def erp(d, classes=None, enforce_equal_n=True):
'''
For each class, calculate the Event Related Potential by averaging the
corresponding trials. Note: no baselining is performed, see
:func:`psychic.baseline`.
Parameters
----------
data : :class:`psychic.DataSet`
The trials
classes: list (optional)
When specified, the ERP is only calculated for the classes with the
given indices.
enforce_equal_n : bool (default=True)
When set, each ERP is calculated by averaging the same number of
trials. For example, if class1 has m and class2 has n trials and m > n.
The ERP for class1 will be calculated by taking n random trials from
class1.
Returns
-------
d : :class:`psychic.DataSet`
A DataSet containing for each class the ERP.
- ``d.data``: [channels x samples x classes]
- ``d.labels``: The class labels. Each class has one instance (one ERP).
'''
assert d.data.ndim > 2
if classes is None or len(classes) == 0:
# Take all classes with >0 instances
classes = [cl for cl in range(d.nclasses)
if d.ninstances_per_class[cl] > 0]
assert len(classes) > 0, \
'No valid classes specified and no classes found with >0 instances'
num_trials = np.min( np.array(d.ninstances_per_class)[classes] )
assert num_trials > 0, 'For one or more classes there are no instances!'
# Calculate ERP
erp = np.zeros(d.data.shape[:-1] + (len(classes),))
for i,cl in enumerate(classes):
trials = d.get_class(cl).data
if enforce_equal_n:
# Enforce an equal number of trials for all classes. Picking them
# at random. Otherwise the ERPs will be skewed, simply because a
# different number of trials are averaged.
idx = range(trials.shape[-1])[:num_trials]
np.random.shuffle(idx)
erp[...,i] = np.mean(trials[...,idx], axis=trials.ndim-1)
else:
erp[...,i] = np.mean(trials, axis=trials.ndim-1)
labels = helpers.to_one_of_n(classes).astype(np.bool)
ids = np.atleast_2d(classes)
cl_lab = [lab for i,lab in enumerate(d.cl_lab) if i in classes]
return DataSet(data=erp, labels=labels, ids=ids, cl_lab=cl_lab,
default=d)
def wieland_spirals():
'''
Famous non-linear binary 2D problem with intertwined spirals.
'''
i = np.arange(97)
theta = np.pi * i / 16.
r = 6.5 * (104 - i) / 104.
data = np.array([r * np.cos(theta), r * np.sin(theta)])
data = np.hstack([data, -data])
labels = to_one_of_n(np.hstack([np.zeros(i.size), np.ones(i.size)]))
return DataSet(data, labels)
def gaussian_dataset(ninstances=[50, 50]):
'''
Simple Gaussian dataset with a variable number of instances for up to 3
classes.
'''
mus = [\
[0, 0],
[2, 1],
[5, 6]]
sigmas = [\
[[1, 2], [2, 5]],
[[1, 2], [2, 5]],
[[1, -1], [-1, 2]]]
assert len(ninstances) <= 3
data, labels = [], []
for (ci, n) in enumerate(ninstances):
data.append(np.random.multivariate_normal(mus[ci], sigmas[ci], n).T)
labels.extend(np.ones(n, np.int) * ci)
return DataSet(np.hstack(data), to_one_of_n(labels))
def gaussian_dataset(ninstances=[50, 50]):
'''
Simple Gaussian dataset with a variable number of instances for up to 3
classes.
'''
mus = [\
[0, 0],
[2, 1],
[5, 6]]
sigmas = [\
[[1, 2], [2, 5]],
[[1, 2], [2, 5]],
[[1, -1], [-1, 2]]]
assert len(ninstances) <= 3
nclasses = len(ninstances)
Xs, Ys = [], []
for (ci, n) in enumerate(ninstances):
Xs.append(np.random.multivariate_normal(mus[ci], sigmas[ci], n).T)
Ys.extend(np.ones(n) * ci)
return DataSet(X=np.hstack(Xs), Y=to_one_of_n(Ys))
def slice(d, markers_to_class, offsets):
'''
Slice function, used to extract fixed-length segments (called trials) of
EEG from a recording. Opposite of :func:`psychic.concatenate_trials`.
Segments are sliced based on the onset of some event code.
Given for example an EEG recording which contains two marker codes:
1. Left finger tapping
2. Right finger tapping
Trials can be extracted in the following manner:
>>> import psychic
>>> d = psychic.load_bdf(psychic.find_data_path('priming-short.bdf'))
>>> mdict = {1:'related', 2:'unrelated'}
>>> sample_rate = psychic.get_samplerate(d)
>>> begin = int(-0.2 * sample_rate)
>>> end = int(1.0 * sample_rate)
>>> trials = psychic.slice(d, mdict, (begin, end))
>>> print trials
DataSet with 208 instances, 12280 features [40x307], 2 classes: [104, 104], extras: []
Parameters
----------
markers_to_class : dict
A dictionary containing as keys the event codes to use as onset of the
trial and as values a class label for the resulting trials. For example
``{1:'left finger tapping', 2:'right finger tapping'}``
offsets : tuple
Indicates the time (start, end), relative to the onset of marker, to
extract as trial. Values are given in samples.
Returns
-------
d : :class:`DataSet`
The extracted segments:
- ``d.data``: [channels x samples x trials]
- ``d.labels``: [classes x trials]
- ``d.ids``: Timestamps indicating the marker onsets
- ``d.cl_lab``: The class labels as specified in the
``markers_to_class`` dictionary
- ``d.feat_lab``: Feature labels for the axes [channels (strings),
time in seconds (floats)]
'''
assert len(d.feat_shape) == 1, 'Data must be continuous EEG.'
assert d.labels.shape[0] == 1 and d.labels.dtype == np.int, ('Labels are'
'the wrong format. It must be an integer marker stream.')
start_off, end_off = offsets
data, labels, ids = [], [], []
cl_lab = sorted(set(markers_to_class.values()))
events, events_i, events_d = markers.markers_to_events(d.labels.flat)
for (mark, cl) in markers_to_class.items():
cl_i = cl_lab.index(cl)
for i in events_i[events==mark]: # fails if there is *ONE* event
(start, end) = i + start_off, i + end_off
if start < 0 or end > d.ninstances:
logging.getLogger('psychic.utils.slice').warning(
'Cannot extract slice [%d, %d] for class %s'
% (start, end, cl))
continue
dslice = d[start:end]
data.append(dslice.data)
labels.append(cl_i)
ids.append(d.ids[:,i])
event_time = np.arange(start_off, end_off) / float(utils.get_samplerate(d))
feat_lab = [d.feat_lab[0], event_time.tolist()]
if len(data) == 0:
data = np.zeros(d.feat_shape + (len(event_time),0))
labels = np.zeros((len(cl_lab),0))
ids = np.zeros((1,0))
else:
data = np.concatenate([x[...,np.newaxis] for x in data], axis=2)
labels = helpers.to_one_of_n(labels, class_rows=range(len(cl_lab)))
ids = np.atleast_2d(np.vstack(ids).T)
feat_dim_lab = ['channels', 'time']
d = DataSet(
data=data,
labels=labels,
ids=ids,
cl_lab=cl_lab,
feat_lab=feat_lab,
feat_dim_lab=feat_dim_lab,
default=d
)
return d.sorted()