def load_data(dataset, norm='none'):
datadir = './data' if os.name == 'posix' else 'd:\\sleep\\data'
sleep = sleeploader.SleepDataset(datadir)
sleep.load_object(str(dataset))
data, target, groups = sleep.get_all_data(groups=True)
target[target == 4] = 3
target[target == 5] = 4
target[target > 5] = 0
if norm is 'all':
print('Normalizing {} over whole set\n...'.format(dataset), end='')
data = tools.normalize(data)
elif norm == 'none':
pass
elif norm == 'group':
print('Normalizing {} per patient\n...'.format(dataset), end='')
data = tools.normalize(data, groups=groups)
else:
print('Normalizing {} with reference {}\n...'.format(dataset, norm),
end='')
compdata, _, _ = load_data(norm, norm='none')
print('...', end='')
data = tools.normalize(data, comp=compdata)
target = keras.utils.to_categorical(target)
return deepcopy(data), deepcopy(target), deepcopy(groups)
def load_data(datadir):
sleep = sleeploader.SleepDataset(datadir)
sleep.load_object()
data, target, groups = sleep.get_all_data(groups=True)
data = tools.normalize(data , groups=groups)
# target[target==5] = 4
target[target==8] = 0
target = keras.utils.to_categorical(target)
return data, target, groups
def prepare(datadir='edfx'):
"""
Download, prepare and save the EDF database
"""
download_edfx(datadir)
convert_hypnograms(datadir)
sleep = sleeploader.SleepDataset(datadir)
sleep.load()
truncate_eeg(sleep)
return sleep
def load_data(datadir, filename='sleepdata', norm=None):
sleep = sleeploader.SleepDataset(datadir)
if not sleep.load_object(filename): sleep.load()
data, target, groups = sleep.get_all_data(groups=True)
del sleep
gc.collect()
target[target == 4] = 3 # S3+S4 = SWS = 3
target[target == 5] = 4 # REM = 4
target[target == 8] = 0 # Movement = 0
return data, target, groups
def load_data(dataset):
datadir = './data' if os.name == 'posix' else 'd:\\sleep\\data'
sleep = sleeploader.SleepDataset(datadir)
sleep.load_object(str(dataset))
data, target, groups = sleep.get_all_data(groups=True)
data = tools.normalize(data)
# data = zscore(data,1)
target[target==4] = 3
target[target==5] = 4
target[target>5] = 0
target = keras.utils.to_categorical(target)
return data, target, groups
def load_data(tsinalis=False):
sleep = sleeploader.SleepDataset(datadir)
gc.collect()
# sleep.load()
# sleep.save_object()
sleep.load_object()
data, target, groups = sleep.get_all_data(groups=True)
data = tools.normalize(data)
target[target == 4] = 3
target[target == 5] = 4
target[target == 8] = 0
target = keras.utils.to_categorical(target)
return deepcopy(data), deepcopy(target), deepcopy(groups)
def load_data(dataset):
sleep = sleeploader.SleepDataset(datadir)
sleep.load_object(dataset)
data, target, groups = sleep.get_all_data(groups=True)
data = data[0:5000]
target = target[0:5000]
groups = groups[0:5000]
data = tools.normalize(data, groups=groups)
target[target == 4] = 3
target[target == 5] = 4
target[target > 5] = 0
target = keras.utils.to_categorical(target)
print(np.unique(groups))
return deepcopy(data), deepcopy(target), deepcopy(groups)
def load_data(dataset):
datadir = './data' if os.name == 'posix' else 'd:\\sleep\\data'
sleep = sleeploader.SleepDataset(datadir)
sleep.load_object(str(dataset))
data, target, groups = sleep.get_all_data(groups=True)
data = tools.normalize(data)
target[target == 4] = 3
target[target == 5] = 4
target[target == 6] = 0
idx = np.where(target == 8)[0]
data = np.delete(data, idx, axis=0)
groups = np.delete(groups, idx)
target = np.delete(target, idx)
target = keras.utils.to_categorical(target)
return data, target, groups
def load_data():
global sleep
global data
sleep = sleeploader.SleepDataset(datadir)
if 'data' in vars():
del data;
gc.collect()
sleep.load_object()
data, target, groups = sleep.get_all_data(groups=True)
data = tools.normalize(data)
target[target==4] = 3
target[target==5] = 4
target[target==8] = 0
target = keras.utils.to_categorical(target)
return data, target, groups
# prepare dataset if it does not exist
if not os.path.isfile(os.path.join(datadir, 'sleepdata.pkl')):
edfx_database.download_edfx(datadir)
edfx_database.convert_hypnograms(datadir)
channels = {
'EEG': 'EEG FPZ-CZ',
'EMG': 'EMG SUBMENTAL',
'EOG': 'EOG HORIZONTAL'
} # set channels that are used
references = {
'RefEEG': False,
'RefEMG': False,
'RefEOG': False
} # we do not set a reference, because the data is already referenced
sleep = sleeploader.SleepDataset(datadir)
# use float16 is you have problems with memory or a small hard disk. Should be around 2.6 GB for float32.
sleep.load(channels=channels,
references=references,
verbose=0,
dtype=np.float16)
edfx_database.truncate_eeg(sleep)
# if the pickle file already exist, just load that one.
else:
sleep = sleeploader.SleepDataset(datadir)
sleep.load_object(
) # load the prepared files. Should be around 2.6 GB for float32
# load data
data, target, groups = sleep.get_all_data(groups=True)
"""
Created on Fri Jul 28 15:28:04 2017
@author: Simon
"""
#create sleepdata objects
if __name__ == '__main__':
#%%
import sleeploader
import tools
import numpy as np
import gc
#%%
sleep = sleeploader.SleepDataset('C:\sleep\cshs50')
sleep.load_object()
# sleep.save_object()
data, target, groups = sleep.get_all_data(groups=True)
feats_eeg = tools.feat_eeg(data[:,:,0])
feats_emg = tools.feat_emg(data[:,:,1])
feats_eog = tools.feat_eog(data[:,:,2])
np.save('target.npy', target)
np.save('groups.npy', groups)
np.save('feats_eeg.npy', feats_eeg)
np.save('feats_eog.npy', feats_eog)
np.save('feats_emg.npy', feats_emg)
del data, target, groups
del feats_eeg, feats_emg, feats_eog
del sleep; gc.collect()
# -*- coding: utf-8 -*-
"""
Created on Fri Jul 28 14:15:31 2017
@author: Simon
"""
import sleeploader
import imp
imp.reload(sleeploader)
if __name__ == '__main__':
sleep = sleeploader.SleepDataset('D:/sleep/isruc')
channels = {
'EEG': ['C4-A1', 'C4-M1'],
'EMG': 'X1',
'EOG': ['LOC-A2', 'E1-M2']
}
references = {'RefEEG': False, 'RefEMG': False, 'RefEOG': False}
sleep.load(channels=channels)
sleep.save_object()
def create_object(datadir):
sleep = sleeploader.SleepDataset(datadir)
sleep.load()
sleep.save_object()
