def events(vhdr_path=None):
if vhdr_path is None:
vhdr_path = ui.ask_file("Pick a Brain Vision EEG Header File",
"Pick a Brain Vision EEG Header File",
ext=[('vhdr', 'Brain Vision Header File')])
if not vhdr_path:
return
hdr = vhdr(vhdr_path)
if hdr.markerfile is None:
raise IOError("No marker file referenced in %r" % vhdr_path)
elif hdr.DataType == 'FREQUENCYDOMAIN':
raise NotImplementedError
txt = open(hdr.markerfile).read()
m = marker_re.findall(txt)
m = np.array(m)
name, _ = os.path.split(os.path.basename(hdr.path))
ds = dataset(name=name)
ds['Mk'] = var(np.array(m[:,0], dtype=int))
ds['event_type'] = factor(m[:,1])
ds['event_ID'] = var(np.array(m[:,3], dtype=int))
ds['i_start'] = var(np.array(m[:,4], dtype=int))
ds['points'] = var(np.array(m[:,5], dtype=int))
ds['channel'] = var(np.array(m[:,6], dtype=int))
ds.info['hdr'] = hdr
ds.info['samplingrate'] = hdr.samplingrate
return ds
def export_durs(self):
ds = dataset()
idx = self.words == 'sp'
words = self.words[~idx]
durs = self.word_durs[~idx]
ds['words'] = factor([first.lower() + second.lower() for first, second in
zip(words[::2], words[1::2])])
ds['c1_dur'] = var(durs[::2])
ds['c2_dur'] = var(durs[1::2])
return ds
def export_durs(self):
ds = dataset()
idx = self.words == 'sp'
words = self.words[~idx]
durs = self.word_durs[~idx]
ds['words'] = factor([
first.lower() + second.lower()
for first, second in zip(words[::2], words[1::2])
])
ds['c1_dur'] = var(durs[::2])
ds['c2_dur'] = var(durs[1::2])
return ds
def get_dataset(self):
"get a dataframe containing Y and covariates"
Y, covs = self._collect_data()
indexes = Y.keys()
Ydata = [Y[index] for index in indexes]
Y = self._get_vessel_for_Y(Ydata)
ds = _vsl.dataset(Y)
# create _data objects
for var, valdict in covs.iteritems():
X = [valdict[index] for index in indexes]
if var.dict_enabled:
Y = _vsl.factor(X, name=var.name, random=var.random,
labels=var.dictionary, colors=var._color_dict)
else:
Y = _vsl.var(X, name=var.name)
ds.add(Y)
return ds
def tsv(path=None, names=True, types='auto', empty='nan', delimiter=None,
skiprows=0):
"""
returns a ``dataset`` with data from a tab-separated values file.
Parameters
----------
names : list of str | bool
* ``['name1', ...]`` use these names
* ``True``: look for names on the first line of the file
* ``False``: use "v1", "v2", ...
types : 'auto' | list of int
* ``'auto'`` -> import as var if all values can be converted float,
otherwise as factor
* list of 0=auto, 1=factor, 2=var. e.g. ``[0,1,1,0]``
empty :
value to substitute for empty cells
delimiter : str
value delimiting cells in the input file (None = any whitespace;
e.g., ``'\\t'``)
skiprows : int
Skip so many rows at the beginning of the file (for tsv files with
headers). Column names (if names==True) are expected to come after
the skipped rows.
"""
if path is None:
path = ui.ask_file("Select file to import as dataframe",
"Select file to import as dataframe")
if not path:
return
with open(path) as f:
for i in xrange(skiprows):
f.readline()
# read / create names
if names == True:
names = f.readline().split(delimiter)
names = [n.strip().strip('"') for n in names]
lines = []
for line in f:
values = []
for v in line.split(delimiter):
v = v.strip()
if not v:
v = empty
values.append(v)
lines.append(values)
n_vars = len(lines[0])
if not names:
names = ['v%i' % i for i in xrange(n_vars)]
n = len(names)
# decide whether to drop first column
if n_vars == n:
start = 0
elif n_vars == n + 1:
start = 1
else:
raise ValueError("number of header different from number of data")
if types in ['auto', None, False, True]:
types = [0] * n
else:
assert len(types) == n
# prepare for reading data
data = []
for _ in xrange(n):
data.append([])
# read rest of the data
for line in lines:
for i, v in enumerate(line[start:]):
for str_del in ["'", '"']:
if v[0] == str_del:
v = v.strip(str_del)
types[i] = 1
data[i].append(v)
ds = _data.dataset(name=os.path.basename(path))
for name, values, force_type in zip(names, data, types):
v = np.array(values)
if force_type in [0, 2]:
try:
v = v.astype(float)
f = _data.var(v, name=name)
except:
f = _data.factor(v, name=name)
else:
f = _data.factor(v, name=name)
ds.add(f)
return ds
