def new_task(args):
name = ' '.join(args.name)
if not name:
print(INVALID_NAME_MSG)
return
date_str = args.date
if date_str:
try:
date = interpret_date(date_str)
except ValueError as e:
print(e)
return
else:
date = None
estimated_hours = float(args.est_hours)
manager = TaskManager(fileio.load())
id = manager.new_task(name, estimated_hours, date)
fileio.save(manager.task_dict)
print_table(manager, id)
def load(self, fname = 'save.dcb'):
''''''
# TODO check if this is dirty.
try:
self.lec = fileio.load(fname)
return True
except fileio.FormatError:
return False
def doOpen(self):
self.__resetFileInfo()
fileName = unicode(QtGui.QFileDialog.getOpenFileName())
try:
self.__rawValues = fileio.load(fileName)
except Exception, e:
msg = QtGui.QMessageBox()
msg.setText('Error while loading file: %s (%s)' % (fileName, str(e)))
msg.exec_()
def load(self, fname='save.dcb'):
''''''
# TODO check if this is dirty.
try:
self.lec = fileio.load(fname)
return True
except fileio.FormatError:
return False
def clock(args):
manager = TaskManager(fileio.load())
task_id = args.id
to_deduct = args.to_deduct
# TODO Complete if less than/eq 0?
try:
old_task: task.Task = manager.task_dict[task_id]
old_task.hours_remaining -= to_deduct
fileio.save(manager.task_dict)
print_table(manager, task_id)
except KeyError:
print(INVALID_ID_MSG)
def load_response_vars(datafile, maskfile=None, vol=True):
""" load response variables (of any data type)"""
if fileio.file_type(datafile) == 'nifti':
dat = fileio.load_nifti(datafile, vol=vol)
volmask = fileio.create_mask(dat, mask=maskfile)
Y = fileio.vol2vec(dat, volmask).T
else:
Y = fileio.load(datafile)
volmask = None
if fileio.file_type(datafile) == 'cifti':
Y = Y.T
return Y, volmask
def complete_task(args):
manager = TaskManager(fileio.load())
ids = args.id
if not ids:
print(INVALID_ID_MSG)
else:
completed_tasks_dict = dict()
for i in ids:
try:
completed_tasks_dict[i] = manager.task_dict[i]
manager.complete(i)
fileio.save(manager.task_dict)
except KeyError:
print(INVALID_ID_MSG)
print_table(manager)
print()
print_completed_tasks(completed_tasks_dict)
def modify_task(args):
manager = TaskManager(fileio.load())
task_id = args.id
try:
old_task: task.Task = manager.task_dict[task_id]
new_name = args.name if args.name else old_task.name
if args.date:
new_date = interpret_date(args.date)
elif args.floating or isinstance(old_task, task.FloatingTask):
new_date = None
else:
new_date = old_task.due_date
new_hours_remaining = args.est_hours if args.est_hours else old_task.hours_remaining
manager.new_task(new_name, new_hours_remaining, new_date, task_id)
fileio.save(manager.task_dict)
print_table(manager, task_id)
except KeyError:
print(INVALID_ID_MSG)
except ValueError as e:
print(e)
def load_jams_range(filename,
feature_name,
annotator=0,
annotator_name=None,
converter=None,
context='large_scale',
confidence=False):
"""Import specific data from a JAMS annotation file. It imports range
data, i.e., data that spans within two time points and it has a label
associated with it.
:parameters:
- filename : str
Path to the annotation file.
- feature_name: str
The key to the JAMS range feature to be extracted
(e.g. "sections", "chords")
- annotator: int
The idx of the annotator from which to extract the annotations.
- annotator_name: str
The name of the annotator from which to extract the annotations. If not
None, this parameter overwrites the "annotator".
- converter : function
Function to convert time-stamp data into numerics. Defaults to float().
- context : str
Context of the labels to be extracted (e.g. "large_scale", "function").
:returns:
- event_times : np.ndarray
array of event times (float).
- event_labels : list of str
list of corresponding event labels.
"""
if converter is None:
converter = float
jam = load(filename)
if annotator_name is not None:
annotator = get_annotator_idx(jam, feature_name, annotator_name,
filename)
try:
jam = load(filename)
except:
print "Error: could not open %s (JAMS module not installed?)" % \
filename
return [], []
times = []
labels = []
conf = []
if len(jam[feature_name]) == 0:
print "Warning: %s empty in file %s" % (feature_name, filename)
return []
for data in jam[feature_name][annotator].data:
if data.label.context == context:
times.append(
[converter(data.start.value),
converter(data.end.value)])
conf.append([
converter(data.start.confidence),
converter(data.end.confidence)
])
labels.append(data.label.value)
times = np.asarray(times)
print 'times', times
if confidence:
return times, labels, conf
else:
return times, labels
#!/usr/bin/python
import sys
sys.path.append('..')
import fileio
from datatypes import *
if len(sys.argv) <= 0: sys.exit()
lec = fileio.load('../saves/ll2.dcb')
ofile = open('tmp.csv', 'w')
it = iter(lec)
try:
last_point = None
while True:
e = it.next()
if isinstance(e, Point):
if last_point is None or last_point.x() != e.x() and last_point.y() != e.y():
ofile.write("%d,%d,%d," % (e.x() * 800, e.y() * 600, e.t * 1000))
last_point = e
elif last_point is not None:
last_point = None
ofile.write("\n")
except StopIteration:
pass
print 'Done!'
ofile.close()
def load_jams_range(filename, feature_name, annotator=0, annotator_name=None, converter=None, context='large_scale', confidence=False): """Import specific data from a JAMS annotation file. It imports range data, i.e., data that spans within two time points and it has a label associated with it. :parameters: - filename : str Path to the annotation file. - feature_name: str The key to the JAMS range feature to be extracted (e.g. "sections", "chords") - annotator: int The idx of the annotator from which to extract the annotations. - annotator_name: str The name of the annotator from which to extract the annotations. If not None, this parameter overwrites the "annotator". - converter : function Function to convert time-stamp data into numerics. Defaults to float(). - context : str Context of the labels to be extracted (e.g. "large_scale", "function"). :returns: - event_times : np.ndarray array of event times (float). - event_labels : list of str list of corresponding event labels. """ if converter is None: converter = float jam = load(filename) # error introduced since here. if annotator_name is not None: annotator = get_annotator_idx(jam, feature_name, annotator_name, filename) try: jam = load(filename) except: print "Error: could not open %s (JAMS module not installed?)" % \ filename return [], [] times = [] labels = [] conf = [] if len(jam[feature_name]) == 0: print "Warning: %s empty in file %s" % (feature_name, filename) return [] for data in jam[feature_name][annotator].data: if data.label.context == context: times.append([converter(data.start.value), converter(data.end.value)]) conf.append([converter(data.start.confidence), converter(data.end.confidence)]) labels.append(data.label.value) else: print '%s != %s, convert not excecuted.' %(data.label.context,context) times = np.asarray(times) if confidence: return times, labels, conf else: return times, labels
# -------------------------------- Testing --------------------------------- #
##############################################################################
def _load_from_file(fname):
f = open(fname, "r")
times = []
try:
while True:
line = f.next().strip()
times.append(int(line[:-3]) * 60 + int(line[-2:]))
except StopIteration:
pass
finally:
f.close()
return times
if __name__ == "__main__":
import sys, fileio
iname = sys.argv[1]
trace, audio = fileio.load(iname)
oname = iname[:-4] if iname[:-1].lower().endswith(".dc") else iname
times = _load_from_file(sys.argv[2]) if len(sys.argv) == 3 else None
if times is not None:
tofe = min(trace.get_time_of_first_event(), audio[0][0])
times = map(lambda x: x + tofe, times)
to_pdf(trace, oname, (480, 320), times)
to_png(trace, oname, (480, 320), times)
if __name__ == '__main__':
# valid video modules in preferred order
VALID_V_MODULES = ['gtkgui', 'macgui', 'qtgui', 'dummy']
# valid audio modules in preferred order
VALID_A_MODULES = ['alsa', 'macaudio', 'qtaudio', 'dummy']
config = parse_args(sys.argv[1:])
if config.help_req:
Configuration.print_usage()
sys.exit(0)
if config.export_fmt is not None:
if config.export_fmt == 'swf':
lec = fileio.load(config.file_to_load)
exporter.to_swf(lec, lec.adats, config.file_to_load[:-4] + '.swf')
elif config.export_fmt == 'pdf':
lec = fileio.load(config.file_to_load)
exporter.to_pdf(lec, config.file_to_load[:-4] + '.swf')
elif config.export_fmt in ['dcd', 'dcb', 'dcx', 'dar', 'dct']:
lec = fileio.load(config.file_to_load)
fileio.save(config.file_to_load[:-3] + config.export_fmt, lec,
lec.adats)
else:
print 'Unknown flag "--exp-%s"' % config.export_fmt
sys.exit(0)
# Something was passed, so use that to
if config.audio_module is not None:
try:
##############################################################################
# -------------------------------- Testing --------------------------------- #
##############################################################################
def _load_from_file(fname):
f = open(fname, 'r')
times = []
try:
while True:
line = f.next().strip()
times.append(int(line[:-3]) * 60 + int(line[-2:]))
except StopIteration:
pass
finally:
f.close()
return times
if __name__ == "__main__":
import sys, fileio
iname = sys.argv[1]
trace, audio = fileio.load(iname)
oname = iname[:-4] if iname[:-1].lower().endswith('.dc') else iname
times = _load_from_file(sys.argv[2]) if len(sys.argv) == 3 else None
if times is not None:
tofe = min(trace.get_time_of_first_event(), audio[0][0])
times = map(lambda x: x + tofe, times)
to_pdf(trace, oname, (480, 320), times)
to_png(trace, oname, (480, 320), times)
def estimate(respfile, covfile, maskfile=None, cvfolds=None,
testcov=None, testresp=None, alg='gpr', configparam=None,
saveoutput=True, outputsuffix=None):
""" Estimate a normative model
This will estimate a model in one of two settings according to the
particular parameters specified (see below):
* under k-fold cross-validation
required settings 1) respfile 2) covfile 3) cvfolds>2
* estimating a training dataset then applying to a second test dataset
required sessting 1) respfile 2) covfile 3) testcov 4) testresp
* estimating on a training dataset ouput of forward maps mean and se
required sessting 1) respfile 2) covfile 3) testcov
The models are estimated on the basis of data stored on disk in ascii or
neuroimaging data formats (nifti or cifti). Ascii data should be in
tab or space delimited format with the number of subjects in rows and the
number of variables in columns. Neuroimaging data will be reshaped
into the appropriate format
Basic usage::
estimate(respfile, covfile, [extra_arguments])
where the variables are defined below. Note that either the cfolds
parameter or (testcov, testresp) should be specified, but not both.
:param respfile: response variables for the normative model
:param covfile: covariates used to predict the response variable
:param maskfile: mask used to apply to the data (nifti only)
:param cvfolds: Number of cross-validation folds
:param testcov: Test covariates
:param testresp: Test responses
:param alg: Algorithm for normative model
:param configparam: Parameters controlling the estimation algorithm
:param saveoutput: Save the output to disk? Otherwise returned as arrays
:param outputsuffix: Text string to add to the output filenames
All outputs are written to disk in the same format as the input. These are:
:outputs: * yhat - predictive mean
* ys2 - predictive variance
* Hyp - hyperparameters
* Z - deviance scores
* Rho - Pearson correlation between true and predicted responses
* pRho - parametric p-value for this correlation
* rmse - root mean squared error between true/predicted responses
* smse - standardised mean squared error
The outputsuffix may be useful to estimate multiple normative models in the
same directory (e.g. for custom cross-validation schemes)
"""
# load data
print("Processing data in " + respfile)
X = fileio.load(covfile)
Y, maskvol = load_response_vars(respfile, maskfile)
if len(Y.shape) == 1:
Y = Y[:, np.newaxis]
if len(X.shape) == 1:
X = X[:, np.newaxis]
Nmod = Y.shape[1]
if testcov is not None:
# we have a separate test dataset
Xte = fileio.load(testcov)
testids = range(X.shape[0], X.shape[0]+Xte.shape[0])
trainids = range(0, X.shape[0])
if len(Xte.shape) == 1:
Xte = Xte[:, np.newaxis]
if testresp is not None:
Yte, testmask = load_response_vars(testresp, maskfile)
if len(Yte.shape) == 1:
Yte = Yte[:, np.newaxis]
else:
sub_te = Xte.shape[0]
Yte = np.zeros([sub_te, Nmod])
# treat as a single train-test split
splits = CustomCV((range(0, X.shape[0]),), (testids,))
Y = np.concatenate((Y, Yte), axis=0)
X = np.concatenate((X, Xte), axis=0)
# force the number of cross-validation folds to 1
if cvfolds is not None and cvfolds != 1:
print("Ignoring cross-valdation specification (test data given)")
cvfolds = 1
else:
# we are running under cross-validation
splits = KFold(n_splits=cvfolds)
testids = range(0, X.shape[0])
# find and remove bad variables from the response variables
# note: the covariates are assumed to have already been checked
nz = np.where(np.bitwise_and(np.isfinite(Y).any(axis=0),
np.var(Y, axis=0) != 0))[0]
# Initialise normative model
nm = norm_init(X, alg=alg, configparam=configparam)
# run cross-validation loop
Yhat = np.zeros_like(Y)
S2 = np.zeros_like(Y)
Hyp = np.zeros((Nmod, nm.n_params, cvfolds))
Z = np.zeros_like(Y)
nlZ = np.zeros((Nmod, cvfolds))
for idx in enumerate(splits.split(X)):
fold = idx[0]
tr = idx[1][0]
te = idx[1][1]
# standardize responses and covariates, ignoring invalid entries
iy, jy = np.ix_(tr, nz)
mY = np.mean(Y[iy, jy], axis=0)
sY = np.std(Y[iy, jy], axis=0)
Yz = np.zeros_like(Y)
Yz[:, nz] = (Y[:, nz] - mY) / sY
mX = np.mean(X[tr, :], axis=0)
sX = np.std(X[tr, :], axis=0)
Xz = (X - mX) / sX
# estimate the models for all subjects
for i in range(0, len(nz)): # range(0, Nmod):
print("Estimating model ", i+1, "of", len(nz))
try:
nm = norm_init(Xz[tr, :], Yz[tr, nz[i]], alg=alg, configparam=configparam)
Hyp[nz[i], :, fold] = nm.estimate(Xz[tr, :], Yz[tr, nz[i]])
# Work around to get stats for subject in th emodel and out. Instead of te for all :
#yhat, s2 = nm.predict(Xz[tr, :], Yz[tr, nz[i]], Xz[te, :], Hyp[nz[i], :, fold])
yhat, s2 = nm.predict(Xz[tr, :], Yz[tr, nz[i]], Xz, Hyp[nz[i], :, fold])
#Yhat[te, nz[i]] = yhat * sY[i] + mY[i]
Yhat[:, nz[i]] = yhat * sY[i] + mY[i]
#S2[te, nz[i]] = s2 * sY[i]**2
S2[:, nz[i]] = s2 * sY[i] ** 2
nlZ[nz[i], fold] = nm.neg_log_lik
if testcov is None:
#Z[te, nz[i]] = (Y[te, nz[i]] - Yhat[te, nz[i]]) / np.sqrt(S2[te, nz[i]])
Z[:, nz[i]] = (Y[:, nz[i]] - Yhat[:, nz[i]]) / np.sqrt(S2[:, nz[i]])
else:
if testresp is not None:
#Z[te, nz[i]] = (Y[te, nz[i]] - Yhat[te, nz[i]]) / np.sqrt(S2[te, nz[i]])
Z[:, nz[i]] = (Y[:, nz[i]] - Yhat[:, nz[i]]) / np.sqrt(S2[:, nz[i]])
except Exception as e:
exc_type, exc_obj, exc_tb = sys.exc_info()
fname = os.path.split(exc_tb.tb_frame.f_code.co_filename)[1]
print("Model ", i+1, "of", len(nz),
"FAILED!..skipping and writing NaN to outputs")
print("Exception:")
print(e)
print(exc_type, fname, exc_tb.tb_lineno)
Hyp[nz[i], :, fold] = float('nan')
Yhat[te, nz[i]] = float('nan')
S2[te, nz[i]] = float('nan')
nlZ[nz[i], fold] = float('nan')
if testcov is None:
Z[te, nz[i]] = float('nan')
else:
if testresp is not None:
Z[te, nz[i]] = float('nan')
# compute performance metrics
if testcov is None:
MSE = np.mean((Y[testids, :] - Yhat[testids, :])**2, axis=0)
MSE_tr = np.mean((Y[0, X.shape[0], :] - Yhat[0, X.shape[0], :])**2, axis=0)
RMSE = np.sqrt(MSE)
# for the remaining variables, we need to ignore zero variances
SMSE = np.zeros_like(MSE)
Rho = np.zeros(Nmod)
pRho = np.ones(Nmod)
iy, jy = np.ix_(testids, nz) # ids for tested samples nonzero values
SMSE[nz] = MSE[nz] / np.var(Y[iy, jy], axis=0)
Rho[nz], pRho[nz] = compute_pearsonr(Y[iy, jy], Yhat[iy, jy])
else:
if testresp is not None:
MSE = np.mean((Y[testids, :] - Yhat[testids, :])**2, axis=0)
MSE_tr = np.mean((Y[0:X.shape[0], :] - Yhat[0:X.shape[0], :]) ** 2, axis=0)
RMSE = np.sqrt(MSE)
RMSE_tr = np.sqrt(MSE_tr)
# for the remaining variables, we need to ignore zero variances
SMSE = np.zeros_like(MSE)
SMSE_tr = np.zeros_like(RMSE_tr)
Rho = np.zeros(Nmod)
Rho_tr = np.zeros(Nmod)
pRho = np.ones(Nmod)
pRho_tr = np.ones(Nmod)
iy, jy = np.ix_(testids, nz) # ids tested samples nonzero values
iy_tr, jy_tr = np.ix_(range(0, X.shape[0]), nz)
SMSE[nz] = MSE[nz] / np.var(Y[iy, jy], axis=0)
SMSE_tr[nz] = MSE[nz] / np.var(Y[iy_tr, jy_tr], axis=0)
Rho[nz], pRho[nz] = compute_pearsonr(Y[iy, jy], Yhat[iy, jy])
Rho_tr[nz], pRho_tr[nz] = compute_pearsonr(Y[iy_tr, jy_tr], Yhat[iy_tr, jy_tr])
# Set writing options
if saveoutput:
print("Writing output ...")
if fileio.file_type(respfile) == 'cifti' or \
fileio.file_type(respfile) == 'nifti':
exfile = respfile
else:
exfile = None
if outputsuffix is not None:
ext = str(outputsuffix) + fileio.file_extension(respfile)
else:
ext = fileio.file_extension(respfile)
# Write output
if testcov is None:
fileio.save(Yhat[testids, :].T, 'yhat' + ext,
example=exfile, mask=maskvol)
fileio.save(S2[testids, :].T, 'ys2' + ext,
example=exfile, mask=maskvol)
fileio.save(Z[testids, :].T, 'Z' + ext, example=exfile,
mask=maskvol)
fileio.save(Rho, 'Rho' + ext, example=exfile, mask=maskvol)
fileio.save(pRho, 'pRho' + ext, example=exfile, mask=maskvol)
fileio.save(RMSE, 'rmse' + ext, example=exfile, mask=maskvol)
fileio.save(SMSE, 'smse' + ext, example=exfile, mask=maskvol)
if cvfolds is None:
fileio.save(Hyp[:,:,0], 'Hyp' + ext, example=exfile, mask=maskvol)
else:
for idx in enumerate(splits.split(X)):
fold = idx[0]
fileio.save(Hyp[:, :, fold], 'Hyp_' + str(fold+1) +
ext, example=exfile, mask=maskvol)
else:
if testresp is None:
fileio.save(Yhat[testids, :].T, 'yhat' + ext,
example=exfile, mask=maskvol)
fileio.save(S2[testids, :].T, 'ys2' + ext,
example=exfile, mask=maskvol)
fileio.save(Hyp[:,:,0], 'Hyp' + ext,
example=exfile, mask=maskvol)
else:
fileio.save(Yhat[testids, :].T, 'yhat' + ext, example=exfile, mask=maskvol)
fileio.save(Yhat[trainids, :].T, 'yhat_controls' + ext, example=exfile, mask=maskvol)
fileio.save(S2[testids, :].T, 'ys2' + ext, example=exfile, mask=maskvol)
fileio.save(S2[trainids, :].T, 'ys2_controls' + ext, example=exfile, mask=maskvol)
fileio.save(Z[testids, :].T, 'Z' + ext, example=exfile, mask=maskvol)
fileio.save(Z[trainids, :].T, 'Z_controls' + ext, example=exfile, mask=maskvol)
fileio.save(Rho, 'Rho' + ext, example=exfile, mask=maskvol)
fileio.save(Rho_tr, 'Rho_controls' + ext, example=exfile, mask=maskvol)
fileio.save(pRho, 'pRho' + ext, example=exfile, mask=maskvol)
fileio.save(pRho_tr, 'pRho_controls' + ext, example=exfile, mask=maskvol)
fileio.save(RMSE, 'rmse' + ext, example=exfile, mask=maskvol)
fileio.save(RMSE_tr, 'rmse_controls' + ext, example=exfile, mask=maskvol)
fileio.save(SMSE, 'smse' + ext, example=exfile, mask=maskvol)
fileio.save(SMSE_tr, 'smse_controls' + ext, example=exfile, mask=maskvol)
if cvfolds is None:
fileio.save(Hyp[:,:,0], 'Hyp' + ext,
example=exfile, mask=maskvol)
else:
for idx in enumerate(splits.split(X)):
fold = idx[0]
fileio.save(Hyp[:, :, fold], 'Hyp_'+ str(fold+1) +
ext, example=exfile, mask=maskvol)
else:
if testcov is None:
output = (Yhat, S2, Hyp, Z, Rho, pRho, RMSE, SMSE)
else:
if testresp is None:
output = (Yhat, S2, Hyp)
else:
output = (Yhat, S2, Hyp, Z, Rho, pRho, RMSE, SMSE)
return output
def estimate(respfile,
covfile,
maskfile=None,
cvfolds=None,
testcov=None,
testresp=None,
saveoutput=True,
outputsuffix=None):
""" Estimate a normative model
This will estimate a model in one of two settings according to the
particular parameters specified (see below):
* under k-fold cross-validation
* estimating a training dataset then applying to a second test dataset
The models are estimated on the basis of data stored on disk in ascii or
neuroimaging data formats (nifti or cifti). Ascii data should be in
tab or space delimited format with the number of subjects in rows and the
number of variables in columns. Neuroimaging data will be reshaped
into the appropriate format
Basic usage::
estimate(respfile, covfile, [extra_arguments])
where the variables are defined below. Note that either the cfolds
parameter or (testcov, testresp) should be specified, but not both.
:param respfile: response variables for the normative model
:param covfile: covariates used to predict the response variable
:param maskfile: mask used to apply to the data (nifti only)
:param cvfolds: Number of cross-validation folds
:param testcov: Test covariates
:param testresp: Test responses
:param saveoutput: Save the output to disk? Otherwise returned as arrays
:param outputsuffix: Text string to add to the output filenames
All outputs are written to disk in the same format as the input. These are:
:outputs: * yhat - predictive mean
* ys2 - predictive variance
* Z - deviance scores
* Rho - Pearson correlation between true and predicted responses
* pRho - parametric p-value for this correlation
* rmse - root mean squared error between true/predicted responses
* smse - standardised mean squared error
The outputsuffix may be useful to estimate multiple normative models in the
same directory (e.g. for custom cross-validation schemes)
"""
# load data
print("Processing data in " + respfile)
X = fileio.load(covfile)
Y, maskvol = load_response_vars(respfile, maskfile)
if len(Y.shape) == 1:
Y = Y[:, np.newaxis]
if len(X.shape) == 1:
X = X[:, np.newaxis]
Nmod = Y.shape[1]
if testcov is not None:
# we have a separate test dataset
Xte = fileio.load(testcov)
Yte, testmask = load_response_vars(testresp, maskfile)
testids = range(X.shape[0], X.shape[0] + Xte.shape[0])
if len(Yte.shape) == 1:
Yte = Yte[:, np.newaxis]
if len(Xte.shape) == 1:
Xte = Xte[:, np.newaxis]
# treat as a single train-test split
splits = CustomCV((range(0, X.shape[0]), ), (testids, ))
Y = np.concatenate((Y, Yte), axis=0)
X = np.concatenate((X, Xte), axis=0)
# force the number of cross-validation folds to 1
if cvfolds is not None and cvfolds != 1:
print("Ignoring cross-valdation specification (test data given)")
cvfolds = 1
else:
# we are running under cross-validation
splits = KFold(n_splits=cvfolds)
testids = range(0, X.shape[0])
# find and remove bad variables from the response variables
# note: the covariates are assumed to have already been checked
nz = np.where(
np.bitwise_and(np.isfinite(Y).any(axis=0),
np.var(Y, axis=0) != 0))[0]
# starting hyperparameters. Could also do random restarts here
covfunc = CovSum(X, ('CovLin', 'CovSqExpARD'))
hyp0 = np.zeros(covfunc.get_n_params() + 1)
# run cross-validation loop
Yhat = np.zeros_like(Y)
S2 = np.zeros_like(Y)
Z = np.zeros_like(Y)
nlZ = np.zeros((Nmod, cvfolds))
Hyp = np.zeros((Nmod, len(hyp0), cvfolds))
for idx in enumerate(splits.split(X)):
fold = idx[0]
tr = idx[1][0]
te = idx[1][1]
# standardize responses and covariates, ignoring invalid entries
iy, jy = np.ix_(tr, nz)
mY = np.mean(Y[iy, jy], axis=0)
sY = np.std(Y[iy, jy], axis=0)
Yz = np.zeros_like(Y)
Yz[:, nz] = (Y[:, nz] - mY) / sY
mX = np.mean(X[tr, :], axis=0)
sX = np.std(X[tr, :], axis=0)
Xz = (X - mX) / sX
# estimate the models for all subjects
for i in range(0, len(nz)): # range(0, Nmod):
print("Estimating model ", i + 1, "of", len(nz))
gpr = GPR(hyp0, covfunc, Xz[tr, :], Yz[tr, nz[i]])
Hyp[nz[i], :, fold] = gpr.estimate(hyp0, covfunc, Xz[tr, :],
Yz[tr, nz[i]])
yhat, s2 = gpr.predict(Hyp[nz[i], :, fold], Xz[tr, :],
Yz[tr, nz[i]], Xz[te, :])
Yhat[te, nz[i]] = yhat * sY[i] + mY[i]
S2[te, nz[i]] = np.diag(s2) * sY[i]**2
Z[te, nz[i]] = (Y[te, nz[i]] - Yhat[te, nz[i]]) / \
np.sqrt(S2[te, nz[i]])
nlZ[nz[i], fold] = gpr.nlZ
# compute performance metrics
MSE = np.mean((Y[testids, :] - Yhat[testids, :])**2, axis=0)
RMSE = np.sqrt(MSE)
# for the remaining variables, we need to ignore zero variances
SMSE = np.zeros_like(MSE)
Rho = np.zeros(Nmod)
pRho = np.ones(Nmod)
iy, jy = np.ix_(testids, nz) # ids for tested samples with nonzero values
SMSE[nz] = MSE[nz] / np.var(Y[iy, jy], axis=0)
Rho[nz], pRho[nz] = compute_pearsonr(Y[iy, jy], Yhat[iy, jy])
# Set writing options
if saveoutput:
print("Writing output ...")
if fileio.file_type(respfile) == 'cifti' or \
fileio.file_type(respfile) == 'nifti':
exfile = respfile
else:
exfile = None
if outputsuffix is not None:
ext = str(outputsuffix) + fileio.file_extension(respfile)
else:
ext = fileio.file_extension(respfile)
# Write output
fileio.save(Yhat[testids, :].T,
'yhat' + ext,
example=exfile,
mask=maskvol)
fileio.save(S2[testids, :].T,
'ys2' + ext,
example=exfile,
mask=maskvol)
fileio.save(Z[testids, :].T, 'Z' + ext, example=exfile, mask=maskvol)
fileio.save(Rho, 'Rho' + ext, example=exfile, mask=maskvol)
fileio.save(pRho, 'pRho' + ext, example=exfile, mask=maskvol)
fileio.save(RMSE, 'rmse' + ext, example=exfile, mask=maskvol)
fileio.save(SMSE, 'smse' + ext, example=exfile, mask=maskvol)
if cvfolds is None:
fileio.save(Hyp, 'Hyp' + ext, example=exfile, mask=maskvol)
else:
for idx in enumerate(splits.split(X)):
fold = idx[0]
fileio.save(Hyp[:, :, fold],
'Hyp_' + str(fold + 1) + ext,
example=exfile,
mask=maskvol)
else:
output = (Yhat, S2, Z, Rho, pRho, RMSE, SMSE)
return output
if __name__ == '__main__':
# valid video modules in preferred order
VALID_V_MODULES = ['gtkgui', 'macgui', 'qtgui', 'dummy']
# valid audio modules in preferred order
VALID_A_MODULES = ['alsa', 'macaudio', 'qtaudio', 'dummy']
config = parse_args(sys.argv[1:])
if config.help_req:
Configuration.print_usage()
sys.exit(0)
if config.export_fmt is not None:
if config.export_fmt == 'swf':
lec = fileio.load(config.file_to_load)
exporter.to_swf(lec, lec.adats, config.file_to_load[:-4] + '.swf')
elif config.export_fmt == 'pdf':
lec = fileio.load(config.file_to_load)
exporter.to_pdf(lec, config.file_to_load[:-4] + '.swf')
elif config.export_fmt in ['dcd', 'dcb', 'dcx', 'dar', 'dct']:
lec = fileio.load(config.file_to_load)
fileio.save(config.file_to_load[:-3] + config.export_fmt, lec, lec.adats)
else:
print 'Unknown flag "--exp-%s"' % config.export_fmt
sys.exit(0)
# Something was passed, so use that to
if config.audio_module is not None:
try:
Audio = __import__(config.audio_module).Audio
def testOcc(self):
name = "health1"
checkOcc(load(name))
def testNoWar(self):
name = "nowar"
expect = State.WAIT
handler = AlertHandle(load(name))
self.assertEqual(handler.state, expect)
def list_tasks(args):
manager = TaskManager(fileio.load())
print_table(manager)
def testHealthOne(self):
name = "health1"
handler = AlertHandle(load(name))
self.assertEqual(handler.state, State.RUN)
self.assertEqual(handler.health, Health.NOFULL)
