def get_sleep_stats(hypno_file, output_file=None):
"""Compute sleep statistics from hypnogram file and export them in csv.
Sleep statistics specifications:
* Time in Bed (TIB) : total duration of the hypnogram.
* Total Dark Time (TDT) : duration of the hypnogram from beginning
to last period of sleep.
* Sleep Period Time (SPT) : duration from first to last period of
sleep.
* Wake After Sleep Onset (WASO) : duration of wake periods within SPT
* Sleep Efficiency (SE) : TST / TDT * 100 (%).
* Total Sleep Time (TST) : SPT - WASO.
* W, N1, N2, N3 and REM: sleep stages duration.
* % (W, ... REM) : sleep stages duration expressed in percentages of
TDT.
* Latencies: latencies of sleep stages from the beginning of the
record.
(All values except SE and percentages are expressed in minutes)
Parameters
----------
hypno_file : string
Full path to the hypnogram file.
output_file : string | None
Full path to the output file. If no file is provided, sleep statictics
are print out to the terminal.
"""
# File conversion :
if output_file is not None: # Check extension
ext = os.path.splitext(output_file)[1][1:].strip().lower()
if ext == '':
output_file = output_file + '.csv'
# Load hypnogram
hypno, sf_hyp = read_hypno(hypno_file)
if sf_hyp < 1:
mult = int(np.round(len(hypno) / sf_hyp))
hypno = oversample_hypno(hypno, mult)
sf_hyp = 1
# Get sleep stats
stats = sleepstats(hypno, sf_hyp=sf_hyp)
stats['File'] = hypno_file
print('\nSLEEP STATS\n===========')
keys, val = [''] * len(stats), [''] * len(stats)
# Fill table :
for num, (k, v) in enumerate(stats.items()):
print(k, '\t', str(v))
# Remember variables :
keys[int(num)] = k
val[int(num)] = str(v)
if output_file is not None:
write_csv(output_file, zip(keys, val))
print('===========\nCSV file saved to:', output_file)
def __init__(self, data, channels, sf, hypno, href, preload, use_mne,
downsample, kwargs_mne, annotations):
"""Init."""
# ========================== LOAD DATA ==========================
# Dialog window if data is None :
if data is None:
data = dialog_load(
self, "Open dataset", '',
"Any EEG files (*.vhdr *.edf *.gdf *.bdf *.eeg "
"*.egi *.mff *.cnt *.trc *.set *.rec);;"
"BrainVision (*.vhdr);;EDF (*.edf);;"
"GDF (*.gdf);;BDF (*.bdf);;Elan (*.eeg);;"
"EGI (*.egi);;MFF (*.mff);;CNT (*.cnt);;"
"Micromed (*.trc);;EEGLab (*.set);;REC (*.rec)")
upath = os.path.split(data)[0]
else:
upath = ''
if isinstance(data, str): # file is defined
# ---------- USE SLEEP or MNE ----------
# Find file extension :
file, ext = get_file_ext(data)
# Force to use MNE if preload is False :
use_mne = True if not preload else use_mne
# Get if the file has to be loaded using Sleep or MNE python :
sleep_ext = ['.eeg', '.vhdr', '.edf', '.trc', '.rec']
use_mne = True if ext not in sleep_ext else use_mne
if use_mne:
is_mne_installed(raise_error=True)
# ---------- LOAD THE FILE ----------
if use_mne: # Load using MNE functions
logger.debug("Load file using MNE-python")
kwargs_mne['preload'] = preload
args = mne_switch(file, ext, downsample, **kwargs_mne)
else: # Load using Sleep functions
logger.debug("Load file using Sleep")
args = sleep_switch(file, ext, downsample)
# Get output arguments :
(sf, downsample, dsf, data, channels, n, offset, annot) = args
info = ("Data successfully loaded (%s):"
"\n- Sampling-frequency : %.2fHz"
"\n- Number of time points (before down-sampling): %i"
"\n- Down-sampling frequency : %.2fHz"
"\n- Number of time points (after down-sampling): %i"
"\n- Number of channels : %i")
n_channels, n_pts_after = data.shape
logger.info(
info %
(file + ext, sf, n, downsample, n_pts_after, n_channels))
PROFILER("Data file loaded", level=1)
elif isinstance(data, np.ndarray): # array of data is defined
if not isinstance(sf, (int, float)):
raise ValueError("When passing raw data, the sampling "
"frequency parameter, sf, must either be an "
"integer or a float.")
file = annot = None
offset = datetime.time(0, 0, 0)
dsf, downsample = get_dsf(downsample, sf)
n = data.shape[1]
data = data[:, ::dsf]
else:
raise IOError("The data should either be a string which refer to "
"the path of a file or an array of raw data of shape"
" (n_electrodes, n_time_points).")
# Keep variables :
self._file = file
self._annot_file = np.c_[merge_annotations(annotations, annot)]
self._N = n
self._dsf = dsf
self._sfori = float(sf)
self._toffset = offset.hour * 3600. + offset.minute * 60. + \
offset.second
time = np.arange(n)[::dsf] / sf
self._sf = float(downsample) if downsample is not None else float(sf)
# ========================== LOAD HYPNOGRAM ==========================
# Dialog window for hypnogram :
if hypno is False:
hypno = None
elif hypno is None:
hypno = dialog_load(
self, "Open hypnogram", upath,
"Text file (*.txt);;Elan (*.hyp);;"
"CSV file (*.csv);;EDF+ file(*.edf);"
";All files (*.*)")
hypno = None if hypno == '' else hypno
if isinstance(hypno, np.ndarray): # array_like
if len(hypno) == n:
hypno = hypno[::dsf]
else:
raise ValueError("Then length of the hypnogram must be the "
"same as raw data")
if isinstance(hypno, str): # (*.hyp / *.txt / *.csv)
hypno, _ = read_hypno(hypno, time=time, datafile=file)
# Oversample then downsample :
hypno = oversample_hypno(hypno, self._N)[::dsf]
PROFILER("Hypnogram file loaded", level=1)
# ========================== CHECKING ==========================
# ---------- DATA ----------
# Check data shape :
if data.ndim is not 2:
raise ValueError("The data must be a 2D array")
nchan, npts = data.shape
# ---------- CHANNELS ----------
if (channels is None) or (len(channels) != nchan):
warn("The number of channels must be " + str(nchan) + ". Default "
"channel names will be used instead.")
channels = ['chan' + str(k) for k in range(nchan)]
# Clean channel names :
patterns = ['eeg', 'EEG', 'ref']
chanc = []
for c in channels:
# Remove informations after . :
c = c.split('.')[0]
c = c.split('-')[0]
# Exclude patterns :
for i in patterns:
c = c.replace(i, '')
# Remove space :
c = c.replace(' ', '')
c = c.strip()
chanc.append(c)
# ---------- STAGE ORDER ----------
# href checking :
absref = ['art', 'wake', 'n1', 'n2', 'n3', 'rem']
absint = [-1, 0, 1, 2, 3, 4]
if href is None:
href = absref
elif (href is not None) and isinstance(href, list):
# Force lower case :
href = [k.lower() for k in href]
# Check that all stage are present :
for k in absref:
if k not in href:
raise ValueError(k + " not found in href.")
# Force capitalize :
href = [k.capitalize() for k in href]
href[href.index('Rem')] = 'REM'
else:
raise ValueError("The href parameter must be a list of string and"
" must contain 'art', 'wake', 'n1', 'n2', 'n3' "
"and 'rem'")
# Conversion variable :
absref = ['Art', 'Wake', 'N1', 'N2', 'N3', 'REM']
conv = {absint[absref.index(k)]: absint[i] for i, k in enumerate(href)}
# ---------- HYPNOGRAM ----------
if hypno is None:
hypno = np.zeros((npts, ), dtype=np.float32)
else:
n = len(hypno)
# Check hypno values :
if (hypno.min() < -1.) or (hypno.max() > 4) or (n != npts):
warn("\nHypnogram values must be comprised between -1 and 4 "
"(see Iber et al. 2007). Use:\n-1 -> Art (optional)\n 0 "
"-> Wake\n 1 -> N1\n 2 -> N2\n 3 -> N4\n 4 -> REM\nEmpty "
"hypnogram will be used instead")
hypno = np.zeros((npts, ), dtype=np.float32)
# ---------- SCALING ----------
# Assume that the inter-quartile amplitude of EEG data is ~50 uV
iqr_chan = iqr(data[:, :int(data.shape[1] / 4)], axis=-1)
bad_iqr = iqr_chan < 1.
if np.any(bad_iqr):
mult_fact = np.zeros_like(iqr_chan)
iqr_chan[iqr_chan == 0.] = 1.
mult_fact[bad_iqr] = np.floor(np.log10(50. / iqr_chan[bad_iqr]))
data *= 10.**mult_fact[..., np.newaxis]
warn("Wrong channel data amplitude. ")
# ---------- CONVERSION ----------=
# Convert data and hypno to be contiguous and float 32 (for vispy):
self._data = vispy_array(data)
self._hypno = vispy_array(hypno)
self._time = vispy_array(time)
self._channels = chanc
self._href = href
self._hconv = conv
PROFILER("Check data", level=1)
def test_oversample_hypno(self):
"""Test function oversample_hypno."""
hyp = self._get_hypno()
hyp_over = oversample_hypno(hyp, 12)
to_hyp = np.array([-1, -1, 4, 4, 2, 2, 3, 3, 0, 0, 0, 0])
assert np.array_equal(hyp_over, to_hyp)
event_dict = {'W': 0, 'N1': 1, 'N2': 2, 'N3': 3, 'REM': 4, 'art': -1}
# event_dict = {'W': 0, 'N1': 1, 'NREM': 2, 'REM': 4, 'art': -1}
# epoch data into 30sec pieces:
epochs = mne.Epochs(raw, events=dummy_events, event_id=event_dict, tmin=0,
tmax=30, baseline=(0, 0), on_missing='ignore')
# epochs.drop(epochs['REM'].selection)
# nrem_raw = mne.io.RawArray(np.concatenate(epochs.get_data(), axis=1), raw.info)
# epochs.save('406_NREM.fif')
# nrem_raw.export('406_NREM.edf')
# write_edf('406_NREM2.edf', nrem_raw)
# rotem_edf(nrem_raw, '406_NREM3.edf')
# plot spectrogram with hypnogram:
data_out = raw.get_data()
hypno_up = oversample_hypno(hypno, data_out.shape[1])
# spectrogram_fig, gs, ax0, ax1 = plot_spectrogram(data_out[0, :], raw.info['sfreq'], hypno_up, trimperc=10)
# ax0.set(title=subject_id)
stage_spect_trls = [None] * len(event_dict)
stage_spect_avg = [None] * len(event_dict)
stage_spect_std = [None] * len(event_dict)
if separate_NREM_power_spectrum:
stages_dict = {'W': 0, 'N2': 2, 'N3': 3, 'REM': 4}
else:
stages_dict = {'W': 0, 'N2': 2, 'REM': 4}
for ind, stage in enumerate(stages_dict):
if epochs[stage].__len__() > 0: # if not empty
if separate_NREM_power_spectrum or stage != 'N2':
psds, freqs = mne.time_frequency.psd_multitaper(epochs[stage], fmin=0.5, fmax=40, n_jobs=1)
def test_oversample_hypno(self):
"""Test function oversample_hypno."""
hyp = self._get_hypno()
hyp_over = oversample_hypno(hyp, 12)
to_hyp = np.array([-1, -1, 4, 4, 2, 2, 3, 3, 0, 0, 0, 0])
assert np.array_equal(hyp_over, to_hyp)