EventData object: " tgt._log += ref_log tgt.cfg = { "method": sys._getframe().f_code.co_name, "EventData object": ref.cfg } ref.log = "updated trial-defnition of {} object".format( tgt.__class__.__name__) return
def validate_taper(taper, tapsmofrq, nTaper, keeptapers, foimax, samplerate, nSamples, output): """ General taper validation and Slepian/dpss input sanitization. The default is to max out `nTaper` to achieve the desired frequency smoothing bandwidth. For details about the Slepion settings see "The Effective Bandwidth of a Multitaper Spectral Estimator, A. T. Walden, E. J. McCoy and D. B. Percival" Parameters ---------- taper : str Windowing function, one of :data:`~syncopy.shared.const_def.availableTapers` tapsmofrq : float or None Taper smoothing bandwidth for `taper='dpss'` nTaper : int_like or None Number of tapers to use for multi-tapering (not recommended) Other Parameters ---------------- keeptapers : bool foimax : float Maximum frequency for the analysis samplerate : float the samplerate in Hz nSamples : int Number of samples output : str, one of {'abs', 'pow', 'fourier'} Fourier transformation output type Returns ------- dpss_opt : dict For multi-tapering (`taper='dpss'`) contains the parameters `NW` and `Kmax` for `scipy.signal.windows.dpss`. For all other tapers this is an empty dictionary. """ # See if taper choice is supported if taper not in availableTapers: lgl = "'" + "or '".join(opt + "' " for opt in availableTapers) raise SPYValueError(legal=lgl, varname="taper", actual=taper) # Warn user about DPSS only settings if taper != "dpss": if tapsmofrq is not None: msg = "`tapsmofrq` is only used if `taper` is `dpss`!" SPYWarning(msg) if nTaper is not None: msg = "`nTaper` is only used if `taper` is `dpss`!" SPYWarning(msg) if keeptapers: msg = "`keeptapers` is only used if `taper` is `dpss`!" SPYWarning(msg) # empty dpss_opt, only Slepians have options return {} # direct mtm estimate (averaging) only valid for spectral power if taper == "dpss" and not keeptapers and output != "pow": lgl = "'pow', the only valid option for taper averaging" raise SPYValueError(legal=lgl, varname="output", actual=output) # Set/get `tapsmofrq` if we're working w/Slepian tapers elif taper == "dpss": # --- minimal smoothing bandwidth --- # --- such that Kmax/nTaper is at least 1 minBw = 2 * samplerate / nSamples # ----------------------------------- # user set tapsmofrq directly if tapsmofrq is not None: try: scalar_parser(tapsmofrq, varname="tapsmofrq", lims=[0, np.inf]) except Exception as exc: raise exc if tapsmofrq < minBw: msg = f'Setting tapsmofrq to the minimal attainable bandwidth of {minBw:.2f}Hz' SPYInfo(msg) tapsmofrq = minBw # we now enforce a user submitted smoothing bw else: lgl = "smoothing bandwidth in Hz, typical values are in the range 1-10Hz" raise SPYValueError(legal=lgl, varname="tapsmofrq", actual=tapsmofrq) # Try to derive "sane" settings by using 3/4 octave # smoothing of highest `foi` # following Hill et al. "Oscillatory Synchronization in Large-Scale # Cortical Networks Predicts Perception", Neuron, 2011 # FIX ME: This "sane setting" seems quite excessive (huuuge bwidths) # tapsmofrq = (foimax * 2**(3 / 4 / 2) - foimax * 2**(-3 / 4 / 2)) / 2 # msg = f'Automatic setting of `tapsmofrq` to {tapsmofrq:.2f}' # SPYInfo(msg) # -------------------------------------------- # set parameters for scipy.signal.windows.dpss NW = tapsmofrq * nSamples / (2 * samplerate) # from the minBw setting NW always is at least 1 Kmax = int(2 * NW - 1) # optimal number of tapers # -------------------------------------------- # the recommended way: # set nTaper automatically to achieve exact effective smoothing bandwidth if nTaper is None: msg = f'Using {Kmax} taper(s) for multi-tapering' SPYInfo(msg) dpss_opt = {'NW': NW, 'Kmax': Kmax} return dpss_opt elif nTaper is not None: try: scalar_parser(nTaper, varname="nTaper", ntype="int_like", lims=[1, np.inf]) except Exception as exc: raise exc if nTaper != Kmax: msg = f''' Manually setting the number of tapers is not recommended and may (strongly) distort the effective smoothing bandwidth!\n The optimal number of tapers is {Kmax}, you have chosen to use {nTaper}. ''' SPYWarning(msg) dpss_opt = {'NW': NW, 'Kmax': nTaper} return dpss_opt
def freqanalysis(data, method='mtmfft', output='fourier', keeptrials=True, foi=None, foilim=None, pad_to_length=None, polyremoval=None, taper="hann", tapsmofrq=None, nTaper=None, keeptapers=False, toi="all", t_ftimwin=None, wavelet="Morlet", width=6, order=None, order_max=None, order_min=1, c_1=3, adaptive=False, out=None, **kwargs): """ Perform (time-)frequency analysis of Syncopy :class:`~syncopy.AnalogData` objects **Usage Summary** Options available in all analysis methods: * **output** : one of :data:`~syncopy.specest.const_def.availableOutputs`; return power spectra, complex Fourier spectra or absolute values. * **foi**/**foilim** : frequencies of interest; either array of frequencies or frequency window (not both) * **keeptrials** : return individual trials or grand average * **polyremoval** : de-trending method to use (0 = mean, 1 = linear or `None`) List of available analysis methods and respective distinct options: "mtmfft" : (Multi-)tapered Fourier transform Perform frequency analysis on time-series trial data using either a single taper window (Hanning) or many tapers based on the discrete prolate spheroidal sequence (DPSS) that maximize energy concentration in the main lobe. * **taper** : one of :data:`~syncopy.shared.const_def.availableTapers` * **tapsmofrq** : spectral smoothing box for slepian tapers (in Hz) * **nTaper** : number of orthogonal tapers for slepian tapers * **keeptapers** : return individual tapers or average * **pad_to_length**: either pad to an absolute length or set to `'nextpow2'` "mtmconvol" : (Multi-)tapered sliding window Fourier transform Perform time-frequency analysis on time-series trial data based on a sliding window short-time Fourier transform using either a single Hanning taper or multiple DPSS tapers. * **taper** : one of :data:`~syncopy.specest.const_def.availableTapers` * **tapsmofrq** : spectral smoothing box for slepian tapers (in Hz) * **nTaper** : number of orthogonal tapers for slepian tapers * **keeptapers** : return individual tapers or average * **toi** : time-points of interest; can be either an array representing analysis window centroids (in sec), a scalar between 0 and 1 encoding the percentage of overlap between adjacent windows or "all" to center a window on every sample in the data. * **t_ftimwin** : sliding window length (in sec) "wavelet" : (Continuous non-orthogonal) wavelet transform Perform time-frequency analysis on time-series trial data using a non-orthogonal continuous wavelet transform. * **wavelet** : one of :data:`~syncopy.specest.const_def.availableWavelets` * **toi** : time-points of interest; can be either an array representing time points (in sec) or "all"(pre-trimming and subsampling of results) * **width** : Nondimensional frequency constant of Morlet wavelet function (>= 6) * **order** : Order of Paul wavelet function (>= 4) or derivative order of real-valued DOG wavelets (2 = mexican hat) "superlet" : Superlet transform Perform time-frequency analysis on time-series trial data using the super-resolution superlet transform (SLT) from [Moca2021]_. * **order_max** : Maximal order of the superlet * **order_min** : Minimal order of the superlet * **c_1** : Number of cycles of the base Morlet wavelet * **adaptive** : If set to `True` perform fractional adaptive SLT, otherwise perform multiplicative SLT **Full documentation below** Parameters ---------- data : `~syncopy.AnalogData` A non-empty Syncopy :class:`~syncopy.datatype.AnalogData` object method : str Spectral estimation method, one of :data:`~syncopy.specest.const_def.availableMethods` (see below). output : str Output of spectral estimation. One of :data:`~syncopy.specest.const_def.availableOutputs` (see below); use `'pow'` for power spectrum (:obj:`numpy.float32`), `'fourier'` for complex Fourier coefficients (:obj:`numpy.complex64`) or `'abs'` for absolute values (:obj:`numpy.float32`). keeptrials : bool If `True` spectral estimates of individual trials are returned, otherwise results are averaged across trials. foi : array-like or None Frequencies of interest (Hz) for output. If desired frequencies cannot be matched exactly, the closest possible frequencies are used. If `foi` is `None` or ``foi = "all"``, all attainable frequencies (i.e., zero to Nyquist / 2) are selected. foilim : array-like (floats [fmin, fmax]) or None or "all" Frequency-window ``[fmin, fmax]`` (in Hz) of interest. Window specifications must be sorted (e.g., ``[90, 70]`` is invalid) and not NaN but may be unbounded (e.g., ``[-np.inf, 60.5]`` is valid). Edges `fmin` and `fmax` are included in the selection. If `foilim` is `None` or ``foilim = "all"``, all frequencies are selected. pad_to_length : int, None or 'nextpow2' Padding of the input data, if set to a number pads all trials to this absolute length. For instance ``pad_to_length = 2000`` pads all trials to an absolute length of 2000 samples, if and only if the longest trial contains at maximum 2000 samples. Alternatively if all trials have the same initial lengths setting `pad_to_length='nextpow2'` pads all trials to the next power of two. If `None` and trials have unequal lengths all trials are padded to match the longest trial. polyremoval : int or None Order of polynomial used for de-trending data in the time domain prior to spectral analysis. A value of 0 corresponds to subtracting the mean ("de-meaning"), ``polyremoval = 1`` removes linear trends (subtracting the least squares fit of a linear polynomial). If `polyremoval` is `None`, no de-trending is performed. Note that for spectral estimation de-meaning is very advisable and hence also the default. taper : str Only valid if `method` is `'mtmfft'` or `'mtmconvol'`. Windowing function, one of :data:`~syncopy.specest.const_def.availableTapers` (see below). tapsmofrq : float Only valid if `method` is `'mtmfft'` or `'mtmconvol'` and `taper` is `'dpss'`. The amount of spectral smoothing through multi-tapering (Hz). Note that smoothing frequency specifications are one-sided, i.e., 4 Hz smoothing means plus-minus 4 Hz, i.e., a 8 Hz smoothing box. nTaper : int or None Only valid if `method` is `'mtmfft'` or `'mtmconvol'` and `taper='dpss'`. Number of orthogonal tapers to use. It is not recommended to set the number of tapers manually! Leave at `None` for the optimal number to be set automatically. keeptapers : bool Only valid if `method` is `'mtmfft'` or `'mtmconvol'`. If `True`, return spectral estimates for each taper. Otherwise power spectrum is averaged across tapers, if and only if `output` is `pow`. toi : float or array-like or "all" **Mandatory input** for time-frequency analysis methods (`method` is either `"mtmconvol"` or `"wavelet"` or `"superlet"`). If `toi` is scalar, it must be a value between 0 and 1 indicating the percentage of overlap between time-windows specified by `t_ftimwin` (only valid if `method` is `'mtmconvol'`). If `toi` is an array it explicitly selects the centroids of analysis windows (in seconds), if `toi` is `"all"`, analysis windows are centered on all samples in the data for `method="mtmconvol"`. For wavelet based methods (`"wavelet"` or `"superlet"`) toi needs to be either an equidistant array of time points or "all". t_ftimwin : positive float Only valid if `method` is `'mtmconvol'`. Sliding window length (in seconds). wavelet : str Only valid if `method` is `'wavelet'`. Wavelet function to use, one of :data:`~syncopy.specest.const_def.availableWavelets` (see below). width : positive float Only valid if `method` is `'wavelet'` and `wavelet` is `'Morlet'`. Nondimensional frequency constant of Morlet wavelet function. This number should be >= 6, which corresponds to 6 cycles within the analysis window to ensure sufficient spectral sampling. order : positive int Only valid if `method` is `'wavelet'` and `wavelet` is `'Paul'` or `'DOG'`. Order of the wavelet function. If `wavelet` is `'Paul'`, `order` should be chosen >= 4 to ensure that the analysis window contains at least a single oscillation. At an order of 40, the Paul wavelet exhibits about the same number of cycles as the Morlet wavelet with a `width` of 6. All other supported wavelets functions are *real-valued* derivatives of Gaussians (DOGs). Hence, if `wavelet` is `'DOG'`, `order` represents the derivative order. The special case of a second order DOG yields a function known as "Mexican Hat", "Marr" or "Ricker" wavelet, which can be selected alternatively by setting `wavelet` to `'Mexican_hat'`, `'Marr'` or `'Ricker'`. **Note**: A real-valued wavelet function encodes *only* information about peaks and discontinuities in the signal and does *not* provide any information about amplitude or phase. order_max : int Only valid if `method` is `'superlet'`. Maximal order of the superlet set. Controls the maximum number of cycles within a SL together with the `c_1` parameter: c_max = c_1 * order_max order_min : int Only valid if `method` is `'superlet'`. Minimal order of the superlet set. Controls the minimal number of cycles within a SL together with the `c_1` parameter: c_min = c_1 * order_min Note that for admissability reasons c_min should be at least 3! c_1 : int Only valid if `method` is `'superlet'`. Number of cycles of the base Morlet wavelet. If set to lower than 3 increase `order_min` as to never have less than 3 cycles in a wavelet! adaptive : bool Only valid if `method` is `'superlet'`. Wether to perform multiplicative SLT or fractional adaptive SLT. If set to True, the order of the wavelet set will increase linearly with the frequencies of interest from `order_min` to `order_max`. If set to False the same SL will be used for all frequencies. out : None or :class:`SpectralData` object None if a new :class:`SpectralData` object is to be created, or an empty :class:`SpectralData` object Returns ------- spec : :class:`~syncopy.SpectralData` (Time-)frequency spectrum of input data Notes ----- .. [Moca2021] Moca, Vasile V., et al. "Time-frequency super-resolution with superlets." Nature communications 12.1 (2021): 1-18. **Options** .. autodata:: syncopy.specest.const_def.availableMethods .. autodata:: syncopy.specest.const_def.availableOutputs .. autodata:: syncopy.specest.const_def.availableTapers .. autodata:: syncopy.specest.const_def.availableWavelets Examples -------- Coming soon... See also -------- syncopy.specest.mtmfft.mtmfft : (multi-)tapered Fourier transform of multi-channel time series data syncopy.specest.mtmconvol.mtmconvol : time-frequency analysis of multi-channel time series data with a sliding window FFT syncopy.specest.wavelet.wavelet : time-frequency analysis of multi-channel time series data using a wavelet transform numpy.fft.fft : NumPy's reference FFT implementation scipy.signal.stft : SciPy's Short Time Fourier Transform """ # Make sure our one mandatory input object can be processed try: data_parser(data, varname="data", dataclass="AnalogData", writable=None, empty=False) except Exception as exc: raise exc timeAxis = data.dimord.index("time") # Get everything of interest in local namespace defaults = get_defaults(freqanalysis) lcls = locals() # check for ineffective additional kwargs check_passed_kwargs(lcls, defaults, frontend_name="freqanalysis") # Ensure a valid computational method was selected if method not in availableMethods: lgl = "'" + "or '".join(opt + "' " for opt in availableMethods) raise SPYValueError(legal=lgl, varname="method", actual=method) # Ensure a valid output format was selected if output not in spectralConversions.keys(): lgl = "'" + "or '".join(opt + "' " for opt in spectralConversions.keys()) raise SPYValueError(legal=lgl, varname="output", actual=output) # Parse all Boolean keyword arguments for vname in ["keeptrials", "keeptapers"]: if not isinstance(lcls[vname], bool): raise SPYTypeError(lcls[vname], varname=vname, expected="Bool") # If only a subset of `data` is to be processed, make some necessary adjustments # of the sampleinfo and trial lengths if data._selection is not None: sinfo = data._selection.trialdefinition[:, :2] trialList = data._selection.trials else: trialList = list(range(len(data.trials))) sinfo = data.sampleinfo lenTrials = np.diff(sinfo).squeeze() if not lenTrials.shape: lenTrials = lenTrials[None] numTrials = len(trialList) # check polyremoval if polyremoval is not None: scalar_parser(polyremoval, varname="polyremoval", ntype="int_like", lims=[0, 1]) # --- Padding --- # Sliding window FFT does not support "fancy" padding if method == "mtmconvol" and isinstance(pad_to_length, str): msg = "method 'mtmconvol' only supports in-place padding for windows " +\ "exceeding trial boundaries. Your choice of `pad_to_length = '{}'` will be ignored. " SPYWarning(msg.format(pad_to_length)) if method == 'mtmfft': # the actual number of samples in case of later padding minSampleNum = validate_padding(pad_to_length, lenTrials) else: minSampleNum = lenTrials.min() # Compute length (in samples) of shortest trial minTrialLength = minSampleNum / data.samplerate # Shortcut to data sampling interval dt = 1 / data.samplerate foi, foilim = validate_foi(foi, foilim, data.samplerate) # see also https://docs.obspy.org/_modules/obspy/signal/detrend.html#polynomial if polyremoval is not None: try: scalar_parser(polyremoval, varname="polyremoval", lims=[0, 1], ntype="int_like") except Exception as exc: raise exc # Prepare keyword dict for logging (use `lcls` to get actually provided # keyword values, not defaults set above) log_dct = {"method": method, "output": output, "keeptapers": keeptapers, "keeptrials": keeptrials, "polyremoval": polyremoval, "pad_to_length": pad_to_length} # -------------------------------- # 1st: Check time-frequency inputs # to prepare/sanitize `toi` # -------------------------------- if method in ["mtmconvol", "wavelet", "superlet"]: # Get start/end timing info respecting potential in-place selection if toi is None: raise SPYTypeError(toi, varname="toi", expected="scalar or array-like or 'all'") if data._selection is not None: tStart = data._selection.trialdefinition[:, 2] / data.samplerate else: tStart = data._t0 / data.samplerate tEnd = tStart + lenTrials / data.samplerate # for these methods only 'all' or an equidistant array # of time points (sub-sampling, trimming) are valid if method in ["wavelet", "superlet"]: valid = True if isinstance(toi, Number): valid = False elif isinstance(toi, str): if toi != "all": valid = False else: # take everything preSelect = [slice(None)] * numTrials postSelect = [slice(None)] * numTrials elif not iter(toi): valid = False # this is the sequence type - can only be an interval! else: try: array_parser(toi, varname="toi", hasinf=False, hasnan=False, lims=[tStart.min(), tEnd.max()], dims=(None,)) except Exception as exc: raise exc toi = np.array(toi) # check for equidistancy if not np.allclose(np.diff(toi, 2), np.zeros(len(toi) - 2)): valid = False # trim (preSelect) and subsample output (postSelect) else: preSelect = [] postSelect = [] # get sample intervals and relative indices from toi for tk in range(numTrials): start = int(data.samplerate * (toi[0] - tStart[tk])) stop = int(data.samplerate * (toi[-1] - tStart[tk]) + 1) preSelect.append(slice(max(0, start), max(stop, stop - start))) smpIdx = np.minimum(lenTrials[tk] - 1, data.samplerate * (toi - tStart[tk]) - start) postSelect.append(smpIdx.astype(np.intp)) # get out if sth wasn't right if not valid: lgl = "array of equidistant time-points or 'all' for wavelet based methods" raise SPYValueError(legal=lgl, varname="toi", actual=toi) # Update `log_dct` w/method-specific options (use `lcls` to get actually # provided keyword values, not defaults set in here) log_dct["toi"] = lcls["toi"] # -------------------------------------------- # Check options specific to mtm*-methods # (particularly tapers and foi/freqs alignment) # -------------------------------------------- if "mtm" in method: if method == "mtmconvol": # get the sliding window size try: scalar_parser(t_ftimwin, varname="t_ftimwin", lims=[dt, minTrialLength]) except Exception as exc: SPYInfo("Please specify 't_ftimwin' parameter.. exiting!") raise exc # this is the effective sliding window FFT sample size minSampleNum = int(t_ftimwin * data.samplerate) # Construct array of maximally attainable frequencies freqs = np.fft.rfftfreq(minSampleNum, dt) # Match desired frequencies as close as possible to # actually attainable freqs # these are the frequencies attached to the SpectralData by the CR! if foi is not None: foi, _ = best_match(freqs, foi, squash_duplicates=True) elif foilim is not None: foi, _ = best_match(freqs, foilim, span=True, squash_duplicates=True) else: msg = (f"Automatic FFT frequency selection from {freqs[0]:.1f}Hz to " f"{freqs[-1]:.1f}Hz") SPYInfo(msg) foi = freqs log_dct["foi"] = foi # Abort if desired frequency selection is empty if foi.size == 0: lgl = "non-empty frequency specification" act = "empty frequency selection" raise SPYValueError(legal=lgl, varname="foi/foilim", actual=act) # sanitize taper selection and retrieve dpss settings taper_opt = validate_taper(taper, tapsmofrq, nTaper, keeptapers, foimax=foi.max(), samplerate=data.samplerate, nSamples=minSampleNum, output=output) # Update `log_dct` w/method-specific options log_dct["taper"] = taper # only dpss returns non-empty taper_opt dict if taper_opt: log_dct["nTaper"] = taper_opt["Kmax"] log_dct["tapsmofrq"] = tapsmofrq # ------------------------------------------------------- # Now, prepare explicit compute-classes for chosen method # ------------------------------------------------------- if method == "mtmfft": check_effective_parameters(MultiTaperFFT, defaults, lcls) # method specific parameters method_kwargs = { 'samplerate': data.samplerate, 'taper': taper, 'taper_opt': taper_opt, 'nSamples': minSampleNum } # Set up compute-class specestMethod = MultiTaperFFT( foi=foi, timeAxis=timeAxis, keeptapers=keeptapers, polyremoval=polyremoval, output_fmt=output, method_kwargs=method_kwargs) elif method == "mtmconvol": check_effective_parameters(MultiTaperFFTConvol, defaults, lcls) # Process `toi` for sliding window multi taper fft, # we have to account for three scenarios: (1) center sliding # windows on all samples in (selected) trials (2) `toi` was provided as # percentage indicating the degree of overlap b/w time-windows and (3) a set # of discrete time points was provided. These three cases are encoded in # `overlap, i.e., ``overlap > 1` => all, `0 < overlap < 1` => percentage, # `overlap < 0` => discrete `toi` # overlap = None if isinstance(toi, str): if toi != "all": lgl = "`toi = 'all'` to center analysis windows on all time-points" raise SPYValueError(legal=lgl, varname="toi", actual=toi) equidistant = True overlap = np.inf elif isinstance(toi, Number): try: scalar_parser(toi, varname="toi", lims=[0, 1]) except Exception as exc: raise exc overlap = toi equidistant = True # this captures all other cases, e.i. toi is of sequence type else: overlap = -1 try: array_parser(toi, varname="toi", hasinf=False, hasnan=False, lims=[tStart.min(), tEnd.max()], dims=(None,)) except Exception as exc: raise exc toi = np.array(toi) tSteps = np.diff(toi) if (tSteps < 0).any(): lgl = "ordered list/array of time-points" act = "unsorted list/array" raise SPYValueError(legal=lgl, varname="toi", actual=act) # Account for round-off errors: if toi spacing is almost at sample interval # manually correct it if np.isclose(tSteps.min(), dt): tSteps[np.isclose(tSteps, dt)] = dt if tSteps.min() < dt: msg = f"`toi` selection too fine, max. time resolution is {dt}s" SPYWarning(msg) # This is imho a bug in NumPy - even `arange` and `linspace` may produce # arrays that are numerically not exactly equidistant - `unique` will # show several entries here - use `allclose` to identify "even" spacings equidistant = np.allclose(tSteps, [tSteps[0]] * tSteps.size) # If `toi` was 'all' or a percentage, use entire time interval of (selected) # trials and check if those trials have *approximately* equal length if toi is None: if not np.allclose(lenTrials, [minSampleNum] * lenTrials.size): msg = "processing trials of different lengths (min = {}; max = {} samples)" +\ " with `toi = 'all'`" SPYWarning(msg.format(int(minSampleNum), int(lenTrials.max()))) # number of samples per window nperseg = int(t_ftimwin * data.samplerate) halfWin = int(nperseg / 2) postSelect = slice(None) # select all is the default if 0 <= overlap <= 1: # `toi` is percentage noverlap = min(nperseg - 1, int(overlap * nperseg)) # windows get shifted exactly 1 sample # to get a spectral estimate at each sample else: noverlap = nperseg - 1 # `toi` is array if overlap < 0: # Compute necessary padding at begin/end of trials to fit sliding windows offStart = ((toi[0] - tStart) * data.samplerate).astype(np.intp) padBegin = halfWin - offStart padBegin = ((padBegin > 0) * padBegin).astype(np.intp) offEnd = ((tEnd - toi[-1]) * data.samplerate).astype(np.intp) padEnd = halfWin - offEnd padEnd = ((padEnd > 0) * padEnd).astype(np.intp) # Compute sample-indices (one slice/list per trial) from time-selections soi = [] if equidistant: # soi just trims the input data to the [toi[0], toi[-1]] interval # postSelect then subsamples the spectral esimate to the user given toi postSelect = [] for tk in range(numTrials): start = max(0, int(round(data.samplerate * (toi[0] - tStart[tk]) - halfWin))) stop = int(round(data.samplerate * (toi[-1] - tStart[tk]) + halfWin + 1)) soi.append(slice(start, max(stop, stop - start))) # chosen toi subsampling interval in sample units, min. is 1; # compute `delta_idx` s.t. stop - start / delta_idx == toi.size delta_idx = int(round((soi[0].stop - soi[0].start) / toi.size)) delta_idx = delta_idx if delta_idx > 1 else 1 postSelect = slice(None, None, delta_idx) else: for tk in range(numTrials): starts = (data.samplerate * (toi - tStart[tk]) - halfWin).astype(np.intp) starts += padBegin[tk] stops = (data.samplerate * (toi - tStart[tk]) + halfWin + 1).astype(np.intp) stops += padBegin[tk] stops = np.maximum(stops, stops - starts, dtype=np.intp) soi.append([slice(start, stop) for start, stop in zip(starts, stops)]) # postSelect here remains slice(None), as resulting spectrum # has exactly one entry for each soi # `toi` is percentage or "all" else: soi = [slice(None)] * numTrials # Collect keyword args for `mtmconvol` in dictionary method_kwargs = {"samplerate": data.samplerate, "nperseg": nperseg, "noverlap": noverlap, "taper" : taper, "taper_opt" : taper_opt} # Set up compute-class specestMethod = MultiTaperFFTConvol( soi, postSelect, equidistant=equidistant, toi=toi, foi=foi, timeAxis=timeAxis, keeptapers=keeptapers, polyremoval=polyremoval, output_fmt=output, method_kwargs=method_kwargs) elif method == "wavelet": check_effective_parameters(WaveletTransform, defaults, lcls) # Check wavelet selection if wavelet not in availableWavelets: lgl = "'" + "or '".join(opt + "' " for opt in availableWavelets) raise SPYValueError(legal=lgl, varname="wavelet", actual=wavelet) if wavelet not in ["Morlet", "Paul"]: msg = "the chosen wavelet '{}' is real-valued and does not provide " +\ "any information about amplitude or phase of the data. This wavelet function " +\ "may be used to isolate peaks or discontinuities in the signal. " SPYWarning(msg.format(wavelet)) # Check for consistency of `width`, `order` and `wavelet` if wavelet == "Morlet": try: scalar_parser(width, varname="width", lims=[1, np.inf]) except Exception as exc: raise exc wfun = getattr(spywave, wavelet)(w0=width) else: if width != lcls["width"]: msg = "option `width` has no effect for wavelet '{}'" SPYWarning(msg.format(wavelet)) if wavelet == "Paul": try: scalar_parser(order, varname="order", lims=[4, np.inf], ntype="int_like") except Exception as exc: raise exc wfun = getattr(spywave, wavelet)(m=order) elif wavelet == "DOG": try: scalar_parser(order, varname="order", lims=[1, np.inf], ntype="int_like") except Exception as exc: raise exc wfun = getattr(spywave, wavelet)(m=order) else: if order is not None: msg = "option `order` has no effect for wavelet '{}'" SPYWarning(msg.format(wavelet)) wfun = getattr(spywave, wavelet)() # automatic frequency selection if foi is None and foilim is None: scales = get_optimal_wavelet_scales( wfun.scale_from_period, # all availableWavelets sport one! int(minTrialLength * data.samplerate), dt) foi = 1 / wfun.fourier_period(scales) msg = (f"Setting frequencies of interest to {foi[0]:.1f}-" f"{foi[-1]:.1f}Hz") SPYInfo(msg) else: if foilim is not None: foi = np.arange(foilim[0], foilim[1] + 1, dtype=float) # 0 frequency is not valid foi[foi < 0.01] = 0.01 scales = wfun.scale_from_period(1 / foi) # Update `log_dct` w/method-specific options (use `lcls` to get actually # provided keyword values, not defaults set in here) log_dct["foi"] = foi log_dct["wavelet"] = lcls["wavelet"] log_dct["width"] = lcls["width"] log_dct["order"] = lcls["order"] # method specific parameters method_kwargs = { 'samplerate' : data.samplerate, 'scales' : scales, 'wavelet' : wfun } # Set up compute-class specestMethod = WaveletTransform( preSelect, postSelect, toi=toi, timeAxis=timeAxis, polyremoval=polyremoval, output_fmt=output, method_kwargs=method_kwargs) elif method == "superlet": check_effective_parameters(SuperletTransform, defaults, lcls) # check and parse superlet specific arguments if order_max is None: lgl = "Positive integer needed for order_max" raise SPYValueError(legal=lgl, varname="order_max", actual=None) else: scalar_parser( order_max, varname="order_max", lims=[1, np.inf], ntype="int_like" ) scalar_parser( order_min, varname="order_min", lims=[1, order_max], ntype="int_like" ) scalar_parser(c_1, varname="c_1", lims=[1, np.inf], ntype="int_like") # if no frequencies are user selected, take a sensitive default if foi is None and foilim is None: scales = get_optimal_wavelet_scales( superlet.scale_from_period, int(minTrialLength * data.samplerate), dt) foi = 1 / superlet.fourier_period(scales) msg = (f"Setting frequencies of interest to {foi[0]:.1f}-" f"{foi[-1]:.1f}Hz") SPYInfo(msg) else: if foilim is not None: # frequency range in 1Hz steps foi = np.arange(foilim[0], foilim[1] + 1, dtype=float) # 0 frequency is not valid foi[foi < 0.01] = 0.01 scales = superlet.scale_from_period(1. / foi) # FASLT needs ordered frequencies low - high # meaning the scales have to go high - low if adaptive: if len(scales) < 2: lgl = "A range of frequencies" act = "Single frequency" raise SPYValueError(legal=lgl, varname="foi", actual=act) if np.any(np.diff(scales) > 0): msg = "Sorting frequencies low to high for adaptive SLT.." SPYWarning(msg) scales = np.sort(scales)[::-1] log_dct["foi"] = foi log_dct["c_1"] = lcls["c_1"] log_dct["order_max"] = lcls["order_max"] log_dct["order_min"] = lcls["order_min"] # method specific parameters method_kwargs = { 'samplerate' : data.samplerate, 'scales' : scales, 'order_max' : order_max, 'order_min' : order_min, 'c_1' : c_1, 'adaptive' : adaptive } # Set up compute-class specestMethod = SuperletTransform( preSelect, postSelect, toi=toi, timeAxis=timeAxis, polyremoval=polyremoval, output_fmt=output, method_kwargs=method_kwargs) # ------------------------------------------------- # Sanitize output and call the ComputationalRoutine # ------------------------------------------------- # If provided, make sure output object is appropriate if out is not None: try: data_parser(out, varname="out", writable=True, empty=True, dataclass="SpectralData", dimord=SpectralData().dimord) except Exception as exc: raise exc new_out = False else: out = SpectralData(dimord=SpectralData._defaultDimord) new_out = True # Perform actual computation specestMethod.initialize(data, out._stackingDim, chan_per_worker=kwargs.get("chan_per_worker"), keeptrials=keeptrials) specestMethod.compute(data, out, parallel=kwargs.get("parallel"), log_dict=log_dct) # Either return newly created output object or simply quit return out if new_out else None
def cleanup(older_than=24, **kwargs): """ Delete old files in temporary Syncopy folder The location of the temporary folder is stored in `syncopy.__storage__`. Parameters ---------- older_than : int Files older than `older_than` hours will be removed Examples -------- >>> spy.cleanup() """ # Make sure age-cutoff is valid try: scalar_parser(older_than, varname="older_than", ntype="int_like", lims=[0, np.inf]) except Exception as exc: raise exc older_than = int(older_than) # For clarification: show location of storage folder that is scanned here funcName = "Syncopy <{}>".format(inspect.currentframe().f_code.co_name) dirInfo = \ "\n{name:s} Analyzing temporary storage folder {dir:s}...\n" print(dirInfo.format(name=funcName, dir=__storage__)) # Parse "hidden" interactive keyword: if `False`, don't ask, just delete interactive = kwargs.get("interactive", True) if not isinstance(interactive, bool): raise SPYTypeError(interactive, varname="interactive", expected="bool") # Get current date + time and scan package's temp directory for session files now = datetime.now() sessions = glob(os.path.join(__storage__, "session*")) allIds = [] for sess in sessions: allIds.append(os.path.splitext(os.path.basename(sess))[0].split("_")[1]) # Also check for dangling data (not associated to any session) data = glob(os.path.join(__storage__, "spy_*")) dangling = [] for dat in data: sessid = os.path.splitext(os.path.basename(dat))[0].split("_")[1] if sessid not in allIds: dangling.append(dat) # Cycle through session-logs and identify stuff older than `older_than` hrs sesList = [] # full path to session files ageList = [] # session age in days usrList = [] # session users sizList = [] # raw session sizes in bytes ownList = [] # session owners (user@machine) flsList = [] # files/directories associated to session for sk, sess in enumerate(sessions): sessid = allIds[sk] if sessid != __sessionid__: with open(sess, "r") as fid: sesslog = fid.read() timestr = sesslog[sesslog.find("<") + 1:sesslog.find(">")] timeobj = datetime.strptime(timestr, '%Y-%m-%d %H:%M:%S') age = round((now - timeobj).total_seconds()/3600) # age in hrs if age >= older_than: sesList.append(sess) files = glob(os.path.join(__storage__, "*_{}_*".format(sessid))) flsList.append(files) ageList.append(round(age/24)) # age in days usrList.append(sesslog[:sesslog.find("@")]) ownList.append(sesslog[:sesslog.find(":")]) sizList.append(sum(os.path.getsize(file) if os.path.isfile(file) else sum(os.path.getsize(os.path.join(dirpth, fname)) \ for dirpth, _, fnames in os.walk(file) for fname in fnames) for file in files)) # Farewell if nothing's to do here if not sesList and not dangling: ext = \ "Did not find any dangling data or Syncopy session remains " +\ "older than {age:d} hours." print(ext.format(name=funcName, age=older_than)) return # Prepare session-related info prompt if sesList: usrList = list(set(usrList)) gbList = [sz/1024**3 for sz in sizList] sesInfo = \ "Found data of {numsess:d} syncopy sessions {ageinfo:s} " +\ "created by user{users:s}'\ntaking up {gbinfo:s} of disk space. \n" sesInfo = sesInfo.format(numsess=len(sesList), ageinfo="between {agemin:d} and {agemax:d} days old".format(agemin=min(ageList), agemax=max(ageList)) \ if min(ageList) < max(ageList) else "from {} days ago".format(ageList[0]), users="(s) '" + ",".join(usr + ", " for usr in usrList)[:-2] \ if len(usrList) > 1 else " '" + usrList[0], gbinfo="a total of {gbsz:4.1f} GB".format(gbsz=sum(gbList)) \ if sum(gbList) > 1 else "less than 1 GB") sesOptions = \ "[I]NTERACTIVE walkthrough to decide which session to remove \n" +\ "[S]ESSION removal to delete all sessions at once " +\ "(you will not be prompted for confirmation) \n" sesValid = ["I", "S"] promptInfo = sesInfo promptOptions = sesOptions promptValid = sesValid # Prepare info prompt for dangling files if dangling: dangInfo = \ "Found {numdang:d} dangling files not associated to any session " +\ "using {szdang:4.1f} GB of disk space. \n" dangInfo = dangInfo.format(numdang=len(dangling), szdang=sum(os.path.getsize(file)/1024**3 if os.path.isfile(file) else \ sum(os.path.getsize(os.path.join(dirpth, fname))/1024**3 \ for dirpth, _, fnames in os.walk(file) \ for fname in fnames) for file in dangling)) dangOptions = \ "[D]ANGLING FILE removal to delete anything not associated to sessions " +\ "(you will not be prompted for confirmation) \n" dangValid = ["D"] promptInfo = dangInfo promptOptions = dangOptions promptValid = dangValid # Put together actual prompt message message promptChoice = "\nPlease choose one of the following options:\n" abortOption = "[C]ANCEL\n" abortValid = ["C"] if sesList and dangling: rmAllOption = \ "[R]EMOVE all (sessions and dangling files) at once " +\ "(you will not be prompted for confirmation)\n" rmAllValid = ["R"] promptInfo = sesInfo + dangInfo promptOptions = sesOptions + dangOptions + rmAllOption promptValid = sesValid + dangValid + rmAllValid # By default, ask what to do; if `interactive` is `False`, remove everything if interactive: choice = user_input(promptInfo + promptChoice + promptOptions + abortOption, valid=promptValid + abortValid) else: choice = "R" # Query removal of data session by session if choice == "I": promptYesNo = \ "Found{numf:s} files created by session {sess:s} {age:d} " +\ "days ago{sizeinfo:s} Do you want to permanently delete these files?" for sk in range(len(sesList)): if user_yesno(promptYesNo.format(numf=" " + str(len(flsList[sk])), sess=ownList[sk], age=ageList[sk], sizeinfo=" using " + \ str(round(sizList[sk]/1024**2)) + \ " MB of disk space.")): _rm_session(flsList[sk]) # Delete all session-remains at once elif choice == "S": for fls in tqdm(flsList, desc="Deleting session data..."): _rm_session(fls) # Deleate all dangling files at once elif choice == "D": for dat in tqdm(dangling, desc="Deleting dangling data..."): _rm_session([dat]) # Delete everything elif choice == "R": for contents in tqdm(flsList + [[dat] for dat in dangling], desc="Deleting temporary data..."): _rm_session(contents) # Don't do anything for now, continue w/dangling data else: print("Aborting...") return
def connectivityanalysis(data, method="coh", keeptrials=False, output="abs", foi=None, foilim=None, pad_to_length=None, polyremoval=None, taper="hann", tapsmofrq=None, nTaper=None, out=None, **kwargs): """ Perform connectivity analysis of Syncopy :class:`~syncopy.AnalogData` objects **Usage Summary** Options available in all analysis methods: * **foi**/**foilim** : frequencies of interest; either array of frequencies or frequency window (not both) * **polyremoval** : de-trending method to use (0 = mean, 1 = linear or `None`) List of available analysis methods and respective distinct options: "coh" : (Multi-) tapered coherency estimate Compute the normalized cross spectral densities between all channel combinations * **output** : one of ('abs', 'pow', 'fourier') * **taper** : one of :data:`~syncopy.shared.const_def.availableTapers` * **tapsmofrq** : spectral smoothing box for slepian tapers (in Hz) * **nTaper** : (optional) number of orthogonal tapers for slepian tapers * **pad_to_length**: either pad to an absolute length or set to `'nextpow2'` "corr" : Cross-correlations Computes the one sided (positive lags) cross-correlations between all channel combinations. The maximal lag is half the trial lengths. * **keeptrials** : set to `True` for single trial cross-correlations "granger" : Spectral Granger-Geweke causality Computes linear causality estimates between all channel combinations. The intermediate cross-spectral densities can be computed via multi-tapering. * **taper** : one of :data:`~syncopy.shared.const_def.availableTapers` * **tapsmofrq** : spectral smoothing box for slepian tapers (in Hz) * **nTaper** : (optional, not recommended) number of slepian tapers * **pad_to_length**: either pad to an absolute length or set to `'nextpow2'` Parameters ---------- data : `~syncopy.AnalogData` A non-empty Syncopy :class:`~syncopy.datatype.AnalogData` object method : str Connectivity estimation method, one of 'coh', 'corr', 'granger' output : str Relevant for cross-spectral density estimation (`method='coh'`) Use `'pow'` for absolute squared coherence, `'abs'` for absolute value of coherence and`'fourier'` for the complex valued coherency. keeptrials : bool Relevant for cross-correlations (`method='corr'`). If `True` single-trial cross-correlations are returned. foi : array-like or None Frequencies of interest (Hz) for output. If desired frequencies cannot be matched exactly, the closest possible frequencies are used. If `foi` is `None` or ``foi = "all"``, all attainable frequencies (i.e., zero to Nyquist / 2) are selected. foilim : array-like (floats [fmin, fmax]) or None or "all" Frequency-window ``[fmin, fmax]`` (in Hz) of interest. The `foi` array will be constructed in 1Hz steps from `fmin` to `fmax` (inclusive). pad_to_length : int, None or 'nextpow2' Padding of the (tapered) signal, if set to a number pads all trials to this absolute length. E.g. `pad_to_length=2000` pads all trials to 2000 samples, if and only if the longest trial is at maximum 2000 samples. Alternatively if all trials have the same initial lengths setting `pad_to_length='nextpow2'` pads all trials to the next power of two. If `None` and trials have unequal lengths all trials are padded to match the longest trial. taper : str Only valid if `method` is `'coh'` or `'granger'`. Windowing function, one of :data:`~syncopy.specest.const_def.availableTapers` tapsmofrq : float Only valid if `method` is `'coh'` or `'granger'` and `taper` is `'dpss'`. The amount of spectral smoothing through multi-tapering (Hz). Note that smoothing frequency specifications are one-sided, i.e., 4 Hz smoothing means plus-minus 4 Hz, i.e., a 8 Hz smoothing box. nTaper : int or None Only valid if `method` is `'coh'` or `'granger'` and ``taper = 'dpss'``. Number of orthogonal tapers to use. It is not recommended to set the number of tapers manually! Leave at `None` for the optimal number to be set automatically. Examples -------- Coming soon... """ # Make sure our one mandatory input object can be processed try: data_parser(data, varname="data", dataclass="AnalogData", writable=None, empty=False) except Exception as exc: raise exc timeAxis = data.dimord.index("time") # Get everything of interest in local namespace defaults = get_defaults(connectivityanalysis) lcls = locals() # check for ineffective additional kwargs check_passed_kwargs(lcls, defaults, frontend_name="connectivity") # Ensure a valid computational method was selected if method not in availableMethods: lgl = "'" + "or '".join(opt + "' " for opt in availableMethods) raise SPYValueError(legal=lgl, varname="method", actual=method) # if a subset selection is present # get sampleinfo and check for equidistancy if data._selection is not None: sinfo = data._selection.trialdefinition[:, :2] trialList = data._selection.trials # user picked discrete set of time points if isinstance(data._selection.time[0], list): lgl = "equidistant time points (toi) or time slice (toilim)" actual = "non-equidistant set of time points" raise SPYValueError(legal=lgl, varname="select", actual=actual) else: trialList = list(range(len(data.trials))) sinfo = data.sampleinfo lenTrials = np.diff(sinfo).squeeze() # check polyremoval if polyremoval is not None: scalar_parser(polyremoval, varname="polyremoval", ntype="int_like", lims=[0, 1]) # --- Padding --- if method == "corr" and pad_to_length: lgl = "`None`, no padding needed/allowed for cross-correlations" actual = f"{pad_to_length}" raise SPYValueError(legal=lgl, varname="pad_to_length", actual=actual) # the actual number of samples in case of later padding nSamples = validate_padding(pad_to_length, lenTrials) # --- Basic foi sanitization --- foi, foilim = validate_foi(foi, foilim, data.samplerate) # only now set foi array for foilim in 1Hz steps if foilim is not None: foi = np.arange(foilim[0], foilim[1] + 1, dtype=float) # Prepare keyword dict for logging (use `lcls` to get actually provided # keyword values, not defaults set above) log_dict = { "method": method, "output": output, "keeptrials": keeptrials, "polyremoval": polyremoval, "pad_to_length": pad_to_length } # --- Setting up specific Methods --- if method in ['coh', 'granger']: # --- set up computation of the single trial CSDs --- if keeptrials is not False: lgl = "False, trial averaging needed!" act = keeptrials raise SPYValueError(lgl, varname="keeptrials", actual=act) # Construct array of maximally attainable frequencies freqs = np.fft.rfftfreq(nSamples, 1 / data.samplerate) # Match desired frequencies as close as possible to # actually attainable freqs # these are the frequencies attached to the SpectralData by the CR! if foi is not None: foi, _ = best_match(freqs, foi, squash_duplicates=True) elif foilim is not None: foi, _ = best_match(freqs, foilim, span=True, squash_duplicates=True) elif foi is None and foilim is None: # Construct array of maximally attainable frequencies msg = (f"Setting frequencies of interest to {freqs[0]:.1f}-" f"{freqs[-1]:.1f}Hz") SPYInfo(msg) foi = freqs # sanitize taper selection and retrieve dpss settings taper_opt = validate_taper( taper, tapsmofrq, nTaper, keeptapers=False, # ST_CSD's always average tapers foimax=foi.max(), samplerate=data.samplerate, nSamples=nSamples, output="pow") # ST_CSD's always have this unit/norm log_dict["foi"] = foi log_dict["taper"] = taper # only dpss returns non-empty taper_opt dict if taper_opt: log_dict["nTaper"] = taper_opt["Kmax"] log_dict["tapsmofrq"] = tapsmofrq check_effective_parameters(ST_CrossSpectra, defaults, lcls) # parallel computation over trials st_compRoutine = ST_CrossSpectra(samplerate=data.samplerate, nSamples=nSamples, taper=taper, taper_opt=taper_opt, polyremoval=polyremoval, timeAxis=timeAxis, foi=foi) # hard coded as class attribute st_dimord = ST_CrossSpectra.dimord if method == 'coh': # final normalization after trial averaging av_compRoutine = NormalizeCrossSpectra(output=output) if method == 'granger': # after trial averaging # hardcoded numerical parameters av_compRoutine = GrangerCausality(rtol=1e-8, nIter=100, cond_max=1e4) if method == 'corr': if lcls['foi'] is not None: msg = 'Parameter `foi` has no effect for `corr`' SPYWarning(msg) check_effective_parameters(ST_CrossCovariance, defaults, lcls) # single trial cross-correlations if keeptrials: av_compRoutine = None # no trial average norm = True # normalize individual trials within the ST CR else: av_compRoutine = NormalizeCrossCov() norm = False # parallel computation over trials st_compRoutine = ST_CrossCovariance(samplerate=data.samplerate, polyremoval=polyremoval, timeAxis=timeAxis, norm=norm) # hard coded as class attribute st_dimord = ST_CrossCovariance.dimord # ------------------------------------------------- # Call the chosen single trial ComputationalRoutine # ------------------------------------------------- # the single trial results need a new DataSet st_out = CrossSpectralData(dimord=st_dimord) # Perform the trial-parallelized computation of the matrix quantity st_compRoutine.initialize( data, st_out._stackingDim, chan_per_worker=None, # no parallelisation over channels possible keeptrials=keeptrials) # we most likely need trial averaging! st_compRoutine.compute(data, st_out, parallel=kwargs.get("parallel"), log_dict=log_dict) # if ever needed.. # for single trial cross-corr results <-> keeptrials is True if keeptrials and av_compRoutine is None: if out is not None: msg = "Single trial processing does not support `out` argument but directly returns the results" SPYWarning(msg) return st_out # ---------------------------------------------------------------------------------- # Sanitize output and call the chosen ComputationalRoutine on the averaged ST output # ---------------------------------------------------------------------------------- # If provided, make sure output object is appropriate if out is not None: try: data_parser(out, varname="out", writable=True, empty=True, dataclass="CrossSpectralData", dimord=st_dimord) except Exception as exc: raise exc new_out = False else: out = CrossSpectralData(dimord=st_dimord) new_out = True # now take the trial average from the single trial CR as input av_compRoutine.initialize(st_out, out._stackingDim, chan_per_worker=None) av_compRoutine.pre_check() # make sure we got a trial_average av_compRoutine.compute(st_out, out, parallel=False, log_dict=log_dict) # Either return newly created output object or simply quit return out if new_out else None
def esi_cluster_setup(partition="8GBS", n_jobs=2, mem_per_job=None, timeout=180, interactive=True, start_client=True, **kwargs): """ Start a distributed Dask cluster of parallel processing workers using SLURM (or local multi-processing) Parameters ---------- partition : str Name of SLURM partition/queue to use n_jobs : int Number of jobs to spawn mem_per_job : None or str Memory booking for each job. Can be specified either in megabytes (e.g., ``mem_per_job = 1500MB``) or gigabytes (e.g., ``mem_per_job = "2GB"``). If `mem_per_job` is `None`, it is attempted to infer a sane default value from the chosen queue, e.g., for ``partition = "8GBS"`` `mem_per_job` is automatically set to the allowed maximum of `'8GB'`. However, even in queues with guaranted memory bookings, it is possible to allocate less memory than the allowed maximum per job to spawn numerous low-memory jobs. See Examples for details. timeout : int Number of seconds to wait for requested jobs to start up. interactive : bool If `True`, user input is required in case not all jobs could be started in the provided waiting period (determined by `timeout`). If `interactive` is `False` and the jobs could not be started within `timeout` seconds, a `TimeoutError` is raised. start_client : bool If `True`, a distributed computing client is launched and attached to the workers. If `start_client` is `False`, only a distributed computing cluster is started to which compute-clients can connect. **kwargs : dict Additional keyword arguments can be used to control job-submission details. Returns ------- proc : object A distributed computing client (if ``start_client = True``) or a distributed computing cluster (otherwise). Examples -------- The following command launches 10 SLURM jobs with 2 gigabytes memory each in the `8GBS` partition >>> spy.esi_cluster_setup(n_jobs=10, partition="8GBS", mem_per_job="2GB") If you want to access properties of the created distributed computing client, assign an explicit return quantity, i.e., >>> client = spy.esi_cluster_setup(n_jobs=10, partition="8GBS", mem_per_job="2GB") The underlying distributed computing cluster can be accessed using >>> client.cluster Notes ----- Syncopy's parallel computing engine relies on the concurrent processing library `Dask <https://docs.dask.org/en/latest/>`_. Thus, the distributed computing clients used by Syncopy are in fact instances of :class:`dask.distributed.Client`. This function specifically acts as a wrapper for :class:`dask_jobqueue.SLURMCluster`. Users familiar with Dask in general and its distributed scheduler and cluster objects in particular, may leverage Dask's entire API to fine-tune parallel processing jobs to their liking (if wanted). See also -------- cluster_cleanup : remove dangling parallel processing job-clusters """ # For later reference: dynamically fetch name of current function funcName = "Syncopy <{}>".format(inspect.currentframe().f_code.co_name) # Be optimistic: prepare success message successMsg = "{name:s} Cluster dashboard accessible at {dash:s}" # Retrieve all partitions currently available in SLURM out, err = subprocess.Popen("sinfo -h -o %P", stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, shell=True).communicate() if len(err) > 0: # SLURM is not installed, either allocate `LocalCluster` or just leave if "sinfo: not found" in err: if interactive: msg = "{name:s} SLURM does not seem to be installed on this machine " +\ "({host:s}). Do you want to start a local multi-processing " +\ "computing client instead? " startLocal = user_yesno(msg.format(name=funcName, host=socket.gethostname()), default="no") else: startLocal = True if startLocal: client = Client() successMsg = "{name:s} Local parallel computing client ready. \n" + successMsg print(successMsg.format(name=funcName, dash=client.cluster.dashboard_link)) if start_client: return client return client.cluster return # SLURM is installed, but something's wrong msg = "SLURM queuing system from node {node:s}. " +\ "Original error message below:\n{error:s}" raise SPYIOError(msg.format(node=socket.gethostname(), error=err)) options = out.split() # Make sure we're in a valid partition (exclude IT partitions from output message) if partition not in options: valid = list(set(options).difference(["DEV", "PPC"])) raise SPYValueError(legal="'" + "or '".join(opt + "' " for opt in valid), varname="partition", actual=partition) # Parse job count try: scalar_parser(n_jobs, varname="n_jobs", ntype="int_like", lims=[1, np.inf]) except Exception as exc: raise exc # Get requested memory per job if mem_per_job is not None: if not isinstance(mem_per_job, str): raise SPYTypeError(mem_per_job, varname="mem_per_job", expected="string") if not any(szstr in mem_per_job for szstr in ["MB", "GB"]): lgl = "string representation of requested memory (e.g., '8GB', '12000MB')" raise SPYValueError(legal=lgl, varname="mem_per_job", actual=mem_per_job) # Query memory limit of chosen partition and ensure that `mem_per_job` is # set for partitions w/o limit idx = partition.find("GB") if idx > 0: mem_lim = int(partition[:idx]) * 1000 else: if partition == "PREPO": mem_lim = 16000 else: if mem_per_job is None: lgl = "explicit memory amount as required by partition '{}'" raise SPYValueError(legal=lgl.format(partition), varname="mem_per_job", actual=mem_per_job) mem_lim = np.inf # Consolidate requested memory with chosen partition (or assign default memory) if mem_per_job is None: mem_per_job = str(mem_lim) + "MB" else: if "MB" in mem_per_job: mem_req = int(mem_per_job[:mem_per_job.find("MB")]) else: mem_req = int(round(float(mem_per_job[:mem_per_job.find("GB")]) * 1000)) if mem_req > mem_lim: msg = "`mem_per_job` exceeds limit of {lim:d}GB for partition {par:s}. " +\ "Capping memory at partition limit. " SPYWarning(msg.format(lim=mem_lim, par=partition)) mem_per_job = str(int(mem_lim)) + "GB" # Parse requested timeout period try: scalar_parser(timeout, varname="timeout", ntype="int_like", lims=[1, np.inf]) except Exception as exc: raise exc # Determine if cluster allocation is happening interactively if not isinstance(interactive, bool): raise SPYTypeError(interactive, varname="interactive", expected="bool") # Determine if a dask client was requested if not isinstance(start_client, bool): raise SPYTypeError(start_client, varname="start_client", expected="bool") # Set/get "hidden" kwargs workers_per_job = kwargs.get("workers_per_job", 1) try: scalar_parser(workers_per_job, varname="workers_per_job", ntype="int_like", lims=[1, 8]) except Exception as exc: raise exc n_cores = kwargs.get("n_cores", 1) try: scalar_parser(n_cores, varname="n_cores", ntype="int_like", lims=[1, np.inf]) except Exception as exc: raise exc slurm_wdir = kwargs.get("slurmWorkingDirectory", None) if slurm_wdir is None: usr = getpass.getuser() slurm_wdir = "/mnt/hpx/slurm/{usr:s}/{usr:s}_{date:s}" slurm_wdir = slurm_wdir.format(usr=usr, date=datetime.now().strftime('%Y%m%d-%H%M%S')) os.makedirs(slurm_wdir, exist_ok=True) else: try: io_parser(slurm_wdir, varname="slurmWorkingDirectory", isfile=False) except Exception as exc: raise exc # Hotfix for upgraded cluster-nodes: point to correct Python executable if working from /home pyExec = sys.executable if sys.executable.startswith("/home"): pyExec = "/mnt/gs" + sys.executable # Create `SLURMCluster` object using provided parameters out_files = os.path.join(slurm_wdir, "slurm-%j.out") cluster = SLURMCluster(cores=n_cores, memory=mem_per_job, processes=workers_per_job, local_directory=slurm_wdir, queue=partition, name="spyswarm", python=pyExec, header_skip=["-t", "--mem"], job_extra=["--output={}".format(out_files)]) # interface="asdf", # interface is set via `psutil.net_if_addrs()` # job_extra=["--hint=nomultithread", # "--threads-per-core=1"] # Compute total no. of workers and up-scale cluster accordingly total_workers = n_jobs * workers_per_job cluster.scale(total_workers) # Fire up waiting routine to avoid premature cluster setups if _cluster_waiter(cluster, funcName, total_workers, timeout, interactive): return # Kill a zombie cluster in non-interactive mode if not interactive and _count_running_workers(cluster) == 0: cluster.close() err = "SLURM jobs could not be started within given time-out " +\ "interval of {0:d} seconds" raise TimeoutError(err.format(timeout)) # Highlight how to connect to dask performance monitor print(successMsg.format(name=funcName, dash=cluster.dashboard_link)) # If client was requested, return that instead of the created cluster if start_client: return Client(cluster) return cluster
def freqanalysis(data, method='mtmfft', output='fourier', keeptrials=True, foi=None, foilim=None, pad=None, padtype='zero', padlength=None, prepadlength=None, postpadlength=None, polyremoval=None, taper="hann", tapsmofrq=None, keeptapers=False, toi=None, t_ftimwin=None, wav="Morlet", width=6, order=None, out=None, **kwargs): """ Perform (time-)frequency analysis of Syncopy :class:`~syncopy.AnalogData` objects **Usage Summary** Options available in all analysis methods: * **output** : one of :data:`~.availableOutputs`; return power spectra, complex Fourier spectra or absolute values. * **foi**/**foilim** : frequencies of interest; either array of frequencies or frequency window (not both) * **keeptrials** : return individual trials or grand average * **polyremoval** : de-trending method to use (0 = mean, 1 = linear, 2 = quadratic, 3 = cubic, etc.) List of available analysis methods and respective distinct options: :func:`~syncopy.specest.mtmfft.mtmfft` : (Multi-)tapered Fourier transform Perform frequency analysis on time-series trial data using either a single taper window (Hanning) or many tapers based on the discrete prolate spheroidal sequence (DPSS) that maximize energy concentration in the main lobe. * **taper** : one of :data:`~.availableTapers` * **tapsmofrq** : spectral smoothing box for tapers (in Hz) * **keeptapers** : return individual tapers or average * **pad** : padding method to use (`None`, `True`, `False`, `'absolute'`, `'relative'`, `'maxlen'` or `'nextpow2'`). If `None`, then `'nextpow2'` is selected by default. * **padtype** : values to pad data with (`'zero'`, `'nan'`, `'mean'`, `'localmean'`, `'edge'` or `'mirror'`) * **padlength** : number of samples to pre-pend and/or append to each trial * **prepadlength** : number of samples to pre-pend to each trial * **postpadlength** : number of samples to append to each trial :func:`~syncopy.specest.mtmconvol.mtmconvol` : (Multi-)tapered sliding window Fourier transform Perform time-frequency analysis on time-series trial data based on a sliding window short-time Fourier transform using either a single Hanning taper or multiple DPSS tapers. * **taper** : one of :data:`~.availableTapers` * **tapsmofrq** : spectral smoothing box for tapers (in Hz) * **keeptapers** : return individual tapers or average * **pad** : flag indicating, whether or not to pad trials. If `None`, trials are padded only if sliding window centroids are too close to trial boundaries for the entire window to cover available data-points. * **toi** : time-points of interest; can be either an array representing analysis window centroids (in sec), a scalar between 0 and 1 encoding the percentage of overlap between adjacent windows or "all" to center a window on every sample in the data. * **t_ftimwin** : sliding window length (in sec) :func:`~syncopy.specest.wavelet.wavelet` : (Continuous non-orthogonal) wavelet transform Perform time-frequency analysis on time-series trial data using a non-orthogonal continuous wavelet transform. * **wav** : one of :data:`~.availableWavelets` * **toi** : time-points of interest; can be either an array representing time points (in sec) to center wavelets on or "all" to center a wavelet on every sample in the data. * **width** : Nondimensional frequency constant of Morlet wavelet function (>= 6) * **order** : Order of Paul wavelet function (>= 4) or derivative order of real-valued DOG wavelets (2 = mexican hat) **Full documentation below** Parameters ---------- data : `~syncopy.AnalogData` A non-empty Syncopy :class:`~syncopy.datatype.AnalogData` object method : str Spectral estimation method, one of :data:`~.availableMethods` (see below). output : str Output of spectral estimation. One of :data:`~.availableOutputs` (see below); use `'pow'` for power spectrum (:obj:`numpy.float32`), `'fourier'` for complex Fourier coefficients (:obj:`numpy.complex128`) or `'abs'` for absolute values (:obj:`numpy.float32`). keeptrials : bool If `True` spectral estimates of individual trials are returned, otherwise results are averaged across trials. foi : array-like or None Frequencies of interest (Hz) for output. If desired frequencies cannot be matched exactly, the closest possible frequencies are used. If `foi` is `None` or ``foi = "all"``, all attainable frequencies (i.e., zero to Nyquist / 2) are selected. foilim : array-like (floats [fmin, fmax]) or None or "all" Frequency-window ``[fmin, fmax]`` (in Hz) of interest. Window specifications must be sorted (e.g., ``[90, 70]`` is invalid) and not NaN but may be unbounded (e.g., ``[-np.inf, 60.5]`` is valid). Edges `fmin` and `fmax` are included in the selection. If `foilim` is `None` or ``foilim = "all"``, all frequencies are selected. pad : str or None or bool One of `None`, `True`, `False`, `'absolute'`, `'relative'`, `'maxlen'` or `'nextpow2'`. If `pad` is `None` or ``pad = True``, then method-specific defaults are chosen. Specifically, if `method` is `'mtmfft'` then `pad` is set to `'nextpow2'` so that all trials in `data` are padded to the next power of two higher than the sample-count of the longest (selected) trial in `data`. Conversely, time-frequency analysis methods (`'mtmconvol'` and `'wavelet'`), only perform padding if necessary, i.e., if time-window centroids are chosen too close to trial boundaries for the entire window to cover available data-points. If `pad` is `False`, then no padding is performed. Then in case of ``method = 'mtmfft'`` all trials have to have approximately the same length (up to the next even sample-count), if ``method = 'mtmconvol'`` or ``method = 'wavelet'``, window-centroids have to keep sufficient distance from trial boundaries. For more details on the padding methods `'absolute'`, `'relative'`, `'maxlen'` and `'nextpow2'` see :func:`syncopy.padding`. padtype : str Values to be used for padding. Can be `'zero'`, `'nan'`, `'mean'`, `'localmean'`, `'edge'` or `'mirror'`. See :func:`syncopy.padding` for more information. padlength : None, bool or positive int Only valid if `method` is `'mtmfft'` and `pad` is `'absolute'` or `'relative'`. Number of samples to pad data with. See :func:`syncopy.padding` for more information. prepadlength : None or bool or int Only valid if `method` is `'mtmfft'` and `pad` is `'relative'`. Number of samples to pre-pend to each trial. See :func:`syncopy.padding` for more information. postpadlength : None or bool or int Only valid if `method` is `'mtmfft'` and `pad` is `'relative'`. Number of samples to append to each trial. See :func:`syncopy.padding` for more information. polyremoval : int or None **FIXME: Not implemented yet** Order of polynomial used for de-trending data in the time domain prior to spectral analysis. A value of 0 corresponds to subtracting the mean ("de-meaning"), ``polyremoval = 1`` removes linear trends (subtracting the least squares fit of a linear polynomial), ``polyremoval = N`` for `N > 1` subtracts a polynomial of order `N` (``N = 2`` quadratic, ``N = 3`` cubic etc.). If `polyremoval` is `None`, no de-trending is performed. taper : str Only valid if `method` is `'mtmfft'` or `'mtmconvol'`. Windowing function, one of :data:`~.availableTapers` (see below). tapsmofrq : float Only valid if `method` is `'mtmfft'` or `'mtmconvol'`. The amount of spectral smoothing through multi-tapering (Hz). Note that smoothing frequency specifications are one-sided, i.e., 4 Hz smoothing means plus-minus 4 Hz, i.e., a 8 Hz smoothing box. keeptapers : bool Only valid if `method` is `'mtmfft'` or `'mtmconvol'`. If `True`, return spectral estimates for each taper, otherwise results are averaged across tapers. toi : float or array-like or "all" **Mandatory input** for time-frequency analysis methods (`method` is either `"mtmconvol"` or `"wavelet"`). If `toi` is scalar, it must be a value between 0 and 1 indicating the percentage of overlap between time-windows specified by `t_ftimwin` (only valid if `method` is `'mtmconvol'`, invalid for `'wavelet'`). If `toi` is an array it explicitly selects the centroids of analysis windows (in seconds). If `toi` is `"all"`, analysis windows are centered on all samples in the data. t_ftimwin : positive float Only valid if `method` is `'mtmconvol'`. Sliding window length (in seconds). wav : str Only valid if `method` is `'wavelet'`. Wavelet function to use, one of :data:`~.availableWavelets` (see below). width : positive float Only valid if `method` is `'wavelet'` and `wav` is `'Morlet'`. Nondimensional frequency constant of Morlet wavelet function. This number should be >= 6, which corresponds to 6 cycles within the analysis window to ensure sufficient spectral sampling. order : positive int Only valid if `method` is `'wavelet'` and `wav` is `'Paul'` or `'DOG'`. Order of the wavelet function. If `wav` is `'Paul'`, `order` should be chosen >= 4 to ensure that the analysis window contains at least a single oscillation. At an order of 40, the Paul wavelet exhibits about the same number of cycles as the Morlet wavelet with a `width` of 6. All other supported wavelets functions are *real-valued* derivatives of Gaussians (DOGs). Hence, if `wav` is `'DOG'`, `order` represents the derivative order. The special case of a second order DOG yields a function known as "Mexican Hat", "Marr" or "Ricker" wavelet, which can be selected alternatively by setting `wav` to `'Mexican_hat'`, `'Marr'` or `'Ricker'`. **Note**: A real-valued wavelet function encodes *only* information about peaks and discontinuities in the signal and does *not* provide any information about amplitude or phase. out : None or :class:`SpectralData` object None if a new :class:`SpectralData` object is to be created, or an empty :class:`SpectralData` object Returns ------- spec : :class:`~syncopy.SpectralData` (Time-)frequency spectrum of input data Notes ----- Coming soon... Examples -------- Coming soon... .. autodata:: syncopy.specest.freqanalysis.availableMethods .. autodata:: syncopy.specest.freqanalysis.availableOutputs .. autodata:: syncopy.specest.freqanalysis.availableTapers .. autodata:: syncopy.specest.freqanalysis.availableWavelets See also -------- syncopy.specest.mtmfft.mtmfft : (multi-)tapered Fourier transform of multi-channel time series data syncopy.specest.mtmconvol.mtmconvol : time-frequency analysis of multi-channel time series data with a sliding window FFT syncopy.specest.wavelet.wavelet : time-frequency analysis of multi-channel time series data using a wavelet transform numpy.fft.fft : NumPy's reference FFT implementation scipy.signal.stft : SciPy's Short Time Fourier Transform """ # Make sure our one mandatory input object can be processed try: data_parser(data, varname="data", dataclass="AnalogData", writable=None, empty=False) except Exception as exc: raise exc timeAxis = data.dimord.index("time") # Get everything of interest in local namespace defaults = get_defaults(freqanalysis) lcls = locals() # Ensure a valid computational method was selected if method not in availableMethods: lgl = "'" + "or '".join(opt + "' " for opt in availableMethods) raise SPYValueError(legal=lgl, varname="method", actual=method) # Ensure a valid output format was selected if output not in spectralConversions.keys(): lgl = "'" + "or '".join(opt + "' " for opt in spectralConversions.keys()) raise SPYValueError(legal=lgl, varname="output", actual=output) # Parse all Boolean keyword arguments for vname in ["keeptrials", "keeptapers"]: if not isinstance(lcls[vname], bool): raise SPYTypeError(lcls[vname], varname=vname, expected="Bool") # If only a subset of `data` is to be processed, make some necessary adjustments # and compute minimal sample-count across (selected) trials if data._selection is not None: trialList = data._selection.trials sinfo = np.zeros((len(trialList), 2)) for tk, trlno in enumerate(trialList): trl = data._preview_trial(trlno) tsel = trl.idx[timeAxis] if isinstance(tsel, list): sinfo[tk, :] = [0, len(tsel)] else: sinfo[tk, :] = [ trl.idx[timeAxis].start, trl.idx[timeAxis].stop ] else: trialList = list(range(len(data.trials))) sinfo = data.sampleinfo lenTrials = np.diff(sinfo).squeeze() numTrials = len(trialList) # Set default padding options: after this, `pad` is either `None`, `False` or `str` defaultPadding = {"mtmfft": "nextpow2", "mtmconvol": None, "wavelet": None} if pad is None or pad is True: pad = defaultPadding[method] # Sliding window FFT does not support "fancy" padding if method == "mtmconvol" and isinstance(pad, str): msg = "method 'mtmconvol' only supports in-place padding for windows " +\ "exceeding trial boundaries. Your choice of `pad = '{}'` will be ignored. " SPYWarning(msg.format(pad)) pad = None # Ensure padding selection makes sense: do not pad on a by-trial basis but # use the longest trial as reference and compute `padlength` from there # (only relevant for "global" padding options such as `maxlen` or `nextpow2`) if pad: if not isinstance(pad, str): raise SPYTypeError(pad, varname="pad", expected="str or None") if pad == "maxlen": padlength = lenTrials.max() prepadlength = True postpadlength = False elif pad == "nextpow2": padlength = 0 for ltrl in lenTrials: padlength = max(padlength, _nextpow2(ltrl)) pad = "absolute" prepadlength = True postpadlength = False padding(data._preview_trial(trialList[0]), padtype, pad=pad, padlength=padlength, prepadlength=prepadlength, postpadlength=postpadlength) # Compute `minSampleNum` accounting for padding minSamplePos = lenTrials.argmin() minSampleNum = padding(data._preview_trial(trialList[minSamplePos]), padtype, pad=pad, padlength=padlength, prepadlength=True).shape[timeAxis] else: if method == "mtmfft" and np.unique( (np.floor(lenTrials / 2))).size > 1: lgl = "trials of approximately equal length for method 'mtmfft'" act = "trials of unequal length" raise SPYValueError(legal=lgl, varname="data", actual=act) minSampleNum = lenTrials.min() # Compute length (in samples) of shortest trial minTrialLength = minSampleNum / data.samplerate # Basic sanitization of frequency specifications if foi is not None: if isinstance(foi, str): if foi == "all": foi = None else: raise SPYValueError(legal="'all' or `None` or list/array", varname="foi", actual=foi) else: try: array_parser(foi, varname="foi", hasinf=False, hasnan=False, lims=[0, data.samplerate / 2], dims=(None, )) except Exception as exc: raise exc foi = np.array(foi, dtype="float") if foilim is not None: if isinstance(foilim, str): if foilim == "all": foilim = None else: raise SPYValueError(legal="'all' or `None` or `[fmin, fmax]`", varname="foilim", actual=foilim) else: try: array_parser(foilim, varname="foilim", hasinf=False, hasnan=False, lims=[0, data.samplerate / 2], dims=(2, )) except Exception as exc: raise exc if foi is not None and foilim is not None: lgl = "either `foi` or `foilim` specification" act = "both" raise SPYValueError(legal=lgl, varname="foi/foilim", actual=act) # FIXME: implement detrending # see also https://docs.obspy.org/_modules/obspy/signal/detrend.html#polynomial if polyremoval is not None: raise NotImplementedError("Detrending has not been implemented yet.") try: scalar_parser(polyremoval, varname="polyremoval", lims=[0, 8], ntype="int_like") except Exception as exc: raise exc # Prepare keyword dict for logging (use `lcls` to get actually provided # keyword values, not defaults set above) log_dct = { "method": method, "output": output, "keeptapers": keeptapers, "keeptrials": keeptrials, "polyremoval": polyremoval, "pad": lcls["pad"], "padtype": lcls["padtype"], "padlength": lcls["padlength"], "foi": lcls["foi"] } # 1st: Check time-frequency inputs to prepare/sanitize `toi` if method in ["mtmconvol", "wavelet"]: # Get start/end timing info respecting potential in-place selection if toi is None: raise SPYTypeError(toi, varname="toi", expected="scalar or array-like or 'all'") if data._selection is not None: tStart = data._selection.trialdefinition[:, 2] / data.samplerate else: tStart = data._t0 / data.samplerate tEnd = tStart + lenTrials / data.samplerate # Process `toi`: we have to account for three scenarios: (1) center sliding # windows on all samples in (selected) trials (2) `toi` was provided as # percentage indicating the degree of overlap b/w time-windows and (3) a set # of discrete time points was provided. These three cases are encoded in # `overlap, i.e., ``overlap > 1` => all, `0 < overlap < 1` => percentage, # `overlap < 0` => discrete `toi` if isinstance(toi, str): if toi != "all": lgl = "`toi = 'all'` to center analysis windows on all time-points" raise SPYValueError(legal=lgl, varname="toi", actual=toi) overlap = 1.1 toi = None equidistant = True elif isinstance(toi, Number): if method == "wavelet": lgl = "array of time-points wavelets are to be centered on" act = "scalar value" raise SPYValueError(legal=lgl, varname="toi", actual=act) try: scalar_parser(toi, varname="toi", lims=[0, 1]) except Exception as exc: raise exc overlap = toi equidistant = True else: overlap = -1 try: array_parser(toi, varname="toi", hasinf=False, hasnan=False, lims=[tStart.min(), tEnd.max()], dims=(None, )) except Exception as exc: raise exc toi = np.array(toi) tSteps = np.diff(toi) if (tSteps < 0).any(): lgl = "ordered list/array of time-points" act = "unsorted list/array" raise SPYValueError(legal=lgl, varname="toi", actual=act) # This is imho a bug in NumPy - even `arange` and `linspace` may produce # arrays that are numerically not exactly equidistant - `unique` will # show several entries here - use `allclose` to identify "even" spacings equidistant = np.allclose(tSteps, [tSteps[0]] * tSteps.size) # If `toi` was 'all' or a percentage, use entire time interval of (selected) # trials and check if those trials have *approximately* equal length if toi is None: if not np.allclose(lenTrials, [minSampleNum] * lenTrials.size): msg = "processing trials of different lengths (min = {}; max = {} samples)" +\ " with `toi = 'all'`" SPYWarning(msg.format(int(minSampleNum), int(lenTrials.max()))) if pad is False: lgl = "`pad` to be `None` or `True` to permit zero-padding " +\ "at trial boundaries to accommodate windows if `0 < toi < 1` " +\ "or if `toi` is 'all'" act = "False" raise SPYValueError(legal=lgl, actual=act, varname="pad") # Code recycling: `overlap`, `equidistant` etc. are really only relevant # for `mtmconvol`, but we use padding calc below for `wavelet` as well if method == "mtmconvol": try: scalar_parser(t_ftimwin, varname="t_ftimwin", lims=[1 / data.samplerate, minTrialLength]) except Exception as exc: raise exc else: t_ftimwin = 0 nperseg = int(t_ftimwin * data.samplerate) minSampleNum = nperseg halfWin = int(nperseg / 2) # `mtmconvol`: compute no. of samples overlapping across adjacent windows if overlap < 0: # `toi` is equidistant range or disjoint points noverlap = nperseg - max(1, int(tSteps[0] * data.samplerate)) elif 0 <= overlap <= 1: # `toi` is percentage noverlap = min(nperseg - 1, int(overlap * nperseg)) else: # `toi` is "all" noverlap = nperseg - 1 # `toi` is array if overlap < 0: # Compute necessary padding at begin/end of trials to fit sliding windows offStart = ((toi[0] - tStart) * data.samplerate).astype(np.intp) padBegin = halfWin - offStart padBegin = ((padBegin > 0) * padBegin).astype(np.intp) offEnd = ((tEnd - toi[-1]) * data.samplerate).astype(np.intp) padEnd = halfWin - offEnd padEnd = ((padEnd > 0) * padEnd).astype(np.intp) # Abort if padding was explicitly forbidden if pad is False and (np.any(padBegin) or np.any(padBegin)): lgl = "windows within trial bounds" act = "windows exceeding trials no. " +\ "".join(str(trlno) + ", "\ for trlno in np.array(trialList)[(padBegin + padEnd) > 0])[:-2] raise SPYValueError(legal=lgl, varname="pad", actual=act) # Compute sample-indices (one slice/list per trial) from time-selections soi = [] if not equidistant: for tk in range(numTrials): starts = (data.samplerate * (toi - tStart[tk]) - halfWin).astype(np.intp) starts += padBegin[tk] stops = (data.samplerate * (toi - tStart[tk]) + halfWin + 1).astype(np.intp) stops += padBegin[tk] stops = np.maximum(stops, stops - starts, dtype=np.intp) soi.append([ slice(start, stop) for start, stop in zip(starts, stops) ]) else: for tk in range(numTrials): start = int(data.samplerate * (toi[0] - tStart[tk]) - halfWin) stop = int(data.samplerate * (toi[-1] - tStart[tk]) + halfWin + 1) soi.append(slice(max(0, start), max(stop, stop - start))) # `toi` is percentage or "all" else: padBegin = np.zeros((numTrials, )) padEnd = np.zeros((numTrials, )) soi = [slice(None)] * numTrials # For wavelets, we need to first trim the data (via `preSelect`), then # extract the wanted time-points (`postSelect`) if method == "wavelet": # Simply recycle the indexing work done for `mtmconvol` (i.e., `soi`) preSelect = [] if not equidistant: for tk in range(numTrials): preSelect.append(slice(soi[tk][0].start, soi[tk][-1].stop)) else: preSelect = soi # If `toi` is an array, convert "global" indices to "local" ones # (select within `preSelect`'s selection), otherwise just take all if overlap < 0: postSelect = [] for tk in range(numTrials): smpIdx = np.minimum( lenTrials[tk] - 1, data.samplerate * (toi - tStart[tk]) - offStart[tk] + padBegin[tk]) postSelect.append(smpIdx.astype(np.intp)) else: postSelect = [slice(None)] * numTrials # Update `log_dct` w/method-specific options (use `lcls` to get actually # provided keyword values, not defaults set in here) if toi is None: toi = "all" log_dct["toi"] = lcls["toi"] # Check options specific to mtm*-methods (particularly tapers and foi/freqs alignment) if "mtm" in method: # See if taper choice is supported if taper not in availableTapers: lgl = "'" + "or '".join(opt + "' " for opt in availableTapers) raise SPYValueError(legal=lgl, varname="taper", actual=taper) taper = getattr(spwin, taper) # Advanced usage: see if `taperopt` was provided - if not, leave it empty taperopt = kwargs.get("taperopt", {}) if not isinstance(taperopt, dict): raise SPYTypeError(taperopt, varname="taperopt", expected="dictionary") # Construct array of maximally attainable frequencies nFreq = int(np.floor(minSampleNum / 2) + 1) freqs = np.linspace(0, data.samplerate / 2, nFreq) # Match desired frequencies as close as possible to actually attainable freqs if foi is not None: foi, _ = best_match(freqs, foi, squash_duplicates=True) elif foilim is not None: foi, _ = best_match(freqs, foilim, span=True, squash_duplicates=True) else: foi = freqs # Abort if desired frequency selection is empty if foi.size == 0: lgl = "non-empty frequency specification" act = "empty frequency selection" raise SPYValueError(legal=lgl, varname="foi/foilim", actual=act) # Set/get `tapsmofrq` if we're working w/Slepian tapers if taper.__name__ == "dpss": # Try to derive "sane" settings by using 3/4 octave smoothing of highest `foi` # following Hipp et al. "Oscillatory Synchronization in Large-Scale # Cortical Networks Predicts Perception", Neuron, 2011 if tapsmofrq is None: foimax = foi.max() tapsmofrq = (foimax * 2**(3 / 4 / 2) - foimax * 2**(-3 / 4 / 2)) / 2 else: try: scalar_parser(tapsmofrq, varname="tapsmofrq", lims=[1, np.inf]) except Exception as exc: raise exc # Get/compute number of tapers to use (at least 1 and max. 50) nTaper = taperopt.get("Kmax", 1) if not taperopt: nTaper = int( max( 2, min( 50, np.floor(tapsmofrq * minSampleNum * 1 / data.samplerate)))) taperopt = {"NW": tapsmofrq, "Kmax": nTaper} else: nTaper = 1 # Warn the user in case `tapsmofrq` has no effect if tapsmofrq is not None and taper.__name__ != "dpss": msg = "`tapsmofrq` is only used if `taper` is `dpss`!" SPYWarning(msg) # Update `log_dct` w/method-specific options (use `lcls` to get actually # provided keyword values, not defaults set in here) log_dct["taper"] = lcls["taper"] log_dct["tapsmofrq"] = lcls["tapsmofrq"] log_dct["nTaper"] = nTaper # Check for non-default values of options not supported by chosen method kwdict = {"wav": wav, "width": width} for name, kwarg in kwdict.items(): if kwarg is not lcls[name]: msg = "option `{}` has no effect in methods `mtmfft` and `mtmconvol`!" SPYWarning(msg.format(name)) # Now, prepare explicit compute-classes for chosen method if method == "mtmfft": # Check for non-default values of options not supported by chosen method kwdict = {"t_ftimwin": t_ftimwin, "toi": toi} for name, kwarg in kwdict.items(): if kwarg is not lcls[name]: msg = "option `{}` has no effect in method `mtmfft`!" SPYWarning(msg.format(name)) # Set up compute-class specestMethod = MultiTaperFFT(samplerate=data.samplerate, foi=foi, nTaper=nTaper, timeAxis=timeAxis, taper=taper, taperopt=taperopt, tapsmofrq=tapsmofrq, pad=pad, padtype=padtype, padlength=padlength, keeptapers=keeptapers, polyremoval=polyremoval, output_fmt=output) elif method == "mtmconvol": # Set up compute-class specestMethod = MultiTaperFFTConvol(soi, list(padBegin), list(padEnd), samplerate=data.samplerate, noverlap=noverlap, nperseg=nperseg, equidistant=equidistant, toi=toi, foi=foi, nTaper=nTaper, timeAxis=timeAxis, taper=taper, taperopt=taperopt, pad=pad, padtype=padtype, padlength=padlength, prepadlength=prepadlength, postpadlength=postpadlength, keeptapers=keeptapers, polyremoval=polyremoval, output_fmt=output) elif method == "wavelet": # Check for non-default values of `taper`, `tapsmofrq`, `keeptapers` and # `t_ftimwin` (set to 0 above) kwdict = { "taper": taper, "tapsmofrq": tapsmofrq, "keeptapers": keeptapers } for name, kwarg in kwdict.items(): if kwarg is not lcls[name]: msg = "option `{}` has no effect in method `wavelet`!" SPYWarning(msg.format(name)) if t_ftimwin != 0: msg = "option `t_ftimwin` has no effect in method `wavelet`!" SPYWarning(msg) # Check wavelet selection if wav not in availableWavelets: lgl = "'" + "or '".join(opt + "' " for opt in availableWavelets) raise SPYValueError(legal=lgl, varname="wav", actual=wav) if wav not in ["Morlet", "Paul"]: msg = "the chosen wavelet '{}' is real-valued and does not provide " +\ "any information about amplitude or phase of the data. This wavelet function " +\ "may be used to isolate peaks or discontinuities in the signal. " SPYWarning(msg.format(wav)) # Check for consistency of `width`, `order` and `wav` if wav == "Morlet": try: scalar_parser(width, varname="width", lims=[1, np.inf]) except Exception as exc: raise exc wfun = getattr(spywave, wav)(w0=width) else: if width != lcls["width"]: msg = "option `width` has no effect for wavelet '{}'" SPYWarning(msg.format(wav)) if wav == "Paul": try: scalar_parser(order, varname="order", lims=[4, np.inf], ntype="int_like") except Exception as exc: raise exc wfun = getattr(spywave, wav)(m=order) elif wav == "DOG": try: scalar_parser(order, varname="order", lims=[1, np.inf], ntype="int_like") except Exception as exc: raise exc wfun = getattr(spywave, wav)(m=order) else: if order is not None: msg = "option `order` has no effect for wavelet '{}'" SPYWarning(msg.format(wav)) wfun = getattr(spywave, wav)() # Process frequency selection (`toi` was taken care of above): `foilim` # selections are wrapped into `foi` thus the seemingly weird if construct # Note: SLURM workers don't like monkey-patching, so let's pretend # `get_optimal_wavelet_scales` is a class method by passing `wfun` as its # first argument if foi is None: scales = _get_optimal_wavelet_scales( wfun, int(minTrialLength * data.samplerate), 1 / data.samplerate) if foilim is not None: foi = np.arange(foilim[0], foilim[1] + 1) if foi is not None: foi[foi < 0.01] = 0.01 scales = wfun.scale_from_period(1 / foi) scales = scales[:: -1] # FIXME: this only makes sense if `foi` was sorted -> cf Issue #94 # Update `log_dct` w/method-specific options (use `lcls` to get actually # provided keyword values, not defaults set in here) log_dct["wav"] = lcls["wav"] log_dct["width"] = lcls["width"] log_dct["order"] = lcls["order"] # Set up compute-class specestMethod = WaveletTransform(preSelect, postSelect, list(padBegin), list(padEnd), samplerate=data.samplerate, toi=toi, scales=scales, timeAxis=timeAxis, wav=wfun, polyremoval=polyremoval, output_fmt=output) # If provided, make sure output object is appropriate if out is not None: try: data_parser(out, varname="out", writable=True, empty=True, dataclass="SpectralData", dimord=SpectralData().dimord) except Exception as exc: raise exc new_out = False else: out = SpectralData(dimord=SpectralData._defaultDimord) new_out = True # Perform actual computation specestMethod.initialize(data, chan_per_worker=kwargs.get("chan_per_worker"), keeptrials=keeptrials) specestMethod.compute(data, out, parallel=kwargs.get("parallel"), log_dict=log_dct) # Either return newly created output object or simply quit return out if new_out else None
def save(out, container=None, tag=None, filename=None, overwrite=False, memuse=100): r"""Save Syncopy data object to disk The underlying array data object is stored in a HDF5 file, the metadata in a JSON file. Both can be placed inside a Syncopy container, which is a regular directory with the extension '.spy'. Parameters ---------- out : Syncopy data object Object to be stored on disk. container : str Path to Syncopy container folder (\*.spy) to be used for saving. If omitted, the extension '.spy' will be added to the folder name. tag : str Tag to be appended to container basename filename : str Explicit path to data file. This is only necessary if the data should not be part of a container folder. An extension (\*.<dataclass>) is added if omitted. The `tag` argument is ignored. overwrite : bool If `True` an existing HDF5 file and its accompanying JSON file is overwritten (without prompt). memuse : scalar Approximate in-memory cache size (in MB) for writing data to disk (only relevant for :class:`syncopy.VirtualData` or memory map data sources) Returns ------- Nothing : None Notes ------ Syncopy objects may also be saved using the class method ``.save`` that acts as a wrapper for :func:`syncopy.save`, e.g., >>> save(obj, container="new_spy_container") is equivalent to >>> obj.save(container="new_spy_container") However, once a Syncopy object has been saved, the class method ``.save`` can be used as a shortcut to quick-save recent changes, e.g., >>> obj.save() writes the current state of `obj` to the data/meta-data files on-disk associated with `obj` (overwriting both in the process). Similarly, >>> obj.save(tag='newtag') saves `obj` in the current container 'new_spy_container' under a different tag. Examples -------- Save the Syncopy data object `obj` on disk in the current working directory without creating a spy-container >>> spy.save(obj, filename="session1") >>> # --> os.getcwd()/session1.<dataclass> >>> # --> os.getcwd()/session1.<dataclass>.info Save `obj` without creating a spy-container using an absolute path >>> spy.save(obj, filename="/tmp/session1") >>> # --> /tmp/session1.<dataclass> >>> # --> /tmp/session1.<dataclass>.info Save `obj` in a new spy-container created in the current working directory >>> spy.save(obj, container="container.spy") >>> # --> os.getcwd()/container.spy/container.<dataclass> >>> # --> os.getcwd()/container.spy/container.<dataclass>.info Save `obj` in a new spy-container created by providing an absolute path >>> spy.save(obj, container="/tmp/container.spy") >>> # --> /tmp/container.spy/container.<dataclass> >>> # --> /tmp/container.spy/container.<dataclass>.info Save `obj` in a new (or existing) spy-container under a different tag >>> spy.save(obj, container="session1.spy", tag="someTag") >>> # --> os.getcwd()/session1.spy/session1_someTag.<dataclass> >>> # --> os.getcwd()/session1.spy/session1_someTag.<dataclass>.info See also -------- syncopy.load : load data created with :func:`syncopy.save` """ # Make sure `out` is a valid Syncopy data object data_parser(out, varname="out", writable=None, empty=False) if filename is None and container is None: raise SPYError('filename and container cannot both be `None`') if container is not None and filename is None: # construct filename from container name if not isinstance(container, str): raise SPYTypeError(container, varname="container", expected="str") if not os.path.splitext(container)[1] == ".spy": container += ".spy" fileInfo = filename_parser(container) filename = os.path.join(fileInfo["folder"], fileInfo["container"], fileInfo["basename"]) # handle tag if tag is not None: if not isinstance(tag, str): raise SPYTypeError(tag, varname="tag", expected="str") filename += '_' + tag elif container is not None and filename is not None: raise SPYError( "container and filename cannot be used at the same time") if not isinstance(filename, str): raise SPYTypeError(filename, varname="filename", expected="str") # add extension if not part of the filename if "." not in os.path.splitext(filename)[1]: filename += out._classname_to_extension() try: scalar_parser(memuse, varname="memuse", lims=[0, np.inf]) except Exception as exc: raise exc if not isinstance(overwrite, bool): raise SPYTypeError(overwrite, varname="overwrite", expected="bool") # Parse filename for validity and construct full path to HDF5 file fileInfo = filename_parser(filename) if fileInfo["extension"] != out._classname_to_extension(): raise SPYError("""Extension in filename ({ext}) does not match data class ({dclass})""".format(ext=fileInfo["extension"], dclass=out.__class__.__name__)) dataFile = os.path.join(fileInfo["folder"], fileInfo["filename"]) # If `out` is to replace its own on-disk representation, be more careful if overwrite and dataFile == out.filename: replace = True else: replace = False # Prevent `out` from trying to re-create its own data file if replace: out.data.flush() h5f = out.data.file dat = out.data trl = h5f["trialdefinition"] else: if not os.path.exists(fileInfo["folder"]): try: os.makedirs(fileInfo["folder"]) except IOError: raise SPYIOError(fileInfo["folder"]) except Exception as exc: raise exc else: if os.path.exists(dataFile): if not os.path.isfile(dataFile): raise SPYIOError(dataFile) if overwrite: try: h5f = h5py.File(dataFile, mode="w") h5f.close() except Exception as exc: msg = "Cannot overwrite {} - file may still be open. " msg += "Original error message below\n{}" raise SPYError(msg.format(dataFile, str(exc))) else: raise SPYIOError(dataFile, exists=True) h5f = h5py.File(dataFile, mode="w") # Save each member of `_hdfFileDatasetProperties` in target HDF file for datasetName in out._hdfFileDatasetProperties: dataset = getattr(out, datasetName) # Member is a memory map if isinstance(dataset, np.memmap): # Given memory cap, compute how many data blocks can be grabbed # per swipe (divide by 2 since we're working with an add'l tmp array) memuse *= 1024**2 / 2 nrow = int( memuse / (np.prod(dataset.shape[1:]) * dataset.dtype.itemsize)) rem = int(dataset.shape[0] % nrow) n_blocks = [nrow] * int( dataset.shape[0] // nrow) + [rem] * int(rem > 0) # Write data block-wise to dataset (use `clear` to wipe blocks of # mem-maps from memory) dat = h5f.create_dataset(datasetName, dtype=dataset.dtype, shape=dataset.shape) for m, M in enumerate(n_blocks): dat[m * nrow:m * nrow + M, :] = out.data[m * nrow:m * nrow + M, :] out.clear() # Member is a HDF5 dataset else: dat = h5f.create_dataset(datasetName, data=dataset) # Now write trial-related information trl_arr = np.array(out.trialdefinition) if replace: trl[()] = trl_arr trl.flush() else: trl = h5f.create_dataset("trialdefinition", data=trl_arr, maxshape=(None, trl_arr.shape[1])) # Write to log already here so that the entry can be exported to json infoFile = dataFile + FILE_EXT["info"] out.log = "Wrote files " + dataFile + "\n\t\t\t" + 2 * " " + infoFile # While we're at it, write cfg entries out.cfg = { "method": sys._getframe().f_code.co_name, "files": [dataFile, infoFile] } # Assemble dict for JSON output: order things by their "readability" outDict = OrderedDict(startInfoDict) outDict["filename"] = fileInfo["filename"] outDict["dataclass"] = out.__class__.__name__ outDict["data_dtype"] = dat.dtype.name outDict["data_shape"] = dat.shape outDict["data_offset"] = dat.id.get_offset() outDict["trl_dtype"] = trl.dtype.name outDict["trl_shape"] = trl.shape outDict["trl_offset"] = trl.id.get_offset() if isinstance(out.data, np.ndarray): if np.isfortran(out.data): outDict["order"] = "F" else: outDict["order"] = "C" for key in out._infoFileProperties: value = getattr(out, key) if isinstance(value, np.ndarray): value = value.tolist() # potentially nested dicts elif isinstance(value, dict): value = dict(value) _dict_converter(value) outDict[key] = value # Save relevant stuff as HDF5 attributes for key in out._hdfFileAttributeProperties: if outDict[key] is None: h5f.attrs[key] = "None" else: try: h5f.attrs[key] = outDict[key] except RuntimeError: msg = "Too many entries in `{}` - truncating HDF5 attribute. " +\ "Please refer to {} for complete listing." info_fle = os.path.split( os.path.split(filename.format(ext=FILE_EXT["info"]))[0])[1] info_fle = os.path.join( info_fle, os.path.basename(filename.format(ext=FILE_EXT["info"]))) SPYWarning(msg.format(key, info_fle)) h5f.attrs[key] = [outDict[key][0], "...", outDict[key][-1]] # Re-assign filename after saving (and remove source in case it came from `__storage__`) if not replace: h5f.close() if __storage__ in out.filename: out.data.file.close() os.unlink(out.filename) out.data = dataFile # Compute checksum and finally write JSON (automatically overwrites existing) outDict["file_checksum"] = hash_file(dataFile) with open(infoFile, 'w') as out_json: json.dump(outDict, out_json, indent=4) return
def _prep_spectral_plots(self, name, **inputArgs): """ Local helper that performs sanity checks and sets up data selection Parameters ---------- self : :class:`~syncopy.SpectralData` object Syncopy :class:`~syncopy.SpectralData` object that is being processed by the respective :meth:`.singlepanelplot` or :meth:`.multipanelplot` class methods defined in this module. name : str Name of caller (i.e., "singlepanelplot" or "multipanelplot") inputArgs : dict Input arguments of caller (i.e., :meth:`.singlepanelplot` or :meth:`.multipanelplot`) collected in dictionary Returns ------- dimArrs : tuple Four-element tuple containing (in this order): `trList`, list of (selected) trials to visualize, `chArr`, 1D :class:`numpy.ndarray` of channel specifiers based on provided user selection, `freqArr`, 1D :class:`numpy.ndarray` of frequency specifiers based on provided user selection, `tpArr`, 1D :class:`numpy.ndarray` of taper specifiers based on provided user selection. Note that `"all"` and `None` selections are converted to arrays ready for indexing. dimCounts : tuple Four-element tuple holding sizes of corresponding selection arrays comprised in `dimArrs`. Elements are (in this order): number of (selected) trials `nTrials`, number of (selected) channels `nChan`, number of (selected) frequencies `nFreq`, number of (selected) tapers `nTap`. isTimeFrequency : bool If `True`, input object contains time-frequency data, `False` otherwise complexConversion : callable Lambda function that performs complex-to-float conversion of Fourier coefficients (if necessary). pltDtype : str or :class:`numpy.dtype` Numeric type of (potentially converted) complex Fourier coefficients. dataLbl : str Caption for y-axis or colorbar (depending on value of `isTimeFrequency`). Notes ----- This is an auxiliary method that is intended purely for internal use. Please refer to the user-exposed methods :func:`~syncopy.singlepanelplot` and/or :func:`~syncopy.multipanelplot` to actually generate plots of Syncopy data objects. See also -------- :meth:`syncopy.plotting.spy_plotting._prep_plots` : General basic input parsing for all Syncopy plotting routines """ # Basic sanity checks for all plotting routines w/any Syncopy object _prep_plots(self, name, **inputArgs) # Ensure our binary flags are actually binary if not isinstance(inputArgs["avg_channels"], bool): raise SPYTypeError(inputArgs["avg_channels"], varname="avg_channels", expected="bool") if not isinstance(inputArgs["avg_tapers"], bool): raise SPYTypeError(inputArgs["avg_tapers"], varname="avg_tapers", expected="bool") if not isinstance(inputArgs.get("avg_trials", True), bool): raise SPYTypeError(inputArgs["avg_trials"], varname="avg_trials", expected="bool") # Pass provided selections on to `Selector` class which performs error # checking and generates required indexing arrays self._selection = { "trials": inputArgs["trials"], "channels": inputArgs["channels"], "tapers": inputArgs["tapers"], "toilim": inputArgs["toilim"], "foilim": inputArgs["foilim"] } # Ensure any optional keywords controlling plotting appearance make sense if inputArgs["title"] is not None: if not isinstance(inputArgs["title"], str): raise SPYTypeError(inputArgs["title"], varname="title", expected="str") if inputArgs["grid"] is not None: if not isinstance(inputArgs["grid"], bool): raise SPYTypeError(inputArgs["grid"], varname="grid", expected="bool") # Get trial/channel/taper count and collect quantities in tuple trList = self._selection.trials nTrials = len(trList) chArr = self.channel[self._selection.channel] nChan = chArr.size freqArr = self.freq[self._selection.freq] nFreq = freqArr.size tpArr = np.arange(self.taper.size)[self._selection.taper] nTap = tpArr.size dimCounts = (nTrials, nChan, nFreq, nTap) dimArrs = (trList, chArr, freqArr, tpArr) # Determine whether we're dealing w/tf data isTimeFrequency = False if any([t.size > 1 for t in self.time]): isTimeFrequency = True # Ensure provided min/max range for plotting TF data makes sense vminmax = False if inputArgs.get("vmin", None) is not None: try: scalar_parser(inputArgs["vmin"], varname="vmin") except Exception as exc: raise exc vminmax = True if inputArgs.get("vmax", None) is not None: try: scalar_parser(inputArgs["vmax"], varname="vmax") except Exception as exc: raise exc vminmax = True if inputArgs.get("vmin", None) and inputArgs.get("vmax", None): if inputArgs["vmin"] >= inputArgs["vmax"]: lgl = "minimal data range bound to be less than provided maximum " act = "vmax < vmin" raise SPYValueError(legal=lgl, varname="vmin/vamx", actual=act) if vminmax and not isTimeFrequency: msg = "`vmin` and `vmax` is only used for time-frequency visualizations" SPYWarning(msg) # Check for complex entries in data and set datatype for plotting arrays # constructed below (always use floats w/same precision as data) if "complex" in self.data.dtype.name: msg = "Found complex Fourier coefficients - visualization will use absolute values." SPYWarning(msg) complexConversion = lambda x: np.absolute(x).real pltDtype = "f{}".format(self.data.dtype.itemsize) dataLbl = "Absolute Frequency [dB]" else: complexConversion = lambda x: x pltDtype = self.data.dtype dataLbl = "Power [dB]" return dimArrs, dimCounts, isTimeFrequency, complexConversion, pltDtype, dataLbl
def padding(data, padtype, pad="absolute", padlength=None, prepadlength=None, postpadlength=None, unit="samples", create_new=True): """ Perform data padding on Syncopy object or :class:`numpy.ndarray` **Usage Summary** Depending on the value of `pad` the following padding length specifications are supported: +------------+----------------------+---------------+----------------------+----------------------+ | `pad` | `data` | `padlength` | `prepadlength` | `postpadlength` | +============+======================+===============+======================+======================+ | 'absolute' | Syncopy object/array | number | `None`/`bool` | `None`/`bool` | +------------+----------------------+---------------+----------------------+----------------------+ | 'relative' | Syncopy object/array | number/`None` | number/`None`/`bool` | number/`None`/`bool` | +------------+----------------------+---------------+----------------------+----------------------+ | 'maxlen' | Syncopy object | `None`/`bool` | `None`/`bool` | `None`/`bool` | +------------+----------------------+---------------+----------------------+----------------------+ | 'nextpow2' | Syncopy object/array | `None`/`bool` | `None`/`bool` | `None`/`bool` | +------------+----------------------+---------------+----------------------+----------------------+ * `data` can be either a Syncopy object containing multiple trials or a :class:`numpy.ndarray` representing a single trial * (pre/post)padlength: can be either `None`, `True`/`False` or a positive number: if `True` indicates where to pad, e.g., by using ``pad = 'maxlen'`` and ``prepadlength = True``, `data` is padded at the beginning of each trial. **Only** if `pad` is 'relative' are scalar values supported for `prepadlength` and `postpadlength` * ``pad = 'absolute'``: pad to desired absolute length, e.g., by using ``pad = 5`` and ``unit = 'time'`` all trials are (if necessary) padded to 5s length. Here, `padlength` **has** to be provided, `prepadlength` and `postpadlength` can be `None` or `True`/`False` * ``pad = 'relative'``: pad by provided `padlength`, e.g., by using ``padlength = 20`` and ``unit = 'samples'``, 20 samples are padded symmetrically around (before and after) each trial. Use ``padlength = 20`` and ``prepadlength = True`` **or** directly ``prepadlength = 20`` to pad before each trial. Here, at least one of `padlength`, `prepadlength` or `postpadlength` **has** to be provided. * ``pad = 'maxlen'``: (only valid for **Syncopy objects**) pad up to maximal trial length found in `data`. All lengths have to be either Boolean indicating padding location or `None` (if all are `None`, symmetric padding is performed) * ``pad = 'nextpow2'``: pad each trial up to closest power of two. All lengths have to be either Boolean indicating padding location or `None` (if all are `None`, symmetric padding is performed) Full documentation below. Parameters ---------- data : Syncopy object or :class:`numpy.ndarray` Non-empty Syncopy data object or array representing numeric data to be padded. **NOTE**: if `data` is a :class:`numpy.ndarray`, it is assumed that it represents recordings from only a single trial, where its first axis corresponds to time. In other words, `data` is a 'time'-by-'channel' array such that its rows reflect samples and its columns represent channels. If `data` is a Syncopy object, trial information and dimensional order are fetched from `data.trials` and `data.dimord`, respectively. padtype : str Padding value(s) to be used. Available options are: * 'zero' : pad using zeros * 'nan' : pad using `np.nan`'s * 'mean' : pad with by-channel mean value across each trial * 'localmean' : pad with by-channel mean value using only `padlength` or `prepadlength`/`postpadlength` number of boundary-entries for averaging * 'edge' : pad with trial-boundary values * 'mirror' : pad with reflections of trial-boundary values pad : str Padding mode to be used. Available options are: * 'absolute' : pad each trial to achieve a desired absolute length such that all trials have identical length post padding. If `pad` is `absolute` a `padlength` **has** to be provided, `prepadlength` and `postpadlength` may be `True` or `False`, respectively (see Examples for details). * 'relative' : pad each trial by provided `padlength` such that all trials are extended by the same amount regardless of their original lengths. If `pad` is `relative`, `prepadlength` and `postpadlength` can either be specified directly (using numerical values) or implicitly by only providing `padlength` and setting `prepadlength` and `postpadlength` to `True` or `False`, respectively (see Examples for details). If `pad` is `relative` at least one of `padlength`, `prepadlength` or `postpadlength` **has** to be provided. * 'maxlen' : only usable if `data` is a Syncopy object. If `pad` is 'maxlen' all trials are padded to achieve the length of the longest trial in `data`, i.e., post padding, all trials have the same length, which equals the size of the longest trial pre-padding. For ``pad = 'maxlen'``, `padlength`, `prepadlength` as well as `postpadlength` have to be either Boolean or `None` indicating the preferred padding location (pre-trial, post-trial or symmetrically pre- and post-trial). If all are `None`, symmetric padding is performed (see Examples for details). * 'nextpow2' : pad each trial to achieve a length equals the closest power of two of its original length. For ``pad = 'nextpow2'``, `padlength`, `prepadlength` as well as `postpadlength` have to be either Boolean or `None` indicating the preferred padding location (pre-trial, post-trial or symmetrically pre- and post-trial). If all are `None`, symmetric padding is performed (see Examples for details). padlength : None, bool or positive scalar Length to be padded to `data` (if `padlength` is scalar-valued) or padding location (if `padlength` is Boolean). Depending on the value of `pad`, `padlength` can be used to pre-pend (if `padlength` is a positive number and `prepadlength` is `True`) or append trials (if `padlength` is a positive number and `postpadlength` is `True`). If neither `prepadlength` nor `postpadlength` are specified (i.e, both are `None`), symmetric pre- and post-trial padding is performed (i.e., ``0.5 * padlength`` before and after each trial - note that odd sample counts are rounded downward to the nearest even integer). If ``unit = 'time'``, `padlength` is assumed to be given in seconds, otherwise (``unit = 'samples'``), `padlength` is interpreted as sample-count. Note that only ``pad = 'relative'`` and ``pad = 'absolute'`` support numeric values of `padlength`. prepadlength : None, bool or positive scalar Length to be pre-pended before each trial (if `prepadlength` is scalar-valued) or pre-padding flag (if `prepadlength` is `True`). If `prepadlength` is `True`, pre-padding length is either directly inferred from `padlength` or implicitly derived from chosen padding mode defined by `pad`. If ``unit = 'time'``, `prepadlength` is assumed to be given in seconds, otherwise (``unit = 'samples'``), `prepadlength` is interpreted as sample-count. Note that only ``pad = 'relative'`` supports numeric values of `prepadlength`. postpadlength : None, bool or positive scalar Length to be appended after each trial (if `postpadlength` is scalar-valued) or post-padding flag (if `postpadlength` is `True`). If `postpadlength` is `True`, post-padding length is either directly inferred from `padlength` or implicitly derived from chosen padding mode defined by `pad`. If ``unit = 'time'``, `postpadlength` is assumed to be given in seconds, otherwise (``unit = 'samples'``), `postpadlength` is interpreted as sample-count. Note that only ``pad = 'relative'`` supports numeric values of `postpadlength`. unit : str Unit of numerical values given by `padlength` and/or `prepadlength` and/or `postpadlength`. If ``unit = 'time'``, `padlength`, `prepadlength`, and `postpadlength` are assumed to be given in seconds, otherwise (``unit = 'samples'``), `padlength`, `prepadlength`, and `postpadlength` are interpreted as sample-counts. **Note** Providing padding lengths in seconds (i.e., ``unit = 'time'``) is only supported if `data` is a Syncopy object. create_new : bool If `True`, a padded copy of the same type as `data` is returned (a :class:`numpy.ndarray` or Syncopy object). If `create_new` is `False`, either a single dictionary (if `data` is a :class:`numpy.ndarray`) or a ``len(data.trials)``-long list of dictionaries (if `data` is a Syncopy object) with all necessary options for performing the actual padding operation with :func:`numpy.pad` is returned. Returns ------- pad_dict : dict, if `data` is a :class:`numpy.ndarray` and ``create_new = False`` Dictionary whose items contain all necessary parameters for calling :func:`numpy.pad` to perform the desired padding operation on `data`. pad_dicts : list, if `data` is a Syncopy object and ``create_new = False`` List of dictionaries for calling :func:`numpy.pad` to perform the desired padding operation on all trials found in `data`. out : :class:`numpy.ndarray`, if `data` is a :class:`numpy.ndarray` and ``create_new = True`` Padded version (deep copy) of `data` out : Syncopy object, if `data` is a Syncopy object and ``create_new = True`` Padded version (deep copy) of `data` Notes ----- This method emulates (and extends) FieldTrip's `ft_preproc_padding` by providing a convenience wrapper for NumPy's :func:`numpy.pad` that performs the actual heavy lifting. Examples -------- Consider the following small array representing a toy-problem-trial of `ns` samples across `nc` channels: >>> nc = 7; ns = 30 >>> trl = np.random.randn(ns, nc) We start by padding a total of 10 zeros symmetrically to `trl` >>> padded = spy.padding(trl, 'zero', pad='relative', padlength=10) >>> padded[:6, :] array([[ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [-1.0866, 2.3358, 0.8758, 0.5196, 0.8049, -0.659 , -0.9173]]) >>> padded[-6:, :] array([[ 0.027 , 1.8069, 1.5249, -0.7953, -0.8933, 1.0202, -0.6862], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ], [ 0. , 0. , 0. , 0. , 0. , 0. , 0. ]]) >>> padded.shape (40, 7) Note that the above call is equivalent to >>> padded_ident = spy.padding(trl, 'zero', pad='relative', padlength=10, prepadlength=True, postpadlength=True) >>> np.array_equal(padded_ident, padded) True >>> padded_ident = spy.padding(trl, 'zero', pad='relative', prepadlength=5, postpadlength=5) >>> np.array_equal(padded_ident, padded) True Similarly, >>> prepad = spy.padding(trl, 'nan', pad='relative', prepadlength=10) is the same as >>> prepad_ident = spy.padding(trl, 'nan', pad='relative', padlength=10, prepadlength=True) >>> np.allclose(prepad, prepad_ident, equal_nan=True) True Define bogus trials on `trl` and create a dummy object with unit samplerate >>> tdf = np.vstack([np.arange(0, ns, 5), np.arange(5, ns + 5, 5), np.ones((int(ns / 5), )), np.ones((int(ns / 5), )) * np.pi]).T >>> adata = spy.AnalogData(trl, trialdefinition=tdf, samplerate=1) Pad each trial to the closest power of two by appending by-trial channel averages. However, do not perform actual padding, but only prepare dictionaries of parameters to be passed on to :func:`numpy.pad` >>> pad_dicts = spy.padding(adata, 'mean', pad='nextpow2', postpadlength=True, create_new=False) >>> len(pad_dicts) == len(adata.trials) True >>> pad_dicts[0] {'pad_width': array([[0, 3], [0, 0]]), 'mode': 'mean'} Similarly, the following call generates a list of dictionaries preparing absolute padding by prepending zeros with :func:`numpy.pad` >>> pad_dicts = spy.padding(adata, 'zero', pad='absolute', padlength=10, prepadlength=True, create_new=False) >>> pad_dicts[0] {'pad_width': array([[5, 0], [0, 0]]), 'mode': 'constant', 'constant_values': 0} See also -------- numpy.pad : fast array padding in NumPy """ # Detect whether input is data object or array-like if any(["BaseData" in str(base) for base in data.__class__.__mro__]): try: data_parser(data, varname="data", dataclass="AnalogData", empty=False) except Exception as exc: raise exc timeAxis = data.dimord.index("time") spydata = True elif data.__class__.__name__ == "FauxTrial": if len(data.shape) != 2: lgl = "two-dimensional AnalogData trial segment" act = "{}-dimensional trial segment" raise SPYValueError(legal=lgl, varname="data", actual=act.format(len(data.shape))) timeAxis = data.dimord.index("time") spydata = False else: try: array_parser(data, varname="data", dims=2) except Exception as exc: raise exc timeAxis = 0 spydata = False # FIXME: Creation of new spy-object currently not supported if not isinstance(create_new, bool): raise SPYTypeError(create_new, varname="create_new", expected="bool") if spydata and create_new: raise NotImplementedError( "Creation of padded spy objects currently not supported. ") # Use FT-compatible options (sans FT option 'remove') if not isinstance(padtype, str): raise SPYTypeError(padtype, varname="padtype", expected="string") options = ["zero", "nan", "mean", "localmean", "edge", "mirror"] if padtype not in options: lgl = "'" + "or '".join(opt + "' " for opt in options) raise SPYValueError(legal=lgl, varname="padtype", actual=padtype) # Check `pad` and ensure we can actually perform the requested operation if not isinstance(pad, str): raise SPYTypeError(pad, varname="pad", expected="string") options = ["absolute", "relative", "maxlen", "nextpow2"] if pad not in options: lgl = "'" + "or '".join(opt + "' " for opt in options) raise SPYValueError(legal=lgl, varname="pad", actual=pad) if pad == "maxlen" and not spydata: lgl = "syncopy data object when using option 'maxlen'" raise SPYValueError(legal=lgl, varname="pad", actual="maxlen") # Make sure a data object was provided if we're working with time values if not isinstance(unit, str): raise SPYTypeError(unit, varname="unit", expected="string") options = ["samples", "time"] if unit not in options: lgl = "'" + "or '".join(opt + "' " for opt in options) raise SPYValueError(legal=lgl, varname="unit", actual=unit) if unit == "time" and not spydata: raise SPYValueError( legal="syncopy data object when using option 'time'", varname="unit", actual="time") # Set up dictionary for type-checking of provided padding lengths nt_dict = {"samples": "int_like", "time": None} # If we're padding up to an absolute bound or the max. length across # trials, compute lower bound for padding (in samples or seconds) if pad in ["absolute", "maxlen"]: if spydata: maxTrialLen = np.diff(data.sampleinfo).max() else: maxTrialLen = data.shape[ timeAxis] # if `pad="absolute" and data is array else: maxTrialLen = np.inf if unit == "time": padlim = maxTrialLen / data.samplerate else: padlim = maxTrialLen # To ease option processing, collect padding length keywords in dict plengths = { "padlength": padlength, "prepadlength": prepadlength, "postpadlength": postpadlength } # In case of relative padding, we need at least one scalar value to proceed if pad == "relative": # If `padlength = None`, pre- or post- need to be set; if `padlength` # is set, both pre- and post- need to be `None` or `True`/`False`. # After this code block, pre- and post- are guaranteed to be numeric. if padlength is None: for key in ["prepadlength", "postpadlength"]: if plengths[key] is not None: try: scalar_parser(plengths[key], varname=key, ntype=nt_dict[unit], lims=[0, np.inf]) except Exception as exc: raise exc else: plengths[key] = 0 else: try: scalar_parser(padlength, varname="padlength", ntype=nt_dict[unit], lims=[0, np.inf]) except Exception as exc: raise exc for key in ["prepadlength", "postpadlength"]: if not isinstance(plengths[key], (bool, type(None))): raise SPYTypeError(plengths[key], varname=key, expected="bool or None") if prepadlength is None and postpadlength is None: prepadlength = True postpadlength = True else: prepadlength = prepadlength is not None postpadlength = postpadlength is not None if prepadlength and postpadlength: plengths["prepadlength"] = padlength / 2 plengths["postpadlength"] = padlength / 2 else: plengths["prepadlength"] = prepadlength * padlength plengths["postpadlength"] = postpadlength * padlength # Under-determined: abort if requested padding length is 0 if all(value == 0 for value in plengths.values() if value is not None): lgl = "either non-zero value of `padlength` or `prepadlength` " + \ "and/or `postpadlength` to be set" raise SPYValueError(legal=lgl, varname="padlength", actual="0|None") else: # For absolute padding, the desired length has to be >= max. trial length if pad == "absolute": try: scalar_parser(padlength, varname="padlength", ntype=nt_dict[unit], lims=[padlim, np.inf]) except Exception as exc: raise exc for key in ["prepadlength", "postpadlength"]: if not isinstance(plengths[key], (bool, type(None))): raise SPYTypeError(plengths[key], varname=key, expected="bool or None") # For `maxlen` or `nextpow2` we don't want any numeric entries at all else: for key, value in plengths.items(): if not isinstance(value, (bool, type(None))): raise SPYTypeError(value, varname=key, expected="bool or None") # Warn of potential conflicts if padlength and (prepadlength or postpadlength): msg = "Found `padlength` and `prepadlength` and/or " +\ "`postpadlength`. Symmetric padding is performed. " SPYWarning(msg) # If both pre-/post- are `None`, set them to `True` to use symmetric # padding, otherwise convert `None` entries to `False` if prepadlength is None and postpadlength is None: plengths["prepadlength"] = True plengths["postpadlength"] = True else: plengths["prepadlength"] = plengths["prepadlength"] is not None plengths["postpadlength"] = plengths["postpadlength"] is not None # Update pre-/post-padding and (if required) convert time to samples prepadlength = plengths["prepadlength"] postpadlength = plengths["postpadlength"] if unit == "time": if pad == "relative": prepadlength = int(prepadlength * data.samplerate) postpadlength = int(postpadlength * data.samplerate) elif pad == "absolute": padlength = int(padlength * data.samplerate) # Construct dict of keywords for ``np.pad`` depending on chosen `padtype` kws = { "zero": { "mode": "constant", "constant_values": 0 }, "nan": { "mode": "constant", "constant_values": np.nan }, "localmean": { "mode": "mean", "stat_length": -1 }, "mean": { "mode": "mean" }, "edge": { "mode": "edge" }, "mirror": { "mode": "reflect" } } # If in put was syncopy data object, padding is done on a per-trial basis if spydata: # A list of input keywords for ``np.pad`` is constructed, no matter if # we actually want to build a new object or not pad_opts = [] for trl in data.trials: nSamples = trl.shape[timeAxis] if pad == "absolute": padding = (padlength - nSamples) / (prepadlength + postpadlength) elif pad == "relative": padding = True elif pad == "maxlen": padding = (maxTrialLen - nSamples) / (prepadlength + postpadlength) elif pad == "nextpow2": padding = (_nextpow2(nSamples) - nSamples) / (prepadlength + postpadlength) pw = np.zeros((2, 2), dtype=int) pw[timeAxis, :] = [prepadlength * padding, postpadlength * padding] pad_opts.append(dict({"pad_width": pw}, **kws[padtype])) if padtype == "localmean": pad_opts[-1]["stat_length"] = pw[timeAxis, :] if create_new: pass else: return pad_opts # Input was a array/FauxTrial (i.e., single trial) - we have to do the padding just once else: nSamples = data.shape[timeAxis] if pad == "absolute": padding = (padlength - nSamples) / (prepadlength + postpadlength) elif pad == "relative": padding = True elif pad == "nextpow2": padding = (_nextpow2(nSamples) - nSamples) / (prepadlength + postpadlength) pw = np.zeros((2, 2), dtype=int) pw[timeAxis, :] = [prepadlength * padding, postpadlength * padding] pad_opts = dict({"pad_width": pw}, **kws[padtype]) if padtype == "localmean": pad_opts["stat_length"] = pw[timeAxis, :] if create_new: if isinstance(data, np.ndarray): return np.pad(data, **pad_opts) else: # FIXME: currently only supports FauxTrial shp = list(data.shape) shp[timeAxis] += pw[timeAxis, :].sum() idx = list(data.idx) if isinstance(idx[timeAxis], slice): idx[timeAxis] = slice(idx[timeAxis].start, idx[timeAxis].start + shp[timeAxis]) else: idx[timeAxis] = pw[timeAxis, 0] * [idx[timeAxis][0]] + idx[timeAxis] \ + pw[timeAxis, 1] * [idx[timeAxis][-1]] return data.__class__(shp, idx, data.dtype, data.dimord) else: return pad_opts
def test_none(self): with pytest.raises(SPYTypeError): scalar_parser(None, varname="value", ntype="int_like", lims=[10, 1000])
def test_complex_invalid(self): value = complex(2, -1) with pytest.raises(SPYValueError): scalar_parser(value, lims=[-3, 1])
def test_complex_valid(self): value = complex(2, -1) scalar_parser(value, lims=[-3, 5]) # valid