def _prep_toilim_avg(self):
"""
Set up averaging data across trials given `toilim` selection
Parameters
----------
self : Syncopy data object
Input object that is being processed by the respective :func:`~syncopy.singlepanelplot`
or :func:`~syncopy.multipanelplot` function/class method.
Returns
-------
tLengths : 1D :class:`numpy.ndarray`
Array of length `nSelectedTrials` with each element encoding the number of
samples contained in the provided `toilim` selection.
Notes
-----
If `tLengths` contains more than one unique element, a
:class:`~syncopy.shared.errors.SPYValueError` is raised.
Note further, that 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
--------
:func:`~syncopy.singlepanelplot` : visualize Syncopy objects using single-panel figure(s)
:func:`~syncopy.multipanelplot` : visualize Syncopy objects using multi-panel figure(s)
"""
tLengths = np.zeros((len(self._selection.trials), ), dtype=np.intp)
for k, tsel in enumerate(self._selection.time):
if not isinstance(tsel, slice):
msg = "Cannot average `toilim` selection. Please check `.time` property for consistency. "
raise SPYError(msg)
start, stop = tsel.start, tsel.stop
if start is None:
start = 0
if stop is None:
stop = self._get_time([self._selection.trials[k]],
toilim=[-np.inf, np.inf])[0].stop
tLengths[k] = stop - start
if np.unique(tLengths).size > 1:
lgl = "time-selections of equal length for averaging across trials"
act = "time-selections of varying length"
raise SPYValueError(legal=lgl, varname="toilim", actual=act)
if tLengths[0] < 2:
lgl = "time-selections containing at least two samples"
act = "time-selections containing fewer than two samples"
raise SPYValueError(legal=lgl, varname="toilim", actual=act)
return tLengths
def data_parser(data, varname="", dataclass=None, writable=None, empty=None, dimord=None):
"""
Docstring
writable = True/False/None
empty=True/False (False: ensure we're working with some contents)
"""
# Make sure `data` is (derived from) `BaseData`
if not any(["BaseData" in str(base) for base in data.__class__.__mro__]):
raise SPYTypeError(data, varname=varname, expected="Syncopy data object")
# If requested, check specific data-class of object
if dataclass is not None:
if data.__class__.__name__ not in str(dataclass):
msg = "Syncopy {} object".format(dataclass)
raise SPYTypeError(data, varname=varname, expected=msg)
# If requested, ensure object contains data (or not)
if empty is not None:
legal = "{status:s} Syncopy data object"
if empty and not data._is_empty():
raise SPYValueError(legal=legal.format(status="empty"),
varname=varname,
actual="non-empty")
elif not empty and data._is_empty():
raise SPYValueError(legal=legal.format(status="non-empty"),
varname=varname,
actual="empty")
# If requested, ensure proper access to object
if writable is not None:
legal = "{access:s} to Syncopy data object"
actual = "mode = {mode:s}"
if writable and data.mode == "r":
raise SPYValueError(legal=legal.format(access="write-access"),
varname=varname,
actual=actual.format(mode=data.mode))
elif not writable and data.mode != "r":
raise SPYValueError(legal=legal.format(access="read-only-access"),
varname=varname,
actual=actual.format(mode=data.mode))
# If requested, check integrity of dimensional information (if non-empty)
if dimord is not None:
base = "Syncopy {diminfo:s} data object"
if data.dimord != dimord:
legal = base.format(diminfo="'" + "' x '".join(str(dim) for dim in dimord) + "'")
actual = base.format(diminfo="'" + "' x '".join(str(dim) for dim in data.dimord)
+ "' " if data.dimord else "empty")
raise SPYValueError(legal=legal, varname=varname, actual=actual)
return
def pre_check(self):
'''
Make sure we have a trial average,
so the input data only consists of `1 trial`.
Can only be performed after initialization!
'''
if self.numTrials is None:
lgl = 'Initialize the computational Routine first!'
act = 'ComputationalRoutine not initialized!'
raise SPYValueError(legal=lgl,
varname=self.__class__.__name__,
actual=act)
if self.numTrials != 1:
lgl = "1 trial: Granger causality can only be computed on trial averages!"
act = f"DataSet contains {self.numTrials} trials"
raise SPYValueError(legal=lgl, varname="data", actual=act)
def data(self):
"""array-like object representing data without trials
Trials are concatenated along the time axis.
"""
if getattr(self._data, "id", None) is not None:
if self._data.id.valid == 0:
lgl = "open HDF5 file"
act = "backing HDF5 file {} has been closed"
raise SPYValueError(legal=lgl, actual=act.format(self.filename),
varname="data")
return self._data
def channel(self, chan):
if chan is None:
self._channel = None
return
if self.data is None:
raise SPYValueError("Syncopy: Cannot assign `channels` without data. " +
"Please assign data first")
try:
array_parser(chan, varname="channel", ntype="str")
except Exception as exc:
raise exc
# Remove duplicate entries from channel array but preserve original order
# (e.g., `[2, 0, 0, 1]` -> `[2, 0, 1`); allows for complex subset-selections
_, idx = np.unique(chan, return_index=True)
chan = np.array(chan)[np.sort(idx)]
nchan = np.unique(self.data[:, self.dimord.index("channel")]).size
if chan.size != nchan:
lgl = "channel label array of length {0:d}".format(nchan)
act = "array of length {0:d}".format(chan.size)
raise SPYValueError(legal=lgl, varname="channel", actual=act)
self._channel = chan
def unit(self, unit):
if unit is None:
self._unit = None
return
if self.data is None:
raise SPYValueError("Syncopy - SpikeData - unit: Cannot assign `unit` without data. " +
"Please assign data first")
nunit = np.unique(self.data[:, self.dimord.index("unit")]).size
try:
array_parser(unit, varname="unit", ntype="str", dims=(nunit,))
except Exception as exc:
raise exc
self._unit = np.array(unit)
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 channel(self, channel):
if channel is None:
self._channel = None
return
if self.avg is None:
raise SPYValueError(
"Syncopy: Cannot assign `channels` without data. " +
"Please assign data first")
try:
array_parser(channel,
varname="channel",
ntype="str",
dims=(self.avg.shape[self.dimord.index("channel")], ))
except Exception as exc:
raise exc
self._channel = np.array(channel)
def channel_j(self, channel_j):
""" :class:`numpy.ndarray` : list of channel labels """
if channel_j is None:
self._channel_j = None
return
if self.data is None:
raise SPYValueError(
"Syncopy: Cannot assign `channels` without data. " +
"Please assign data first")
try:
array_parser(
channel_j,
varname="channel_j",
ntype="str",
dims=(self.data.shape[self.dimord.index("channel_j")], ))
except Exception as exc:
raise exc
self._channel_j = np.array(channel_j)
def _sizeof(self, obj):
"""
Estimate memory consumption of Python objects
Parameters
----------
obj : Python object
Any valid Python object whose memory footprint is of interest.
Returns
-------
objsize : float
Approximate memory footprint of `obj` in megabytes (MB).
Notes
-----
Memory consumption is is estimated by recursively calling :meth:`sys.getsizeof`.
Circular object references are followed up to a (preset) maximal recursion
depth. This method was inspired by a routine in
`Nifty <https://github.com/mwojnars/nifty/blob/master/util.py>`_.
"""
# Protect against circular object references by adhering to max. no. of
# recursive calls `self._callMax`
self._callCount += 1
if self._callCount >= self._callMax:
lgl = "minimally nested positional arguments"
act = "argument with nesting depth >= {}"
raise SPYValueError(legal=lgl, varname="argv", actual=act.format(self._callMax))
# Use `sys.getsizeof` to estimate memory consumption of primitive objects
objsize = sys.getsizeof(obj) / 1024**2
if isinstance(obj, dict):
return objsize + sum(list(map(self._sizeof, obj.keys()))) + sum(list(map(self._sizeof, obj.values())))
if isinstance(obj, (list, tuple, set)):
return objsize + sum(list(map(self._sizeof, obj)))
return objsize
def filename_parser(filename, is_in_valid_container=None):
"""Extract information from Syncopy file and folder names
Parameters
----------
filename: str
Syncopy data file (\*.<dataclass>.info), Syncopy info
file (\*.<dataclass>) or Syncopy container folder (\*.spy)
is_in_valid_container: bool
If `True`, the `filename` must be inside a folder with a .spy
extension.
If `False`, `filename` must not be inside a .spy folder.
If `None`, the extension of the parent folder is not checked.
Returns
-------
fileinfo : dict
Information extracted from filename and foldername with keys
['filename', 'container', 'folder', 'tag', 'basename', 'extension'].
Examples
--------
>>> filename_parser('/home/user/monkeyB_20190709_rfmapping_1_amua-stimon.analog')
{'filename': 'monkeyB_20190709_rfmapping_1_amua-stimon.analog',
'container': None,
'folder': '/home/schmiedtj_it/Projects/SyNCoPy',
'tag': None,
'basename': 'monkeyB_20190709_rfmapping_1_amua-stimon',
'extension': '.analog'}
>>> filename_parser('/home/user/monkeyB_20190709_rfmapping_1_amua-stimon.analog.info')
{'filename': 'monkeyB_20190709_rfmapping_1_amua-stimon.analog',
'container': None,
'folder': '/home/user',
'tag': None,
'basename': 'monkeyB_20190709_rfmapping_1_amua-stimon',
'extension': '.analog'}
>>> filename_parser('session_1.spy/session_1_amua-stimon.analog')
{'filename': 'session_1_amua-stimon.analog',
'container': 'session_1.spy',
'folder': '/home/user/session_1.spy',
'tag': 'amua-stimon',
'basename': 'session_1',
'extension': '.analog'}
>>> filename_parser('session_1.spy')
{'filename': None,
'container': 'session_1.spy',
'folder': '/home/user',
'tag': None,
'basename': 'session_1',
'extension': '.spy'}
See also
--------
io_parser : check file and folder names for existence
"""
if filename is None:
return {
"filename": None,
"container": None,
"folder": None,
"tag": None,
"basename": None,
"extension": None
}
filename = os.path.abspath(os.path.expanduser(filename))
folder, filename = os.path.split(filename)
container = folder.split(os.path.sep)[-1]
basename, ext = os.path.splitext(filename)
if filename.count(".") > 2:
raise SPYValueError(legal="single extension, found {}".format(filename.count(".")),
actual=filename, varname="filename")
if ext == FILE_EXT["dir"] and basename.count(".") > 0:
raise SPYValueError(legal="no extension, found {}".format(basename.count(".")),
actual=basename, varname="container")
if ext == FILE_EXT["info"]:
filename = basename
basename, ext = os.path.splitext(filename)
elif ext == FILE_EXT["dir"]:
return {
"filename": None,
"container": filename,
"folder": folder,
"tag": None,
"basename": basename,
"extension": ext
}
if ext not in FILE_EXT["data"] + (FILE_EXT["dir"],):
raise SPYValueError(legal=FILE_EXT["data"],
actual=ext, varname="filename extension")
folderExtIsSpy = os.path.splitext(container)[1] == FILE_EXT["dir"]
if is_in_valid_container is not None:
if not folderExtIsSpy and is_in_valid_container:
raise SPYValueError(legal=FILE_EXT["dir"],
actual=os.path.splitext(container)[1],
varname="folder extension")
elif folderExtIsSpy and not is_in_valid_container:
raise SPYValueError(legal='not ' + FILE_EXT["dir"],
actual=os.path.splitext(container)[1],
varname="folder extension")
if folderExtIsSpy:
containerBasename = os.path.splitext(container)[0]
if not basename.startswith(containerBasename):
raise SPYValueError(legal=containerBasename,
actual=filename,
varname='start of filename')
tag = basename.partition(containerBasename)[-1]
if tag == "":
tag = None
else:
if tag[0] == '_': tag = tag[1:]
basename = containerBasename
else:
container = None
tag = None
return {
"filename": filename,
"container": container,
"folder": folder,
"tag": tag,
"basename": basename,
"extension": ext
}
def array_parser(var, varname="", ntype=None, hasinf=None, hasnan=None,
lims=None, dims=None, issorted=None):
"""
Parse array-like objects
Parameters
----------
var : array_like
Array object to verify
varname : str
Local variable name used in caller, see Examples for details.
ntype : None or str
Expected data type of `var`. Possible options are any valid
builtin type, all NumPy dtypes as as well as `"numeric"` (a catch-all
to ensure `var` only contains numeric elements) and "int_like"`
(all elements of `var` are expected to have no significant digits
after the decimal point, e.g., 3.0, -12.0 etc.).
If `ntype` is `None` the data type of `var` is not checked.
hasinf : None or bool
If `hasinf` is `False` the input array `var` is considered invalid
if it contains non-finite elements (`np.inf`), vice-versa if `hasinf`
is `True`. If `hasinf` is `None` elements of `var` are not probed
for finiteness.
hasnan : None or bool
If `hasnan` is `False` the input array `var` is considered invalid
if it contains undefined elements (`np.nan`), vice-versa if `hasnan`
is `True`. If `hasnan` is `None` elements of `var` are not probed
for well-posedness.
lims : None or two-element list_like
Lower (`lims[0]`) and upper (`lims[1]`) bounds for legal values of `var`'s
elements. Note that the code checks for non-strict inequality,
i.e., `var[i] = lims[0]` or `var[i] = lims[1]` are both considered
to be valid elements of `var`.
For complex arrays bounds-checking is performed on both real and
imaginary parts of each component of `var`. That is, all elements of
`var` have to satisfy `lims[0] <= var[i].real <= lims[1]` as well as
`lims[0] <= var[i].imag <= lims[1]` (see Examples for details).
Note that `np.inf` and `np.nan` entries are ignored during bounds-
checking. Use the keywords `hasinf` and `hasnan` to probe an array
for infinite and non-numeric entries, respectively.
If `lims` is `None` bounds-checking is not performed.
dims : None or int or tuple
Expected number of dimensions (if `dims` is an integer) or shape
(if `dims` is a tuple) of `var`. By default, singleton dimensions
of `var` are ignored if `dims` is a tuple, i.e., for `dims = (10, )`
an array `var` with `var.shape = (10, 1)` is considered valid. However,
if singleton dimensions are explicitly queried by setting `dims = (10, 1)`
any array `var` with `var.shape = (10, )` or `var.shape = (1, 10)` is
considered invalid.
Unknown dimensions can be represented as `None`, i.e., for
`dims = (10, None)` arrays with shape `(10, 1)`, `(10, 100)` or
`(10, 0)` are all considered valid, however, any 1d-array (e.g.,
`var.shape = (10,)`) is invalid.
If `dims` is an integer, `var.ndim` has to match `dims` exactly, i.e.,
any array `var` with `var.shape = (10, )` is considered invalid if
`dims = 2` and conversely, `dims = 1` and `var.shape = (10, 1)`
triggers an exception.
issorted : None or bool
If `issorted` is `True`, `var` is expected to be a 1d-array (or 2d-array
with a single singleton-dimension, i.e., a row- or column-vector) with
elements in ascending order. Conversely, if `issorted` is `False`, `var`
is considered invalid if its elements are ordered by magnitude. If
`issorted` is `None`, order of array elements is not inspected.
Returns
-------
Nothing : None
Examples
--------
Assume `time` is supposed to be a 1d-array with floating point components
bounded by 0 and 10. The following calls confirm the validity of `time`
>>> time = np.linspace(0, 10, 100)
>>> array_parser(time, varname="time", lims=[0, 10], dims=1)
>>> array_parser(time, varname="time", lims=[0, 10], dims=(100,))
Ensure additionally that all elements of `time` are ordered by magnitude
>>> array_parser(time, varname="time", lims=[0, 10], dims=(100,), issorted=True)
Artificially appending a singleton dimension to `time` does not affect
parsing:
>>> time = time[:,np.newaxis]
>>> time.shape
(100, 1)
>>> array_parser(time, varname="time", lims=[0, 10], dims=(100,), issorted=True)
However, explicitly querying for a row-vector fails
>>> array_parser(time, varname="time", lims=[0, 10], dims=(1,100))
Complex arrays are parsed analogously:
>>> spec = np.array([np.complex(2,3), np.complex(2,-2)])
>>> array_parser(spec, varname="spec", dims=1)
>>> array_parser(spec, varname="spec", dims=(2,))
Note that bounds-checking is performed component-wise on both real and
imaginary parts:
>>> array_parser(spec, varname="spec", lims=[-3, 5]) # valid
>>> array_parser(spec, varname="spec", lims=[-1, 5]) # invalid since spec[1].imag < lims[0]
However, complex numbers do not admit an order relationship:
>>> array_parser(spec, varname="spec", lims=[-3, 5], issorted=True) # invalid
Character lists can be parsed as well:
>>> channels = ["channel1", "channel2", "channel3"]
>>> array_parser(channels, varname="channels", dims=1)
>>> array_parser(channels, varname="channels", dims=(3,))
See also
--------
scalar_parser : similar functionality for parsing numeric scalars
"""
# Make sure `var` is array-like and convert it to ndarray to simplify parsing
if not isinstance(var, (np.ndarray, list)):
raise SPYTypeError(var, varname=varname, expected="array_like")
arr = np.array(var)
# If bounds-checking is requested but `ntype` is not set, use the
# generic "numeric" option to ensure array is actually numeric
if (lims is not None or hasnan is not None or hasinf is not None) and ntype is None:
ntype = "numeric"
# If array-element order parsing is requested by `ntype` and/or `dims` are not
# set, use sane defaults to ensure array is numeric and one-dimensional
if issorted is not None:
if ntype is None:
ntype = "numeric"
if dims is None:
dims = (None, )
# If required, parse type (handle "int_like" and "numeric" separately)
if ntype is not None:
msg = "dtype = {dt:s}"
if ntype in ["numeric", "int_like"]:
if not np.issubdtype(arr.dtype, np.number):
raise SPYValueError(msg.format(dt="numeric"), varname=varname,
actual=msg.format(dt=str(arr.dtype)))
if ntype == "int_like":
if not np.all([np.round(a) == a for a in arr]):
raise SPYValueError(msg.format(dt=ntype), varname=varname)
else:
if not np.issubdtype(arr.dtype, np.dtype(ntype).type):
raise SPYValueError(msg.format(dt=ntype), varname=varname,
actual=msg.format(dt=str(arr.dtype)))
# If required, parse finiteness of array-elements
if hasinf is not None:
if not hasinf and np.isinf(arr).any():
lgl = "finite numerical array"
act = "array with {} `inf` entries".format(str(np.isinf(arr).sum()))
raise SPYValueError(legal=lgl, varname=varname, actual=act)
if hasinf and not np.isinf(arr).any():
lgl = "numerical array with infinite (`np.inf`) entries"
act = "finite numerical array"
raise SPYValueError(legal=lgl, varname=varname, actual=act)
# If required, parse well-posedness of array-elements
if hasnan is not None:
if not hasnan and np.isnan(arr).any():
lgl = "well-defined numerical array"
act = "array with {} `NaN` entries".format(str(np.isnan(arr).sum()))
raise SPYValueError(legal=lgl, varname=varname, actual=act)
if hasnan and not np.isnan(arr).any():
lgl = "numerical array with undefined (`np.nan`) entries"
act = "well-defined numerical array"
raise SPYValueError(legal=lgl, varname=varname, actual=act)
# If required perform component-wise bounds-check (remove NaN's and Inf's first)
if lims is not None:
fi_arr = arr[np.isfinite(arr)]
if np.issubdtype(fi_arr.dtype, np.dtype("complex").type):
amin = min(fi_arr.real.min(), fi_arr.imag.min())
amax = max(fi_arr.real.max(), fi_arr.imag.max())
else:
amin = fi_arr.min()
amax = fi_arr.max()
if amin < lims[0] or amax > lims[1]:
legal = "all array elements to be bounded by {lb:s} and {ub:s}"
raise SPYValueError(legal.format(lb=str(lims[0]), ub=str(lims[1])),
varname=varname)
# If required parse dimensional layout of array
if dims is not None:
# Account for the special case of 1d character arrays (that
# collapse to 0d-arrays when squeezed)
ischar = int(np.issubdtype(arr.dtype, np.dtype("str").type))
# Compare shape or dimension number
if isinstance(dims, tuple):
if len(dims) > 1:
ashape = arr.shape
else:
if arr.size == 1:
ashape = arr.shape
else:
ashape = max((ischar,), arr.squeeze().shape)
if len(dims) != len(ashape):
msg = "{}-dimensional array"
raise SPYValueError(legal=msg.format(len(dims)), varname=varname,
actual=msg.format(len(ashape)))
for dk, dim in enumerate(dims):
if dim is not None and ashape[dk] != dim:
raise SPYValueError("array of shape " + str(dims),
varname=varname, actual="shape = " + str(arr.shape))
else:
ndim = max(ischar, arr.ndim)
if ndim != dims:
raise SPYValueError(str(dims) + "d-array", varname=varname,
actual=str(ndim) + "d-array")
# If required check if array elements are orderd by magnitude
if issorted is not None:
if not np.all(np.isreal(arr)):
lgl = "real-valued array"
act = "array containing complex elements"
raise SPYValueError(legal=lgl, varname=varname, actual=act)
if arr.size <= 1:
lgl = "array with at least two elements"
act = "array containing (fewer than) one element"
raise SPYValueError(legal=lgl, varname=varname, actual=act)
ascending = np.diff(arr.flatten()).min() > 0
if issorted and not ascending:
lgl = "array with elements in ascending order"
act = "unsorted array"
raise SPYValueError(legal=lgl, varname=varname, actual=act)
if not issorted and ascending:
lgl = "unsorted array"
act = "array with elements in ascending order"
raise SPYValueError(legal=lgl, varname=varname, actual=act)
return
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 scalar_parser(var, varname="", ntype=None, lims=None):
"""
Parse scalars
Parameters
----------
var : scalar
Scalar quantity to verify
varname : str
Local variable name used in caller, see Examples for details.
ntype : None or str
Expected numerical type of `var`. Possible options include any valid
builtin type as well as `"int_like"` (`var` is expected to have
no significant digits after its decimal point, e.g., 3.0, -12.0 etc.).
If `ntype` is `None` the numerical type of `var` is not checked.
lims : None or two-element list_like
Lower (`lims[0]`) and upper (`lims[1]`) bounds for legal values of `var`.
Note that the code checks for non-strict inequality, i.e., `var = lims[0]` or
`var = lims[1]` are both considered to be valid values of `var`.
Using `lims = [-np.inf, np.inf]` may be employed to ensure that `var` is
finite and non-NaN. For complex scalars bounds-checking is performed
element-wise, that is both real and imaginary part of `var` have to be
inside the bounds provided by `lims` (see Examples for details).
If `lims` is `None` bounds-checking is not performed.
Returns
-------
Nothing : None
Examples
--------
Assume `freq` is supposed to be a scalar with integer-like values between
10 and 1000. The following calls confirm the validity of `freq`
>>> freq = 440
>>> scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000])
>>> freq = 440.0
>>> scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000])
Conversely, these values of `freq` yield errors
>>> freq = 440.5 # not integer-like
>>> scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000])
>>> freq = 2 # outside bounds
>>> scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000])
>>> freq = '440' # not a scalar
>>> scalar_parser(freq, varname="freq", ntype="int_like", lims=[10, 1000])
For complex scalars bounds-checking is performed element-wise on both
real and imaginary part:
>>> scalar_parser(complex(2,-1), lims=[-3, 5]) # valid
>>> scalar_parser(complex(2,-1), lims=[-3, 1]) # invalid since real part is greater than 1
See also
--------
array_parser : similar functionality for parsing array-like objects
"""
# Make sure `var` is a scalar-like number
if not isinstance(var, numbers.Number):
raise SPYTypeError(var, varname=varname, expected="scalar")
# If required, parse type ("int_like" is a bit of a special case here...)
if ntype is not None:
if ntype == "int_like":
if np.round(var) != var:
raise SPYValueError(ntype, varname=varname, actual=str(var))
else:
if type(var) != getattr(__builtins__, ntype):
raise SPYTypeError(var, varname=varname, expected=ntype)
# If required perform bounds-check: transform scalar to NumPy array
# to be able to handle complex scalars too
if lims is not None:
if isinstance(var, complex):
val = np.array([var.real, var.imag])
legal = "both real and imaginary part to be "
else:
val = np.array([var])
legal = "value to be "
if np.any(val < lims[0]) or np.any(val > lims[1]) or not np.isfinite(var):
legal += "greater or equals {lb:s} and less or equals {ub:s}"
raise SPYValueError(legal.format(lb=str(lims[0]), ub=str(lims[1])),
varname=varname, actual=str(var))
return
def io_parser(fs_loc, varname="", isfile=True, ext="", exists=True):
"""
Parse file-system location strings for reading/writing files/directories
Parameters
----------
fs_loc : str
String pointing to (hopefully valid) file-system location
(absolute/relative path of file or directory ).
varname : str
Local variable name used in caller, see Examples for details.
isfile : bool
Indicates whether `fs_loc` points to a file (`isfile = True`) or
directory (`isfile = False`)
ext : str or 1darray-like
Valid filename extension(s). Can be a single string (e.g., `ext = "lfp"`)
or a list/1darray of valid extensions (e.g., `ext = ["lfp", "mua"]`).
exists : bool
If `exists = True` ensure that file-system location specified by `fs_loc` exists
(typically used when reading from `fs_loc`), otherwise (`exists = False`)
check for already present conflicting files/directories (typically used when
creating/writing to `fs_loc`).
Returns
-------
fs_path : str
Absolute path of `fs_loc`.
fs_name : str (only if `isfile = True`)
Name (including extension) of input file (without path).
Examples
--------
To test whether `"/path/to/dataset.lfp"` points to an existing file, one
might use
>>> io_parser("/path/to/dataset.lfp")
'/path/to', 'dataset.lfp'
The following call ensures that a folder called "mydata" can be safely
created in the current working directory
>>> io_parser("mydata", isfile=False, exists=False)
'/path/to/cwd/mydata'
Suppose a routine wants to save data to a file with potential
extensions `".lfp"` or `".mua"`. The following call may be used to ensure
the user input `dsetname = "relative/dir/dataset.mua"` is a valid choice:
>>> abs_path, filename = io_parser(dsetname, varname="dsetname", ext=["lfp", "mua"], exists=False)
>>> abs_path
'/full/path/to/relative/dir/'
>>> filename
'dataset.mua'
"""
# Start by resovling potential conflicts
if not isfile and len(ext) > 0:
msg = "filename extension(s) specified but `isfile = False`. Exiting..."
SPYWarning(msg)
return
# Make sure `fs_loc` is actually a string
if not isinstance(fs_loc, str):
raise SPYTypeError(fs_loc, varname=varname, expected=str)
# Avoid headaches, use absolute paths...
fs_loc = os.path.abspath(os.path.expanduser(fs_loc))
# Ensure that filesystem object does/does not exist
if exists and not os.path.exists(fs_loc):
raise SPYIOError(fs_loc, exists=False)
if not exists and os.path.exists(fs_loc):
raise SPYIOError(fs_loc, exists=True)
# First, take care of directories...
if not isfile:
isdir = os.path.isdir(fs_loc)
if (isdir and not exists):
raise SPYIOError (fs_loc, exists=isdir)
elif (not isdir and exists):
raise SPYValueError(legal="directory", actual="file")
else:
return fs_loc
# ...now files
else:
# Separate filename from its path
file_name = os.path.basename(fs_loc)
# If wanted, parse filename extension(s)
if len(ext):
# Extract filename extension and get rid of its dot
file_ext = os.path.splitext(file_name)[1]
file_ext = file_ext.replace(".", "")
# In here, having no extension counts as an error
error = False
if len(file_ext) == 0:
error = True
if file_ext not in str(ext) or error:
if isinstance(ext, (list, np.ndarray)):
ext = "'" + "or '".join(ex + "' " for ex in ext)
raise SPYValueError(ext, varname="filename-extension", actual=file_ext)
# Now make sure file does or does not exist
isfile = os.path.isfile(fs_loc)
if (isfile and not exists):
raise SPYIOError(fs_loc, exists=isfile)
elif (not isfile and exists):
raise SPYValueError(legal="file", actual="directory")
else:
return fs_loc.split(file_name)[0], file_name
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 csd(trl_dat,
samplerate=1,
nSamples=None,
taper="hann",
taper_opt=None,
norm=False,
fullOutput=False):
"""
Single trial Fourier cross spectral estimates between all channels
of the input data. First all the individual Fourier transforms
are calculated via a (multi-)tapered FFT, then the pairwise
cross-spectra are computed.
Averaging over tapers is done implicitly
for multi-taper analysis with `taper="dpss"`.
Output consists of all (``nChannels x nChannels + 1) / 2`` different complex
estimates arranged in a symmetric fashion (``CS_ij == CS_ji*``). The
elements on the main diagonal (`CS_ii`) are the (real) auto-spectra.
This is NOT the same as what is commonly referred to as
"cross spectral density" as there is no (time) averaging!!
Multi-tapering alone is not necessarily sufficient to get enough
statitstical power for a robust csd estimate. Yet for completeness
and testing the option ``norm = True`` returns a single-trial
coherence estimate for ``taper = "dpss"``.
Parameters
----------
trl_dat : (N, K) :class:`numpy.ndarray`
Uniformly sampled multi-channel time-series data
The 1st dimension is interpreted as the time axis,
columns represent individual channels.
samplerate : float
Samplerate in Hz
nSamples : int or None
Absolute length of the (potentially to be padded) signals
or `None` for no padding (`N` is the number of samples)
taper : str or None
Taper function to use, one of :module:`scipy.signal.windows`
Set to `None` for no tapering.
taper_opt : dict, optional
Additional keyword arguments passed to the `taper` function.
For multi-tapering with ``taper = 'dpss'`` set the keys
`'Kmax'` and `'NW'`.
For further details, please refer to the
`SciPy docs <https://docs.scipy.org/doc/scipy/reference/signal.windows.html>`_
norm : bool, optional
Set to `True` to normalize for a single-trial coherence measure.
Only meaningful in a multi-taper (``taper = "dpss"``) setup and if no
additional (trial-)averaging is performed afterwards.
fullOutput : bool
For backend testing or stand-alone applications, set to `True`
to return also the `freqs` array.
Returns
-------
CS_ij : (nFreq, K, K) :class:`numpy.ndarray`
Complex cross spectra for all channel combinations ``i,j``.
`K` corresponds to number of input channels.
freqs : (nFreq,) :class:`numpy.ndarray`
The Fourier frequencies if ``fullOutput = True``
See also
--------
normalize_csd : :func:`~syncopy.connectivity.csd.normalize_csd`
Coherence from trial averages
mtmfft : :func:`~syncopy.specest.mtmfft.mtmfft`
(Multi-)tapered Fourier analysis
"""
# compute the individual spectra
# specs have shape (nTapers x nFreq x nChannels)
specs, freqs = mtmfft(trl_dat, samplerate, nSamples, taper, taper_opt)
# outer product along channel axes
# has shape (nTapers x nFreq x nChannels x nChannels)
CS_ij = specs[:, :, np.newaxis, :] * specs[:, :, :, np.newaxis].conj()
# average tapers and transpose:
# now has shape (nChannels x nChannels x nFreq)
CS_ij = CS_ij.mean(axis=0).T
if norm:
# only meaningful for multi-tapering
if taper != 'dpss':
msg = "Normalization of single trial csd only possible with taper='dpss'"
raise SPYValueError(legal=msg, varname="taper", actual=taper)
# main diagonal has shape (nChannels x nFreq): the auto spectra
diag = CS_ij.diagonal()
# get the needed product pairs of the autospectra
Ciijj = np.sqrt(diag[:, :, None] * diag[:, None, :]).T
CS_ij = CS_ij / Ciijj
if fullOutput:
return CS_ij.transpose(2, 0, 1), freqs
else:
return CS_ij.transpose(2, 0, 1)
def _prep_analog_plots(self, name, **inputArgs):
"""
Local helper that performs sanity checks and sets up data selection
Parameters
----------
self : :class:`~syncopy.AnalogData` object
Syncopy :class:`~syncopy.AnalogData` 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
Tuple containing (in this order) `trList`, list of (selected)
trials to visualize and `chArr`, 1D :class:`numpy.ndarray` of channel specifiers
based on provided user selection. Note that `"all"` and `None` selections
are converted to arrays ready for indexing.
dimCounts : tuple
Tuple holding sizes of corresponding selection arrays comprised
in `dimArrs`. Elements are `nTrials`, number of (selected) trials and `nChan`,
number of (selected) channels.
idx : list
Three element indexing list (respecting non-default `dimord`s) intended
for use with trial-array data.
timeIdx : int
Position of time-axis within indexing list `idx` (either 0 or 1).
chanIdx : int
Position of channel-axis within indexing list `idx` (either 0 or 1).
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.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"],
"toilim": inputArgs["toilim"]
}
# 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 and channel counts
if inputArgs["trials"] is None:
trList = []
nTrials = 0
if inputArgs["toilim"] is not None:
lgl = "`trials` to be not `None` to perform timing selection"
act = "`toilim` was provided but `trials` is `None`"
raise SPYValueError(legal=lgl, varname="trials/toilim", actual=act)
else:
trList = self._selection.trials
nTrials = len(trList)
chArr = self.channel[self._selection.channel]
nChan = chArr.size
# Collect arrays and counts in tuples
dimCounts = (nTrials, nChan)
dimArrs = (trList, chArr)
# Prepare indexing list respecting potential non-default `dimord`s
idx = [slice(None), slice(None)]
chanIdx = self.dimord.index("channel")
timeIdx = self.dimord.index("time")
idx[chanIdx] = self._selection.channel
return dimArrs, dimCounts, idx, timeIdx, chanIdx
def best_match(source,
selection,
span=False,
tol=None,
squash_duplicates=False):
"""
Find matching elements in a given 1d-array/list
Parameters
----------
source : NumPy 1d-array/list
Reference array whose elements are to be matched by `selection`
selection: NumPy 1d-array/list
Array of query-values whose closest matches are to be found in `source`.
Note that `source` and `selection` need not be the same length.
span : bool
If `True`, `selection` is interpreted as (closed) interval ``[lo, hi]`` and
`source` is queried for all elements contained in the interval, i.e.,
``lo <= src <= hi for src in source`` (typically used for
`toilim`/`foilim`-like selections).
tol : None or float
If `None` for each component of `selection` the closest value in `source`
is selected, e.g., for ``source = [10, 20]`` and ``selection = [-50, 0, 50]``
the closest values are `[10, 10, 20]`.
If not `None`, ensures values in `selection` do not deviate further
than `tol` from `source`. If any element `sel` of `selection` is outside
a `tol`-neighborhood around `source`, i.e.,
``np.abs(sel - source).max() >= tol``,
a :class:`~syncopy.shared.errors.SPYValueError` is raised.
squash_duplicates : bool
If `True`, identical matches are removed from the result.
Returns
-------
values : NumPy 1darray
Values of `source` that most closely match given elements in `selection`
idx : NumPy 1darray
Indices of `values` with respect to `source`, such that,
``source[idx] == values``
Notes
-----
This is an auxiliary method that is intended purely for internal use. Thus,
no error checking is performed.
Examples
--------
Exact matching, ordered `source` and `selection`:
>>> best_match(np.arange(10), [2,5])
(array([2, 5]), array([2, 5]))
Inexact matching, ordered `source` and `selection`:
>>> source = np.arange(10)
>>> selection = np.array([1.5, 1.5, 2.2, 6.2, 8.8])
>>> best_match(source, selection)
(array([2, 2, 2, 6, 9]), array([2, 2, 2, 6, 9]))
Inexact matching, unordered `source` and `selection`:
>>> source = np.array([2.2, 1.5, 1.5, 6.2, 8.8])
>>> selection = np.array([1.9, 9., 1., -0.4, 1.2, 0.2, 9.3])
>>> best_match(source, selection)
(array([2.2, 8.8, 1.5, 1.5, 1.5, 1.5, 8.8]), array([0, 4, 1, 1, 1, 1, 4]))
Same as above, but ignore duplicate matches
>>> best_match(source, selection, squash_duplicates=True)
(array([2.2, 8.8, 1.5]), array([0, 4, 1]))
Interval-matching:
>>> best_match(np.arange(10), [2.9, 6.1], span=True)
(array([3, 4, 5, 6]), array([3, 4, 5, 6]))
"""
# Make `source` a NumPy array if necessary
if isinstance(source, list):
source = np.array(source)
# Ensure selection is within `tol` bounds from `source`
if tol is not None:
if not np.all(
[np.all((np.abs(source - value)) < tol) for value in selection]):
lgl = "all elements of `selection` to be within a {0:2.4f}-band around `source`"
act = "values in `selection` deviating further than given tolerance " +\
"of {0:2.4f} from source"
raise SPYValueError(legal=lgl.format(tol),
varname="selection",
actual=act.format(tol))
# Do not perform O(n) potentially unnecessary sort operations...
issorted = True
# Interval-selections are a lot easier than discrete time-points...
if span:
idx = np.intersect1d(
np.where(source >= selection[0])[0],
np.where(source <= selection[1])[0])
else:
issorted = True
if np.diff(source).min() < 0:
issorted = False
orig = np.array(source, copy=True)
idx_orig = np.argsort(orig)
source = orig[idx_orig]
idx = np.searchsorted(source, selection, side="left")
leftNbrs = np.abs(
selection -
source[np.maximum(idx - 1, np.zeros(idx.shape, dtype=np.intp))])
rightNbrs = np.abs(selection - source[np.minimum(
idx, np.full(idx.shape, source.size - 1, dtype=np.intp))])
shiftLeft = ((idx == source.size) | (leftNbrs < rightNbrs))
idx[shiftLeft] -= 1
# Account for potentially unsorted selections (and thus unordered `idx`)
if squash_duplicates:
_, xdi = np.unique(idx.astype(np.intp), return_index=True)
idx = idx[np.sort(xdi)]
# Re-order discrete-selection index arrays in case `source` was unsorted
if not issorted and not span:
idx_sort = idx_orig[idx]
return orig[idx_sort], idx_sort
else:
return source[idx], idx
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 multipanelplot(self,
trials="all",
channels="all",
toilim=None,
avg_channels=False,
avg_trials=True,
title=None,
grid=None,
fig=None,
**kwargs):
"""
Plot contents of :class:`~syncopy.AnalogData` objects using multi-panel figure(s)
Please refer to :func:`syncopy.multipanelplot` for detailed usage information.
Examples
--------
Use :func:`~syncopy.tests.misc.generate_artificial_data` to create two synthetic
:class:`~syncopy.AnalogData` objects.
>>> from syncopy.tests.misc import generate_artificial_data
>>> adata = generate_artificial_data(nTrials=10, nChannels=32)
>>> bdata = generate_artificial_data(nTrials=5, nChannels=16)
Show overview of first 5 channels, averaged across trials 2, 4, and 6:
>>> fig = spy.multipanelplot(adata, channels=range(5), trials=[2, 4, 6])
Overlay last 5 channels, averaged across trials 1, 3, 5:
>>> fig = spy.multipanelplot(adata, channels=range(27, 32), trials=[1, 3, 5], fig=fig)
Do not average trials:
>>> fig = spy.multipanelplot(adata, channels=range(27, 32), trials=[1, 3, 5], avg_trials=False)
Plot `adata` and `bdata` simultaneously in two separate figures:
>>> fig1, fig2 = spy.multipanelplot(adata, bdata, channels=range(5), overlay=False)
Overlay `adata` and `bdata`; use channel and trial selections that are valid
for both datasets:
>>> fig3 = spy.multipanelplot(adata, bdata, channels=range(5), trials=[1, 2, 3], avg_trials=False)
See also
--------
syncopy.multipanelplot : visualize Syncopy data objects using multi-panel plots
"""
# Collect input arguments in dict `inputArgs` and process them
inputArgs = locals()
inputArgs.pop("self")
dimArrs, dimCounts, idx, timeIdx, chanIdx = _prep_analog_plots(
self, "singlepanelplot", **inputArgs)
(nTrials, nChan) = dimCounts
(trList, chArr) = dimArrs
# Get trial/channel count ("raw" plotting constitutes a special case)
if trials is None:
nTrials = 0
if avg_trials:
msg = "`trials` is `None` but `avg_trials` is `True`. " +\
"Cannot perform trial averaging without trial specification - " +\
"setting ``avg_trials = False``. "
SPYWarning(msg)
avg_trials = False
if avg_channels:
msg = "Averaging across channels w/o trial specifications results in " +\
"single-panel plot. Please use `singlepanelplot` instead"
SPYWarning(msg)
return
# If we're overlaying, ensure settings match up
if hasattr(fig, "singlepanelplot"):
lgl = "overlay-figure generated by `multipanelplot`"
act = "figure generated by `singlepanelplot`"
raise SPYValueError(legal=lgl,
varname="fig/singlepanelplot",
actual=act)
if hasattr(fig, "nTrialPanels"):
if nTrials != fig.nTrialPanels:
lgl = "number of trials to plot matching existing panels in figure"
act = "{} panels but {} trials for plotting".format(
fig.nTrialPanels, nTrials)
raise SPYValueError(legal=lgl,
varname="trials/figure panels",
actual=act)
if avg_trials:
lgl = "overlay of multi-trial plot"
act = "trial averaging was requested for multi-trial plot overlay"
raise SPYValueError(legal=lgl,
varname="trials/avg_trials",
actual=act)
if trials is None:
lgl = "`trials` to be not `None` to append to multi-trial plot"
act = "multi-trial plot overlay was requested but `trials` is `None`"
raise SPYValueError(legal=lgl,
varname="trials/overlay",
actual=act)
if not avg_channels and not hasattr(fig, "chanOffsets"):
lgl = "single-channel or channel-averages for appending to multi-trial plot"
act = "multi-trial multi-channel plot overlay was requested"
raise SPYValueError(legal=lgl,
varname="avg_channels/overlay",
actual=act)
if hasattr(fig, "nChanPanels"):
if nChan != fig.nChanPanels:
lgl = "number of channels to plot matching existing panels in figure"
act = "{} panels but {} channels for plotting".format(
fig.nChanPanels, nChan)
raise SPYValueError(legal=lgl,
varname="channels/figure panels",
actual=act)
if avg_channels:
lgl = "overlay of multi-channel plot"
act = "channel averaging was requested for multi-channel plot overlay"
raise SPYValueError(legal=lgl,
varname="channels/avg_channels",
actual=act)
if not avg_trials:
lgl = "overlay of multi-channel plot"
act = "mulit-trial plot was requested for multi-channel plot overlay"
raise SPYValueError(legal=lgl,
varname="channels/avg_trials",
actual=act)
if hasattr(fig, "chanOffsets"):
if avg_channels:
lgl = "multi-channel plot"
act = "channel averaging was requested for multi-channel plot overlay"
raise SPYValueError(legal=lgl,
varname="channels/avg_channels",
actual=act)
if nChan != len(fig.chanOffsets):
lgl = "channel-count matching existing multi-channel panels in figure"
act = "{} channels per panel but {} channels for plotting".format(
len(fig.chanOffsets), nChan)
raise SPYValueError(legal=lgl,
varname="channels/channels per panel",
actual=act)
# Generic title for overlay figures
overlayTitle = "Overlay of {} datasets"
# Either construct subplot panel layout/vet provided layout or fetch existing
if fig is None:
# Determine no. of required panels
if avg_trials and not avg_channels:
npanels = nChan
elif not avg_trials and avg_channels:
npanels = nTrials
elif not avg_trials and not avg_channels:
npanels = int(nTrials == 0) * nChan + nTrials
else:
msg = "Averaging across both trials and channels results in " +\
"single-panel plot. Please use `singlepanelplot` instead"
SPYWarning(msg)
return
# Although, `_setup_figure` can call `_layout_subplot_panels` for us, we
# need `nrow` and `ncol` below, so do it here
if nTrials > 0:
xLabel = "Time [s]"
else:
xLabel = "Samples"
nrow = kwargs.get("nrow", None)
ncol = kwargs.get("ncol", None)
nrow, ncol = _layout_subplot_panels(npanels, nrow=nrow, ncol=ncol)
fig, ax_arr = _setup_figure(npanels,
nrow=nrow,
ncol=ncol,
xLabel=xLabel,
grid=grid)
fig.analogPlot = True
# Get existing layout
else:
ax_arr = fig.get_axes()
nrow, ncol = ax_arr[0].numRows, ax_arr[0].numCols
# Panels correspond to channels
if avg_trials and not avg_channels:
# Ensure provided timing selection can actually be averaged (leverage
# the fact that `toilim` selections exclusively generate slices)
tLengths = _prep_toilim_avg(self)
# Compute trial-averaged time-courses: 2D array with slice/list
# selection does not require fancy indexing - no need to check this here
pltArr = np.zeros((tLengths[0], nChan), dtype=self.data.dtype)
for k, trlno in enumerate(trList):
idx[timeIdx] = self._selection.time[k]
pltArr += np.swapaxes(
self._get_trial(trlno)[tuple(idx)], timeIdx, 0)
pltArr /= nTrials
# Cycle through channels and plot trial-averaged time-courses (time-
# axis must be identical for all channels, set up `idx` just once)
idx[timeIdx] = self._selection.time[0]
time = self.time[trList[k]][self._selection.time[0]]
for k, chan in enumerate(chArr):
ax_arr[k].plot(time,
pltArr[:, k],
label=os.path.basename(self.filename))
# If we're overlaying datasets, adjust panel- and sup-titles: include
# legend in top-right axis (note: `ax_arr` is row-major flattened)
if fig.objCount == 0:
for k, chan in enumerate(chArr):
ax_arr[k].set_title(chan, size=pltConfig["multiTitleSize"])
fig.nChanPanels = nChan
if title is None:
if nTrials > 1:
title = "Average of {} trials".format(nTrials)
else:
title = "Trial #{}".format(trList[0])
fig.suptitle(title, size=pltConfig["singleTitleSize"])
else:
for k, chan in enumerate(chArr):
ax_arr[k].set_title("{0}/{1}".format(ax_arr[k].get_title(),
chan))
ax = ax_arr[ncol - 1]
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles, labels)
if title is None:
title = overlayTitle.format(len(handles))
fig.suptitle(title, size=pltConfig["singleTitleSize"])
# Panels correspond to trials
elif not avg_trials and avg_channels:
# Cycle through panels to plot by-trial channel-averages
for k, trlno in enumerate(trList):
idx[timeIdx] = self._selection.time[k]
time = self.time[trList[k]][self._selection.time[k]]
ax_arr[k].plot(time,
self._get_trial(trlno)[tuple(idx)].mean(
axis=chanIdx).squeeze(),
label=os.path.basename(self.filename))
# If we're overlaying datasets, adjust panel- and sup-titles: include
# legend in top-right axis (note: `ax_arr` is row-major flattened)
if fig.objCount == 0:
for k, trlno in enumerate(trList):
ax_arr[k].set_title("Trial #{}".format(trlno),
size=pltConfig["multiTitleSize"])
fig.nTrialPanels = nTrials
if title is None:
if nChan > 1:
title = "Average of {} channels".format(nChan)
else:
title = chArr[0]
fig.suptitle(title, size=pltConfig["singleTitleSize"])
else:
for k, trlno in enumerate(trList):
ax_arr[k].set_title("{0}/#{1}".format(ax_arr[k].get_title(),
trlno))
ax = ax_arr[ncol - 1]
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles, labels)
if title is None:
title = overlayTitle.format(len(handles))
fig.suptitle(title, size=pltConfig["singleTitleSize"])
# Panels correspond to channels (if `trials` is `None`) otherwise trials
elif not avg_trials and not avg_channels:
# Plot each channel in separate panel
if nTrials == 0:
chanSec = np.arange(self.channel.size)[self._selection.channel]
for k, chan in enumerate(chanSec):
idx[chanIdx] = chan
ax_arr[k].plot(self.data[tuple(idx)].squeeze(),
label=os.path.basename(self.filename))
# If we're overlaying datasets, adjust panel- and sup-titles: include
# legend in top-right axis (note: `ax_arr` is row-major flattened)
if fig.objCount == 0:
for k, chan in enumerate(chArr):
ax_arr[k].set_title(chan, size=pltConfig["multiTitleSize"])
fig.nChanPanels = nChan
if title is None:
title = "Entire Data Timecourse"
fig.suptitle(title, size=pltConfig["singleTitleSize"])
else:
for k, chan in enumerate(chArr):
ax_arr[k].set_title("{0}/{1}".format(
ax_arr[k].get_title(), chan))
ax = ax_arr[ncol - 1]
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles, labels)
if title is None:
title = overlayTitle.format(len(handles))
fig.suptitle(title, size=pltConfig["singleTitleSize"])
# Each trial gets its own panel w/multiple channels per panel
else:
# If required, compute max amplitude across provided trials + channels
if not hasattr(fig, "chanOffsets"):
maxAmps = np.zeros((nTrials, ), dtype=self.data.dtype)
tickOffsets = maxAmps.copy()
for k, trlno in enumerate(trList):
idx[timeIdx] = self._selection.time[k]
pltArr = np.abs(self._get_trial(trlno)[tuple(idx)])
maxAmps[k] = pltArr.max()
tickOffsets[k] = pltArr.mean()
fig.chanOffsets = np.cumsum([0] + [maxAmps.max()] *
(nChan - 1))
fig.tickOffsets = fig.chanOffsets + tickOffsets.mean()
# Cycle through panels to plot by-trial multi-channel time-courses
for k, trlno in enumerate(trList):
idx[timeIdx] = self._selection.time[k]
time = self.time[trList[k]][self._selection.time[k]]
pltArr = np.swapaxes(
self._get_trial(trlno)[tuple(idx)], timeIdx, 0)
ax_arr[k].plot(
time, (pltArr + fig.chanOffsets.reshape(1, nChan)).reshape(
time.size, nChan),
color=plt.rcParams["axes.prop_cycle"].by_key()["color"][
fig.objCount],
label=os.path.basename(self.filename))
# If we're overlaying datasets, adjust panel- and sup-titles: include
# legend in top-right axis (note: `ax_arr` is row-major flattened)
# Note: y-axis is shared across panels, so `yticks` need only be set once
if fig.objCount == 0:
for k, trlno in enumerate(trList):
ax_arr[k].set_title("Trial #{}".format(trlno),
size=pltConfig["multiTitleSize"])
ax_arr[0].set_yticks(fig.tickOffsets)
ax_arr[0].set_yticklabels(chArr)
fig.nTrialPanels = nTrials
if title is None:
if nChan > 1:
title = "{} channels".format(nChan)
else:
title = chArr[0]
fig.suptitle(title, size=pltConfig["singleTitleSize"])
else:
for k, trlno in enumerate(trList):
ax_arr[k].set_title("{0}/#{1}".format(
ax_arr[k].get_title(), trlno))
ax_arr[0].set_yticklabels([" "] * chArr.size)
ax = ax_arr[ncol - 1]
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles[::(nChan + 1)], labels[::(nChan + 1)])
if title is None:
title = overlayTitle.format(len(handles))
fig.suptitle(title, size=pltConfig["singleTitleSize"])
# Increment overlay-counter, draw figure and wipe data-selection slot
fig.objCount += 1
plt.draw()
self._selection = None
return fig
def data_parser(data,
varname="",
dataclass=None,
writable=None,
empty=None,
dimord=None):
"""
Parse syncopy data objects
Parameters
----------
data : syncopy data object
Syncopy data object to verify
varname : str
Local variable name used in caller, see Examples for details.
dataclass : None or str
Expected class of `data`. If `None` the type of `data` is not inspected.
writeable : None or bool
If `True` a :class:`~syncopy.shared.errors.SPYValueError` is raised if
`data` is read-only, vice versa if `writeable` is `False`. If `None`
then `data` is not checked for read/write access.
empty : None or bool
If `True` a :class:`~syncopy.shared.errors.SPYValueError` is raised if
`data` already has contents, if `False` then `data` is checked
for non-emptiness. If `None` then `data` is not inspected for contents.
dimord : None or list
If provided, then `data.dimord` is matched with `dimord` (raising
a :class:`~syncopy.shared.errors.SPYValueError` in case of discrepancies).
If `None` then `data.dimord` is not inspected.
Returns
-------
Nothing : None
Examples
--------
Ensure `adata` is a :class:`~syncopy.datatype.continuous_data.AnalogData` object:
>>> data_parser(adata, varname="adata", dataclass="AnalogData")
Query adata for write-access and emptiness (e.g., before writing results):
>>> data_parser(adata, varname="adata", writeable=True, empty=True)
See also
--------
array_parser : similar functionality for parsing array-like objects
"""
# Make sure `data` is (derived from) `BaseData`
if not any(["BaseData" in str(base) for base in data.__class__.__mro__]):
raise SPYTypeError(data,
varname=varname,
expected="Syncopy data object")
# If requested, check specific data-class of object
if dataclass is not None:
if data.__class__.__name__ != str(dataclass):
msg = "Syncopy {} object".format(dataclass)
raise SPYTypeError(data, varname=varname, expected=msg)
# If requested, ensure object contains data (or not)
if empty is not None:
legal = "{status:s} Syncopy data object"
if empty and not data._is_empty():
raise SPYValueError(legal=legal.format(status="empty"),
varname=varname,
actual="non-empty")
elif not empty and data._is_empty():
raise SPYValueError(legal=legal.format(status="non-empty"),
varname=varname,
actual="empty")
# If requested, ensure proper access to object
if writable is not None:
legal = "{access:s} to Syncopy data object"
actual = "mode = {mode:s}"
if writable and data.mode == "r":
raise SPYValueError(legal=legal.format(access="write-access"),
varname=varname,
actual=actual.format(mode=data.mode))
elif not writable and data.mode != "r":
raise SPYValueError(legal=legal.format(access="read-only-access"),
varname=varname,
actual=actual.format(mode=data.mode))
# If requested, check integrity of dimensional information (if non-empty)
if dimord is not None:
base = "Syncopy {diminfo:s} data object"
if data.dimord != dimord:
legal = base.format(diminfo="'" +
"' x '".join(str(dim) for dim in dimord) + "'")
actual = base.format(diminfo="'" +
"' x '".join(str(dim)
for dim in data.dimord) +
"' " if data.dimord else "empty")
raise SPYValueError(legal=legal, varname=varname, actual=actual)
return
def selectdata(data,
trials=None,
channels=None,
channels_i=None,
channels_j=None,
toi=None,
toilim=None,
foi=None,
foilim=None,
tapers=None,
units=None,
eventids=None,
out=None,
inplace=False,
clear=False,
**kwargs):
"""
Create a new Syncopy object from a selection
**Usage Notice**
Syncopy offers two modes for selecting data:
* **in-place** selections mark subsets of a Syncopy data object for processing
via a ``select`` dictionary *without* creating a new object
* **deep-copy** selections copy subsets of a Syncopy data object to keep and
preserve in a new object created by :func:`~syncopy.selectdata`
All Syncopy metafunctions, such as :func:`~syncopy.freqanalysis`, support
**in-place** data selection via a ``select`` keyword, effectively avoiding
potentially slow copy operations and saving disk space. The keys accepted
by the `select` dictionary are identical to the keyword arguments discussed
below. In addition, ``select = "all"`` can be used to select entire object
contents. Examples
>>> select = {"toilim" : [-0.25, 0]}
>>> spy.freqanalysis(data, select=select)
>>> # or equivalently
>>> cfg = spy.get_defaults(spy.freqanalysis)
>>> cfg.select = select
>>> spy.freqanalysis(cfg, data)
**Usage Summary**
List of Syncopy data objects and respective valid data selectors:
:class:`~syncopy.AnalogData` : trials, channels, toi/toilim
Examples
>>> spy.selectdata(data, trials=[0, 3, 5], channels=["channel01", "channel02"])
>>> cfg = spy.StructDict()
>>> cfg.trials = [5, 3, 0]; cfg.toilim = [0.25, 0.5]
>>> spy.selectdata(cfg, data)
:class:`~syncopy.SpectralData` : trials, channels, toi/toilim, foi/foilim, tapers
Examples
>>> spy.selectdata(data, trials=[0, 3, 5], channels=["channel01", "channel02"])
>>> cfg = spy.StructDict()
>>> cfg.foi = [30, 40, 50]; cfg.tapers = slice(2, 4)
>>> spy.selectdata(cfg, data)
:class:`~syncopy.EventData` : trials, toi/toilim, eventids
Examples
>>> spy.selectdata(data, toilim=[-1, 2.5], eventids=[0, 1])
>>> cfg = spy.StructDict()
>>> cfg.trials = [0, 0, 1, 0]; cfg.eventids = slice(2, None)
>>> spy.selectdata(cfg, data)
:class:`~syncopy.SpikeData` : trials, toi/toilim, units, channels
Examples
>>> spy.selectdata(data, toilim=[-1, 2.5], units=range(0, 10))
>>> cfg = spy.StructDict()
>>> cfg.toi = [1.25, 3.2]; cfg.trials = [0, 1, 2, 3]
>>> spy.selectdata(cfg, data)
**Note** Any property that is not specifically accessed via one of the provided
selectors is taken as is, e.g., ``spy.selectdata(data, trials=[1, 2])``
selects the entire contents of trials no. 2 and 3, while
``spy.selectdata(data, channels=range(0, 50))`` selects the first 50 channels
of `data` across all defined trials. Consequently, if no keywords are specified,
the entire contents of `data` is selected.
**Full documentation below**
Parameters
----------
data : Syncopy data object
A non-empty Syncopy data object. **Note** the type of `data` determines
which keywords can be used. Some keywords are only valid for certain
types of Syncopy objects, e.g., "freqs" is not a valid selector for an
:class:`~syncopy.AnalogData` object.
trials : list (integers) or None or "all"
List of integers representing trial numbers to be selected; can include
repetitions and need not be sorted (e.g., ``trials = [0, 1, 0, 0, 2]``
is valid) but must be finite and not NaN. If `trials` is `None`, or
``trials = "all"`` all trials are selected.
channels : list (integers or strings), slice, range or None or "all"
Channel-selection; can be a list of channel names (``['channel3', 'channel1']``),
a list of channel indices (``[3, 5]``), a slice (``slice(3, 10)``) or
range (``range(3, 10)``). Note that following Python conventions, channels
are counted starting at zero, and range and slice selections are half-open
intervals of the form `[low, high)`, i.e., low is included , high is
excluded. Thus, ``channels = [0, 1, 2]`` or ``channels = slice(0, 3)``
selects the first up to (and including) the third channel. Selections can
be unsorted and may include repetitions but must match exactly, be finite
and not NaN. If `channels` is `None`, or ``channels = "all"`` all channels
are selected.
toi : list (floats) or None or "all"
Time-points to be selected (in seconds) in each trial. Timing is expected
to be on a by-trial basis (e.g., relative to trigger onsets). Selections
can be approximate, unsorted and may include repetitions but must be
finite and not NaN. Fuzzy matching is performed for approximate selections
(i.e., selected time-points are close but not identical to timing information
found in `data`) using a nearest-neighbor search for elements of `toi`.
If `toi` is `None` or ``toi = "all"``, the entire time-span in each trial
is selected.
toilim : list (floats [tmin, tmax]) or None or "all"
Time-window ``[tmin, tmax]`` (in seconds) to be extracted from each trial.
Window specifications must be sorted (e.g., ``[2.2, 1.1]`` is invalid)
and not NaN but may be unbounded (e.g., ``[1.1, np.inf]`` is valid). Edges
`tmin` and `tmax` are included in the selection.
If `toilim` is `None` or ``toilim = "all"``, the entire time-span in each
trial is selected.
foi : list (floats) or None or "all"
Frequencies to be selected (in Hz). Selections can be approximate, unsorted
and may include repetitions but must be finite and not NaN. Fuzzy matching
is performed for approximate selections (i.e., selected frequencies are
close but not identical to frequencies found in `data`) using a nearest-
neighbor search for elements of `foi` in `data.freq`. If `foi` is `None`
or ``foi = "all"``, all frequencies are selected.
foilim : list (floats [fmin, fmax]) or None or "all"
Frequency-window ``[fmin, fmax]`` (in Hz) to be extracted. 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.
tapers : list (integers or strings), slice, range or None or "all"
Taper-selection; can be a list of taper names (``['dpss-win-1', 'dpss-win-3']``),
a list of taper indices (``[3, 5]``), a slice (``slice(3, 10)``) or range
(``range(3, 10)``). Note that following Python conventions, tapers are
counted starting at zero, and range and slice selections are half-open
intervals of the form `[low, high)`, i.e., low is included , high is
excluded. Thus, ``tapers = [0, 1, 2]`` or ``tapers = slice(0, 3)`` selects
the first up to (and including) the third taper. Selections can be unsorted
and may include repetitions but must match exactly, be finite and not NaN.
If `tapers` is `None` or ``tapers = "all"``, all tapers are selected.
units : list (integers or strings), slice, range or None or "all"
Unit-selection; can be a list of unit names (``['unit10', 'unit3']``), a
list of unit indices (``[3, 5]``), a slice (``slice(3, 10)``) or range
(``range(3, 10)``). Note that following Python conventions, units are
counted starting at zero, and range and slice selections are half-open
intervals of the form `[low, high)`, i.e., low is included , high is
excluded. Thus, ``units = [0, 1, 2]`` or ``units = slice(0, 3)`` selects
the first up to (and including) the third unit. Selections can be unsorted
and may include repetitions but must match exactly, be finite and not NaN.
If `units` is `None` or ``units = "all"``, all units are selected.
eventids : list (integers), slice, range or None or "all"
Event-ID-selection; can be a list of event-id codes (``[2, 0, 1]``), slice
(``slice(0, 2)``) or range (``range(0, 2)``). Note that following Python
conventions, range and slice selections are half-open intervals of the
form `[low, high)`, i.e., low is included , high is excluded. Selections
can be unsorted and may include repetitions but must match exactly, be
finite and not NaN. If `eventids` is `None` or ``eventids = "all"``, all
events are selected.
inplace : bool
If `inplace` is `True` **no** new object is created. Instead the provided
selection is stored in the input object's `_selection` attribute for later
use. By default `inplace` is `False` and all calls to `selectdata` create
a new Syncopy data object.
Returns
-------
dataselection : Syncopy data object
Syncopy data object of the same type as `data` but containing only the
subset specified by provided selectors.
Notes
-----
This routine represents a convenience function for creating new Syncopy objects
based on existing data entities. However, in many situations, the creation
of a new object (and thus the allocation of additional disk-space) might not
be necessary: all Syncopy metafunctions, such as :func:`~syncopy.freqanalysis`,
support **in-place** data selection.
Consider the following example: assume `data` is an :class:`~syncopy.AnalogData`
object representing 220 trials of LFP recordings containing baseline (between
second -0.25 and 0) and stimulus-on data (on the interval [0.25, 0.5]).
To compute the baseline spectrum, data-selection does **not**
have to be performed before calling :func:`~syncopy.freqanalysis` but instead
can be done in-place:
>>> import syncopy as spy
>>> cfg = spy.get_defaults(spy.freqanalysis)
>>> cfg.method = 'mtmfft'
>>> cfg.taper = 'dpss'
>>> cfg.output = 'pow'
>>> cfg.tapsmofrq = 10
>>> # define baseline/stimulus-on ranges
>>> baseSelect = {"toilim": [-0.25, 0]}
>>> stimSelect = {"toilim": [0.25, 0.5]}
>>> # in-place selection of baseline interval performed by `freqanalysis`
>>> cfg.select = baseSelect
>>> baselineSpectrum = spy.freqanalysis(cfg, data)
>>> # in-place selection of stimulus-on time-frame performed by `freqanalysis`
>>> cfg.select = stimSelect
>>> stimonSpectrum = spy.freqanalysis(cfg, data)
Especially for large data-sets, in-place data selection performed by Syncopy's
metafunctions does not only save disk-space but can significantly increase
performance.
Examples
--------
Use :func:`~syncopy.tests.misc.generate_artificial_data` to create a synthetic
:class:`syncopy.AnalogData` object.
>>> from syncopy.tests.misc import generate_artificial_data
>>> adata = generate_artificial_data(nTrials=10, nChannels=32)
Assume a hypothetical trial onset at second 2.0 with the first second of each
trial representing baseline recordings. To extract only the stimulus-on period
from `adata`, one could use
>>> stimon = spy.selectdata(adata, toilim=[2.0, np.inf])
Note that this is equivalent to
>>> stimon = adata.selectdata(toilim=[2.0, np.inf])
See also
--------
:func:`syncopy.show` : Show (subsets) of Syncopy objects
"""
# Ensure our one mandatory input is usable
try:
data_parser(data, varname="data", empty=False)
except Exception as exc:
raise exc
# Vet the only inputs not checked by `Selector`
if not isinstance(inplace, bool):
raise SPYTypeError(inplace, varname="inplace", expected="Boolean")
if not isinstance(inplace, bool):
raise SPYTypeError(clear, varname="clear", expected="Boolean")
# If provided, make sure output object is appropriate
if not inplace:
if out is not None:
try:
data_parser(out,
varname="out",
writable=True,
empty=True,
dataclass=data.__class__.__name__,
dimord=data.dimord)
except Exception as exc:
raise exc
new_out = False
else:
out = data.__class__(dimord=data.dimord)
new_out = True
else:
if out is not None:
lgl = "no output object for in-place selection"
raise SPYValueError(lgl,
varname="out",
actual=out.__class__.__name__)
# FIXME: remove once tests are in place (cf #165)
if channels_i is not None or channels_j is not None:
SPYWarning(
"CrossSpectralData channel selection currently untested and experimental!"
)
# Collect provided keywords in dict
selectDict = {
"trials": trials,
"channels": channels,
"channels_i": channels_i,
"channels_j": channels_j,
"toi": toi,
"toilim": toilim,
"foi": foi,
"foilim": foilim,
"tapers": tapers,
"units": units,
"eventids": eventids
}
# First simplest case: determine whether we just need to clear an existing selection
if clear:
if any(value is not None for value in selectDict.values()):
lgl = "no data selectors if `clear = True`"
raise SPYValueError(lgl, varname="select", actual=selectDict)
if data._selection is None:
SPYInfo("No in-place selection found. ")
else:
data._selection = None
SPYInfo("In-place selection cleared")
return
# Pass provided selections on to `Selector` class which performs error checking
data._selection = selectDict
# If an in-place selection was requested we're done
if inplace:
SPYInfo("In-place selection attached to data object: {}".format(
data._selection))
return
# Create inventory of all available selectors and actually provided values
# to create a bookkeeping dict for logging
log_dct = {"inplace": inplace, "clear": clear}
log_dct.update(selectDict)
log_dct.update(**kwargs)
# Fire up `ComputationalRoutine`-subclass to do the actual selecting/copying
selectMethod = DataSelection()
selectMethod.initialize(data,
out._stackingDim,
chan_per_worker=kwargs.get("chan_per_worker"))
selectMethod.compute(data,
out,
parallel=kwargs.get("parallel"),
log_dict=log_dct)
# Wipe data-selection slot to not alter input object
data._selection = None
# Either return newly created output object or simply quit
return out if new_out else None
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 wrapper_cfg(*args, **kwargs):
# First, parse positional arguments for dict-type inputs (`k` counts the
# no. of dicts provided) and convert tuple of positional args to list
cfg = None
k = 0
args = list(args)
for argidx, arg in enumerate(args):
if isinstance(arg, dict):
cfgidx = argidx
k += 1
# If a dict was found, assume it's a `cfg` dict and extract it from
# the positional argument list; if more than one dict was found, abort
if k == 1:
cfg = args.pop(cfgidx)
elif k > 1:
raise SPYValueError(
legal="single `cfg` input",
varname="cfg",
actual="{0:d} `cfg` objects in input arguments".format(k))
# Now parse provided keywords for `cfg` entry - if `cfg` was already
# provided as positional argument, abort
if kwargs.get("cfg") is not None:
if cfg:
lgl = "`cfg` either as positional or keyword argument, not both"
raise SPYValueError(legal=lgl, varname="cfg")
cfg = kwargs.pop("cfg")
# If `cfg` was detected either in positional or keyword arguments, process it
if cfg:
# If `cfg` is not dict-like, abort (`StructDict` is a `dict` child)
if not isinstance(cfg, dict):
raise SPYTypeError(cfg,
varname="cfg",
expected="dictionary-like")
# IMPORTANT: create a copy of `cfg` using `StructDict` constructor to
# not manipulate `cfg` in user's namespace!
cfg = StructDict(cfg) # FIXME
# If a method is called using `cfg`, non-default values for
# keyword arguments must *only* to be provided via `cfg`
defaults = get_defaults(func)
for key, value in kwargs.items():
if defaults.get(key, value) != value:
raise SPYValueError(
legal="no keyword arguments",
varname=key,
actual="non-default value for {}".format(key))
# Translate any existing "yes" and "no" fields to `True` and `False`
for key in cfg.keys():
if str(cfg[key]) == "yes":
cfg[key] = True
elif str(cfg[key]) == "no":
cfg[key] = False
# No explicit `cfg`: rename `kwargs` to `cfg` to consolidate processing below;
# IMPORTANT: this does *not* create a copy of `kwargs`, thus the `pop`-ing
# below actually manipulates `kwargs` as well - crucial for the `kwargs.get("data")`
# error checking!
else:
cfg = kwargs
# If `cfg` contains keys 'data' or 'dataset' extract corresponding
# entry and make it a positional argument (abort if both 'data'
# and 'dataset' are present)
data = cfg.pop("data", None)
if cfg.get("dataset"):
if data:
lgl = "either 'data' or 'dataset' in `cfg`/keywords, not both"
raise SPYValueError(legal=lgl, varname="cfg")
data = cfg.pop("dataset")
# If `cfg` did not contain `data`, look into `kwargs`
if data is None:
data = kwargs.pop("data", None)
if kwargs.get("dataset"):
if data:
lgl = "either `data` or `dataset` keyword, not both"
raise SPYValueError(legal=lgl, varname="data/dataset")
data = kwargs.pop("dataset")
# If Syncopy data object(s) were provided convert single objects to one-element
# lists, ensure positional args do *not* contain add'l objects; ensure keyword
# args (besides `cfg`) do *not* contain add'l objects; ensure `data` exclusively
# contains Syncopy data objects. Finally, rename remaining positional arguments
if data:
if not isinstance(data, (tuple, list)):
data = [data]
if any([
isinstance(arg, spy.datatype.base_data.BaseData)
for arg in args
]):
lgl = "Syncopy data object(s) provided either via `cfg`/keyword or " +\
"positional arguments, not both"
raise SPYValueError(legal=lgl, varname="cfg/data")
if kwargs.get("data") or kwargs.get("dataset"):
lgl = "Syncopy data object(s) provided either via `cfg` or as " +\
"keyword argument, not both"
raise SPYValueError(legal=lgl, varname="cfg.data")
if any([
not isinstance(obj, spy.datatype.base_data.BaseData)
for obj in data
]):
raise SPYError("`data` must be Syncopy data object(s)!")
posargs = args
# If `data` was not provided via `cfg` or as kw-arg, parse positional arguments
if data is None:
data = []
posargs = []
while args:
arg = args.pop(0)
if isinstance(arg, spy.datatype.base_data.BaseData):
data.append(arg)
else:
posargs.append(arg)
# Call function with unfolded `data` + modified positional/keyword args
return func(*data, *posargs, **cfg)
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 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 initialize(self, data, chan_per_worker=None, keeptrials=True):
"""
Perform dry-run of calculation to determine output shape
Parameters
----------
data : syncopy data object
Syncopy data object to be processed (has to be the same object
that is passed to :meth:`compute` for the actual calculation).
chan_per_worker : None or int
Number of channels to be processed by each worker (only relevant in
case of concurrent processing). If `chan_per_worker` is `None` (default)
by-trial parallelism is used, i.e., each worker processes
data corresponding to a full trial. If `chan_per_worker > 0`, trials
are split into channel-groups of size `chan_per_worker` (+ rest if the
number of channels is not divisible by `chan_per_worker` without
remainder) and workers are assigned by-trial channel-groups for
processing.
keeptrials : bool
Flag indicating whether to return individual trials or average
Returns
-------
Nothing : None
Notes
-----
This class method **has** to be called prior to performing the actual
computation realized in :meth:`computeFunction`.
See also
--------
compute : core routine performing the actual computation
"""
# First store `keeptrial` keyword value (important for output shapes below)
self.keeptrials = keeptrials
# Determine if data-selection was provided; if so, extract trials and check
# whether selection requires fancy array indexing
if data._selection is not None:
self.trialList = data._selection.trials
self.useFancyIdx = data._selection._useFancy
else:
self.trialList = list(range(len(data.trials)))
self.useFancyIdx = False
numTrials = len(self.trialList)
# If lists/tuples are in positional arguments, ensure `len == numTrials`
# Scalars are duplicated to fit trials, e.g., ``self.argv = [3, [0, 1, 1]]``
# then ``argv = [[3, 3, 3], [0, 1, 1]]``
for ak, arg in enumerate(self.argv):
# Ensure arguments are within reasonable size for distribution across workers
# (protect against circular object references by imposing max. calls)
self._callCount = 0
argsize = self._sizeof(arg)
if argsize > self._maxArgSize:
lgl = "positional arguments less than 100 MB each"
act = "positional argument with memory footprint of {0:4.2f} MB"
raise SPYValueError(legal=lgl, varname="argv", actual=act.format(argsize))
if isinstance(arg, (list, tuple)):
if len(arg) != numTrials:
lgl = "list/tuple of positional arguments for each trial"
act = "length of list/tuple does not correspond to number of trials"
raise SPYValueError(legal=lgl, varname="argv", actual=act)
continue
elif isinstance(arg, np.ndarray):
if arg.size == numTrials:
msg = "found NumPy array with size == #Trials. " +\
"Regardless, every worker will receive an identical copy " +\
"of this array. To propagate elements across workers, use " +\
"a list or tuple instead!"
SPYWarning(msg)
self.argv[ak] = [arg] * numTrials
# Prepare dryrun arguments and determine geometry of trials in output
dryRunKwargs = copy(self.cfg)
dryRunKwargs["noCompute"] = True
chk_list = []
dtp_list = []
trials = []
for tk, trialno in enumerate(self.trialList):
trial = data._preview_trial(trialno)
trlArg = tuple(arg[tk] for arg in self.argv)
chunkShape, dtype = self.computeFunction(trial,
*trlArg,
**dryRunKwargs)
chk_list.append(list(chunkShape))
dtp_list.append(dtype)
trials.append(trial)
# The aggregate shape is computed as max across all chunks
chk_arr = np.array(chk_list)
if np.unique(chk_arr[:, 0]).size > 1 and not self.keeptrials:
err = "Averaging trials of unequal lengths in output currently not supported!"
raise NotImplementedError(err)
if np.any([dtp_list[0] != dtp for dtp in dtp_list]):
lgl = "unique output dtype"
act = "{} different output dtypes".format(np.unique(dtp_list).size)
raise SPYValueError(legal=lgl, varname="dtype", actual=act)
chunkShape = tuple(chk_arr.max(axis=0))
self.outputShape = (chk_arr[:, 0].sum(),) + chunkShape[1:]
self.cfg["chunkShape"] = chunkShape
self.dtype = np.dtype(dtp_list[0])
# Ensure channel parallelization can be done at all
if chan_per_worker is not None and "channel" not in data.dimord:
msg = "input object does not contain `channel` dimension for parallelization!"
SPYWarning(msg)
chan_per_worker = None
if chan_per_worker is not None and self.keeptrials is False:
msg = "trial-averaging does not support channel-block parallelization!"
SPYWarning(msg)
chan_per_worker = None
if data._selection is not None:
if chan_per_worker is not None and data._selection.channel != slice(None, None, 1):
msg = "channel selection and simultaneous channel-block " +\
"parallelization not yet supported!"
SPYWarning(msg)
chan_per_worker = None
# Allocate control variables
trial = trials[0]
trlArg0 = tuple(arg[0] for arg in self.argv)
chunkShape0 = chk_arr[0, :]
lyt = [slice(0, stop) for stop in chunkShape0]
sourceLayout = []
targetLayout = []
targetShapes = []
ArgV = []
# If parallelization across channels is requested the first trial is
# split up into several chunks that need to be processed/allocated
if chan_per_worker is not None:
# Set up channel-chunking
nChannels = data.channel.size
rem = int(nChannels % chan_per_worker)
n_blocks = [chan_per_worker] * int(nChannels//chan_per_worker) + [rem] * int(rem > 0)
inchanidx = data.dimord.index("channel")
# Perform dry-run w/first channel-block of first trial to identify
# changes in output shape w.r.t. full-trial output (`chunkShape`)
shp = list(trial.shape)
idx = list(trial.idx)
shp[inchanidx] = n_blocks[0]
idx[inchanidx] = slice(0, n_blocks[0])
trial.shape = tuple(shp)
trial.idx = tuple(idx)
res, _ = self.computeFunction(trial, *trlArg0, **dryRunKwargs)
outchan = [dim for dim in res if dim not in chunkShape0]
if len(outchan) != 1:
lgl = "exactly one output dimension to scale w/channel count"
act = "{0:d} dimensions affected by varying channel count".format(len(outchan))
raise SPYValueError(legal=lgl, varname="chan_per_worker", actual=act)
outchanidx = res.index(outchan[0])
# Get output chunks and grid indices for first trial
chanstack = 0
blockstack = 0
for block in n_blocks:
shp = list(trial.shape)
idx = list(trial.idx)
shp[inchanidx] = block
idx[inchanidx] = slice(blockstack, blockstack + block)
trial.shape = tuple(shp)
trial.idx = tuple(idx)
res, _ = self.computeFunction(trial, *trlArg0, **dryRunKwargs)
lyt[outchanidx] = slice(chanstack, chanstack + res[outchanidx])
targetLayout.append(tuple(lyt))
targetShapes.append(tuple([slc.stop - slc.start for slc in lyt]))
sourceLayout.append(trial.idx)
ArgV.append(trlArg0)
chanstack += res[outchanidx]
blockstack += block
# Simple: consume all channels simultaneously, i.e., just take the entire trial
else:
targetLayout.append(tuple(lyt))
targetShapes.append(chunkShape0)
sourceLayout.append(trial.idx)
ArgV.append(trlArg0)
# Construct dimensional layout of output
stacking = targetLayout[0][0].stop
for tk in range(1, len(self.trialList)):
trial = trials[tk]
trlArg = tuple(arg[tk] for arg in self.argv)
chkshp = chk_list[tk]
lyt = [slice(0, stop) for stop in chkshp]
lyt[0] = slice(stacking, stacking + chkshp[0])
stacking += chkshp[0]
if chan_per_worker is None:
targetLayout.append(tuple(lyt))
targetShapes.append(tuple([slc.stop - slc.start for slc in lyt]))
sourceLayout.append(trial.idx)
ArgV.append(trlArg)
else:
chanstack = 0
blockstack = 0
for block in n_blocks:
shp = list(trial.shape)
idx = list(trial.idx)
shp[inchanidx] = block
idx[inchanidx] = slice(blockstack, blockstack + block)
trial.shape = tuple(shp)
trial.idx = tuple(idx)
res, _ = self.computeFunction(trial, *trlArg, **dryRunKwargs) # FauxTrial
lyt[outchanidx] = slice(chanstack, chanstack + res[outchanidx])
targetLayout.append(tuple(lyt))
targetShapes.append(tuple([slc.stop - slc.start for slc in lyt]))
sourceLayout.append(trial.idx)
chanstack += res[outchanidx]
blockstack += block
ArgV.append(trlArg)
# If the determined source layout contains unordered lists and/or index
# repetitions, set `self.useFancyIdx` to `True` and prepare a separate
# `sourceSelectors` list that is used in addition to `sourceLayout` for
# data extraction.
# In this case `sourceLayout` uses ABSOLUTE indices (indices wrt to size
# of ENTIRE DATASET) that are SORTED W/O REPS to extract a NumPy array
# of appropriate size from HDF5.
# Then `sourceLayout` uses RELATIVE indices (indices wrt to size of CURRENT
# TRIAL) that can be UNSORTED W/REPS to actually perform the requested
# selection on the NumPy array extracted w/`sourceLayout`.
for grd in sourceLayout:
if any([np.diff(sel).min() <= 0 if isinstance(sel, list)
and len(sel) > 1 else False for sel in grd]):
self.useFancyIdx = True
break
if self.useFancyIdx:
sourceSelectors = []
for gk, grd in enumerate(sourceLayout):
ingrid = list(grd)
sigrid = []
for sk, sel in enumerate(grd):
if isinstance(sel, list):
selarr = np.array(sel, dtype=np.intp)
else: # sel is a slice
step = sel.step
if sel.step is None:
step = 1
selarr = np.array(list(range(sel.start, sel.stop, step)), dtype=np.intp)
if selarr.size > 0:
sigrid.append(np.array(selarr) - selarr.min())
ingrid[sk] = slice(selarr.min(), selarr.max() + 1, 1)
else:
sigrid.append([])
ingrid[sk] = []
sourceSelectors.append(tuple(sigrid))
sourceLayout[gk] = tuple(ingrid)
else:
sourceSelectors = [Ellipsis] * len(sourceLayout)
# Store determined shapes and grid layout
self.sourceLayout = sourceLayout
self.sourceSelectors = sourceSelectors
self.targetLayout = targetLayout
self.targetShapes = targetShapes
self.ArgV = ArgV
# Compute max. memory footprint of chunks
if chan_per_worker is None:
self.chunkMem = np.prod(self.cfg["chunkShape"]) * self.dtype.itemsize
else:
self.chunkMem = max([np.prod(shp) for shp in self.targetShapes]) * self.dtype.itemsize
# Get data access mode (only relevant for parallel reading access)
self.dataMode = data.mode
def validate_foi(foi, foilim, samplerate):
"""
Parameters
----------
foi : 'all' or array like or None
frequencies of interest
foilim : 2-element sequence or None
foi limits
Other Parameters
----------------
samplerate : float
the samplerate in Hz
Returns
-------
foi, foilim : tuple
Either both are `None` or the
user submitted one is parsed and returned
Notes
-----
Setting both `foi` and `foilim` to `None` is valid, the
subsequent analysis methods should all have a default way to
select a standard set of frequencies (e.g. np.fft.fftfreq).
"""
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)
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, 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, samplerate / 2],
dims=(2, ))
except Exception as exc:
raise exc
# foilim is of shape (2,)
if foilim[0] > foilim[1]:
msg = "Sorting foilim low to high.."
SPYInfo(msg)
foilim = np.sort(foilim)
return foi, foilim
def singlepanelplot(self,
trials="all",
channels="all",
toilim=None,
avg_channels=True,
title=None,
grid=None,
fig=None,
**kwargs):
"""
Plot contents of :class:`~syncopy.AnalogData` objects using single-panel figure(s)
Please refer to :func:`syncopy.singlepanelplot` for detailed usage information.
Examples
--------
Use :func:`~syncopy.tests.misc.generate_artificial_data` to create two synthetic
:class:`~syncopy.AnalogData` objects.
>>> from syncopy.tests.misc import generate_artificial_data
>>> adata = generate_artificial_data(nTrials=10, nChannels=32)
>>> bdata = generate_artificial_data(nTrials=5, nChannels=16)
Plot an average of the first 16 channels, averaged across trials 2, 4, and 6:
>>> fig = spy.singlepanelplot(adata, channels=range(16), trials=[2, 4, 6])
Overlay average of latter half of channels, averaged across trials 1, 3, 5:
>>> fig = spy.singlepanelplot(adata, channels=range(16,32), trials=[1, 3, 5], fig=fig)
Do not average channels:
>>> fig = spy.singlepanelplot(adata, channels=range(16,32), trials=[1, 3, 5], avg_channels=False)
Plot `adata` and `bdata` simultaneously in two separate figures:
>>> fig1, fig2 = spy.singlepanelplot(adata, bdata, overlay=False)
Overlay `adata` and `bdata`; use channel and trial selections that are valid
for both datasets:
>>> fig3 = spy.singlepanelplot(adata, bdata, channels=range(16), trials=[1, 2, 3])
See also
--------
syncopy.singlepanelplot : visualize Syncopy data objects using single-panel plots
"""
# Collect input arguments in dict `inputArgs` and process them
inputArgs = locals()
inputArgs.pop("self")
dimArrs, dimCounts, idx, timeIdx, chanIdx = _prep_analog_plots(
self, "singlepanelplot", **inputArgs)
(nTrials, nChan) = dimCounts
(trList, chArr) = dimArrs
# If we're overlaying a multi-channel plot, ensure settings match up; also,
# do not try to overlay on top of multi-panel plots
if hasattr(fig, "multipanelplot"):
lgl = "single-panel figure generated by `singleplot`"
act = "multi-panel figure generated by `multipanelplot`"
raise SPYValueError(legal=lgl, varname="fig", actual=act)
if hasattr(fig, "chanOffsets"):
if avg_channels:
lgl = "multi-channel plot"
act = "channel averaging was requested for multi-channel plot overlay"
raise SPYValueError(legal=lgl,
varname="channels/avg_channels",
actual=act)
if nChan != len(fig.chanOffsets):
lgl = "channel-count matching existing multi-channel panels in figure"
act = "{} channels per panel but {} channels for plotting".format(
len(fig.chanOffsets), nChan)
raise SPYValueError(legal=lgl,
varname="channels/channels per panel",
actual=act)
# Ensure provided timing selection can actually be averaged (leverage
# the fact that `toilim` selections exclusively generate slices)
if nTrials > 0:
tLengths = _prep_toilim_avg(self)
# Generic titles for figures
overlayTitle = "Overlay of {} datasets"
# Either create new figure or fetch existing
if fig is None:
if nTrials > 0:
xLabel = "Time [s]"
else:
xLabel = "Samples"
fig, ax = _setup_figure(1, xLabel=xLabel, grid=grid)
fig.analogPlot = True
else:
ax, = fig.get_axes()
# Single-channel panel
if avg_channels:
# Set up pieces of generic figure titles
if nChan > 1:
chanTitle = "Average of {} channels".format(nChan)
else:
chanTitle = chArr[0]
# Plot entire timecourse
if nTrials == 0:
# Do not fetch entire dataset at once, but channel by channel
chanSec = np.arange(self.channel.size)[self._selection.channel]
pltArr = np.zeros((self.data.shape[timeIdx], ),
dtype=self.data.dtype)
for chan in chanSec:
idx[chanIdx] = chan
pltArr += self.data[tuple(idx)].squeeze()
pltArr /= nChan
# The actual plotting command...
ax.plot(pltArr)
# Set plot title depending on dataset overlay
if fig.objCount == 0:
if title is None:
title = chanTitle
ax.set_title(title, size=pltConfig["singleTitleSize"])
else:
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles, labels)
if title is None:
title = overlayTitle.format(len(handles))
ax.set_title(title, size=pltConfig["singleTitleSize"])
# Average across trials
else:
# Compute channel-/trial-average time-course: 2D array with slice/list
# selection does not require fancy indexing - no need to check this here
pltArr = np.zeros((tLengths[0], ), dtype=self.data.dtype)
for k, trlno in enumerate(trList):
idx[timeIdx] = self._selection.time[k]
pltArr += self._get_trial(trlno)[tuple(idx)].mean(
axis=chanIdx).squeeze()
pltArr /= nTrials
# The actual plotting command is literally one line...
time = self.time[trList[0]][self._selection.time[0]]
ax.plot(time, pltArr, label=os.path.basename(self.filename))
ax.set_xlim([time[0], time[-1]])
# Set plot title depending on dataset overlay
if fig.objCount == 0:
if title is None:
if nTrials > 1:
trTitle = "{0}across {1} trials".format(
"averaged " if nChan == 1 else "", nTrials)
else:
trTitle = "Trial #{}".format(trList[0])
title = "{}, {}".format(chanTitle, trTitle)
ax.set_title(title, size=pltConfig["singleTitleSize"])
else:
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles, labels)
if title is None:
title = overlayTitle.format(len(handles))
ax.set_title(title, size=pltConfig["singleTitleSize"])
# Multi-channel panel
else:
# "Raw" data, do not respect any trials
if nTrials == 0:
# If required, compute max amplitude across provided channels
if not hasattr(fig, "chanOffsets"):
maxAmps = np.zeros((nChan, ), dtype=self.data.dtype)
tickOffsets = maxAmps.copy()
chanSec = np.arange(self.channel.size)[self._selection.channel]
for k, chan in enumerate(chanSec):
idx[chanIdx] = chan
pltArr = np.abs(self.data[tuple(idx)].squeeze())
maxAmps[k] = pltArr.max()
tickOffsets[k] = pltArr.mean()
fig.chanOffsets = np.cumsum([0] + [maxAmps.max()] *
(nChan - 1))
fig.tickOffsets = fig.chanOffsets + tickOffsets.mean()
# Do not plot all at once but cycle through channels to not overflow memory
for k, chan in enumerate(chanSec):
idx[chanIdx] = chan
ax.plot(self.data[tuple(idx)].squeeze() + fig.chanOffsets[k],
color=plt.rcParams["axes.prop_cycle"].by_key()["color"]
[fig.objCount],
label=os.path.basename(self.filename))
if grid is not None:
ax.grid(grid)
# Set plot title depending on dataset overlay
if fig.objCount == 0:
if title is None:
if nChan > 1:
title = "Entire Data Timecourse of {} channels".format(
nChan)
else:
title = "Entire Data Timecourse of {}".format(chArr[0])
ax.set_yticks(fig.tickOffsets)
ax.set_yticklabels(chArr)
ax.set_title(title, size=pltConfig["singleTitleSize"])
else:
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles[::(nChan + 1)], labels[::(nChan + 1)])
if title is None:
title = overlayTitle.format(len(handles))
ax.set_title(title, size=pltConfig["singleTitleSize"])
# Average across trial(s)
else:
# Compute trial-average
pltArr = np.zeros((tLengths[0], nChan), dtype=self.data.dtype)
for k, trlno in enumerate(trList):
idx[timeIdx] = self._selection.time[k]
pltArr += np.swapaxes(
self._get_trial(trlno)[tuple(idx)], timeIdx, 0)
pltArr /= nTrials
# If required, compute offsets for multi-channel plot
if not hasattr(fig, "chanOffsets"):
fig.chanOffsets = np.cumsum([0] + [np.abs(pltArr).max()] *
(nChan - 1))
fig.tickOffsets = fig.chanOffsets + np.abs(pltArr).mean()
# Plot the entire trial-averaged array at once
time = self.time[trList[0]][self._selection.time[0]]
ax.plot(time, (pltArr + fig.chanOffsets.reshape(1, nChan)).reshape(
time.size, nChan),
color=plt.rcParams["axes.prop_cycle"].by_key()["color"][
fig.objCount],
label=os.path.basename(self.filename))
if grid is not None:
ax.grid(grid)
# Set plot title depending on dataset overlay
if fig.objCount == 0:
if title is None:
title = "{0} channels {1}across {2} trials".format(
nChan, "averaged " if nTrials > 1 else "", nTrials)
ax.set_title(title, size=pltConfig["singleTitleSize"])
else:
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles[::(nChan + 1)], labels[::(nChan + 1)])
if title is None:
title = overlayTitle.format(len(handles))
ax.set_title(title, size=pltConfig["singleTitleSize"])
# Increment overlay-counter and draw figure
fig.objCount += 1
plt.draw()
self._selection = None
return fig